update: touchups

* Added new Stage 1 notebook to create unlabelled
Vertex AI AutoML text entity extraction dataset
from collection of PDF files on Google Cloud Storage

* Linted notebook

* Removed TODOs

* Updates per PR comments

* Revered to multiple imports per line

.cloud-build/cleanup/cleanup.py

@@ -1,45 +1,49 @@
 from typing import List
+from ratemate import RateLimit
 from resource_cleanup_manager import (
-	ResourceCleanupManager,
-	DatasetResourceCleanupManager,
-	EndpointResourceCleanupManager,
-	ModelResourceCleanupManager,
+    DatasetResourceCleanupManager,
+    ModelResourceCleanupManager,
+    EndpointResourceCleanupManager,
+    ResourceCleanupManager,
 )
 
+rate_limit = RateLimit(max_count=25, per=60, greedy=False)
+
 
 def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: bool):
-	for manager in managers:
-		type_name = manager.type_name
+    for manager in managers:
+        type_name = manager.type_name
 
-		print(f"Fetching {type_name}'s...")
-		resources = manager.list()
-		print(f"Found {len(resources)} {type_name}'s")
-		for resource in resources:
-			if not manager.is_deletable(resource):
-				continue
+        print(f"Fetching {type_name}'s...")
+        resources = manager.list()
+        print(f"Found {len(resources)} {type_name}'s")
+        for resource in resources:
+            try:
+                if not manager.is_deletable(resource):
+                    continue
 
-			if is_dry_run:
-				resource_name = manager.resource_name(resource)
-				print(f"Will delete '{type_name}': {resource_name}")
-			else:
-				try:
-					manager.delete(resource)
-				except Exception as exception:
-					print(exception)
+                if is_dry_run:
+                    resource_name = manager.resource_name(resource)
+                    print(f"Will delete '{type_name}': {resource_name}")
+                else:
+                    rate_limit.wait()  # wait before deleting
+                    manager.delete(resource)
+            except Exception as exception:
+                print(exception)
 
-		print("")
+        print("")
 
 
 is_dry_run = False
 
 if is_dry_run:
-	print("Starting cleanup in dry run mode...")
+    print("Starting cleanup in dry run mode...")
 
 # List of all cleanup managers
 managers = [
-	DatasetResourceCleanupManager(),
-	EndpointResourceCleanupManager(),
-	ModelResourceCleanupManager(),
+    DatasetResourceCleanupManager(),
+    EndpointResourceCleanupManager(),
+    ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
 ]
 
 run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -1,8 +1,9 @@
 import abc
+from typing import Any, Type
+
 from google.cloud import aiplatform
-from typing import Any
-from proto.datetime_helpers import DatetimeWithNanoseconds
 from google.cloud.aiplatform import base
+from proto.datetime_helpers import DatetimeWithNanoseconds
 
 # If a resource was updated within this number of seconds, do not delete.
 RESOURCE_UPDATE_BUFFER_IN_SECONDS = 60 * 60 * 8
@@ -40,7 +41,7 @@ class ResourceCleanupManager(abc.ABC):
         # Check that it wasn't created too recently, to prevent race conditions
         if time_difference <= RESOURCE_UPDATE_BUFFER_IN_SECONDS:
             print(
-                f"Skipping '{resource}' due update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
+                f"Skipping '{resource}' due to update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
             )
             return False
 
@@ -50,7 +51,7 @@ class ResourceCleanupManager(abc.ABC):
 class VertexAIResourceCleanupManager(ResourceCleanupManager):
     @property
     @abc.abstractmethod
-    def vertex_ai_resource(self) -> base.VertexAiResourceNounWithFutureManager:
+    def vertex_ai_resource(self) -> Type[base.VertexAiResourceNounWithFutureManager]:
         pass
 
     @property
@@ -60,7 +61,9 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
     def list(self) -> Any:
         return self.vertex_ai_resource.list()
 
-    def resource_name(self, resource: Any) -> str:
+    def resource_name(
+        self, resource: Type[base.VertexAiResourceNounWithFutureManager]
+    ) -> str:
         return resource.display_name
 
     def delete(self, resource):
@@ -74,12 +77,33 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
 
 class DatasetResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.datasets._Dataset
+    dataset_types = [
+        aiplatform.ImageDataset,
+        aiplatform.TabularDataset,
+        aiplatform.TextDataset,
+        aiplatform.TimeSeriesDataset,
+        aiplatform.VideoDataset,
+    ]
+
+    def list(self) -> Any:
+        return [
+            dataset
+            for dataset_type in self.dataset_types
+            for dataset in dataset_type.list()
+        ]
 
 
 class EndpointResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Endpoint
 
     def delete(self, resource):
+        # TODO: Remove this once https://github.com/googleapis/python-aiplatform/issues/1441 is fixed
+        resource._sync_gca_resource()
+        for deployed_model_id in [
+            models.id for models in resource._gca_resource.deployed_models
+        ]:
+            resource._undeploy(deployed_model_id=deployed_model_id)
+
         resource.delete(force=True)
 
 

.cloud-build/execute_changed_notebooks_cli.py

@@ -17,6 +17,7 @@
 
 import argparse
 import pathlib
+
 import execute_changed_notebooks_helper
 
 
@@ -73,6 +74,13 @@ parser.add_argument(
     help="The GCP directory for storing executed notebooks.",
     required=True,
 )
+parser.add_argument(
+    "--timeout",
+    type=int,
+    help="Timeout in seconds",
+    default=86400,
+    required=False,
+)
 parser.add_argument(
     "--private_pool_id",
     type=str,
@@ -102,6 +110,7 @@ execute_changed_notebooks_helper.process_and_execute_notebooks(
     artifacts_bucket=args.artifacts_bucket,
     variable_project_id=args.variable_project_id,
     variable_region=args.variable_region,
-    private_pool_id=args.private_pool_id if not "default" else None,
+    private_pool_id=args.private_pool_id,
     should_parallelize=args.should_parallelize,
+    timeout=args.timeout,
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -17,18 +17,24 @@ import concurrent
 import dataclasses
 import datetime
 import functools
+import git
+import operator
 import os
 import pathlib
-import nbformat
 import re
 import subprocess
 from typing import List, Optional
-from tabulate import tabulate
-import operator
 
+import execute_notebook_helper
 import execute_notebook_remote
-from utils import util, NotebookProcessors
+import nbformat
 from google.cloud.devtools.cloudbuild_v1.types import BuildOperationMetadata
+from ratemate import RateLimit
+from tabulate import tabulate
+from utils import NotebookProcessors, util
+
+# A buffer so that workers finish before the orchestrating job
+WORKER_TIMEOUT_BUFFER_IN_SECONDS: int = 60 * 60
 
 
 def format_timedelta(delta: datetime.timedelta) -> str:
@@ -103,6 +109,9 @@ def _create_tag(filepath: str) -> str:
     return tag
 
 
+rate_limit = RateLimit(max_count=50, per=60, greedy=True)
+
+
 def process_and_execute_notebook(
     container_uri: str,
     staging_bucket: str,
@@ -110,9 +119,12 @@ def process_and_execute_notebook(
     variable_project_id: str,
     variable_region: str,
     private_pool_id: Optional[str],
+    deadline: datetime,
     notebook: str,
     should_get_tail_logs: bool = False,
 ) -> NotebookExecutionResult:
+    rate_limit.wait()  # wait before creating the task
+
     print(f"Running notebook: {notebook}")
 
     # Create paths
@@ -145,14 +157,20 @@ def process_and_execute_notebook(
         # Upload the pre-processed code to a GCS bucket
         code_archive_uri = util.archive_code_and_upload(staging_bucket=staging_bucket)
 
+        # Calculate timeout in seconds
+        timeout_in_seconds = max(
+            int((deadline - datetime.datetime.now()).total_seconds()), 1
+        )
+
         operation = execute_notebook_remote.execute_notebook_remote(
             code_archive_uri=code_archive_uri,
             notebook_uri=notebook,
             notebook_output_uri=notebook_output_uri,
             container_uri=container_uri,
             tag=tag,
-            region=variable_region,
             private_pool_id=private_pool_id,
+            private_pool_region=variable_region,
+            timeout_in_seconds=timeout_in_seconds,
         )
 
         operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
@@ -215,20 +233,39 @@ def get_changed_notebooks(
 
     # Find notebooks
     notebooks = []
+
+    # Instantiate GitPython objects
+    repo = git.Repo(os.getcwd())
+    index = repo.index
+
     if base_branch:
-        print(f"Looking for notebooks that changed from branch: {base_branch}")
-        notebooks = subprocess.check_output(
-            ["git", "diff", "--name-only", f"origin/{base_branch}..."] + test_paths
-        )
+        # Get the point at which this branch branches off from main
+        branching_commits = repo.merge_base("HEAD", f"origin/{base_branch}")
+
+        if len(branching_commits) > 0:
+            branching_commit = branching_commits[0]
+            print(f"Looking for notebooks that changed from branch: {branching_commit}")
+
+            notebooks = [
+                diff.b_path
+                for diff in index.diff(branching_commit, paths=test_paths)
+                if diff.b_path is not None
+            ]
+        else:
+            notebooks = []
     else:
         print(f"Looking for all notebooks.")
         notebooks = subprocess.check_output(["git", "ls-files"] + test_paths)
 
-    notebooks = notebooks.decode("utf-8").split("\n")
     notebooks = [notebook for notebook in notebooks if notebook.endswith(".ipynb")]
     notebooks = [notebook for notebook in notebooks if len(notebook) > 0]
     notebooks = [notebook for notebook in notebooks if pathlib.Path(notebook).exists()]
 
+    if len(notebooks) > 0:
+        print(f"Found {len(notebooks)} notebooks:")
+        for notebook in notebooks:
+            print(f"\t{notebook}")
+
     return notebooks
 
 
@@ -241,6 +278,7 @@ def process_and_execute_notebooks(
     variable_region: str,
     private_pool_id: Optional[str],
     should_parallelize: bool,
+    timeout: int,
 ):
     """
     Run the notebooks that exist under the folders defined in the test_paths_file.
@@ -267,17 +305,27 @@ def process_and_execute_notebooks(
             Required. The value for REGION to inject into notebooks.
         should_parallelize (bool):
             Required. Should run notebooks in parallel using a thread pool as opposed to in sequence.
+        timeout (str):
+            Required. Timeout string according to https://cloud.google.com/build/docs/build-config-file-schema#timeout.
     """
-    notebook_execution_results: List[NotebookExecutionResult] = []
 
-    if len(notebooks) > 0:
+    # Calculate deadline
+    deadline = datetime.datetime.now() + datetime.timedelta(
+        seconds=max(timeout - WORKER_TIMEOUT_BUFFER_IN_SECONDS, 0)
+    )
+
+    if len(notebooks) > 1:
+        notebook_execution_results: List[NotebookExecutionResult] = []
+
         print(f"Found {len(notebooks)} modified notebooks: {notebooks}")
 
         if should_parallelize and len(notebooks) > 1:
             print(
                 "Running notebooks in parallel, so no logs will be displayed. Please wait..."
             )
-            with concurrent.futures.ThreadPoolExecutor(max_workers=None) as executor:
+            with concurrent.futures.ThreadPoolExecutor(max_workers=100) as executor:
+                print(f"Max workers: {executor._max_workers}")
+
                 notebook_execution_results = list(
                     executor.map(
                         functools.partial(
@@ -288,6 +336,7 @@ def process_and_execute_notebooks(
                             variable_project_id,
                             variable_region,
                             private_pool_id,
+                            deadline,
                         ),
                         notebooks,
                     )
@@ -301,47 +350,69 @@ def process_and_execute_notebooks(
                     variable_project_id=variable_project_id,
                     variable_region=variable_region,
                     private_pool_id=private_pool_id,
+                    deadline=deadline,
                     notebook=notebook,
                 )
                 for notebook in notebooks
             ]
+
+        print("\n=== RESULTS ===\n")
+
+        results_sorted = sorted(
+            notebook_execution_results,
+            key=lambda result: result.is_pass,
+            reverse=True,
+        )
+
+        # Print results
+        print(
+            tabulate(
+                [
+                    [
+                        result.name,
+                        "PASSED" if result.is_pass else "FAILED",
+                        format_timedelta(result.duration),
+                        result.log_url,
+                        result.output_uri,
+                    ]
+                    for result in results_sorted
+                ],
+                headers=["build_tag", "status", "duration", "log_url", "output_url"],
+            )
+        )
+
+        print("\n=== END RESULTS===\n")
+
+        total_notebook_duration = functools.reduce(
+            operator.add,
+            [datetime.timedelta(seconds=0)]
+            + [result.duration for result in results_sorted],
+        )
+
+        print(
+            f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}"
+        )
+
+        # Raise error if any notebooks failed
+        if not all([result.is_pass for result in results_sorted]):
+            raise RuntimeError("Notebook failures detected. See logs for details")
+
+    elif len(notebooks) == 1:
+        notebook = notebooks[0]
+
+        # Pre-process notebook by substituting variable names
+        _process_notebook(
+            notebook_path=notebook,
+            variable_project_id=variable_project_id,
+            variable_region=variable_region,
+        )
+
+        execute_notebook_helper.execute_notebook(
+            notebook_source=notebook,
+            output_file_or_uri="/".join(
+                [artifacts_bucket, pathlib.Path(notebook).name]
+            ),
+            should_log_output=True,
+        )
     else:
         print("No notebooks modified in this pull request.")
-
-    print("\n=== RESULTS ===\n")
-
-    results_sorted = sorted(
-        notebook_execution_results,
-        key=lambda result: result.is_pass,
-        reverse=True,
-    )
-
-    # Print results
-    print(
-        tabulate(
-            [
-                [
-                    result.name,
-                    "PASSED" if result.is_pass else "FAILED",
-                    format_timedelta(result.duration),
-                    result.log_url,
-                ]
-                for result in results_sorted
-            ],
-            headers=["build_tag", "status", "duration", "log_url"],
-        )
-    )
-
-    print("\n=== END RESULTS===\n")
-
-    total_notebook_duration = functools.reduce(
-        operator.add,
-        [datetime.timedelta(seconds=0)]
-        + [result.duration for result in results_sorted],
-    )
-
-    print(f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}")
-
-    # Raise error if any notebooks failed
-    if not all([result.is_pass for result in results_sorted]):
-        raise RuntimeError("Notebook failures detected. See logs for details")

.cloud-build/execute_notebook_cli.py

@@ -16,6 +16,7 @@
 """A CLI to download (optional) and run a single notebook locally"""
 
 import argparse
+
 import execute_notebook_helper
 
 parser = argparse.ArgumentParser(description="Run a single notebook locally.")

.cloud-build/execute_notebook_helper.py

@@ -15,14 +15,14 @@
 
 """Methods to run a notebook locally"""
 
-import sys
-import os
 import errno
-import papermill as pm
+import os
 import shutil
+import sys
 
-from utils import util
+import papermill as pm
 from google.cloud.aiplatform import utils
+from utils import util
 
 # This script is used to execute a notebook and write out the output notebook.
 

.cloud-build/execute_notebook_remote.py

@@ -16,22 +16,18 @@
 """Methods to run a notebook on Google Cloud Build"""
 
 from re import sub
+from typing import Optional
+
+import google.auth
+import yaml
+from google.api_core import client_options, operation
+from google.cloud.aiplatform import utils
+from google.cloud.devtools import cloudbuild_v1
+from google.cloud.devtools.cloudbuild_v1.types import Source, StorageSource
 from google.protobuf import duration_pb2
 from yaml.loader import FullLoader
 
-import google.auth
-from google.cloud.devtools import cloudbuild_v1
-from google.cloud.devtools.cloudbuild_v1.types import Source, StorageSource
-
-from typing import Optional
-import yaml
-
-from google.cloud.aiplatform import utils
-from google.api_core import operation, client_options
-
-
 CLOUD_BUILD_FILEPATH = ".cloud-build/notebook-execution-test-cloudbuild-single.yaml"
-TIMEOUT_IN_SECONDS = 86400
 SERVICE_BASE_PATH = "cloudbuild.googleapis.com"
 
 
@@ -40,12 +36,14 @@ def execute_notebook_remote(
     notebook_uri: str,
     notebook_output_uri: str,
     container_uri: str,
-    region: str,
     private_pool_id: Optional[str],
+    private_pool_region: Optional[str],
     tag: Optional[str],
+    timeout_in_seconds: Optional[int] = None,
 ) -> operation.Operation:
     """Create and execute a single notebook on Google Cloud Build"""
     # Load build steps from YAML
+
     cloudbuild_config = yaml.load(open(CLOUD_BUILD_FILEPATH), Loader=FullLoader)
 
     substitutions = {
@@ -57,13 +55,14 @@ def execute_notebook_remote(
     build = cloudbuild_v1.Build()
 
     options: Optional[client_options.ClientOptions] = None
-    if private_pool_id:
-        substitutions["_PRIVATE_POOL_NAME"] = private_pool_id
-        build.options = cloudbuild_config["options"]
+    if private_pool_id and private_pool_region:
+        # substitutions["_PRIVATE_POOL_NAME"] = private_pool_id
+        build.options = cloudbuild_config.get("options")
+        build.options.pool = {"name": private_pool_id}
 
         # Switch to the regional endpoint of the pool
         options = client_options.ClientOptions(
-            api_endpoint=f"{region}-{SERVICE_BASE_PATH}"
+            api_endpoint=f"{private_pool_region}-{SERVICE_BASE_PATH}"
         )
 
     # Authorize the client with Google defaults
@@ -85,8 +84,8 @@ def execute_notebook_remote(
 
     build.steps = cloudbuild_config["steps"]
     build.substitutions = substitutions
-    build.timeout = duration_pb2.Duration(seconds=TIMEOUT_IN_SECONDS)
-    build.queue_ttl = duration_pb2.Duration(seconds=TIMEOUT_IN_SECONDS)
+    build.timeout = duration_pb2.Duration(seconds=timeout_in_seconds)
+    build.queue_ttl = duration_pb2.Duration(seconds=timeout_in_seconds)
 
     if tag:
         build.tags = [tag]

.cloud-build/notebook-execution-test-cloudbuild-single.yaml

@@ -25,7 +25,4 @@ steps:
     - 'python3 -m pip install -U pip && python3 -m pip freeze && python3 .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"'
     env:
     - 'IS_TESTING=1'
-timeout: 86400s
-options:
-  pool:
-    name: ${_PRIVATE_POOL_NAME}
+timeout: 86400s

.cloud-build/notebook-execution-test-cloudbuild.yaml

@@ -11,12 +11,9 @@ steps:
     args:
     - -c
     - 'python3 .cloud-build/CheckPythonVersion.py'
-  # Fetch base branch if required
-  - name: ${_PYTHON_IMAGE}
-    entrypoint: /bin/sh
-    args:
-    - -c
-    - 'if [ -n "${_BASE_BRANCH}" ]; then git fetch origin "${_BASE_BRANCH}":refs/remotes/origin/"${_BASE_BRANCH}"; else echo "Skipping fetch."; fi'
+  # Fetch full repo for diff purposes
+  - name: gcr.io/cloud-builders/git
+    args: [fetch, --unshallow]
   # Install Python dependencies
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh

.cloud-build/requirements.txt

@@ -9,4 +9,5 @@ tabulate
 google-cloud-aiplatform
 google-cloud-storage
 google-cloud-build
-gcloud
+ratemate
+GitPython

.cloud-build/utils/NotebookProcessors.py

@@ -13,8 +13,10 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from nbconvert.preprocessors import Preprocessor
 from typing import Dict
+
+from nbconvert.preprocessors import Preprocessor
+
 from . import UpdateNotebookVariables as update_notebook_variables
 
 
@@ -60,4 +62,4 @@ class UpdateVariablesPreprocessor(Preprocessor):
 
             executable_cells.append(cell)
         notebook.cells = executable_cells
-        return notebook, resources
+        return notebook, resources

.cloud-build/utils/UpdateNotebookVariables.py

@@ -78,4 +78,4 @@ def test_region():
         variable_name="REGION",
         variable_value="us-central1",
     )
-    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'
+    assert new_content == 'REGION = "us-central1"  # @param {type:"string"}'

.cloud-build/utils/util.py

@@ -1,13 +1,13 @@
-from datetime import datetime
-from typing import Optional
-from google.cloud import storage
-from google.cloud.aiplatform import utils
-from google.auth import credentials as auth_credentials
 import os
-
 import subprocess
 import tarfile
 import uuid
+from datetime import datetime
+from typing import Optional
+
+from google.auth import credentials as auth_credentials
+from google.cloud import storage
+from google.cloud.aiplatform import utils
 
 
 def download_file(bucket_name: str, blob_name: str, destination_file: str) -> str:
@@ -57,4 +57,4 @@ def archive_code_and_upload(staging_bucket: str):
 
     print(f"Uploaded source code archive to {source_archived_file_gcs}")
 
-    return source_archived_file_gcs
+    return source_archived_file_gcs

.github/PULL_REQUEST_TEMPLATE.md

@@ -2,17 +2,17 @@ If you are opening a PR for `Official Notebooks` under the [notebooks/official](
 - [ ] Use the [notebook template](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb) as a starting point.
 - [ ] Follow the style and grammar rules outlined in the above notebook template.
 - [ ] Verify the notebook runs successfully in Colab since the automated tests cannot guarantee this even when it passes.
-- [ ] Passes all the required automated checks. You can locally test for formatting and linting with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] Passes all the required automated checks. You can locally test for formatting and linting with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).
 - [ ] You have consulted with a tech writer to see if tech writer review is necessary. If so, the notebook has been reviewed by a tech writer, and they have approved it.
-- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under `# Official Notebooks` section, pointing to the author or the author's team.
+- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/CODEOWNERS) file under the `Official Notebooks` section, pointing to the author or the author's team.
 - [ ] The Jupyter notebook cleans up any artifacts it has created (datasets, ML models, endpoints, etc) so as not to eat up unnecessary resources.
 
 
 If you are opening a PR for `Community Notebooks` under the [notebooks/community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder:
-- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under the `# Community Notebooks` section, pointing to the author or the author's team.
-- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] This notebook has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/CODEOWNERS) file under the `Community Notebooks` section, pointing to the author or the author's team.
+- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).
 
 If you are opening a PR for `Community Content` under the [community-content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/community-content) folder:
 - [ ] Make sure your main `Content Directory Name` is descriptive, informative, and includes some of the key products and attributes of your content, so that it is differentiable from other content
-- [ ] The main content directory has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/CODEOWNERS) file under the `# Community Content` section, pointing to the author or the author's team.
-- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/docs/contributing.md#code-quality-checks).
+- [ ] The main content directory has been added to the [CODEOWNERS](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/community-content/CODEOWNERS) file under the `Community Content` section, pointing to the author or the author's team.
+- [ ] Passes all the required formatting and linting checks. You can locally test with these [instructions](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/CONTRIBUTING.md#code-quality-checks).

.github/workflows/ci.yaml

@@ -7,9 +7,11 @@ jobs:
     runs-on: ubuntu-latest
     steps:
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
+      with:
+        python-version: '3.x'      
     - name: Fetch pull request branch
-      uses: actions/checkout@v2
+      uses: actions/checkout@v3
       with:
         fetch-depth: 0      
     - name: Fetch base main branch

.github/workflows/linter/requirements.txt

@@ -2,8 +2,9 @@ git+https://github.com/tensorflow/docs
 ipython
 jupyter
 nbconvert
-black==22.1.0
-pyupgrade==2.31.0
+black==22.3.0
+pyupgrade==2.34.0
 isort==5.10.1
 flake8==4.0.1
-nbqa==1.2.3
+nbqa==1.3.1
+

CONTRIBUTING.md

@@ -48,8 +48,8 @@ then you will need to manually address them before submitting your PR.
 nbqa black "$notebook"
 nbqa pyupgrade "$notebook"
 nbqa isort "$notebook"
-python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
 nbqa flake8 "$notebook" --extend-ignore=W391,E501,F821,E402,F404,W503,E203,E722,W293,W291
+python3 -m tensorflow_docs.tools.nbfmt --remove_outputs "$notebook"
 ```
 
 ## Code Reviews

README.md

@@ -6,7 +6,19 @@ Welcome to the Google Cloud [Vertex AI](https://cloud.google.com/vertex-ai/docs/
 
 ## Overview
 
-The repository contains [Notebooks](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks) and [Community Content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/community-content) that demonstrate how to develop and manage ML workflows using Google Cloud Vertex AI.
+The repository contains [notebooks](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks) and [community content](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/community-content) that demonstrate how to develop and manage ML workflows using Google Cloud Vertex AI.
+
+## Repository structure
+
+```bash
+├── community-content - Sample code and tutorials contributed by the community
+├── notebooks
+│   ├── community - Notebooks contributed by the community
+│   ├── official - Notebooks demonstrating use of each Vertex AI service
+│   │   ├── automl
+│   │   ├── custom
+│   │   ├── ...
+```
 
 ## Contributing
 

community-content/CODEOWNERS

@@ -3,3 +3,4 @@
 /pytorch_text_classification_using_vertex_sdk_and_gcloud  @RajeshThallam
 /pytorch_text_classification_using_vertex_sdk_and_gcloud		@RajeshThallam @ultrons
 /sklearn_text_classification_from_script_using_vertex_sdk       @maxhardt
+/pluto_on_workbench @wkharold

community-content/pluto_on_workbench/README.md

@@ -0,0 +1,52 @@
+# Overview
+*Pluto* is a programming environment for Julia, designed to be interactive and helpful. It provides a familiar notebook interface but it is not a Jupyter notebook. The biggest difference is that Pluto notebooks are reactive, changing a variable or function in one cell causes the cells that depend on that variable or function to be reevaluated. Pluto also provides useful interaction mechanisms that allow users to dynamically interact with the notebooks computation state.
+
+The JuliaCon 2020 presentation: [Interactive notebooks ~ Pluto.jl]() provides a good introduction to Pluto. The source is at [fonsp/Pluto.jl]()
+
+# Install Pluto
+
+## Create a Vertex AI JupyterLab Instance
+
+1. From the [GCP console](https://console.cloud.google.com) "hamburger menu"
+
+   select Vertex AI > Workbench
+2. Click NEW NOTEBOOK
+   
+   * Choose Python 3 if you won't be using a GPU
+   * Choose Python 3 (CUDA Toolkit xx.y) if you do want use a GPU
+3. Give the notebook an appropriate name
+4. Edit Notebook properties if you have special requirements otherwise accept the defaults and click CREATE
+5. When the notebook instance is ready click OPEN JUPYTERLAB
+
+## Configure JupyterLab
+
+1. Open a terminal by clicking the Terminal icon.
+1. Install the plutoserver
+pip3 install git+https://github.com/fonsp/pluto-on-jupyterlab.git
+1. In a browser go to [julialang.org/downloads](https://julialang.org/downloads/)
+1. In the Current stable release right click on the `Generic Linux on x86 / 64-bit (glibc)` link
+Select copy link address
+1. Back in the terminal switch to root via
+sudo -i
+1. Download the release to /opt and install julia in /usr/local/bin
+    ```bash
+    cd /opt
+    wget <paste the release link address>
+    tar xf <name of the downloaded tar file>
+    ln -s /opt/<julia-x.y.z>/bin/julia /usr/local/bin
+    ^d
+    ```
+1. Add the Pluto package to Julia
+   ```bash
+    julia
+    julia> ]add Pluto
+    julia> bksp
+    julia> using Pluto
+    julia> ^d
+    ```
+1. From the JupyterLab menu bar select File > Shut Down
+
+# Start Pluto
+1. Click OPEN JUPYTERLAB in the Workbench
+1. In the Notebook section of the Launcher click Pluto.jl
+1. The welcome to Pluto.jl screen should appear

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/predictor/Dockerfile

@@ -2,10 +2,13 @@
 FROM pytorch/torchserve:latest-cpu
 
 # install dependencies
+RUN python3 -m pip install --upgrade pip
 RUN pip3 install transformers
 
+USER model-server
+
 # copy model artifacts, custom handler and other dependencies
-COPY ./custom_text_handler.py /home/model-server/
+COPY ./custom_handler.py /home/model-server/
 COPY ./index_to_name.json /home/model-server/
 COPY ./model/finetuned-bert-classifier/ /home/model-server/
 
@@ -21,7 +24,7 @@ EXPOSE 7080
 EXPOSE 7081
 
 # create model archive file packaging model artifacts and dependencies
-RUN torch-model-archiver -f   --model-name=finetuned-bert-classifier   --version=1.0   --serialized-file=/home/model-server/pytorch_model.bin   --handler=/home/model-server/custom_text_handler.py   --extra-files "/home/model-server/config.json,/home/model-server/tokenizer.json,/home/model-server/training_args.bin,/home/model-server/tokenizer_config.json,/home/model-server/special_tokens_map.json,/home/model-server/vocab.txt,/home/model-server/index_to_name.json"   --export-path=/home/model-server/model-store
+RUN torch-model-archiver -f   --model-name=finetuned-bert-classifier   --version=1.0   --serialized-file=/home/model-server/pytorch_model.bin   --handler=/home/model-server/custom_handler.py   --extra-files "/home/model-server/config.json,/home/model-server/tokenizer.json,/home/model-server/training_args.bin,/home/model-server/tokenizer_config.json,/home/model-server/special_tokens_map.json,/home/model-server/vocab.txt,/home/model-server/index_to_name.json"   --export-path=/home/model-server/model-store
 
 # run Torchserve HTTP serve to respond to prediction requests
-CMD ["torchserve",      "--start",      "--ts-config=/home/model-server/config.properties",      "--models",      "finetuned-bert-classifier=finetuned-bert-classifier.mar",      "--model-store",      "/home/model-server/model-store"]
+CMD ["torchserve",      "--start",      "--ts-config=/home/model-server/config.properties",      "--models",      "finetuned-bert-classifier=finetuned-bert-classifier.mar",      "--model-store",      "/home/model-server/model-store"]

community-content/pytorch_text_classification_using_vertex_sdk_and_gcloud/pytorch-text-classification-vertex-ai-train-tune-deploy.ipynb

@@ -63,12 +63,12 @@
         "- [Training](#Training)\n",
         "    - [Run Training Locally in the Notebook](#Training-locally-in-the-notebook)\n",
         "    - [Run Training Job on Vertex AI](#Training-on-Vertex-AI)\n",
-        "        - [Training with pre-built container](#Run-Custom-Job-on-Vertex-Training-with-a-pre-built-container)\n",
-        "        - [Training with custom container](#Run-Custom-Job-on-Vertex-Training-with-custom-container)\n",
+        "        - [Training with pre-built container](#Run-Custom-Job-on-Vertex-AI-Training-with-a-pre-built-container)\n",
+        "        - [Training with custom container](#Run-Custom-Job-on-Vertex-AI-Training-with-custom-container)\n",
         "- [Tuning](#Hyperparameter-Tuning) \n",
         "    - [Run Hyperparameter Tuning job on Vertex AI](#Run-Hyperparameter-Tuning-Job-on-Vertex-AI)\n",
         "- [Deploying](#Deploying)\n",
-        "    - [Deploying model on Vertex Predictions with custom container](#Deploying-model-on-Vertex-Predictions-with-custom-container)\n",
+        "    - [Deploying model on Vertex AI Predictions with custom container](#Deploying-model-on-Vertex AI-Predictions-with-custom-container)\n",
         "\n",
         "### Costs \n",
         "\n",
@@ -202,9 +202,9 @@
         "id": "e0c1dcadc2c8"
       },
       "source": [
-        "We will be using [Vertex SDK for Python](https://cloud.google.com/vertex-ai/docs/start/client-libraries#python) to interact with Vertex AI services. The high-level `aiplatform` library is designed to simplify common data science workflows by using wrapper classes and opinionated defaults. \n",
+        "We will be using [Vertex AI SDK for Python](https://cloud.google.com/vertex-ai/docs/start/client-libraries#python) to interact with Vertex AI services. The high-level `aiplatform` library is designed to simplify common data science workflows by using wrapper classes and opinionated defaults. \n",
         "\n",
-        "#### Install Vertex SDK for Python"
+        "#### Install Vertex AI SDK for Python"
       ]
     },
     {
@@ -1199,7 +1199,7 @@
       "source": [
         "### Run predictions locally with sample examples\n",
         "\n",
-        "Using the trained model, we can predict the sentiment label for an input text after applying the preprocessing function that was used during the training. We will run the predictions locally in the notebook and later show how you can deploy the model to an endpoint using [TorchServe](https://pytorch.org/serve/) on Vertex Predictions."
+        "Using the trained model, we can predict the sentiment label for an input text after applying the preprocessing function that was used during the training. We will run the predictions locally in the notebook and later show how you can deploy the model to an endpoint using [TorchServe](https://pytorch.org/serve/) on Vertex AI Predictions."
       ]
     },
     {
@@ -1382,7 +1382,7 @@
         "id": "f7466d414a0e"
       },
       "source": [
-        "### Run Custom Job on Vertex Training with a pre-built container"
+        "### Run Custom Job on Vertex AI Training with a pre-built container"
       ]
     },
     {
@@ -1395,7 +1395,7 @@
         "\n",
         "In this notebook, we are using Hugging Face Datasets and fine tuning a transformer model from Hugging Face Transformers Library for sentiment analysis task using PyTorch. We will use [pre-built container for PyTorch](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers#pytorch) and package the training application code by adding standard Python dependencies - `transformers`, `datasets` and `tqdm` - in the `setup.py` file. \n",
         "\n",
-        "![Training with Prebuilt Containers on Vertex Training](./images/training-with-prebuilt-containers-on-vertex-training.png)"
+        "![Training with Prebuilt Containers on Vertex AI Training](./images/training-with-prebuilt-containers-on-vertex-training.png)"
       ]
     },
     {
@@ -1569,7 +1569,7 @@
       "source": [
         "#### **Run custom training job on Vertex AI**\n",
         "\n",
-        "We use [Vertex SDK for Python](https://cloud.google.com/vertex-ai/docs/start/client-libraries#client_libraries) to create and submit training job to the Vertex training service."
+        "We use [Vertex AI SDK for Python](https://cloud.google.com/vertex-ai/docs/start/client-libraries#client_libraries) to create and submit training job to the Vertex AI training service."
       ]
     },
     {
@@ -1578,7 +1578,7 @@
         "id": "5d2957ef04fd"
       },
       "source": [
-        "##### **Initialize the Vertex SDK for Python**"
+        "##### **Initialize the Vertex AI SDK for Python**"
       ]
     },
     {
@@ -1598,7 +1598,7 @@
         "id": "6b0fed34b728"
       },
       "source": [
-        "##### **Configure and submit Custom Job to Vertex Training service**"
+        "##### **Configure and submit Custom Job to Vertex AI Training service**"
       ]
     },
     {
@@ -1609,7 +1609,7 @@
       "source": [
         "Configure a [Custom Job](https://cloud.google.com/vertex-ai/docs/training/create-custom-job) with the [pre-built container](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers) image for PyTorch and training code packaged as Python source distribution. \n",
         "\n",
-        "**NOTE:** When using Vertex SDK for Python for submitting a training job, it creates a [Training Pipeline](https://cloud.google.com/vertex-ai/docs/training/create-training-pipeline) which launches the Custom Job on Vertex Training service."
+        "**NOTE:** When using Vertex AI SDK for Python for submitting a training job, it creates a [Training Pipeline](https://cloud.google.com/vertex-ai/docs/training/create-training-pipeline) which launches the Custom Job on Vertex AI Training service."
       ]
     },
     {
@@ -1686,7 +1686,7 @@
         "\n",
         "You can monitor the custom job launched from Cloud Console following the link [here](https://console.cloud.google.com/vertex-ai/training/training-pipelines/) or use gcloud CLI command [`gcloud beta ai custom-jobs stream-logs`](https://cloud.google.com/sdk/gcloud/reference/beta/ai/custom-jobs/stream-logs)\n",
         "\n",
-        "![Monitor custom job progress in Vertex Training](./images/vertex-training-monitor-custom-job.png)"
+        "![Monitor custom job progress in Vertex AI Training](./images/vertex-training-monitor-custom-job.png)"
       ]
     },
     {
@@ -1798,7 +1798,7 @@
         "id": "c170d386492b"
       },
       "source": [
-        "### Run Custom Job on Vertex Training with custom container"
+        "### Run Custom Job on Vertex AI Training with custom container"
       ]
     },
     {
@@ -1807,7 +1807,7 @@
         "id": "035227b6e581"
       },
       "source": [
-        "To create a [training job with custom container](https://cloud.google.com/vertex-ai/docs/training/create-custom-container?hl=hr), you define a `Dockerfile` to install or add the dependencies required for the training job. Then, you build and test your Docker image locally to verify, push the image to Container Registry and submit a Custom Job to Vertex Training service.\n",
+        "To create a [training job with custom container](https://cloud.google.com/vertex-ai/docs/training/create-custom-container?hl=hr), you define a `Dockerfile` to install or add the dependencies required for the training job. Then, you build and test your Docker image locally to verify, push the image to Container Registry and submit a Custom Job to Vertex AI Training service.\n",
         "\n",
         "![Training with custom containers on Vertex AI](./images/training-with-custom-containers-on-vertex-training.png)"
       ]
@@ -1834,7 +1834,7 @@
         "%%writefile ./custom_container/Dockerfile\n",
         "\n",
         "# Use pytorch GPU base image\n",
-        "FROM gcr.io/cloud-aiplatform/training/pytorch-gpu.1-7\n",
+        "FROM us-docker.pkg.dev/vertex-ai/training/pytorch-gpu.1-10:latest\n",
         "\n",
         "# set working directory\n",
         "WORKDIR /app\n",
@@ -1968,7 +1968,7 @@
         "id": "a23e5e34bea9"
       },
       "source": [
-        "##### **Initialize the Vertex SDK for Python**"
+        "##### **Initialize the Vertex AI SDK for Python**"
       ]
     },
     {
@@ -1988,11 +1988,11 @@
         "id": "abf1fa4085cb"
       },
       "source": [
-        "##### **Configure and submit Custom Job to Vertex Training service**\n",
+        "##### **Configure and submit Custom Job to Vertex AI Training service**\n",
         "\n",
         "Configure a [Custom Job](https://cloud.google.com/vertex-ai/docs/training/create-custom-job) with the [custom container](https://cloud.google.com/vertex-ai/docs/training/create-custom-container) image with training code and other dependencies\n",
         "\n",
-        "**NOTE:** When using Vertex SDK for Python for submitting a training job, it creates a [Training Pipeline](https://cloud.google.com/vertex-ai/docs/training/create-training-pipeline) which launches the Custom Job to train on Vertex Training."
+        "**NOTE:** When using Vertex AI SDK for Python for submitting a training job, it creates a [Training Pipeline](https://cloud.google.com/vertex-ai/docs/training/create-training-pipeline) which launches the Custom Job to train on Vertex AI Training."
       ]
     },
     {
@@ -2044,7 +2044,7 @@
       },
       "outputs": [],
       "source": [
-        "# submit the custom job to Vertex training service\n",
+        "# submit the custom job to Vertex AI training service\n",
         "model = job.run(\n",
         "    replica_count=1,\n",
         "    machine_type=\"n1-standard-8\",\n",
@@ -2065,7 +2065,7 @@
         "\n",
         "You can monitor the custom job launched from Cloud Console following the link [here](https://console.cloud.google.com/vertex-ai/training/training-pipelines/) or use gcloud CLI command [`gcloud beta ai custom-jobs stream-logs`](https://cloud.google.com/sdk/gcloud/reference/beta/ai/custom-jobs/stream-logs)\n",
         "\n",
-        "![Monitor custom job progress in Vertex Training](./images/vertex-training-monitor-custom-job-container.png)"
+        "![Monitor custom job progress in Vertex AI Training](./images/vertex-training-monitor-custom-job-container.png)"
       ]
     },
     {
@@ -2148,11 +2148,11 @@
         "id": "ba6122f929e3"
       },
       "source": [
-        "The training application code for fine-tuning a transformer model for sentiment analysis task uses hyperparameters such as learning rate and weight decay. These hyperparameters control the behavior of the training algorithm and can have a significant effect on the performance of the resulting model. This part of the notebook show how you can automate tuning these hyperparameters with Vertex Training service.\n",
+        "The training application code for fine-tuning a transformer model for sentiment analysis task uses hyperparameters such as learning rate and weight decay. These hyperparameters control the behavior of the training algorithm and can have a significant effect on the performance of the resulting model. This part of the notebook show how you can automate tuning these hyperparameters with Vertex AI Training service.\n",
         "\n",
-        "We submit a [Hyperparameter Tuning job](https://cloud.google.com/vertex-ai/docs/training/hyperparameter-tuning-overview) to Vertex Training service by packaging the training application code and dependencies in a Docker container and push the container to Google Container Registry, similar to running a Custom Job on Vertex AI with Custom Container.\n",
+        "We submit a [Hyperparameter Tuning job](https://cloud.google.com/vertex-ai/docs/training/hyperparameter-tuning-overview) to Vertex AI Training service by packaging the training application code and dependencies in a Docker container and push the container to Google Container Registry, similar to running a Custom Job on Vertex AI with Custom Container.\n",
         "\n",
-        "![Hyperparameter Tuning with Custom Containers on Vertex Training](./images/hp-tuning-with-custom-containers-on-vertex-training.png)"
+        "![Hyperparameter Tuning with Custom Containers on Vertex AI Training](./images/hp-tuning-with-custom-containers-on-vertex-training.png)"
       ]
     },
     {
@@ -2163,7 +2163,7 @@
       "source": [
         "### How hyperparameter tuning works in Vertex AI?\n",
         "\n",
-        "Following are the high level steps involved in running a Hyperparameter Tuning job on Vertex Training service:\n",
+        "Following are the high level steps involved in running a Hyperparameter Tuning job on Vertex AI Training service:\n",
         "\n",
         "- You define the hyperparameters to tune the model along with the metric (or goal) to optimize\n",
         "- Vertex AI runs multiple trials of your training application with the hyperparameters and limits you specified - maximum number of trials to run and number of parallel trials. \n",
@@ -2297,7 +2297,7 @@
       "source": [
         "### Run Hyperparameter Tuning Job on Vertex AI\n",
         "\n",
-        "Before submitting the hyperparameter tuning job to Vertex AI, push the custom container image with training application to Google Cloud Container Registry and then submit the job to Vertex AI. We will be using the same image used for running Custom Job on Vertex Training service."
+        "Before submitting the hyperparameter tuning job to Vertex AI, push the custom container image with training application to Google Cloud Container Registry and then submit the job to Vertex AI. We will be using the same image used for running Custom Job on Vertex AI Training service."
       ]
     },
     {
@@ -2326,7 +2326,7 @@
         "id": "f60fab07d67c"
       },
       "source": [
-        "##### **Initialize the Vertex SDK for Python**"
+        "##### **Initialize the Vertex AI SDK for Python**"
       ]
     },
     {
@@ -2346,7 +2346,7 @@
         "id": "6652aa63ddff"
       },
       "source": [
-        "##### **Configure and submit Hyperparameter Tuning Job to Vertex Training service**\n",
+        "##### **Configure and submit Hyperparameter Tuning Job to Vertex AI Training service**\n",
         "\n",
         "Configure a [Hyperparameter Tuning Job](https://cloud.google.com/vertex-ai/docs/training/using-hyperparameter-tuning) with the [custom container](https://cloud.google.com/vertex-ai/docs/training/create-custom-container) image with training code and other dependencies.\n",
         "\n",
@@ -2374,7 +2374,7 @@
         "id": "9d46db3a8b23"
       },
       "source": [
-        "Define the training arguments with `hp-tune` argument set to `y` so that training application code can report metrics to Vertex"
+        "Define the training arguments with `hp-tune` argument set to `y` so that training application code can report metrics to Vertex AI"
       ]
     },
     {
@@ -2548,7 +2548,7 @@
         "\n",
         "You can monitor the hyperparameter tuning job launched from Cloud Console following the link [here](https://console.cloud.google.com/vertex-ai/training/hyperparameter-tuning-jobs/) or use gcloud CLI command [`gcloud beta ai custom-jobs stream-logs`](https://cloud.google.com/sdk/gcloud/reference/beta/ai/custom-jobs/stream-logs)\n",
         "\n",
-        "![Monitor hyperparameter tuning job progress in Vertex Training](./images/vertex-training-monitor-hptuning-job-container.png)"
+        "![Monitor hyperparameter tuning job progress in Vertex AI Training](./images/vertex-training-monitor-hptuning-job-container.png)"
       ]
     },
     {
@@ -2557,7 +2557,7 @@
         "id": "ba934b434f03"
       },
       "source": [
-        "After the job is finished, you can view and format the results of the hyperparameter tuning Trials (run by Vertex Training service) as a Pandas dataframe"
+        "After the job is finished, you can view and format the results of the hyperparameter tuning Trials (run by Vertex AI Training service) as a Pandas dataframe"
       ]
     },
     {
@@ -2612,7 +2612,7 @@
         "id": "5dbccb2b7d32"
       },
       "source": [
-        "Now from the results of Trials, you can pick the best performing Trial to deploy to Vertex Predictions"
+        "Now from the results of Trials, you can pick the best performing Trial to deploy to Vertex AI Predictions"
       ]
     },
     {
@@ -2701,8 +2701,8 @@
         "JOB_NAME=${JOB_PREFIX}-pytorch-hptune-$(date +%Y%m%d%H%M%S)\n",
         "echo \"Launching hyperparameter tuning job with display name as \"$JOB_NAME\n",
         "\n",
-        "# BUCKET_NAME: Change to your bucket name\n",
-        "BUCKET_NAME=$1 # <-- CHANGE TO YOUR BUCKET NAME\n",
+        "# BUCKET_NAME is a required parameter to run the cell.\n",
+        "BUCKET_NAME=$1\n",
         "\n",
         "# APP_NAME: get application name\n",
         "APP_NAME=$2\n",
@@ -2711,7 +2711,7 @@
         "JOB_DIR=${BUCKET_NAME}/${JOB_PREFIX}/model/${JOB_NAME}\n",
         "\n",
         "# custom container image URI\n",
-        "CUSTOM_TRAIN_IMAGE_URI=f'gcr.io/'${PROJECT_ID}'/pytorch_gpu_train_'${APP_NAME}\n",
+        "CUSTOM_TRAIN_IMAGE_URI='gcr.io/'${PROJECT_ID}'/pytorch_gpu_train_'${APP_NAME}\n",
         "\n",
         "# ========================================================\n",
         "# create hyperparameter tuning configuration file\n",
@@ -2772,20 +2772,20 @@
       "source": [
         "## Deploying\n",
         "\n",
-        "Deploying a PyTorch model on [Vertex Predictions](https://cloud.google.com/vertex-ai/docs/predictions/getting-predictions) requires to use a custom container that serves online predictions. You will deploy a container running [PyTorch's TorchServe](https://pytorch.org/serve/) tool in order to serve predictions from a fine-tuned transformer model from Hugging Face Transformers for sentiment analysis task. You can then use Vertex Predictions to classify sentiment of input texts. \n",
+        "Deploying a PyTorch model on [Vertex AI Predictions](https://cloud.google.com/vertex-ai/docs/predictions/getting-predictions) requires to use a custom container that serves online predictions. You will deploy a container running [PyTorch's TorchServe](https://pytorch.org/serve/) tool in order to serve predictions from a fine-tuned transformer model from Hugging Face Transformers for sentiment analysis task. You can then use Vertex AI Predictions to classify sentiment of input texts. \n",
         "\n",
-        "### Deploying model on Vertex Predictions with custom container\n",
+        "### Deploying model on Vertex AI Predictions with custom container\n",
         "\n",
-        "To use a custom container to serve predictions from a PyTorch model, you must provide Vertex AI with a Docker container image that runs an HTTP server, such as TorchServe in this case. Please refer to [documentation](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements) that describes the container image requirements to be compatible with Vertex Predictions.\n",
+        "To use a custom container to serve predictions from a PyTorch model, you must provide Vertex AI with a Docker container image that runs an HTTP server, such as TorchServe in this case. Please refer to [documentation](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements) that describes the container image requirements to be compatible with Vertex AI Predictions.\n",
         "\n",
-        "![Serving with Custom Containers on Vertex Predictions](./images/serve-pytorch-model-on-vertex-predictions-with-custom-containers.png)\n",
+        "![Serving with Custom Containers on Vertex AI Predictions](./images/serve-pytorch-model-on-vertex-predictions-with-custom-containers.png)\n",
         "\n",
-        "Essentially, to deploy a PyTorch model on Vertex Predictions following are the steps:\n",
+        "Essentially, to deploy a PyTorch model on Vertex AI Predictions following are the steps:\n",
         "\n",
         "1. Package the trained model artifacts including [default](https://pytorch.org/serve/#default-handlers) or [custom](https://pytorch.org/serve/custom_service.html) handlers by creating an archive file using [Torch model archiver](https://github.com/pytorch/serve/tree/master/model-archiver)\n",
-        "2. Build a [custom container](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements) compatible with Vertex Predictions to serve the model using Torchserve\n",
-        "3. Upload the model with custom container image to serve predictions as a Vertex Model resource\n",
-        "4. Create a Vertex Endpoint and [deploy the model](https://cloud.google.com/vertex-ai/docs/predictions/deploy-model-api) resource"
+        "2. Build a [custom container](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements) compatible with Vertex AI Predictions to serve the model using Torchserve\n",
+        "3. Upload the model with custom container image to serve predictions as a Vertex AI Model resource\n",
+        "4. Create a Vertex AI Endpoint and [deploy the model](https://cloud.google.com/vertex-ai/docs/predictions/deploy-model-api) resource"
       ]
     },
     {
@@ -3048,10 +3048,13 @@
         "FROM pytorch/torchserve:latest-cpu\n",
         "\n",
         "# install dependencies\n",
+        "RUN python3 -m pip install --upgrade pip\n",
         "RUN pip3 install transformers\n",
         "\n",
+        "USER model-server\n",
+        "\n",
         "# copy model artifacts, custom handler and other dependencies\n",
-        "COPY ./custom_text_handler.py /home/model-server/\n",
+        "COPY ./custom_handler.py /home/model-server/\n",
         "COPY ./index_to_name.json /home/model-server/\n",
         "COPY ./model/$APP_NAME/ /home/model-server/\n",
         "\n",
@@ -3071,7 +3074,7 @@
         "  --model-name=$APP_NAME \\\n",
         "  --version=1.0 \\\n",
         "  --serialized-file=/home/model-server/pytorch_model.bin \\\n",
-        "  --handler=/home/model-server/custom_text_handler.py \\\n",
+        "  --handler=/home/model-server/custom_handler.py \\\n",
         "  --extra-files \"/home/model-server/config.json,/home/model-server/tokenizer.json,/home/model-server/training_args.bin,/home/model-server/tokenizer_config.json,/home/model-server/special_tokens_map.json,/home/model-server/vocab.txt,/home/model-server/index_to_name.json\" \\\n",
         "  --export-path=/home/model-server/model-store\n",
         "\n",
@@ -3130,7 +3133,7 @@
       "source": [
         "#### **Run the container locally** ***[Optional]***\n",
         "\n",
-        "Before push the container image to Container Registry to use it with Vertex Predictions, you can run it as a container in your local environment to verify that the server works as expected"
+        "Before push the container image to Container Registry to use it with Vertex AI Predictions, you can run it as a container in your local environment to verify that the server works as expected"
       ]
     },
     {
@@ -3268,9 +3271,9 @@
         "id": "69477b3a00c0"
       },
       "source": [
-        "#### **Deploying the serving container to Vertex Predictions**\n",
+        "#### **Deploying the serving container to Vertex AI Predictions**\n",
         "\n",
-        "We create a model resource on Vertex AI and deploy the model to a Vertex Endpoints. You must deploy a model to an endpoint before using the model. The deployed model runs the custom container image to serve predictions. "
+        "We create a model resource on Vertex AI and deploy the model to a Vertex AI Endpoints. You must deploy a model to an endpoint before using the model. The deployed model runs the custom container image to serve predictions. "
       ]
     },
     {
@@ -3301,7 +3304,7 @@
         "id": "a3da91e19af4"
       },
       "source": [
-        "##### **Initialize the Vertex SDK for Python**"
+        "##### **Initialize the Vertex AI SDK for Python**"
       ]
     },
     {
@@ -3438,7 +3441,7 @@
         "id": "bc4673478269"
       },
       "source": [
-        "#### **Invoking the Endpoint with deployed Model using Vertex SDK to make predictions**"
+        "#### **Invoking the Endpoint with deployed Model using Vertex AI SDK to make predictions**"
       ]
     },
     {
@@ -3488,7 +3491,7 @@
       "source": [
         "##### **Formatting input for online prediction**\n",
         "\n",
-        "For online prediction requests, the prediction input instances must be formatted as JSON with base64 encoding as shown here:\n",
+        "This notebook uses [Torchserve's KServe based inference API](https://pytorch.org/serve/inference_api.html#kserve-inference-api) which is also [Vertex AI Predictions compatible format](https://cloud.google.com/vertex-ai/docs/predictions/custom-container-requirements#prediction). For online prediction requests, format the prediction input instances as JSON with base64 encoding as shown here:\n",
         "\n",
         "```\n",
         "[\n",
@@ -3561,9 +3564,9 @@
       },
       "source": [
         "##### ***[Optional]*** **Make prediction requests using gcloud CLI**\n",
-        "You can also call the Vertex Endpoint to make predictions using [`gcloud beta ai endpoints predict`](https://cloud.google.com/sdk/gcloud/reference/beta/ai/endpoints/predict). \n",
+        "You can also call the Vertex AI Endpoint to make predictions using [`gcloud beta ai endpoints predict`](https://cloud.google.com/sdk/gcloud/reference/beta/ai/endpoints/predict). \n",
         "\n",
-        "The following cell shows how to make a prediction request to Vertex Endpoints using `gcloud` CLI: "
+        "The following cell shows how to make a prediction request to Vertex AI Endpoints using `gcloud` CLI: "
       ]
     },
     {
@@ -3654,12 +3657,12 @@
       },
       "outputs": [],
       "source": [
-        "delete_custom_job = True\n",
-        "delete_hp_tuning_job = True\n",
+        "delete_custom_job = False\n",
+        "delete_hp_tuning_job = False\n",
         "delete_endpoint = True\n",
-        "delete_model = True\n",
-        "delete_bucket = True\n",
-        "delete_image = True"
+        "delete_model = False\n",
+        "delete_bucket = False\n",
+        "delete_image = False"
       ]
     },
     {
@@ -3687,7 +3690,7 @@
         "\n",
         "client_options = {\"api_endpoint\": API_ENDPOINT}\n",
         "\n",
-        "# Initialize Vertex SDK\n",
+        "# Initialize Vertex AI SDK\n",
         "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
       ]
     },

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/mlops_pipeline_tf_agents_bandits_movie_recommendation.ipynb

@@ -188,11 +188,14 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install {USER_FLAG} google-cloud-aiplatform==1.0.1\n",
-        "! pip3 install {USER_FLAG} google-cloud-pipeline-components==0.1.3\n",
+        "! pip3 install {USER_FLAG} google-cloud-aiplatform\n",
+        "! pip3 install {USER_FLAG} google-cloud-pipeline-components\n",
         "! pip3 install {USER_FLAG} --upgrade kfp\n",
-        "! pip3 install {USER_FLAG} numpy==1.20.3\n",
-        "! pip3 install {USER_FLAG} --upgrade tensorflow"
+        "! pip3 install {USER_FLAG} numpy\n",
+        "! pip3 install {USER_FLAG} --upgrade tensorflow\n",
+        "! pip3 install {USER_FLAG} --upgrade pillow\n",
+        "! pip3 install {USER_FLAG} --upgrade tf-agents\n",
+        "! pip3 install {USER_FLAG} --upgrade fastapi"
       ]
     },
     {
@@ -287,7 +290,7 @@
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output=!gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
         "    PROJECT_ID = shell_output[0]\n",
         "    print(\"Project ID: \", PROJECT_ID)"
       ]
@@ -518,6 +521,7 @@
         "import os\n",
         "import sys\n",
         "\n",
+        "from google.cloud import aiplatform\n",
         "from google_cloud_pipeline_components import aiplatform as gcc_aip\n",
         "from kfp.v2 import compiler, dsl\n",
         "from kfp.v2.google.client import AIPlatformClient"
@@ -561,13 +565,34 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "H3530hdGGilo"
+        "id": "895ac243c125"
       },
       "outputs": [],
       "source": [
         "# Dataset parameters\n",
-        "RAW_DATA_PATH = \"gs://cloud-samples-data/vertex-ai/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/u.data\"  # Location of the MovieLens 100K dataset's \"u.data\" file.\n",
-        "\n",
+        "RAW_DATA_PATH = \"gs://[your-bucket-name]/raw_data/u.data\"   # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "62bfb9a820f6"
+      },
+      "outputs": [],
+      "source": [
+        "# Download the sample data into your RAW_DATA_PATH\n",
+        "! gsutil cp \"gs://cloud-samples-data/vertex-ai/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/u.data\" $RAW_DATA_PATH"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "H3530hdGGilo"
+      },
+      "outputs": [],
+      "source": [
         "# Pipeline parameters\n",
         "PIPELINE_NAME = \"movielens-pipeline\"  # Pipeline display name.\n",
         "ENABLE_CACHING = False  # Whether to enable execution caching for the pipeline.\n",
@@ -635,7 +660,7 @@
       "source": [
         "#### Run unit tests on the Generator component\n",
         "\n",
-        "Before running the command, fill in `RAW_DATA_PATH` in [`src/generator/test_generator_component.py`](src/generator/test_generator_component.py)."
+        "Before running the command, you should update the `RAW_DATA_PATH` in [`src/generator/test_generator_component.py`](src/generator/test_generator_component.py)."
       ]
     },
     {
@@ -713,12 +738,12 @@
         "TRAINING_ARTIFACTS_DIR = (\n",
         "    f\"{BUCKET_NAME}/artifacts\"  # Root directory for training artifacts.\n",
         ")\n",
-        "TRAINING_REPLICA_COUNT = \"1\"  # Number of replica to run the custom training job.\n",
+        "TRAINING_REPLICA_COUNT = 1  # Number of replica to run the custom training job.\n",
         "TRAINING_MACHINE_TYPE = (\n",
         "    \"n1-standard-4\"  # Type of machine to run the custom training job.\n",
         ")\n",
         "TRAINING_ACCELERATOR_TYPE = \"ACCELERATOR_TYPE_UNSPECIFIED\"  # Type of accelerators to run the custom training job.\n",
-        "TRAINING_ACCELERATOR_COUNT = \"0\"  # Number of accelerators for the custom training job."
+        "TRAINING_ACCELERATOR_COUNT = 0  # Number of accelerators for the custom training job."
       ]
     },
     {
@@ -769,8 +794,12 @@
         "TRAINED_POLICY_DISPLAY_NAME = (\n",
         "    \"movielens-trained-policy\"  # Display name of the uploaded and deployed policy.\n",
         ")\n",
+        "TRAFFIC_SPLIT = {\"0\": 100}\n",
         "ENDPOINT_DISPLAY_NAME = \"movielens-endpoint\"  # Display name of the prediction endpoint.\n",
-        "ENDPOINT_MACHINE_TYPE = \"n1-standard-4\"  # Type of machine of the prediction endpoint."
+        "ENDPOINT_MACHINE_TYPE = \"n1-standard-4\"  # Type of machine of the prediction endpoint.\n",
+        "ENDPOINT_REPLICA_COUNT = 1  # Number of replicas of the prediction endpoint.\n",
+        "ENDPOINT_ACCELERATOR_TYPE = \"ACCELERATOR_TYPE_UNSPECIFIED\"  # Type of accelerators to run the custom training job.\n",
+        "ENDPOINT_ACCELERATOR_COUNT = 0  # Number of accelerators for the custom training job."
       ]
     },
     {
@@ -900,16 +929,17 @@
       },
       "outputs": [],
       "source": [
+        "from google_cloud_pipeline_components.experimental.custom_job import utils\n",
         "from kfp.components import load_component_from_url\n",
         "\n",
         "generate_op = load_component_from_url(\n",
-        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/68d6cf46ee22a9b9295d62ea71996150baf8db94/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/generator/component.yaml\"\n",
+        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/62a2a7611499490b4b04d731d48a7ba87c2d636f/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/generator/component.yaml\"\n",
         ")\n",
         "ingest_op = load_component_from_url(\n",
-        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/68d6cf46ee22a9b9295d62ea71996150baf8db94/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/ingester/component.yaml\"\n",
+        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/62a2a7611499490b4b04d731d48a7ba87c2d636f/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/ingester/component.yaml\"\n",
         ")\n",
         "train_op = load_component_from_url(\n",
-        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/68d6cf46ee22a9b9295d62ea71996150baf8db94/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/trainer/component.yaml\"\n",
+        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/62a2a7611499490b4b04d731d48a7ba87c2d636f/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/trainer/component.yaml\"\n",
         ")\n",
         "\n",
         "\n",
@@ -978,7 +1008,7 @@
         "        bigquery_location=bigquery_location,\n",
         "        bigquery_table_id=bigquery_table_id,\n",
         "    )\n",
-        "\n",
+        "    \n",
         "    # Run the Ingester component.\n",
         "    ingest_task = ingest_op(\n",
         "        project_id=project_id,\n",
@@ -988,7 +1018,16 @@
         "    )\n",
         "\n",
         "    # Run the Trainer component and submit custom job to Vertex AI.\n",
-        "    train_task = train_op(\n",
+        "    # Convert the train_op component into a Vertex AI Custom Job pre-built component\n",
+        "    custom_job_training_op = utils.create_custom_training_job_op_from_component(\n",
+        "        component_spec=train_op,\n",
+        "        replica_count=TRAINING_REPLICA_COUNT,\n",
+        "        machine_type=TRAINING_MACHINE_TYPE,\n",
+        "        accelerator_type=TRAINING_ACCELERATOR_TYPE,\n",
+        "        accelerator_count=TRAINING_ACCELERATOR_COUNT,\n",
+        "    )\n",
+        "\n",
+        "    train_task = custom_job_training_op(\n",
         "        training_artifacts_dir=training_artifacts_dir,\n",
         "        tfrecord_file=ingest_task.outputs[\"tfrecord_file\"],\n",
         "        num_epochs=num_epochs,\n",
@@ -996,28 +1035,10 @@
         "        num_actions=num_actions,\n",
         "        tikhonov_weight=tikhonov_weight,\n",
         "        agent_alpha=agent_alpha,\n",
+        "        project=PROJECT_ID,\n",
+        "        location=REGION,\n",
         "    )\n",
         "\n",
-        "    worker_pool_specs = [\n",
-        "        {\n",
-        "            \"containerSpec\": {\n",
-        "                \"imageUri\": train_task.container.image,\n",
-        "            },\n",
-        "            \"replicaCount\": TRAINING_REPLICA_COUNT,\n",
-        "            \"machineSpec\": {\n",
-        "                \"machineType\": TRAINING_MACHINE_TYPE,\n",
-        "                \"acceleratorType\": TRAINING_ACCELERATOR_TYPE,\n",
-        "                \"acceleratorCount\": TRAINING_ACCELERATOR_COUNT,\n",
-        "            },\n",
-        "        },\n",
-        "    ]\n",
-        "    train_task.custom_job_spec = {\n",
-        "        \"displayName\": train_task.name,\n",
-        "        \"jobSpec\": {\n",
-        "            \"workerPoolSpecs\": worker_pool_specs,\n",
-        "        },\n",
-        "    }\n",
-        "\n",
         "    # Run the Deployer components.\n",
         "    # Upload the trained policy as a model.\n",
         "    model_upload_op = gcc_aip.ModelUploadOp(\n",
@@ -1034,11 +1055,14 @@
         "    # Deploy the uploaded, trained policy to the created endpoint. (This operation\n",
         "    # has to occur after both model uploading and endpoint creation complete.)\n",
         "    gcc_aip.ModelDeployOp(\n",
-        "        project=project_id,\n",
         "        endpoint=endpoint_create_op.outputs[\"endpoint\"],\n",
         "        model=model_upload_op.outputs[\"model\"],\n",
         "        deployed_model_display_name=TRAINED_POLICY_DISPLAY_NAME,\n",
-        "        machine_type=ENDPOINT_MACHINE_TYPE,\n",
+        "        traffic_split=TRAFFIC_SPLIT,\n",
+        "        dedicated_resources_machine_type=ENDPOINT_MACHINE_TYPE,\n",
+        "        dedicated_resources_accelerator_type=ENDPOINT_ACCELERATOR_TYPE,\n",
+        "        dedicated_resources_accelerator_count=ENDPOINT_ACCELERATOR_COUNT,\n",
+        "        dedicated_resources_min_replica_count=ENDPOINT_REPLICA_COUNT,\n",
         "    )"
       ]
     },
@@ -1053,12 +1077,11 @@
         "# Compile the authored pipeline.\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=PIPELINE_SPEC_PATH)\n",
         "\n",
-        "# Createa Vertex AI client.\n",
-        "api_client = AIPlatformClient(project_id=PROJECT_ID, region=REGION)\n",
-        "\n",
         "# Create a pipeline run job.\n",
-        "response = api_client.create_run_from_job_spec(\n",
-        "    job_spec_path=PIPELINE_SPEC_PATH,\n",
+        "job = aiplatform.PipelineJob(\n",
+        "    display_name=f\"{PIPELINE_NAME}-startup\",\n",
+        "    template_path=PIPELINE_SPEC_PATH,\n",
+        "    pipeline_root=PIPELINE_ROOT,\n",
         "    parameter_values={\n",
         "        # Pipeline configs\n",
         "        \"project_id\": PROJECT_ID,\n",
@@ -1070,7 +1093,9 @@
         "        \"bigquery_table_id\": BIGQUERY_TABLE_ID,\n",
         "    },\n",
         "    enable_caching=ENABLE_CACHING,\n",
-        ")"
+        ")\n",
+        "\n",
+        "job.run()"
       ]
     },
     {
@@ -1111,7 +1136,11 @@
         "SIMULATOR_SCHEDULE = \"*/5 * * * *\"  # Cloud Scheduler cron job schedule for the Simulator. Eg. \"*/5 * * * *\" means every 5 mins.\n",
         "SIMULATOR_SCHEDULER_MESSAGE = (\n",
         "    \"simulator-message\"  # Cloud Scheduler message for the Simulator.\n",
-        ")"
+        ")\n",
+        "# TF-Agents RL configs\n",
+        "BATCH_SIZE = 8\n",
+        "RANK_K = 20\n",
+        "NUM_ACTIONS = 20"
       ]
     },
     {
@@ -1221,7 +1250,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoints = ! gcloud beta ai endpoints list \\\n",
+        "endpoints = ! gcloud ai endpoints list \\\n",
         "    --region=$REGION \\\n",
         "    --filter=display_name=$ENDPOINT_DISPLAY_NAME\n",
         "print(\"\\n\".join(endpoints), \"\\n\")\n",
@@ -1424,13 +1453,11 @@
       },
       "outputs": [],
       "source": [
-        "from kfp.components import load_component_from_url\n",
-        "\n",
         "ingest_op = load_component_from_url(\n",
-        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/68d6cf46ee22a9b9295d62ea71996150baf8db94/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/ingester/component.yaml\"\n",
+        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/62a2a7611499490b4b04d731d48a7ba87c2d636f/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/ingester/component.yaml\"\n",
         ")\n",
         "train_op = load_component_from_url(\n",
-        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/68d6cf46ee22a9b9295d62ea71996150baf8db94/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/trainer/component.yaml\"\n",
+        "    \"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/62a2a7611499490b4b04d731d48a7ba87c2d636f/community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/trainer/component.yaml\"\n",
         ")\n",
         "\n",
         "\n",
@@ -1481,7 +1508,16 @@
         "    )\n",
         "\n",
         "    # Run the Trainer component and submit custom job to Vertex AI.\n",
-        "    train_task = train_op(\n",
+        "    # Convert the train_op component into a Vertex AI Custom Job pre-built component\n",
+        "    custom_job_training_op = utils.create_custom_training_job_op_from_component(\n",
+        "        component_spec=train_op,\n",
+        "        replica_count=TRAINING_REPLICA_COUNT,\n",
+        "        machine_type=TRAINING_MACHINE_TYPE,\n",
+        "        accelerator_type=TRAINING_ACCELERATOR_TYPE,\n",
+        "        accelerator_count=TRAINING_ACCELERATOR_COUNT,\n",
+        "    )\n",
+        "\n",
+        "    train_task = custom_job_training_op(\n",
         "        training_artifacts_dir=training_artifacts_dir,\n",
         "        tfrecord_file=ingest_task.outputs[\"tfrecord_file\"],\n",
         "        num_epochs=num_epochs,\n",
@@ -1489,28 +1525,10 @@
         "        num_actions=num_actions,\n",
         "        tikhonov_weight=tikhonov_weight,\n",
         "        agent_alpha=agent_alpha,\n",
+        "        project=PROJECT_ID,\n",
+        "        location=REGION,\n",
         "    )\n",
         "\n",
-        "    worker_pool_specs = [\n",
-        "        {\n",
-        "            \"containerSpec\": {\n",
-        "                \"imageUri\": train_task.container.image,\n",
-        "            },\n",
-        "            \"replicaCount\": TRAINING_REPLICA_COUNT,\n",
-        "            \"machineSpec\": {\n",
-        "                \"machineType\": TRAINING_MACHINE_TYPE,\n",
-        "                \"acceleratorType\": TRAINING_ACCELERATOR_TYPE,\n",
-        "                \"acceleratorCount\": TRAINING_ACCELERATOR_COUNT,\n",
-        "            },\n",
-        "        },\n",
-        "    ]\n",
-        "    train_task.custom_job_spec = {\n",
-        "        \"displayName\": train_task.name,\n",
-        "        \"jobSpec\": {\n",
-        "            \"workerPoolSpecs\": worker_pool_specs,\n",
-        "        },\n",
-        "    }\n",
-        "\n",
         "    # Run the Deployer components.\n",
         "    # Upload the trained policy as a model.\n",
         "    model_upload_op = gcc_aip.ModelUploadOp(\n",
@@ -1527,11 +1545,13 @@
         "    # Deploy the uploaded, trained policy to the created endpoint. (This operation\n",
         "    # has to occur after both model uploading and endpoint creation complete.)\n",
         "    gcc_aip.ModelDeployOp(\n",
-        "        project=project_id,\n",
         "        endpoint=endpoint_create_op.outputs[\"endpoint\"],\n",
         "        model=model_upload_op.outputs[\"model\"],\n",
         "        deployed_model_display_name=TRAINED_POLICY_DISPLAY_NAME,\n",
-        "        machine_type=ENDPOINT_MACHINE_TYPE,\n",
+        "        dedicated_resources_machine_type=ENDPOINT_MACHINE_TYPE,\n",
+        "        dedicated_resources_accelerator_type=ENDPOINT_ACCELERATOR_TYPE,\n",
+        "        dedicated_resources_accelerator_count=ENDPOINT_ACCELERATOR_COUNT,\n",
+        "        dedicated_resources_min_replica_count=ENDPOINT_REPLICA_COUNT,\n",
         "    )"
       ]
     },

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/generator/component.yaml

@@ -39,14 +39,15 @@ outputs:
 - {name: bigquery_table_id, type: String}
 implementation:
   container:
-    image: tensorflow/tensorflow:2.5.0
+    image: python:3.7
     command:
     - sh
     - -c
     - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'google-cloud-bigquery==2.20.0' 'tensorflow==2.5.0' 'tf-agents==0.8.0' || PIP_DISABLE_PIP_VERSION_CHECK=1
-      python3 -m pip install --quiet --no-warn-script-location 'google-cloud-bigquery==2.20.0'
-      'tensorflow==2.5.0' 'tf-agents==0.8.0' --user) && "$0" "$@"
+      'google-cloud-bigquery==2.20.0' 'pillow' 'tensorflow==2.5.0' 'tf-agents==0.8.0'
+      || PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
+      'google-cloud-bigquery==2.20.0' 'pillow' 'tensorflow==2.5.0' 'tf-agents==0.8.0'
+      --user) && "$0" "$@"
     - sh
     - -ec
     - |
@@ -296,7 +297,8 @@ implementation:
 
       def _serialize_str(str_value: str) -> str:
           if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
+              raise TypeError('Value "{}" has type "{}" instead of str.'.format(
+                  str(str_value), str(type(str_value))))
           return str_value
 
       import argparse

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/ingester/component.yaml

@@ -20,7 +20,7 @@ outputs:
 - {name: tfrecord_file, type: String}
 implementation:
   container:
-    image: tensorflow/tensorflow:2.5.0
+    image: python:3.7
     command:
     - sh
     - -c
@@ -187,7 +187,8 @@ implementation:
 
       def _serialize_str(str_value: str) -> str:
           if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
+              raise TypeError('Value "{}" has type "{}" instead of str.'.format(
+                  str(str_value), str(type(str_value))))
           return str_value
 
       import argparse

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/logger/requirements.txt

@@ -1,3 +1,4 @@
 google-cloud-bigquery==2.20.0
-tensorflow==2.5.3
+tensorflow==2.7.2
+pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/prediction_container/requirements.txt

@@ -1,2 +1,4 @@
+google-cloud-pubsub==2.5.0
+pillow==9.0.1
 tf-agents==0.8.0
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/simulator/requirements.txt

@@ -0,0 +1,5 @@
+dataclasses==0.6
+google-cloud-aiplatform==1.8.1
+tensorflow==2.7.2
+pillow==9.0.1
+tf-agents==0.8.0

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/mlops_pipeline_tf_agents_bandits_movie_recommendation/src/trainer/component.yaml

@@ -27,14 +27,14 @@ outputs:
 - {name: training_artifacts_dir, type: String}
 implementation:
   container:
-    image: tensorflow/tensorflow:2.5.0
+    image: python:3.7
     command:
     - sh
     - -c
     - (PIP_DISABLE_PIP_VERSION_CHECK=1 python3 -m pip install --quiet --no-warn-script-location
-      'tensorflow==2.5.0' 'tf-agents==0.8.0' || PIP_DISABLE_PIP_VERSION_CHECK=1 python3
-      -m pip install --quiet --no-warn-script-location 'tensorflow==2.5.0' 'tf-agents==0.8.0'
-      --user) && "$0" "$@"
+      'tensorflow==2.5.0' 'tf-agents==0.8.0' 'Pillow' || PIP_DISABLE_PIP_VERSION_CHECK=1
+      python3 -m pip install --quiet --no-warn-script-location 'tensorflow==2.5.0'
+      'tf-agents==0.8.0' 'Pillow' --user) && "$0" "$@"
     - sh
     - -ec
     - |
@@ -270,7 +270,8 @@ implementation:
 
       def _serialize_str(str_value: str) -> str:
           if not isinstance(str_value, str):
-              raise TypeError('Value "{}" has type "{}" instead of str.'.format(str(str_value), str(type(str_value))))
+              raise TypeError('Value "{}" has type "{}" instead of str.'.format(
+                  str(str_value), str(type(str_value))))
           return str_value
 
       import argparse

community-content/tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk/step_by_step_sdk_tf_agents_bandits_movie_recommendation/src/tests/test_task.py

@@ -22,13 +22,13 @@ from src.training import task
 
 
 # Paths and configurations
-DATA_PATH = "gs://[your-bucket-name]/[your-dataset-dir]/u.data"  # FILL IN
+DATA_PATH = "gs://[your-bucket-name]/artifacts/u.data"  # FILL IN
 ROOT_DIR = "gs://[your-bucket-name]/artifacts"  # FILL IN
 ARTIFACTS_DIR = "gs://[your-bucket-name]/artifacts"  # FILL IN
 PROFILER_DIR = "gs://[your-bucket-name]/profiler"  # FILL IN
 HPTUNING_RESULT_DIR = "[your-hptuning-result-dir]/"  # FILL IN
 HPTUNING_RESULT_PATH = os.path.join(HPTUNING_RESULT_DIR,
-                                    "[your-file-name].json")  # FILL IN
+                                    "result.json")  # FILL IN
 RAW_BUCKET_NAME = "[your-hptuning-result-bucket-name]"  # FILL IN
 
 # Hyperparameters

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/trainer/requirements.txt

@@ -1 +1 @@
-tensorflow==2.5.3
+tensorflow==2.7.2

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/vertex_training_with_local_mode_container.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -113,8 +113,8 @@
       },
       "outputs": [],
       "source": [
-        "! gcloud beta ai custom-jobs local-run \\\n",
-        "  --base-image=$BASE_IMAGE_URI \\\n",
+        "! gcloud ai custom-jobs local-run \\\n",
+        "  --executor-image-uri=$BASE_IMAGE_URI \\\n",
         "  --script=$SCRIPT_PATH \\\n",
         "  --output-image-uri=$OUTPUT_IMAGE_NAME \\\n",
         "  -- \\\n",

notebooks/README.md

@@ -0,0 +1,5 @@
+The [official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder contains notebooks organized by Google Cloud product. These are tested weekly and maintained by Google.
+
+The [community](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/community) folder contains notebooks that may be created by Google or external contributors. They are not necessary maintained.
+
+Contributions to the repo should use the [notebook template](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb) as a starting point.

notebooks/community/CODEOWNERS

@@ -3,18 +3,24 @@
 # @global-owner1 and @global-owner2 will be requested for
 # review when someone opens a pull request.
 
-/sdk/sdk_* @aferlitsch
-/gapic @aferlitsch
-/ml_ops @aferlitsch
-/model_monitoring/* @mco
+/sdk/sdk_* @andrewferlitsch
+/gapic @andrewferlitsch
+/ml_ops @andrewferlitsch
+/model_monitoring/* @mco-gh
 /structured_data/rapid_prototyping_* @rafael-carvalho
 
-/managed_notebooks/ @notebooks-team
-/sdk/SDK_FBProphet_Forecasting_Online.ipynb			@brianchunkang
+/managed_notebooks/
+/sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
 /pipelines/google_cloud_pipeline_components_TPU_model_train_upload_deploy.ipynb @brianchunkang
-/sdk/SDK_AutoML_Forecasting_Model_Training_Example.ipynb @thehardikv
-/sdk/sdk_automl_forecasting_evaluating_a_model.ipynb @thehardikv
-/matching_engine @yinghsienwu
-/neo4j @benofben @htappen
+/explainable_ai/SDK_Custom_Container_XAI.ipynb @brianchunkang
+/matching_engine/sdk_matching_engine_for_indexing.ipynb @ivanmkc
+/matching_engine/matching_engine_for_indexing.ipynb @yinghsienwu
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
-/tensorboard @yfang1 @wattli
+/tensorboard @yfang1
+/feature_store @nayaknishant @morgandu
+/vertex_endpoints/tf_hub_obj_detection/deploy_tfhub_object_detection_on_vertex_endpoints.ipynb @entrpn
+/vertex_endpoints/nvidia-triton/nvidia-triton-custom-container-prediction.ipynb @RajeshThallam
+/vertex_endpoints/optimized_tensorflow_runtime @vlasenkoalexey
+/notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
+/notebooks/community/neo4j/graph_paysim.ipynb @benofben @laeg
+/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb @mansari

notebooks/community/managed_notebooks/chicago_taxi_fare_prediction/chicago_taxi_fare_prediction.ipynb

@@ -6,16 +6,17 @@
         "id": "c8c4e360024a"
       },
       "source": [
-        "# Taxi fare prediction using chicago taxi-cab dataset\n",
+        "# Taxi fare prediction using the Chicago Taxi Trips dataset\n",
         "\n",
         "## Table of contents\n",
+        "\n",
         "* [Overview](#section-1)\n",
         "* [Dataset](#section-2)\n",
         "* [Objective](#section-3)\n",
         "* [Costs](#section-4)\n",
         "* [Data analysis](#section-5)\n",
         "* [Fit a simple linear regression model](#section-6)\n",
-        "* [Save the model and upload to a GCS bucket](#section-7)\n",
+        "* [Save the model and upload to a Cloud Storage bucket](#section-7)\n",
         "* [Deploy the model on Vertex AI with support for Vertex Explainable AI](#section-8)\n",
         "* [Get explanations from the deployed model](#section-9)\n",
         "* [Clean up](#section-10)\n",
@@ -23,23 +24,23 @@
         "## Overview\n",
         "<a name=\"section-1\"></a>\n",
         "\n",
-        "This notebooks demonstrates analysis, feature selection, model building and deployment with Vertex Explainable AI configured on Vertex AI on a subset of the Chicago Taxi-cab dataset for Taxi-fare prediction problem.\n",
+        "This notebook demonstrates analysis, feature selection, model building, and deployment with Vertex Explainable AI configured on Vertex AI, using a subset of the Chicago Taxi Trips dataset for taxi-fare prediction.\n",
         "\n",
-        "Note: This notebook file was developed to run in a [Vertex AI Workbench managed notebooks](https://console.cloud.google.com/vertex-ai/workbench/list/managed) instance using the Python(Local) kernel. Some components of this notebook may not work in other notebook environments.\n",
+        "*Note: This notebook file was developed to run in a [Vertex AI Workbench managed notebooks](https://console.cloud.google.com/vertex-ai/workbench/list/managed) instance using the Python (Local) kernel. Some components of this notebook may not work in other notebook environments.*\n",
         "\n",
         "## Dataset\n",
         "<a name=\"section-2\"></a>\n",
         "\n",
-        "The Chicago Taxi-cab dataset includes taxi trips from 2013 to the present, reported to the City of Chicago in its role as a regulatory agency. To protect privacy but allow for aggregate analyses, the Taxi ID is consistent for any given taxi medallion number but does not show the number, Census Tracts are suppressed in some cases, and times are rounded to the nearest 15 minutes. Due to the data reporting process, not all trips are reported but the City believes that most are. This dataset is publicly available on Bigquery under the public datasets with the Table ID : `bigquery-public-data.chicago_taxi_trips.taxi_trips` and also as public dataset on Kaggle Datasets at : [Chicago Taxi Trips Dataset](https://www.kaggle.com/chicago/chicago-taxi-trips-bq).\n",
+        "The Chicago Taxi Trips dataset includes taxi trips from 2013 to the present, reported to the city of Chicago in its role as a regulatory agency. To protect privacy but allow for aggregate analyses, the taxi ID is consistent for any given taxi medallion number but does not show the number, census tracts are suppressed in some cases, and times are rounded to the nearest 15 minutes. Due to the data reporting process, not all trips are reported but the city believes that most are. This dataset is publicly available on BigQuery as a public dataset with the table ID `bigquery-public-data.chicago_taxi_trips.taxi_trips` and also as a public dataset on Kaggle at [Chicago Taxi Trips](https://www.kaggle.com/chicago/chicago-taxi-trips-bq).\n",
         "\n",
-        " For more information about this dataset and how it was created, please refer [Chicago Digital website](http://digital.cityofchicago.org/index.php/chicago-taxi-data-released).\n",
+        "For more information about this dataset and how it was created, see the [Chicago Digital website](http://digital.cityofchicago.org/index.php/chicago-taxi-data-released).\n",
         "\n",
         "## Objective\n",
         "<a name=\"section-3\"></a>\n",
         "\n",
-        "The goal of this notebook is to provide an overview on the latest Vertex AI features like Explainable AI  and Bigquery in Notebook by trying to solve a Taxi-fare prediction problem. The steps followed in this notebook include : \n",
+        "The goal of this notebook is to provide an overview on the latest Vertex AI features like Explainable AI and \"BigQuery in Notebooks\" by trying to solve a taxi fare prediction problem. The steps followed in this notebook include: \n",
         "\n",
-        "- Loading the dataset using `Bigquery in Notebooks`.\n",
+        "- Loading the dataset using \"BigQuery in Notebooks\".\n",
         "- Performing exploratory data analysis on the dataset.\n",
         "- Feature selection and preprocessing.\n",
         "- Building a linear regression model using scikit-learn.\n",
@@ -54,12 +55,12 @@
         "This tutorial uses the following billable components of Google Cloud:\n",
         "\n",
         "- Vertex AI\n",
-        "- Bigquery\n",
+        "- BigQuery\n",
         "- Cloud Storage\n",
         "\n",
         "\n",
         "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), [Bigquery pricing](https://cloud.google.com/bigquery/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and [Cloud Storage\n",
         "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
         "Calculator](https://cloud.google.com/products/calculator/)\n",
         "to generate a cost estimate based on your projected usage."
@@ -71,7 +72,9 @@
         "id": "5ed1f5e85640"
       },
       "source": [
-        "#### Set your project ID\n",
+        "## Before you begin\n",
+        "\n",
+        "### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
@@ -84,6 +87,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"\"\n",
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
@@ -120,11 +125,11 @@
         "id": "fed4b24ea061"
       },
       "source": [
-        "## Select or Create Cloud Storage Bucket for storing the model\n",
+        "## Select or create a Cloud Storage bucket for storing the model\n",
         "\n",
-        "When you create a model resource on Vertex AI using the Cloud SDK, you need to give a Cloud Storage bucket uri of the model where the model is stored. Using the model saved, you can then create Vertex AI model and endpoint resources in order to serve online predictions.\n",
+        "When you create a model resource on Vertex AI using the Cloud SDK, you need to give a Cloud Storage bucket uri of the model where the model is stored. Using the model saved, you can then create a Vertex AI model and endpoint resources in order to serve online predictions.\n",
         "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets.You may also change the REGION variable, which is used for operations throughout the rest of this notebook. Make sure to choose a region where Vertex AI services are available."
+        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets. You may also change the `LOCATION` variable, which is used for operations throughout the rest of this notebook. Make sure to choose a region where Vertex AI services are available."
       ]
     },
     {
@@ -148,7 +153,9 @@
       },
       "outputs": [],
       "source": [
-        "# Set a default bucketname in case bucket name is not given\n",
+        "from datetime import datetime\n",
+        "\n",
+        "# Set a default bucket name in case bucket name is not given\n",
         "if BUCKET_NAME == \"\" or BUCKET_NAME == \"[your-bucket-name]\" or BUCKET_NAME is None:\n",
         "\n",
         "    TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
@@ -165,15 +172,6 @@
         "<b>Only if your bucket doesn't already exist</b>: Run the following cell to create your Cloud Storage bucket."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "95702536e547"
-      },
-      "source": [
-        "## Import the required libraries and define constants"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -205,6 +203,15 @@
         "! gsutil ls -al $BUCKET_NAME"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2e52fd6d4854"
+      },
+      "source": [
+        "## Import the required libraries and define constants"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -231,12 +238,14 @@
         "id": "5166f42557ad"
       },
       "source": [
-        "The dataset is quite a large and noisy one and so data from a specific date range will be used. Based on various blogs and resources that are available online, many of them seem to have used the data from around May-2018 which gave some really good results compared to the other date ranges. While there are also some complicated research models propsed for the same problem like considering the weather data, holidays and seasons etc., the current notebook only explores a simple linear regression model as our main objective is to demonstrate the model deployment with Vertex Explainable AI configured on Vertex AI.\n",
+        "The dataset is quite a large and noisy one, so data from a specific date range will be used. Based on various blogs and resources that are available online, many of them seem to have used the data from around May 2018 which gave some really good results compared to the other date ranges. While there are also some complicated research models proposed for the same problem, like considering the weather data, holidays and seasons, the current notebook only explores a simple linear regression model, as our main objective is to demonstrate the model deployment with Vertex Explainable AI configured on Vertex AI.\n",
         "\n",
-        "## Accessing the data through Bigquery in Notebooks\n",
-        "`Bigquery in Notebooks` feature of Vertex AI's managed notebooks allows us to use Bigquery and its features from the notebook itself eliminating the need to switch between tabs everytime. For every cell in the notebook, there is an option for Bigquery integration at the top right selecting which would enable us to compose a SQL query that can be executed in Bigquery. \n",
+        "## Accessing the data through \"BigQuery in Notebooks\"\n",
+        "\n",
+        "The \"BigQuery in Notebooks\" feature of Vertex AI Workbench managed notebooks lets you use BigQuery and its features from the notebook itself eliminating the need to switch between tabs everytime. For every cell in the notebook, there is an option for the BigQuery integration at the top right, and selecting it enables you to compose an SQL query that can be executed in BigQuery. \n",
+        "\n",
+        "The chosen dataset consists of the following fields:\n",
         "\n",
-        "The chosen dataset consists of the following fields :\n",
         "- `unique_key` : Unique identifier for the trip.\n",
         "- `taxi_id` : A unique identifier for the taxi.\n",
         "- `trip_start_timestamp`: When the trip started, rounded to the nearest 15 minutes.\n",
@@ -261,12 +270,12 @@
         "- `dropoff_longitude`: The longitude of the center of the dropoff census tract or the community area if the census tract has been hidden for privacy.\n",
         "- `dropoff_location`: The location of the center of the dropoff census tract or the community area if the census tract has been hidden for privacy.\n",
         "\n",
-        "Among the available fields in the dataset, only the fields that seem common and relevant for analysis and modeling like `taxi_id`, `trip_start_timestamp`, `trip_seconds`, `trip_miles`, `payment_type` and `trip_total` are selected. Further, the field `trip_total` is treated as the target variable that would be predicted by the machine learning model. Apparently, this field is a summation of `fare`,`tips`,`tolls` and `extras` fields and so because of their correlation with the target variable, they are being excluded for modeling. Due to the volume of the data, a subset of the dataset over the course of one week i.e., 12-May-2018 to 18-May-2018 is being considered. Within this date range itself, the datapoints can be noisy and so a few conditions like the following are considered : \n",
+        "Among the available fields in the dataset, only the fields that seem common and relevant for analysis and modeling like `taxi_id`, `trip_start_timestamp`, `trip_seconds`, `trip_miles`, `payment_type` and `trip_total` are selected. Further, the field `trip_total` is treated as the target variable that would be predicted by the machine learning model. Apparently, this field is a summation of the `fare`,`tips`,`tolls` and `extras` fields and so because of their correlation with the target variable, they are being excluded for modeling. Due to the volume of the data, a subset of the dataset over the course of one week, 12-May-2018 to 18-May-2018 is being considered. Within this date range itself, the datapoints can be noisy and so a few conditions like the following are considered: \n",
         "\n",
         "- Time taken for the trip > 0.\n",
         "- Distance covered during the trip > 0.\n",
         "- Total trip charges > 0 and\n",
-        "- Pickup and dropoff areas are valid(not empty)."
+        "- Pickup and dropoff areas are valid (not empty)."
       ]
     },
     {
@@ -301,7 +310,7 @@
         "id": "781341730c28"
       },
       "source": [
-        "The Bigquery integration also allows us to load the queried data into a pandas dataframe using the `Query and load as DataFrame` button. Clicking the button adds a new cell below that provides a code snippet to load the data into a dataframe."
+        "The BigQuery integration also lets you load the queried data into a pandas dataframe using the `Query and load as DataFrame` button. Clicking the button adds a new cell below that provides a code snippet to load the data into a dataframe."
       ]
     },
     {
@@ -343,7 +352,7 @@
         "id": "96d61011e159"
       },
       "source": [
-        "Check the fields in the data and the shape."
+        "Check the fields in the data and their shape."
       ]
     },
     {
@@ -426,7 +435,7 @@
         "id": "f0feadc628e4"
       },
       "source": [
-        "Depending on the percentage of null values in the data, one can choose to either drop them or impute them with mean/median(for numerical values) and mode(for categorical values). In the current data, there doesn't seem to be any null values."
+        "Depending on the percentage of null values in the data, one can choose to either drop them or impute them with mean/median (for numerical values) and mode (for categorical values). In the current data, there doesn't seem to be any null values."
       ]
     },
     {
@@ -480,7 +489,7 @@
         "## Analyze numerical data\n",
         "<a name=\"section-5\"></a>\n",
         "\n",
-        "To further anaylyze the data, there are various plots that can be used on numerical and categorical fields. In case of numerical data, one can use histograms and box-plots while bar charts are suited for categorical data to better understand the distribution of the data and the outliers in the data."
+        "To further anaylyze the data, there are various plots that can be used on numerical and categorical fields. In case of numerical data, one can use histograms and box plots while bar charts are suited for categorical data to better understand the distribution of the data and the outliers in the data."
       ]
     },
     {
@@ -489,7 +498,7 @@
         "id": "fa2d6258b509"
       },
       "source": [
-        "Plot Histograms and Box-plots on the numerical fields."
+        "Plot histograms and box plots on the numerical fields."
       ]
     },
     {
@@ -515,7 +524,7 @@
         "id": "c3672976d67b"
       },
       "source": [
-        "The field `trip_seconds` describes the time taken for the trip in seconds. Optionally, it can be converted into hours for an easier understanding."
+        "The field `trip_seconds` describes the time taken for the trip in seconds. Optionally, it can be converted into hours."
       ]
     },
     {
@@ -557,7 +566,7 @@
         "id": "58d57879aa8a"
       },
       "source": [
-        "So far we've only considered to look at the univariate plots. To better understand the relationship between the variables, a pair-plot can be plotted."
+        "So far you've only looked at the univariate plots. To better understand the relationship between the variables, a pair-plot can be plotted."
       ]
     },
     {
@@ -580,7 +589,7 @@
         "id": "b69e8094ba39"
       },
       "source": [
-        "From the box-plots and the histograms plotted so far, it is evident that there are some outliers causing skewness in the data which perhaps could be removed. Also, we can certainly see some linear relationship between the independent variables considered in the pair-plot i.e., `trip_seconds` and `trip_miles` and the dependant variable `trip_total`."
+        "From the box plots and the histograms visualized so far, it is evident that there are some outliers causing skewness in the data which perhaps could be removed. Also, you can see some linear relationships between the independent variables considered in the pair-plot, for example, `trip_seconds` and `trip_miles` and the dependant variable `trip_total`."
       ]
     },
     {
@@ -627,7 +636,7 @@
         "id": "341b581e2155"
       },
       "source": [
-        "## Analyze Categorical data\n",
+        "## Analyze categorical data\n",
         "\n",
         "Further, explore the categorical data by plotting the distribution of all the levels in each field."
       ]
@@ -653,9 +662,9 @@
         "id": "a40a4b2d9d6a"
       },
       "source": [
-        "From the above analysis, one can see that almost 99% of the transaction types are Cash and Credit Card. While there are also other type of transactions, their distribution is very less. In such a case, the lower distribution levels can be dropped. On the other hand, total number of pickup and dropoff community areas both seem to have the same levels which make sense. In this case also, one can choose to omit the lower distribution levels but it has to be made sure that both the fields have the same levels afterwards. In the current notebook, we'd keep them as is and proceed with the modeling.\n",
+        "From the above analysis, one can see that almost 99% of the transaction types are Cash and Credit Card. While there are also other type of transactions, their distribution is negligible. In such a case, the lower distribution levels can be dropped. On the other hand, the total number of pickup and dropoff community areas both seem to have the same levels which make sense. In this case also, one can choose to omit the lower distribution levels but you'd have to make sure that both the fields have the same levels afterward. In the current notebook, keep them as is and proceed with the modeling.\n",
         "\n",
-        "The relationships between the target variable and the categorical fields can be represented through boxplots. For each level, the corresponding distribution of the target variable can be identified."
+        "The relationships between the target variable and the categorical fields can be represented through box plots. For each level, the corresponding distribution of the target variable can be identified."
       ]
     },
     {
@@ -680,7 +689,7 @@
         "id": "f49125a8a866"
       },
       "source": [
-        "There seems to be one case where the `trip_total` is over 3000 and has the same pickup and dropoff community area i.e., 28 which is clearly an outlier compared to the rest of the points. This datapoint can be removed."
+        "There seems to be one case where the `trip_total` is over 3000 and has the same pickup and dropoff community area: 28 is clearly an outlier compared to the rest of the points. This datapoint can be removed."
       ]
     },
     {
@@ -725,7 +734,7 @@
         "id": "58a1d9f0a122"
       },
       "source": [
-        "There are also timestamp fields in the data that can prove to be useful. `trip_start_timestamp` represents the start timestamp of the taxi-trip and fields like what day of week it was and what hour it was can be dervied from it."
+        "There are also useful timestamp fields in the data. `trip_start_timestamp` represents the start timestamp of the taxi trip and fields like what day of week it was and what hour it was can be derived from it."
       ]
     },
     {
@@ -747,7 +756,7 @@
         "id": "30ae02a15aa1"
       },
       "source": [
-        "Since the current dataset is considered only for a week, if there isn't much variation in the newly dervied fields with respect to the target variable, they can be dropped.\n",
+        "Since the current dataset is limited to only a week, if there isn't much variation in the newly derived fields with respect to the target variable, they can be dropped.\n",
         "\n",
         "Plot sum and average of the `trip_total` with respect to the `dayofweek`."
       ]
@@ -804,9 +813,9 @@
         "id": "739e985af704"
       },
       "source": [
-        "As these plots don't seem to have constant figures with respect to the target variable across their levels, they can be considered for training. In fact, to simplify things these dervied features can be bucketed into less number of levels.\n",
+        "As these plots don't seem to have constant figures with respect to the target variable across their levels, they can be considered for training. In fact, to simplify things these derived features can be bucketed into fewer levels.\n",
         "\n",
-        "`dayofweek` field can be bucketed into a binary field considering whether or not it was a weekend. If it is a weekday, the record can be assigned 1, else 0. Similarly, `hour` field can also be bucketed and encoded. The normal working hours in Chicago can be assumed to be between *8AM*-*10PM* and if the value falls in between the working hours, it can be encoded as 1, else 0."
+        "The `dayofweek` field can be bucketed into a binary field considering whether or not it was a weekend. If it is a weekday, the record can be assigned 1, else 0. Similarly, the `hour` field can also be bucketed and encoded. The normal working hours in Chicago can be assumed to be between *8AM*-*10PM* and if the value falls in between the working hours, it can be encoded as 1, else 0."
       ]
     },
     {
@@ -848,7 +857,7 @@
         "id": "fe87612faa94"
       },
       "source": [
-        "## Divide the data in Train and Test sets\n",
+        "## Divide the data into train and test sets\n",
         "\n",
         "Split the preprocessed dataset into train and test sets so that the linear regression model can be validated on the test set."
       ]
@@ -887,10 +896,10 @@
         "id": "5b7e470de1da"
       },
       "source": [
-        "## Fit a Simple Linear Regression model\n",
+        "## Fit a simple linear regression model\n",
         "<a name=\"section-6\"></a>\n",
         "\n",
-        "Fit a linear regression model using Sklearn's LinearRegression method on the train data."
+        "Fit a linear regression model using scikit-learn's LinearRegression method on the train data."
       ]
     },
     {
@@ -940,7 +949,7 @@
         "id": "2ef6b44f0f93"
       },
       "source": [
-        "A low RMSE error and a train and test R2 score of 0.93 suggests that the model has fitted well on the data. Further, the coefficients learned by the model for each of its independent variables can also be checked by checking the `coef_` attribute of the sklearn model. \n",
+        "A low RMSE error and a train and test R2 score of 0.93 suggests that the model is fitted well. Further, the coefficients learned by the model for each of its independent variables can also be checked by checking the `coef_` attribute of the sklearn model. \n",
         "\n",
         "Check the coefficients learned by the model."
       ]
@@ -963,7 +972,7 @@
         "id": "bcaed0b52e60"
       },
       "source": [
-        "## Save the model and upload to a GCS bucket.\n",
+        "## Save the model and upload to a Cloud Storage bucket\n",
         "<a name=\"section-7\"></a>\n",
         "\n",
         "To deploy the model on Vertex AI, the model needs to be stored in a Cloud Storage bucket first."
@@ -999,10 +1008,10 @@
         "id": "9f8ecfa6a19b"
       },
       "source": [
-        "## Deploy the Model on Vertex AI with support for Vertex Explainable AI\n",
+        "## Deploy the model on Vertex AI with support for Vertex Explainable AI\n",
         "<a name=\"section-8\"></a>\n",
         "\n",
-        "Configure the Vertex Explainable AI before deploying the model. For further details, see [Configuring Vertex Explainable AI in Vertex AI models](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations#scikit-learn-and-xgboost-pre-built-containers)."
+        "Configure Vertex Explainable AI before deploying the model. For further details, see [Configuring Vertex Explainable AI in Vertex AI models](https://cloud.google.com/vertex-ai/docs/explainable-ai/configuring-explanations#scikit-learn-and-xgboost-pre-built-containers)."
       ]
     },
     {
@@ -1114,7 +1123,7 @@
         "id": "9eaab1c54d66"
       },
       "source": [
-        "Deploy the model to the created endpoint with the required machine-type."
+        "Deploy the model to the created endpoint with the required machine type."
       ]
     },
     {
@@ -1167,7 +1176,7 @@
         "id": "b751978ff665"
       },
       "source": [
-        "## Get explanations from the deployed model.\n",
+        "## Get explanations from the deployed model\n",
         "<a name=\"section-9\"></a>\n",
         "\n",
         "For testing the deployed online model, select two instances from the test data as payload."
@@ -1191,7 +1200,7 @@
         "id": "01532047a99e"
       },
       "source": [
-        "Call the endpoint with the payload request and parse the response for explanations. The explanations consists of attributions on the independent variables used for training the model which are based on the configured attribution method. In this case, we've used the `Sampled Shapely` method which assigns credit for the outcome to each feature, and considers different permutations of the features. This method provides a sampling approximation of exact Shapley values. Further information on the attribution methods for explantions can be found at [Overview of ExplainableAI](https://cloud.google.com/vertex-ai/docs/explainable-ai/overview) page."
+        "Call the endpoint with the payload request and parse the response for explanations. The explanations consists of attributions on the independent variables used for training the model which are based on the configured attribution method. In this case, we've used the `Sampled Shapely` method which assigns credit for the outcome to each feature, and considers different permutations of the features. This method provides a sampling approximation of exact Shapely values. Further information on the attribution methods for explanations can be found at [Overview of Explainable AI](https://cloud.google.com/vertex-ai/docs/explainable-ai/overview)."
       ]
     },
     {
@@ -1266,9 +1275,9 @@
         "id": "87cf259efb64"
       },
       "source": [
-        "## Next Steps\n",
+        "## Next steps\n",
         "\n",
-        "Since the Chicago-Taxicab dataset is continuously updating, one can preform the same kind of analysis and model training every time a new set of data is available. The date range can also be increased from a week to a month or more depending on the quality of data. Most of the steps followed in this notebook would still be valid and can be applied over the new data unless the data is too noisy. Perhaps, the notebook itself can be scheduled to run at the specified times to retrain the model using the scheduling option of the [Vertex AI workbench's Executor](https://console.cloud.google.com/vertex-ai/workbench/list/executions) feature. "
+        "Since the Chicago Taxi Trips dataset is continuously updating, one can preform the same kind of analysis and model training every time a new set of data is available. The date range can also be increased from a week to a month or more depending on the quality of the data. Most of the steps followed in this notebook would still be valid and can be applied over the new data unless the data is too noisy. Perhaps, the notebook itself can be scheduled to run at the specified times to retrain the model using the scheduling option of [Vertex AI Workbench's executor](https://console.cloud.google.com/vertex-ai/workbench/list/executions). "
       ]
     },
     {
@@ -1277,7 +1286,7 @@
         "id": "eae8d94e3641"
       },
       "source": [
-        "## Clean Up\n",
+        "## Clean up\n",
         "<a name=\"section-10\"></a>\n",
         "\n",
         "Delete the resources created in this notebook.\n",

notebooks/community/managed_notebooks/inventory-prediction/inventory_prediction.ipynb

@@ -2,7 +2,6 @@
   "cells": [
     {
       "cell_type": "markdown",
-      "id": "ed3b25b1-ce38-4930-97d7-3346165d8d4e",
       "metadata": {
         "id": "12cb1b47a1b7"
       },
@@ -10,64 +9,61 @@
         "# Inventory prediction on ecommerce data using Vertex AI\n",
         "\n",
         "## Table of contents\n",
+        "\n",
         "* [Overview](#section-1)\n",
         "* [Dataset](#section-2)\n",
         "* [Objective](#section-3)\n",
         "* [Costs](#section-4)\n",
         "* [Load the required data from BigQuery](#section-5)\n",
-        "* [Explore and Analyze the dataset](#section-6)\n",
-        "* [Feature Preprocessing](#section-7)\n",
+        "* [Explore and analyze the dataset](#section-6)\n",
+        "* [Feature preprocessing](#section-7)\n",
         "* [Model building](#section-8) \n",
-        "\t* [Train the model](#section-9)\n",
-        "\t*[Evaluate the model](#section-10)\n",
+        "  * [Train the model](#section-9)\n",
+        "  * [Evaluate the model](#section-10)\n",
         "* [Save the model to a Cloud Storage bucket](#section-11) \n",
         "* [Create a model in Vertex AI](#section-12) \n",
-        "* [Create an Endpoint](#section-13) \n",
-        "* [Deploy the model to the created Endpoint](#section-14)\n",
+        "* [Create an endpoint](#section-13) \n",
+        "* [Deploy the model to the created endpoint](#section-14)\n",
         "* [What-If Tool](#section-15) \n",
         "* [Clean up](#section-16) \n",
         "\n",
-        "    \n",
-        "    \n",
-        "    \n",
-        "\n",
-        "\n",
         "## Overview\n",
         "<a name=\"section-1\"></a>\n",
         "\n",
-        "This notebook explores how one can build a machine-learning model for *Inventory prediction* on an e-commerce dataset. Further, there are also steps included in this notebook to deploy the model on Vertex AI using the Vertex AI sdk and analyze the deployed model using the [What-If tool](https://pair-code.github.io/what-if-tool/).\n",
+        "This notebook explores how to build a machine learning model for inventory prediction on an ecommerce dataset. This notebook includes steps for deploying the model on Vertex AI using the Vertex AI SDK and analyzing the deployed model using the [What-If Tool](https://pair-code.github.io/what-if-tool/).\n",
         "\n",
-        "*Note:* This notebook file was designed to run in a Vertex AI Workbench managed notebooks instance using the TensorFlow 2 (Local) kernel. Some components of this notebook may not work in other notebook environments.\n",
+        "*Note: This notebook file was designed to run in a Vertex AI Workbench managed notebooks instance using the TensorFlow 2 (Local) kernel. Some components of this notebook may not work in other notebook environments.*\n",
         "\n",
         "## Dataset\n",
         "<a name=\"section-2\"></a>\n",
         "\n",
-        "The dataset used in this notebook consists of inventory data since 2018 for an online ecommerce store. This dataset is publicly available at `looker-private-demo.ecomm.inventory_items` BigQuery table which can be accessed by pinning the `looker-private-demo` project in BigQuery. The table consists of various fields related to each of the inventory items like the item's `id`,`product_id`, price, when it came to the inventory, when it has been sold etc. Among these fields, the current notebook makes use of the following fields assuming their purpose is as described below :\n",
+        "The dataset used in this notebook consists of inventory data since 2018 for an ecommerce store. This dataset is publicly available as a BigQuery table named `looker-private-demo.ecomm.inventory_items`, which can be accessed by pinning the `looker-private-demo` project in BigQuery. The table consists of various fields related to ecommerce inventory items such as `id`, `product_id`, `cost`, when the item arrived at the store, and when it was sold. This notebook makes use of the following fields assuming their purpose is as described below:\n",
         "\n",
-        "- `id`: The Id of the inventory item.\n",
-        "- `product_id`: The Id of the product.\n",
-        "- `created_at`: When the item has arrived at the inventory/store.\n",
-        "- `sold_at`: When the item was sold(*Null if still unsold*).\n",
-        "- `cost`: Cost at which the item was sold.\n",
-        "- `product_category`: Category of the product.\n",
-        "- `product_brand`: Brand of the product (dropped later as there are too many values).\n",
-        "- `product_retail_price`: Price of of the product.\n",
-        "- `product_department`: Department to which the product belongs to.\n",
-        "- `product_distribution_center_id`: Which distribution center(probably region) the product is being sold from.\n",
+        "- `id`: The ID of the inventory item\n",
+        "- `product_id`: The ID of the product\n",
+        "- `created_at`: When the item arrived in the inventory/at the store\n",
+        "- `sold_at`: When the item was sold (*Null if still unsold*)\n",
+        "- `cost`: Cost at which the item was sold\n",
+        "- `product_category`: Category of the product\n",
+        "- `product_brand`: Brand of the product (dropped later as there are too many values)\n",
+        "- `product_retail_price`: Price of the product\n",
+        "- `product_department`: Department to which the product belonged to\n",
+        "- `product_distribution_center_id`: Which distribution center (an approximation of regions) the product was sold from\n",
         "\n",
-        "The dataset can be found encoded already to hide any private information of the store. For example, the distribution centers have been assigned ids ranging from 1-10.\n",
+        "The dataset is encoded to hide any private information. For example, the distribution centers have been assigned ID numbers ranging from 1 to 10.\n",
         "\n",
         "## Objectives\n",
         "<a name=\"section-3\"></a>\n",
         "\n",
-        "The objectvies of this notebook includes :\n",
-        "* Load the dataset from BigQuery using *Bigquery In Notebooks* integration.\n",
+        "The objectives of this notebook include:\n",
+        "\n",
+        "* Load the dataset from BigQuery using the \"BigQuery in Notebooks\" integration.\n",
         "* Analyze the dataset.\n",
         "* Preprocess the features in the dataset.\n",
-        "* Build a RandomForest Classifier model that predicts if a product will get sold in the next 60 days.\n",
+        "* Build a random forest classifier model that predicts whether a product will get sold in the next 60 days.\n",
         "* Evaluate the model.\n",
         "* Deploy the model using Vertex AI.\n",
-        "* Configure and test the What-If tool.\n",
+        "* Configure and test the What-If Tool.\n",
         "\n",
         "## Costs\n",
         "<a name=\"section-4\"></a>\n",
@@ -75,30 +71,33 @@
         "This tutorial uses the following billable components of Google Cloud:\n",
         "\n",
         "- Vertex AI\n",
-        "- Bigquery\n",
+        "- BigQuery\n",
         "- Cloud Storage\n",
         "\n",
         "\n",
         "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), [Bigquery pricing](https://cloud.google.com/bigquery/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and [Cloud Storage\n",
         "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
         "Calculator](https://cloud.google.com/products/calculator/)\n",
         "to generate a cost estimate based on your projected usage.\n",
         "\n",
         "## Before you begin\n",
+        "\n",
         "### Set your project ID\n",
+        "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "ddb2d6ba-3028-458c-8afd-eb72ea1530d7",
       "metadata": {
         "id": "4be1250b19cf"
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"\"\n",
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
@@ -110,7 +109,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "b008e8ae-ae48-4933-89f4-65cb96983c4c",
       "metadata": {
         "id": "7aa7d44eefc3"
       },
@@ -121,7 +119,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "6f26b5fa-828b-4104-8b9e-b2728dac30e5",
       "metadata": {
         "id": "81351cf1ced9"
       },
@@ -133,7 +130,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "66b70318-b75e-4f8d-9fd3-10521adeeee0",
       "metadata": {
         "id": "a47045884647"
       },
@@ -145,7 +141,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "e90c1e94-79ac-4aba-8589-d6348181937a",
       "metadata": {
         "id": "2171869c7cef"
       },
@@ -158,7 +153,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "fecaa4fb-c8a3-4538-9112-9875c99e4353",
       "metadata": {
         "id": "15d91ce9a98e"
       },
@@ -176,7 +170,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "d2db85b7-050f-4ac8-8548-01c493c7c985",
       "metadata": {
         "id": "814a9c014e16"
       },
@@ -190,7 +183,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "b2a5ab69-b45e-45f5-aeea-433782e889f4",
       "metadata": {
         "id": "ce71cab23cda"
       },
@@ -204,7 +196,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "ee5bd777-6b5c-4433-a671-026e6db7aaa1",
       "metadata": {
         "id": "aa6e246297be"
       },
@@ -215,7 +206,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "0d744577-19fb-4a7c-a84d-9cf787ffe98a",
       "metadata": {
         "id": "a0cc49ab6e69"
       },
@@ -226,7 +216,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "bd137de6-ea0c-4ac6-b192-a896885205a5",
       "metadata": {
         "id": "df4ee328db14"
       },
@@ -237,7 +226,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "d5611c3b-2f10-45eb-b457-6cfa1306b86e",
       "metadata": {
         "id": "637ea7607c58"
       },
@@ -248,7 +236,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d7c1aeea-6411-4d2e-9e98-3a95c6dba963",
       "metadata": {
         "id": "9c1d4f460b09"
       },
@@ -260,7 +247,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "31a9ce5d-699c-4aac-9b9a-098048a7c22f",
       "metadata": {
         "id": "a36a786f4538"
       },
@@ -283,7 +269,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "2350fd00-96d3-46c8-9bdd-63ace0dce921",
       "metadata": {
         "id": "34f2b9e8bc9a"
       },
@@ -291,15 +276,13 @@
         "### Load the required data from BigQuery\n",
         "<a name=\"section-5\"></a>\n",
         "\n",
-        "The following cell integrates with BigQuery from the same project through the Vertex AI's *BigQuery In Notebooks* feature. It can run a SQL query similarly as it would run in the BigQuery console. \n",
+        "The following cell integrates with BigQuery data from the same project through the Vertex AI's \"BigQuery in Notebooks\" integration. It can run an SQL query as it would run in the BigQuery console. \n",
         "\n",
-        "\n",
-        "*Note:* This feature would only work in a notebook on Vertex AI Workbench's managed-notebook instances."
+        "*Note:* This feature only works in a notebook running on a Vertex AI Workbench managed-notebook instance."
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "57e10d7f-a5a8-46f6-a45d-818ffd66acb2",
       "metadata": {
         "id": "13863517f8c8"
       },
@@ -322,7 +305,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d59fa3c1-d412-4bf6-9ebd-c80a86a1c6ce",
       "metadata": {
         "id": "50ed21be5ab7"
       },
@@ -333,7 +315,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a62782c2-9b17-44c3-84a1-480978c846fd",
       "metadata": {
         "id": "e89e5832338a"
       },
@@ -362,7 +343,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a1d50372-b5ad-4123-85ae-8284bfeab903",
       "metadata": {
         "id": "4f9fc651fa8e"
       },
@@ -376,7 +356,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "0b44ba3b-ade9-445e-bf91-5b03ca596966",
       "metadata": {
         "id": "da9f53ab3559"
       },
@@ -387,18 +366,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "df2ec583-1122-47d2-bf2a-f6c0d5ba201f",
       "metadata": {
         "id": "5aa703b3f070"
       },
       "source": [
-        "Check the fields in the dataset and their data-types and number of null values."
+        "Check the fields in the dataset and their data types and number of null values."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "0296df18-5a86-4a0f-8c58-7e3997d31d3f",
       "metadata": {
         "id": "b00164626bad"
       },
@@ -409,20 +386,18 @@
     },
     {
       "cell_type": "markdown",
-      "id": "c019a7ea-aa2f-4f66-a9b8-01ea185e5ddd",
       "metadata": {
         "id": "730f6c2954f5"
       },
       "source": [
-        "We can notice that apart from the `sold_at` datetime field, there aren't any fields that consist of null values in the dataset. As we are dealing with the inventory-item data, it is absolutely plausible that there will be some items that haven't been sold yet and hence the null values.\n",
+        "Apart from the `sold_at` datetime field, there aren't any fields that consist of null values in the dataset. As you are dealing with the inventory-item data, it is absolutely plausible that there will be some items that haven't been sold yet and hence the null values.\n",
         "\n",
-        "Further, we convert the date fields to a proper date format to process them in the next steps."
+        "Next, convert the date fields to a proper date format to process them in the next steps."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "16a9d896-43d7-4594-80bc-7da5eaa6cd67",
       "metadata": {
         "id": "1ff70c9450ee"
       },
@@ -435,7 +410,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "c46034da-2024-4e24-a4e3-d2339e70ff9a",
       "metadata": {
         "id": "50fc83a65c71"
       },
@@ -446,7 +420,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "b911c489-5118-47ff-8b14-a2c26cabdc23",
       "metadata": {
         "id": "db6ac4523678"
       },
@@ -462,18 +435,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "6a2e850f-9590-4cb2-a6f5-8b4c918e1137",
       "metadata": {
         "id": "c8ec80d03032"
       },
       "source": [
-        "Extract month from the date field `created_at`."
+        "Extract the month from the date field `created_at`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "5d44f325-35bd-4840-a8fd-33ce0b17f4cf",
       "metadata": {
         "id": "2694255a5bf2"
       },
@@ -485,7 +456,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "760efdbb-3db6-48aa-8d32-58f21a477491",
       "metadata": {
         "id": "5d9a610a5c10"
       },
@@ -496,7 +466,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "e2decd13-e171-4ca5-8f5e-3f4da0fe092b",
       "metadata": {
         "id": "5d4df4604949"
       },
@@ -508,18 +477,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "567c2ac3-1066-4e4d-aa3b-4ce81c066e3a",
       "metadata": {
         "id": "d276e789a9a1"
       },
       "source": [
-        "Calculate the discount-percentages that apply to the products."
+        "Calculate the discount percentages that apply to the products."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "5d681d9e-ead2-4b49-bac4-7abba52c7d39",
       "metadata": {
         "id": "c143c79dc7d1"
       },
@@ -533,7 +500,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a5ff14a1-cfdd-4623-aec7-5dc4eadb64cb",
       "metadata": {
         "id": "d5d9ce9bb19b"
       },
@@ -544,7 +510,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "b325a469-8dae-4963-bccb-8ab24fe729d5",
       "metadata": {
         "id": "ac2e5ca3912e"
       },
@@ -556,12 +521,11 @@
     },
     {
       "cell_type": "markdown",
-      "id": "2ca6d78d-7ffb-4ef5-b3cb-aa95d1788323",
       "metadata": {
         "id": "e667cd5fbb35"
       },
       "source": [
-        "The fields `product_id` and `product_brand` seem to have a lot of unique values. For the purpose of prediction, we will use `product_id` as the primary-key and `product_brand` is dropped as it has too many values/levels. \n",
+        "The fields `product_id` and `product_brand` seem to have a lot of unique values. For the purpose of prediction, use `product_id` as the primary-key and `product_brand` is dropped as it has too many values/levels. \n",
         "\n",
         "Segregate the required numerical and categorical fields to analyze the dataset."
       ]
@@ -569,7 +533,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "273f8d73-d09d-4b30-8898-35bfdd8b7d9e",
       "metadata": {
         "id": "042f5cd1ff2e"
       },
@@ -586,7 +549,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "8774598c-ab9a-4812-9377-333d816f7555",
       "metadata": {
         "id": "6fa0a2d8b5ca"
       },
@@ -597,7 +559,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cb985ca5-dafb-4447-aa9f-d0555bb114f5",
       "metadata": {
         "id": "16da0524b2ed"
       },
@@ -609,18 +570,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "b2ed531e-957c-4a64-a794-fa4461af220d",
       "metadata": {
         "id": "268ed7b88e23"
       },
       "source": [
-        "Check the distribution of the numerial fields."
+        "Check the distribution of the numerical fields."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c4901cc0-1d13-418b-a309-0f0c0477055f",
       "metadata": {
         "id": "bf50a707aa90"
       },
@@ -631,18 +590,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "91e5c972-5d9c-48ca-a922-bac76fcd0db2",
       "metadata": {
         "id": "8888f572c8d1"
       },
       "source": [
-        "Generate bar-plots for categorical fields and histograms and box-plots for numerical fields to check their distributions in the dataset."
+        "Generate bar plots for categorical fields and histograms and box plots for numerical fields to check their distributions in the dataset."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "2dbf4d3f-9528-4802-a385-dbe0783fd99c",
       "metadata": {
         "id": "112fe37b915f"
       },
@@ -664,25 +621,23 @@
     },
     {
       "cell_type": "markdown",
-      "id": "f39269f2-15b1-451b-b9c1-9fdb150e60e3",
       "metadata": {
         "id": "0250e32de345"
       },
       "source": [
-        "Most of the fields like discount, department, distribution center-id have a decent dsitribution. For the field `product_category`, there are some categories that don't constitute 2% of the dataset at least. Although there are  outliers noticed for some numerical fields, they are exempted from removing as there can be products that are expensive or belonging to a particular category that doesn't often see many sales. \n",
+        "Most of the fields like discount, department, distribution center-id have a decent distribution. For the field `product_category`, there are some categories that don't constitute 2% of the dataset at least. Although there are outliers in some numerical fields, they are exempted from removing as there can be products that are expensive or belonging to a particular category that doesn't often see many sales. \n",
         "\n",
         "## Feature preprocessing\n",
         "<a name=\"section-7\"></a>\n",
         "\n",
-        "Next, we aggregate the data based on suitable categorical fields in the data and take the average of number of days it took for the product to get sold. For a given `product_id`, there can be multiple item `id`s in this dataset and we want to predict at the product level if that particular product is going to be sold in the next couple of months or not. More accurately describing, we are aggregating the data based on each of the product configurations present in this dataset like the price, cost, category and at which center it is being sold. This way the model can predict *whether a product with so and so properties is going to be sold in the next couple of months or not*.\n",
+        "Next, aggregate the data based on suitable categorical fields in the data and take the average number of days it took for the product to get sold. For a given `product_id`, there can be multiple item `id`'s in this dataset and you want to predict at the product level whether that particular product is going to be sold in the next couple of months. You are aggregating the data based on each of the product configurations present in this dataset like the price, cost, category and at which center it is being sold. This way the model can predict *whether a product with so and so properties is going to be sold in the next couple of months*.\n",
         "\n",
-        "For the number of days a product got sold in, we will find the average of the `shelf_days` field."
+        "For the number of days a product got sold in, find the average of the `shelf_days` field."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "93f19503-3077-402c-93a6-54e3a3c8ff7a",
       "metadata": {
         "id": "8daf9985aa23"
       },
@@ -706,7 +661,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "7fb93904-bf61-4c77-84a7-d99952f21d2e",
       "metadata": {
         "id": "fbaf4c3f5a83"
       },
@@ -717,7 +671,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "97e4208c-7f69-4b95-99c9-c72a2aca6e6b",
       "metadata": {
         "id": "74afffc4380a"
       },
@@ -728,7 +681,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "07d57144-c0ba-4d66-aac3-13b983df81e3",
       "metadata": {
         "id": "c9aafbab9c88"
       },
@@ -739,7 +691,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "aa06a557-cb3d-4b92-b80e-c5af02d6ae69",
       "metadata": {
         "id": "26523245c145"
       },
@@ -750,20 +701,18 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d7b9a807-c72f-49f2-8811-61af54ea4ef9",
       "metadata": {
         "id": "bafab84172e7"
       },
       "source": [
-        "Only the `shelf_days` field has null values that correspond to the `product_id`s that have no sold items. \n",
+        "Only the `shelf_days` field has null values that correspond to the `product_id`'s that have no sold items. \n",
         "\n",
-        "Plot the distribution of the aggregated `shelf_days` field by generating a box-plot."
+        "Plot the distribution of the aggregated `shelf_days` field by generating a box plot."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a206e6eb-3d36-4db4-8e0d-58158174d041",
       "metadata": {
         "id": "efe00052e1fd"
       },
@@ -774,21 +723,19 @@
     },
     {
       "cell_type": "markdown",
-      "id": "2227dad0-9472-4ed8-9f38-25ed77f67de1",
       "metadata": {
         "id": "8acaa01b21bd"
       },
       "source": [
-        "Here, we can see that most of the products are sold within 60 days since they've arrived in the inventory/store. For this tutorial, we will train a machine-learning model that predicts the probability of a product being sold in 60 days.\n",
+        "Here, you can see that most of the products are sold within 60 days since they've arrived in the inventory/store. In this tutorial, you will train a machine learning model that predicts the probability of a product being sold within 60 days.\n",
         "\n",
         "### Encode the categorical fields\n",
-        "Encode the the `shelf_days` field to generate the target field `sold_in_2mnt` indicitating if the product was sold in 60 days or not."
+        "Encode the the `shelf_days` field to generate the target field `sold_in_2mnt` indicating whether the product was sold in 60 days."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "7dbe2b11-bb27-4138-a959-36d8a6b07ccf",
       "metadata": {
         "id": "383915875d38"
       },
@@ -802,7 +749,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "6893a836-f036-4433-bfbf-f3c1859c69e6",
       "metadata": {
         "id": "4dd380c38579"
       },
@@ -813,7 +759,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cdc4e307-ae39-4a17-b03e-fbd241fb71dc",
       "metadata": {
         "id": "40d373151be5"
       },
@@ -831,7 +776,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "89d3d4b7-a47b-4a46-9ce8-da521df8d014",
       "metadata": {
         "id": "87ce893f2d45"
       },
@@ -842,7 +786,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "315e495a-8ad5-4503-8c47-ffcf0d65efea",
       "metadata": {
         "id": "bd68935d2a12"
       },
@@ -855,7 +798,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a35c5134-05d3-492d-a45d-bac0eae97987",
       "metadata": {
         "id": "6d23387828fd"
       },
@@ -866,7 +808,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a8a9755a-221c-43a5-a62b-5a305247bc53",
       "metadata": {
         "id": "8bbdbfa3a4cf"
       },
@@ -883,7 +824,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a3047754-24d2-4baf-9f78-b3fd7352b8fa",
       "metadata": {
         "id": "f8c85be588b4"
       },
@@ -896,7 +836,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c5356cb6-db25-40ed-b0f8-76e8a7a5c7b5",
       "metadata": {
         "id": "0790352a2ce9"
       },
@@ -911,7 +850,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "f5e9da54-53e7-4bab-835f-2e3546c29c25",
       "metadata": {
         "id": "86e444ca1e02"
       },
@@ -928,7 +866,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "30b93d6f-0abd-467b-9f28-37a92a853c7e",
       "metadata": {
         "id": "360ab6634571"
       },
@@ -954,7 +891,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a3e69f75-eabf-4ce3-b8ab-c38cbc04b78a",
       "metadata": {
         "id": "500051a07ae8"
       },
@@ -965,7 +901,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "6088da78-16be-4ed0-8b45-e06ca8054290",
       "metadata": {
         "id": "44ab347a30da"
       },
@@ -980,7 +915,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "fe69185f-ea51-4f07-a73c-458bf89bdc6d",
       "metadata": {
         "id": "c29820548054"
       },
@@ -991,7 +925,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cbd1ed9b-9bc4-46f8-b036-38a57e55bf63",
       "metadata": {
         "id": "5b88ca090e82"
       },
@@ -1003,7 +936,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "1b2aaab8-db9e-4dd0-91c9-e285231b6c0b",
       "metadata": {
         "id": "ef4e662be2c3"
       },
@@ -1018,7 +950,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "79121b25-13af-4a53-9929-b3b87c689a0e",
       "metadata": {
         "id": "22f02b56dfb4"
       },
@@ -1033,7 +964,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "417935ae-d48d-4deb-9a04-fa4d5ee25e72",
       "metadata": {
         "id": "6f8bd1bc40c8"
       },
@@ -1044,7 +974,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "12717f8f-71d6-4cff-b15c-00e52c13636f",
       "metadata": {
         "id": "c6f38583e47b"
       },
@@ -1060,12 +989,11 @@
     },
     {
       "cell_type": "markdown",
-      "id": "78efc529-9ff3-4506-a280-cd220434037d",
       "metadata": {
         "id": "e5be657cf605"
       },
       "source": [
-        "The model performance can be stated in terms of specificity(True-negative rate) and sensitivity(True-postivie rate). In the normalized confusion matrix, the top left value represents the True-negative rate and the bottom right value represents the True-positive rate.\n",
+        "The model performance can be stated in terms of specificity (True-negative rate) and sensitivity (True-positive rate). In the normalized confusion matrix, the top left value represents the True-negative rate and the bottom right value represents the True-positive rate.\n",
         "\n",
         "## Save the model to a Cloud Storage bucket\n",
         "<a name=\"section-11\"></a>\n",
@@ -1076,7 +1004,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "ef7d10f4-57e0-4763-805d-cb6d5d5c7168",
       "metadata": {
         "id": "f133a2b37e72"
       },
@@ -1098,7 +1025,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "696e17b0-9267-4fcd-b86a-a2267a153ef1",
       "metadata": {
         "id": "870deb700dbe"
       },
@@ -1112,7 +1038,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "159002c4-2929-49ca-8a94-107956cda0e0",
       "metadata": {
         "id": "abba6fb0e95e"
       },
@@ -1124,7 +1049,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "bdcbc8a2-488e-47b8-a7c1-d3ac95ddda93",
       "metadata": {
         "id": "abdf27ad5868"
       },
@@ -1135,7 +1059,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "0e599258-ad35-427d-abe7-91db89bd8f8f",
       "metadata": {
         "id": "7f5056eebe27"
       },
@@ -1159,7 +1082,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "bbc7ec92-1d4b-456a-bdfc-75b90c1bc328",
       "metadata": {
         "id": "b79b95b76f04"
       },
@@ -1173,7 +1095,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "7f255545-cca7-4dc1-8354-5bd960b376cd",
       "metadata": {
         "id": "3772df492ba8"
       },
@@ -1184,7 +1105,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "76cc86d8-3800-46ac-bb73-abd8d62dc1ec",
       "metadata": {
         "id": "7a7a33af9232"
       },
@@ -1195,7 +1115,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "ff43e472-4396-40e7-8515-cbc909894768",
       "metadata": {
         "id": "de9b0b9098f9"
       },
@@ -1209,7 +1128,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "35f1fc9b-138c-4e0c-a6b0-5a6efad3eab2",
       "metadata": {
         "id": "8013ca32c1a3"
       },
@@ -1223,7 +1141,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "7f9a595e-ceec-4c63-b419-dace7227362d",
       "metadata": {
         "id": "f70de6008667"
       },
@@ -1235,7 +1152,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "add5fb0f-d1cb-472f-be85-c7c2659c6f2a",
       "metadata": {
         "id": "9a20c48a5cc9"
       },
@@ -1246,7 +1162,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "70d28a77-1cbc-4d9d-b431-c4c7a2c8773c",
       "metadata": {
         "id": "7739e77d3a4a"
       },
@@ -1267,7 +1182,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "f43e82b0-676c-419d-ba6f-8c49451bfa8a",
       "metadata": {
         "id": "0566b8cbd2e8"
       },
@@ -1278,7 +1192,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "fa572fbf-07bf-484e-bb9b-bb8e87ca9c97",
       "metadata": {
         "id": "2c1f8add7fcb"
       },
@@ -1289,7 +1202,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "fc83f210-3b53-478f-a5f2-016927b43fd6",
       "metadata": {
         "id": "75cbc77cbcd9"
       },
@@ -1297,7 +1209,7 @@
         "## What-If Tool\n",
         "<a name=\"section-15\"></a>\n",
         "\n",
-        "The What-If Tool can be used to analyze the model predictions on test data. See a brief introduction to the [What-If Tool](https://pair-code.github.io/what-if-tool/get-started/). In this tutorial, the What-If Tool will be configured and run on the model deployed on Vertex AI Endpoints in the previous steps.\n",
+        "The What-If Tool can be used to analyze the model predictions on test data. See a brief introduction to the [What-If Tool](https://pair-code.github.io/what-if-tool/get-started/). In this tutorial, the What-If Tool is configured and run on the model deployed on Vertex AI Endpoints in the previous steps.\n",
         "\n",
         "WitConfigBuilder provides the set_ai_platform_model() method to configure the What-If Tool with a model deployed as a version on Ai Platform models. This feature currently supports only Ai Platform but not Vertex AI models. Fortunately, there is also an option to pass a custom function for generating predictions through the set_custom_predict_fn() method where either the locally trained model or a function that returns predictions from a Vertex AI model can be passed.\n",
         "\n",
@@ -1308,7 +1220,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a82618cf-1570-443d-a13b-0b27fc2c6d32",
       "metadata": {
         "id": "81839e084a9e"
       },
@@ -1324,7 +1235,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "4890b3d7-efb8-4a4d-8fa8-0d2f55af29e5",
       "metadata": {
         "id": "8974bf829a5f"
       },
@@ -1337,7 +1247,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "ecd0a712-a15a-4a45-8818-f1ab9d39baef",
       "metadata": {
         "id": "1cf06d79a585"
       },
@@ -1375,14 +1284,13 @@
     },
     {
       "cell_type": "markdown",
-      "id": "53cab026-5022-44b2-a055-bf654a47e12d",
       "metadata": {
         "id": "6638bb7caaeb"
       },
       "source": [
         "### Understanding the What-If tool\n",
         "\n",
-        "In the **Datapoint editor** tab, you can highlight a dot in the result set and ask the What If tool to pick the \"nearest counterfactual\". This is a row of data closest to the row of data you selected but with the opposite outcome. Features in the left-hand table are editable and can show what tweaks are needed to get a particular row of data to flip from one outcome to another. For example, altering the *discount_percentage* feature would show how it impacts the prediction. \n",
+        "In the **Datapoint editor** tab, you can highlight a dot in the result set and ask the What-If Tool to pick the \"nearest counterfactual\". This is a row of data closest to the row of data you selected but with the opposite outcome. Features in the left-hand table are editable and can show what tweaks are needed to get a particular row of data to flip from one outcome to another. For example, altering the *discount_percentage* feature would show how it impacts the prediction. \n",
         "\n",
         "<img src=\"images/Datapoint_editor.png\">\n",
         "\n",
@@ -1390,14 +1298,13 @@
         "\n",
         "<img src=\"images/Performance_and_fairness.png\">\n",
         "\n",
-        "The **Features** tab in the end provides you an intuitive and interactive way to understand the features present in the data. Similar to the exploratory data analysis steps performed in this notebook, What-If tool provides a visual and statistical description on the features.\n",
+        "The **Features** tab in the end provides you an intuitive and interactive way to understand the features present in the data. Similar to the exploratory data analysis steps performed in this notebook, the What-If Tool provides a visual and statistical description on the features.\n",
         "\n",
         "<img src=\"images/features.PNG\">"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "a8a49790-0167-428c-8c00-d16d255832ee",
       "metadata": {
         "id": "d17d23fab0b1"
       },
@@ -1415,7 +1322,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "ce29713a-ae90-4c2b-9bb6-34b9893e4e51",
       "metadata": {
         "id": "ff1d9ce89db8"
       },
@@ -1426,7 +1332,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "e227459d-d1ca-4952-8e21-4e7439743f6e",
       "metadata": {
         "id": "e741829407b5"
       },
@@ -1437,7 +1342,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a5a4a2eb-23ac-4389-ab55-c6a5eac33341",
       "metadata": {
         "id": "c9675acf4eab"
       },
@@ -1448,7 +1352,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "cb80d62e-a34d-4841-a2ce-f07817f2c111",
       "metadata": {
         "id": "c2034b17325e"
       },
@@ -1459,7 +1362,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "e5c65d7d-230a-4108-b0b3-da0182bcb1b5",
       "metadata": {
         "id": "5adff8193eae"
       },
@@ -1470,7 +1372,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "88ea4b9b-062c-4b41-8e5a-bd570011d3c5",
       "metadata": {
         "id": "7bfcf86db9ca"
       },
@@ -1481,7 +1382,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "fca19ad7-35fa-45f3-b47e-fff2eb03e5a2",
       "metadata": {
         "id": "f68de1489758"
       },

notebooks/community/managed_notebooks/predictive_maintainance/predictive_maintenance_usecase.ipynb

@@ -7,49 +7,53 @@
       },
       "source": [
         "# Predictive Maintenance \n",
+        "\n",
         "## Table of contents\n",
         "* [Overview](#section-1)\n",
         "* [Dataset](#section-2)\n",
         "* [Objective](#section-3)\n",
         "* [Costs](#section-4)\n",
-        "* [Data Analysis](#section-5)\n",
-        "* [Fit a Regression model](#section-6)\n",
+        "* [Data analysis](#section-5)\n",
+        "* [Fit a regression model](#section-6)\n",
         "* [Evaluate the trained model](#section-7)\n",
         "* [Save the model](#section-8)\n",
-        "* [Running a notebook end-to-end using **Executor**](#section-9)\n",
+        "* [Running a notebook end-to-end using the executor](#section-9)\n",
         "* [Hosting the model on Vertex AI](#section-10)\n",
-        "   * [Create an Endpoint](#section-11)\n",
-        "   * [Deploy the model to the created Endpoint](#section-12)\n",
-        "   * [Test calling the endpoint](#section-13)\n",
+        "  * [Create an endpoint](#section-11)\n",
+        "  * [Deploy the model to the created endpoint](#section-12)\n",
+        "  * [Test calling the endpoint](#section-13)\n",
         "* [Clean up](#section-14)\n",
         "\n",
         "\n",
         "## Overview\n",
         "<a name=\"section-1\"></a>\n",
-        "This notebook demonstrates performing predictive maintenance on industrial data using machine learning techniques, deploying the machine learning model on Vertex-AI and automating the workflow using executor feature of Vertex-AI.\n",
         "\n",
-        "<b>Note</b>: This notebook is designed to run on managed notebooks instance of Vertex AI Workbench. Some components of this notebook may not work in other notebook environments.\n",
+        "This notebook demonstrates how to perform predictive maintenance on industrial data using machine learning techniques, deploy the machine learning model on Vertex AI, and automate the workflow using the executor feature of Vertex AI Workbench.\n",
+        "\n",
+        "*Note: This notebook file was developed to run in a [Vertex AI Workbench managed notebooks](https://console.cloud.google.com/vertex-ai/workbench/list/managed) instance using the XGBoost (Local) kernel. Some components of this notebook may not work in other notebook environments.*\n",
         "\n",
         "## Dataset\n",
         "<a name=\"section-2\"></a>\n",
-        "The dataset used in this notebook is a part of the [NASA Turbofan Engine Degradation Dataset](https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/) which consists of simulated time-series data for four sets of fleet-engines under different combinations of operational conditions and fault modes. In this notebook, only one of the engine's simulated data(FD001) has been considered to analyze and train a model that can predict the engine's remaining useful life.\n",
         "\n",
-        "## Objective\n",
+        "The dataset used in this notebook is a part of the [NASA Turbofan Engine Degradation Simulation dataset](https://ti.arc.nasa.gov/tech/dash/groups/pcoe/prognostic-data-repository/), which consists of simulated time-series data for four sets of fleet engines under different combinations of operational conditions and fault modes. In this notebook, only one of the engine's simulated data (FD001) has been used to analyze and train a model that can predict the engine's remaining useful life.\n",
+        "\n",
+        "## Objectives\n",
         "<a name=\"section-3\"></a>\n",
-        "In this notebook :\n",
         "\n",
-        "- Loading the required dataset from Cloud Storage bucket.\n",
+        "The objectives of this notebook include:\n",
+        "\n",
+        "- Loading the required dataset from a Cloud Storage bucket.\n",
         "- Analyzing the fields present in the dataset.\n",
         "- Selecting the required data for the predictive maintenance model.\n",
         "- Training an XGBoost regression model for predicting the remaining useful life.\n",
         "- Evaluating the model.\n",
         "- Running the notebook end-to-end as a training job using Executor.\n",
-        "- Deploying the model on Vertex-AI.\n",
+        "- Deploying the model on Vertex AI.\n",
         "- Clean up.\n",
         "\n",
-        "\n",
         "## Costs\n",
         "<a name=\"section-4\"></a>\n",
+        "\n",
         "This tutorial uses the following billable components of Google Cloud:\n",
         "\n",
         "- Vertex AI\n",
@@ -68,8 +72,10 @@
         "id": "5b15a97278df"
       },
       "source": [
-        "## Kernel selection\n",
-        "Select <b>XGBoost</b> kernel while running this notebook on Vertex-AIs managed instances or ensure that the following libraries are installed in the environment where this notebook is being run.\n",
+        "## Before you begin\n",
+        "\n",
+        "### Kernel selection\n",
+        "Select <b>XGBoost</b> kernel while running this notebook on Vertex AI Workbench managed notebooks instances or ensure that the following libraries are installed in the environment where this notebook is being run.\n",
         "- XGBoost\n",
         "- Pandas\n",
         "- Seaborn\n",
@@ -80,7 +86,9 @@
         "- google.cloud.aiplatform\n",
         "- google.cloud.storage\n",
         "\n",
-        "## Set your project ID"
+        "### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
@@ -91,7 +99,36 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\""
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\"\n",
+        "\n",
+        "# Get your Google Cloud project ID from gcloud\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "750bf2883c2d"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3c6db1ca88b9"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -124,11 +161,11 @@
         "id": "ea53caa30628"
       },
       "source": [
-        "## Select or Create Cloud Storage Bucket for storing the model\n",
+        "## Select or Create a Cloud Storage Bucket for storing the model\n",
         "\n",
         "When you create a model resource on Vertex AI using the Cloud SDK, you need to give a Cloud Storage bucket URI of the model where the model is stored. Using the model saved, you can then create Vertex AI model and endpoint resources in order to serve online predictions.\n",
         "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets.You may also change the REGION variable, which is used for operations throughout the rest of this notebook. Make sure to choose a region where Vertex AI services are available."
+        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets. You may also change the `REGION` variable, which is used for operations throughout the rest of this notebook. Make sure to choose a region where Vertex AI services are available."
       ]
     },
     {
@@ -263,7 +300,7 @@
         "id": "8cfc304d35b5"
       },
       "source": [
-        "The data itself doesn't contain any feature names and thus needs its columns to be re-named. The data source already provides us with some data description. Apparently, the <b>ID</b> column represents the unit-number of the fleet-engine and <b>Cycle</b> represents the time in cycles. <b>OpSet1</b>,<b>Opset2</b> & <b>Opset3</b> represent the three operational settings that are described in the original data source and have a substantial effect on engine performance. The rest of the fields show sensor readings collected from 21 different sensors."
+        "The data itself doesn't contain any feature names and thus needs its columns to be renamed. The data source already provides some data description. Apparently, the <b>ID</b> column represents the unit-number of the fleet-engine and <b>Cycle</b> represents the time in cycles. <b>OpSet1</b>,<b>Opset2</b> & <b>Opset3</b> represent the three operational settings that are described in the original data source and have a substantial effect on engine performance. The rest of the fields show sensor readings collected from 21 different sensors."
       ]
     },
     {
@@ -336,7 +373,7 @@
         "id": "43c3f01352ad"
       },
       "source": [
-        "On an average, there seems to be around 225 cycles per each ID in the dataset. Further, lets check the data-types of the fields and the number of null records in the data."
+        "On an average, there seem to be around 225 cycles per each ID in the dataset. Next, lets check the data types of the fields and the number of null records in the data."
       ]
     },
     {
@@ -418,7 +455,7 @@
         "id": "284debdf4294"
       },
       "source": [
-        "Fields **SensorMeasure7**, **SensorMeasure12**, **SensorMeasure20** & **SensorMeasure21** correlate highly with many other fields. These fields can be omitted. Further, **SensorMeasure8**, **SensorMeasure11** and **SensorMeasure4** seem highly correlated with each other and so any one of them, say **SensorMeasure4** can be kept and the rest can be omitted."
+        "Fields **SensorMeasure7**, **SensorMeasure12**, **SensorMeasure20** & **SensorMeasure21** correlate highly with many other fields. These fields can be omitted. Further, **SensorMeasure8**, **SensorMeasure11** and **SensorMeasure4** seem highly correlated with each other and so any one of them, for example, **SensorMeasure4**, can be kept and the rest can be omitted."
       ]
     },
     {
@@ -455,7 +492,7 @@
         "id": "8197cdef2cff"
       },
       "source": [
-        "As the current objective is to predict the remaining useful life(RUL) of each unit(ID), the target variable needs to be identified. Since we're dealing with a timeseries data that represents the lifetime of a unit, remaining useful life of a unit can be calculated by subtracting the current cycle from the maximum cycle of that unit.\n",
+        "As the current objective is to predict the remaining useful life (RUL) of each unit (ID), the target variable needs to be identified. Since we're dealing with a timeseries data that represents the lifetime of a unit, remaining useful life of a unit can be calculated by subtracting the current cycle from the maximum cycle of that unit.\n",
         "\n",
         "\t\t\t\t\tRUL = Max. Cycle - Current Cycle    \n",
         "## RUL calculation and Feature selection"
@@ -518,7 +555,7 @@
         "id": "fc3b82355cdc"
       },
       "source": [
-        "The above plot suggests that the RUL i.e., the remaining cycles is decreasing as the current cycle increases which is expected. Further, lets see the how the other fields relate to RUL in the current dataset."
+        "The above plot suggests that the RUL, in other words, the remaining cycles, is decreasing as the current cycle increases which is expected. Further, lets see the how the other fields relate to RUL in the current dataset."
       ]
     },
     {
@@ -557,7 +594,7 @@
         "- Fields **SensorMeasure5** and **SensorMeasure16** don't show much variance with the RUL and seem constant all the time. Hence, they can be removed.\n",
         "- Fields **SensorMeasure2**, **SensorMeasure3**, **SensorMeasure4**, **SensorMeasure13**, **SensorMeasure15** & **SensorMeasure17** show a similar rising trend.\n",
         "- **SensorMeasure9** and **SensorMeasure14** show a similar trend.\n",
-        "- **SensorMeasure6** shows flatline most of the time except at a very few places and therefore can be ignored."
+        "- **SensorMeasure6** shows a flatline most of the time except in a very few places and therefore can be ignored."
       ]
     },
     {
@@ -583,7 +620,7 @@
         "id": "cae198bd96ef"
       },
       "source": [
-        "## Split the data into Train and Test\n",
+        "## Split the data into train and test\n",
         "\n",
         "Divide the dataset with the selected features into train and test sets."
       ]
@@ -613,9 +650,10 @@
         "id": "43a26d74c687"
       },
       "source": [
-        "## Fit a Regression model\n",
+        "## Fit a regression model\n",
         "<a name=\"section-6\"></a>\n",
-        "Initialize and train a regression model using XGBoost library with the calculated RUL as the target feature."
+        "\n",
+        "Initialize and train a regression model using the XGBoost library with the calculated RUL as the target feature."
       ]
     },
     {
@@ -769,23 +807,25 @@
         "id": "4bd88d7f4bbb"
       },
       "source": [
-        "## Running a notebook end-to-end using **Executor**\n",
+        "## Running a notebook end-to-end using executor\n",
         "<a name=\"section-9\"></a>\n",
         "\n",
         "### Automating the notebook execution\n",
-        "All the steps followed till now can be run as a training job without using any additional code using the Notebook executor. Notebook executor can help you run a notebook file from start to end, with your choice of the environment, machine type, input parameters, and other characteristics. After setting up an execution, the notebook is executed as a job in Vertex AI custom training. Your jobs can be monitored from the Notebook Executor pane in the menu on the left.\n",
+        "All the steps followed until now can be run as a training job without using any additional code using the Vertex AI Workbench executor. The executor can help you run a notebook file from start to end, with your choice of the environment, machine type, input parameters, and other characteristics. After setting up an execution, the notebook is executed as a job in Vertex AI custom training. Your jobs can be monitored from the Executor pane in the left sidebar.\n",
         "\n",
         "<img src=\"images/executor.PNG\">\n",
         "\n",
-        "Executor also lets you choose the environment and machine type while automating the runs similar to Vertex AI training jobs without switching to the training jobs UI. Apart from the custom container that replicates the existing kernel by default, pre-built environments like TensorFlow Enterprise, PyTorch, and others can also be selected to run the notebook. Furthermore the required compute power can be specified by choosing from the list of machine types available, including GPUs.\n",
+        "The executor also lets you choose the environment and machine type while automating the runs similar to Vertex AI training jobs without switching to the training jobs UI. Apart from the custom container that replicates the existing kernel by default, pre-built environments like TensorFlow Enterprise, PyTorch, and others can also be selected to run the notebook. The required compute power can be specified by choosing from the list of machine types available, including GPUs.\n",
         "\n",
         "## Scheduled runs on executor\n",
+        "\n",
         "Notebook runs can also be scheduled recurringly with the executor. To do so, select Schedule-based recurring executions as the run type instead of One-time execution. The frequency of the job and the time when it executes is provided when you create the execution.\n",
         "\n",
         "<img src=\"https://storage.googleapis.com/gweb-cloudblog-publish/images/7_Vertex_AI_Workbench.max-1100x1100.jpg\">\n",
         "\n",
         "## Parameterizing the variables\n",
-        "Executor lets you run a notebook with different sets of input parameters.If you’ve added parameter tags to any of your notebook cells, you can pass in your parameter values to the executor. More about how to use this feature can be found on this [blog](https://cloud.google.com/blog/products/ai-machine-learning/schedule-and-execute-notebooks-with-vertex-ai-workbench).\n",
+        "\n",
+        "The executor lets you run a notebook with different sets of input parameters. If you’ve added parameter tags to any of your notebook cells, you can pass in your parameter values to the executor. More about how to use this feature can be found on this [blog](https://cloud.google.com/blog/products/ai-machine-learning/schedule-and-execute-notebooks-with-vertex-ai-workbench).\n",
         "\n",
         "<img src=\"https://storage.googleapis.com/gweb-cloudblog-publish/images/6_Vertex_AI_Workbench.max-700x700.jpg\">\n"
       ]
@@ -944,7 +984,7 @@
         "## Clean up\n",
         "<a name=\"section-14\"></a>\n",
         "\n",
-        "Undeploy the model from endpoint."
+        "Undeploy the model from the endpoint."
       ]
     },
     {
@@ -1022,7 +1062,7 @@
   ],
   "metadata": {
     "colab": {
-      "name": "Predictive_maintenance_usecase.ipynb",
+      "name": "predictive_maintenance_usecase.ipynb",
       "toc_visible": true
     },
     "kernelspec": {

notebooks/community/managed_notebooks/pricing_optimization/pricing-optimization.ipynb

@@ -14,48 +14,50 @@
         "* [Costs](#section-4)\n",
         "* [Create a BigQuery dataset](#section-5)\n",
         "* [Load the dataset from Cloud Storage](#section-6)\n",
-        "* [Data Analysis](#section-7)\n",
+        "* [Data analysis](#section-7)\n",
         "* [Preprocess the data for training](#section-8)\n",
         "* [Train the model using BigQuery ML](#section-9)\n",
         "* [Generate forecasts from the model](#section-10)\n",
         "* [Interpret the results to choose the best price](#section-11)\n",
-        "* [Clean Up](#section-12)\n",
-        "\n",
+        "* [Clean up](#section-12)\n",
         "\n",
         "## Overview\n",
         "<a name=\"section-1\"></a>\n",
-        "This notebook demonstrates analysis of pricing optimization on [CDM Pricing Data](https://github.com/trifacta/trifacta-google-cloud/tree/main/design-pattern-pricing-optimization) and automating the workflow using Vertex AI Workbench's managed notebooks.\n",
         "\n",
-        "<b>Note</b>: This notebook is designed to run on managed notebooks instance of Vertex AI Workbench. Some components of this notebook may not work in other notebook environments.\n",
+        "This notebook demonstrates analysis of pricing optimization on [CDM Pricing Data](https://github.com/trifacta/trifacta-google-cloud/tree/main/design-pattern-pricing-optimization) and automating the workflow using Vertex AI Workbench managed notebooks.\n",
+        "\n",
+        "*Note: This notebook file was developed to run in a [Vertex AI Workbench managed notebooks](https://console.cloud.google.com/vertex-ai/workbench/list/managed) instance using the Python (Local) kernel. Some components of this notebook may not work in other notebook environments.*\n",
         "\n",
         "## Dataset\n",
         "<a name=\"section-2\"></a>\n",
-        "The dataset used in this notebook is a part of the [CDM Pricing Data](https://github.com/trifacta/trifacta-google-cloud/blob/main/design-pattern-pricing-optimization/CDM_Pricing_large_table.csv) which consists of products sales information on specified dates.\n",
+        "\n",
+        "The dataset used in this notebook is a part of the [CDM Pricing dataset](https://github.com/trifacta/trifacta-google-cloud/blob/main/design-pattern-pricing-optimization/CDM_Pricing_large_table.csv), which consists of product sales information on specified dates.\n",
         "\n",
         "## Objective\n",
         "<a name=\"section-3\"></a>\n",
-        "The objective of this notebook is to build a pricing optimization model using Vertex AI on GCP. The following steps have been followed in this usecase :  \n",
+        "\n",
+        "The objective of this notebook is to build a pricing optimization model using Vertex AI. The following steps have been followed:  \n",
         "\n",
         "- Load the required dataset from a Cloud Storage bucket.\n",
         "- Analyze the fields present in the dataset.\n",
         "- Process the data to build a model.\n",
         "- Build a BigQuery ML forecast model on the processed data.\n",
         "- Get forecasted values from the BigQuery ML model.\n",
-        "- Interpret the forecasts to identify best prices.\n",
+        "- Interpret the forecasts to identify the best prices.\n",
         "- Clean up.\n",
         "\n",
-        "\n",
         "## Costs\n",
         "<a name=\"section-4\"></a>\n",
+        "\n",
         "This tutorial uses the following billable components of Google Cloud:\n",
         "\n",
         "- Vertex AI\n",
-        "- Bigquery\n",
+        "- BigQuery\n",
         "- Cloud Storage\n",
         "\n",
         "\n",
         "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), [Bigquery pricing](https://cloud.google.com/bigquery/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and [Cloud Storage\n",
         "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
         "Calculator](https://cloud.google.com/products/calculator/)\n",
         "to generate a cost estimate based on your projected usage.\n"
@@ -67,7 +69,9 @@
         "id": "5ed1f5e85640"
       },
       "source": [
-        "#### Set your project ID\n",
+        "## Before you begin\n",
+        "\n",
+        "### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
@@ -144,8 +148,8 @@
       },
       "outputs": [],
       "source": [
-        "DATASET = \"[your-bigquery-dataset-id]\"  # set the Bigquery dataset-id\n",
-        "TRAINING_DATA_TABLE = \"[your-bigquery-table-id-to-store-the-training-data]\"  # set the Bigquery table-id to store the training data"
+        "DATASET = \"[your-bigquery-dataset-id]\"  # set the BigQuery dataset-id\n",
+        "TRAINING_DATA_TABLE = \"[your-bigquery-table-id-to-store-the-training-data]\"  # set the BigQuery table-id to store the training data"
       ]
     },
     {
@@ -203,7 +207,8 @@
         "id": "7b98d5f09842"
       },
       "source": [
-        "We will build a forecast model on this data and thus determine the best price for a product. For this type of model, we may not be using many fields but just the sales and price related ones. For the current execrcise, we will just focus on the following fields :\n",
+        "You will build a forecast model on this data and thus determine the best price for a product. For this type of model, you will not be using many fields: only the sales and price related ones. For the current execrcise, focus on the following fields:\n",
+        "\n",
         "- `Product_ID`\n",
         "- `Customer_Hierarchy`\n",
         "- `Fiscal_Date`\n",
@@ -211,12 +216,10 @@
         "- `Invoiced_quantity_in_Pieces`\n",
         "- `Net_Sales`\n",
         "\n",
-        "\n",
-        "\n",
         "## Data Analysis\n",
         "<a name=\"section-7\"></a>\n",
         "\n",
-        "First, we will explore the data and distributions.\n",
+        "First, explore the data and distributions.\n",
         "\n",
         "Select the required columns from the dataframe."
       ]
@@ -335,7 +338,7 @@
         "id": "f9b9c2e58380"
       },
       "source": [
-        "Check maximum date and minimum date in Fiscal_Date column."
+        "Check the maximum date and minimum date in Fiscal_Date column."
       ]
     },
     {
@@ -447,14 +450,14 @@
         "id": "8259e916fe25"
       },
       "source": [
-        "For most of the products, we see that the percentage change in orders are high where the percentage changes in the prices are low. This suggests that too much change in the prices can affect the number of orders. \n",
+        "For most of the products, the percentage change in orders are high where the percentage changes in the prices are low. This suggests that too much change in the prices can affect the number of orders. \n",
         "\n",
-        "**Note**: There seem to be some outliers in the data as percentage changes greater than 800 are found and as evident from the box plots made earlier. In the current exercise, we will not take any manual measures to deal with outliers as we will create a BigQuery ML timeseries model that already deals with outliers.\n",
+        "**Note**: There seem to be some outliers in the data as percentage changes greater than 800 are found. In the current exercise, do not take any manual measures to deal with outliers as you will create a BigQuery ML timeseries model that already deals with outliers.\n",
         "\n",
         "## Preprocess the data for training\n",
         "<a name=\"section-8\"></a>\n",
         "\n",
-        "Check which `Product_ID`s that have the maximum orders."
+        "Check which `Product_ID`'s  have the maximum orders."
       ]
     },
     {
@@ -479,17 +482,17 @@
         "id": "fd6d227e513e"
       },
       "source": [
-        "From the above result, we can infer the following :\n",
+        "From the above result, you can infer the following:\n",
         "\n",
-        "- Under **Food** category, **SKU 62** has maximum orders.\n",
-        "- Under **Manufacturing** category, **SKU 17** has maximum orders.\n",
-        "- Under **Paper** category, **SKU 107** has maximum orders.\n",
-        "- Under **Publishing** category, **SKU 8** has maximum orders.\n",
-        "- Under **Utilities** category, **SKU 140** has maximum orders.\n",
+        "- Under the **Food** category, **SKU 62** has the maximum orders.\n",
+        "- Under the **Manufacturing** category, **SKU 17** has the maximum orders.\n",
+        "- Under the **Paper** category, **SKU 107** has the maximum orders.\n",
+        "- Under the **Publishing** category, **SKU 8** has the maximum orders.\n",
+        "- Under the **Utilities** category, **SKU 140** has the maximum orders.\n",
         "\n",
-        "Given there are too many ids and only a few records for most of them, we will consider only the above `Product_ID`s for which there are maximum number of orders. \n",
+        "Given that there are too many ids and only a few records for most of them, consider only the above `Product_ID`s for which there are a maximum number of orders. \n",
         "\n",
-        "**Note**: The `Invoiced_quantity_in_Pieces` field seem to be a *float* type rather than an *int* type as it should be. This could be probably because of the data itself might be averaged in the first place."
+        "**Note**: The `Invoiced_quantity_in_Pieces` field seems to be a *float* type rather than an *int* type as it should be. This could be because the data itself might be averaged in the first place."
       ]
     },
     {
@@ -540,7 +543,7 @@
         "id": "f023af578c0f"
       },
       "source": [
-        "In the publishing category, `Product_ID` `SKU 8` and `SKU 17` has less than or equal to two different prices in the entire data and so we will exclude them and consider the rest for building the forecast model. The idea here is to train a forecast model on the timeseries data for products with different prices.\n",
+        "In the publishing category, `Product_ID` `SKU 8` and `SKU 17` are less than or equal to two different prices in the entire data and so you will exclude them and consider the rest for building the forecast model. The idea here is to train a forecast model on the timeseries data for products with different prices.\n",
         "\n",
         "Join the data for all the `Product_ID`s into one dataframe and remove duplicate records."
       ]
@@ -766,7 +769,8 @@
         "id": "67ff3acc74a5"
       },
       "source": [
-        "Based on the plots for price vs. the average forecasted orders, it can be said that to avail the maximum orders, each of the considered `Product_ID`s can follow the below prices :\n",
+        "Based on the plots for price vs. the average forecasted orders, it can be said that to use the maximum orders, each of the considered `Product_ID`s can follow the below prices:\n",
+        "\n",
         "- SKU 107's price range can be from 4.44 - 4.73 units\n",
         "- SKU 140's price can be 1.95 units\n",
         "- SKU 62's price can be 4.23 units\n",

notebooks/community/managed_notebooks/sentiment_analysis/Sentiment_Analysis.ipynb

@@ -2,7 +2,6 @@
   "cells": [
     {
       "cell_type": "markdown",
-      "id": "cfb58b58-3e92-4583-9173-04cfeaeb465e",
       "metadata": {
         "id": "87e8ba66a90f"
       },
@@ -13,41 +12,46 @@
         "* [Dataset](#section-2)\n",
         "* [Objective](#section-3)\n",
         "* [Costs](#section-4)\n",
-        "* [Data Loading](#section-5)\n",
-        "* [Preparing training data](#section-6)\n",
-        "* [Creating Dataset in Vertex AI](#section-7)\n",
-        "* [Training the model using Vertex AI](#section-8)\n",
-        "* [Deploy the Model to the endpoint](#section-9)\n",
+        "* [Load the data](#section-5)\n",
+        "* [Prepare the training data](#section-6)\n",
+        "* [Create a dataset in Vertex AI](#section-7)\n",
+        "* [Train the model using Vertex AI](#section-8)\n",
+        "* [Deploy the model to the endpoint](#section-9)\n",
         "* [Prediction](#section-10)\n",
-        "* [Reviews visualisation](#section-11)\n",
-        "* [Clean-up](#section-12)\n",
+        "* [Review visualization](#section-11)\n",
+        "* [Clean up](#section-12)\n",
         "\n",
         "## Overview\n",
         "<a name=\"section-1\"></a>\n",
-        "This notebook demonstrates performing sentiment analysis on stanford movie reviews dataset using AutoML NLP, deploying the sentimental model on Vertex AI and getting predictions. \n",
-        "<b>Note</b>: This notebook is designed to run on managed notebooks instance of Vertex AI Workbench. Some components of this notebook may not work in other notebook environments.\n",
+        "\n",
+        "This notebook demonstrates how to perform sentiment analysis on a Stanford movie reviews dataset using AutoML Natural Language and how to deploy the sentiment analysis model on Vertex AI to get predictions. \n",
+        "\n",
+        "*Note: This notebook file was developed to run in a [Vertex AI Workbench managed notebooks](https://console.cloud.google.com/vertex-ai/workbench/list/managed) instance using the Python (Local) kernel. Some components of this notebook may not work in other notebook environments.*\n",
         "\n",
         "## Dataset\n",
         "<a name=\"section-2\"></a>\n",
-        "The dataset used in this notebook is a part of the [Stanford Sentiment Treebank Dataset](https://nlp.stanford.edu/sentiment/) which consists of all movie review phrases and the corresponding sentiment scores.\n",
         "\n",
-        "## Objective\n",
+        "The dataset used in this notebook is a part of the [Stanford Sentiment Treebank dataset](https://nlp.stanford.edu/sentiment/), which consists of movie review phrases and their corresponding sentiment scores.\n",
+        "\n",
+        "## Objectives\n",
         "<a name=\"section-3\"></a>\n",
-        "In this notebook :\n",
+        "\n",
+        "The objectives of this notebook include:\n",
         "\n",
         "- Loading the required data. \n",
-        "- Preprocessing the data \n",
+        "- Preprocessing the data.\n",
         "- Selecting the required data for the model.\n",
-        "- Load the dataset into Vertex AI Managed datasets.\n",
-        "- Training a sentimental model using AutoML NLP.\n",
+        "- Loading the dataset into Vertex AI managed datasets.\n",
+        "- Training a sentiment model using AutoML Natural Language.\n",
         "- Evaluating the model.\n",
         "- Deploying the model on Vertex AI.\n",
-        "- Getting Predictions\n",
+        "- Getting predictions.\n",
         "- Clean up.\n",
         "\n",
         "\n",
         "## Costs\n",
         "<a name=\"section-4\"></a>\n",
+        "\n",
         "This tutorial uses the following billable components of Google Cloud:\n",
         "\n",
         "- Vertex AI\n",
@@ -62,17 +66,19 @@
     },
     {
       "cell_type": "markdown",
-      "id": "823afb59-968f-4cac-a3d9-77898ccf971d",
       "metadata": {
         "id": "dc07534b5fed"
       },
       "source": [
-        "## Kernel selection\n",
+        "## Before you begin\n",
+        "\n",
+        "### Kernel selection\n",
+        "\n",
         "Select <b>Python</b> kernel while running this notebook on Vertex AI's managed instances and ensure that the following libraries are installed in the environment where this notebook is being run.\n",
+        "\n",
         "- wordcloud\n",
         "- Pandas \n",
         "\n",
-        "\n",
         "Along with the above libraries, the following google-cloud libraries are also used in this notebook.\n",
         "\n",
         "- google.cloud.aiplatform\n",
@@ -81,61 +87,67 @@
     },
     {
       "cell_type": "markdown",
-      "id": "73c7a12e-7b57-47c3-976a-030140422428",
       "metadata": {
         "id": "cf3f84c87bdb"
       },
       "source": [
-        "## Install required packages"
+        "### Install required packages"
       ]
     },
     {
-      "cell_type": "markdown",
-      "id": "4ad9e4d6-888f-4f56-af14-8ee4c9452e8a",
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "id": "03c928ef2566"
       },
+      "outputs": [],
       "source": [
         "! pip install wordcloud"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "1b290e00-3f91-489d-9982-49a11d74b400",
       "metadata": {
         "id": "8053acfd33e4"
       },
       "source": [
-        "If you are using Vertex AI Workbench, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
-        "- ! pip install google-cloud-aiplatform\n",
-        "- ! pip install fsspec\n",
-        "- ! pip install gcsfs\n"
+        "If you are using Vertex AI Workbench, your environment already meets all the requirements to run this notebook. You can skip this step."
       ]
     },
     {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e7bfa731d8b0"
+      },
+      "outputs": [],
+      "source": [
+        "! pip install google-cloud-aiplatform\n",
+        "! pip install fsspec\n",
+        "! pip install gcsfs"
+      ]
+    },
+    {
       "cell_type": "markdown",
-      "id": "ed6a2f21-f490-4bc4-82bf-d2a3f66e297e",
       "metadata": {
         "id": "e092f34aa304"
       },
       "source": [
-        "## Set your project ID"
+        "### Set your project ID"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "65a82cf5-5d72-4906-bd22-4759c0c68779",
       "metadata": {
         "id": "55354f114f2a"
       },
       "source": [
-        "If you don't know your project ID, you may be able to get your project ID using gcloud."
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "ac63128b-59b0-447c-ad49-4ef0a48234ff",
       "metadata": {
         "id": "94f36c0f4a00"
       },
@@ -154,7 +166,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "359d171e-b8a8-4345-a62f-299fb2675696",
       "metadata": {
         "id": "e4373c1899ed"
       },
@@ -165,7 +176,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "3d29a7b4-79c5-4143-a12a-56d047f83f40",
       "metadata": {
         "id": "3ecacf9ae574"
       },
@@ -179,7 +189,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "4276d8cd-d6b4-43c6-bc68-febaa5aa7b7a",
       "metadata": {
         "id": "b32c908a390c"
       },
@@ -192,7 +201,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cfd0248b-b096-47d1-801e-f05bbe45b875",
       "metadata": {
         "id": "d598bcdd2f4e"
       },
@@ -205,7 +213,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "91385138-96ad-4897-b6e9-645025ee89da",
       "metadata": {
         "id": "262a312bcd87"
       },
@@ -215,12 +222,11 @@
     },
     {
       "cell_type": "markdown",
-      "id": "ef8a5d4c-de14-4a73-bfa3-dc8b146b79f3",
       "metadata": {
         "id": "5e18b2d160e4"
       },
       "source": [
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench managed notebooks or user-managed notebooks**, your environment is already authenticated. Skip this step.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -242,7 +248,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "50c0913e-f67c-45c5-bc18-bb8c1a2c60af",
       "metadata": {
         "id": "0ffb57911177"
       },
@@ -275,7 +280,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d599e91d-9cc2-46da-a103-09e91310199a",
       "metadata": {
         "id": "543fd0a71f4d"
       },
@@ -286,7 +290,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "bfa3220b-4eaa-44be-97c7-597dd916aa22",
       "metadata": {
         "id": "5e0383e0444d"
       },
@@ -305,7 +308,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cccba4a7-2fef-4861-bac3-5de6d9a0cdb9",
       "metadata": {
         "id": "7a7dd63eef70"
       },
@@ -317,19 +319,17 @@
     },
     {
       "cell_type": "markdown",
-      "id": "5fa0d9c7-a3cc-4a5a-ba82-d7f494b5752d",
       "metadata": {
         "id": "5563f402e958"
       },
       "source": [
-        "## Loading data \n",
+        "## Load the data \n",
         "<a name=\"section-5\"></a>"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a10d8894-c279-4306-ba63-6c9e35d8feab",
       "metadata": {
         "id": "e9bed419ca1b"
       },
@@ -351,7 +351,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "64943564-78d7-4eec-b67d-37467e27320c",
       "metadata": {
         "id": "d88a752930ac"
       },
@@ -362,29 +361,27 @@
     },
     {
       "cell_type": "markdown",
-      "id": "ed79e7d8-c74d-410d-8c07-023ac410dee9",
       "metadata": {
         "id": "c83b75fb3279"
       },
       "source": [
-        "The data itself doesn't contain any feature names and thus needs its columns to be re-named. dictionary.txt contains all phrases and their IDs, separated by a vertical line |. sentiment_labels.txt contains all phrase ids and the corresponding sentiment scores, separated by a vertical line. 4 classes are created by mapping the positivity probability using the following cut-offs:\n",
+        "The data itself doesn't contain any feature names and thus needs its columns to be renamed. dictionary.txt contains all phrases and their IDs, separated by a vertical line |. sentiment_labels.txt contains all phrase ids and the corresponding sentiment scores, separated by a vertical line. Four classes are created by mapping the positivity probability using the following cut-offs:\n",
+        "\n",
         "[0, 0.25], (0.25, 0.5], (0.5, 0.75],(0.75, 1.0]"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "70223fcc-fc51-494a-b057-79b4e3dcba1e",
       "metadata": {
         "id": "44443815a2fc"
       },
       "source": [
-        "### Creating labels "
+        "### Create labels "
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "e8bf4d6c-e6fe-47e4-80a9-7741d97e71ee",
       "metadata": {
         "id": "97bbb7218788"
       },
@@ -399,7 +396,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "8b855383-15c5-4374-85ff-b5d42ec75663",
       "metadata": {
         "id": "e971f9f576cf"
       },
@@ -413,35 +409,32 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a90fcf66-9cdd-42ea-a7e9-eb44038964e7",
       "metadata": {
         "id": "87b38faf9a85"
       },
       "source": [
-        "## Preparing training data\n",
+        "## Prepare the training data\n",
         "<a name=\"section-6\"></a>"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "d546ce1a-2464-4371-b40e-5ca5e48d39c4",
       "metadata": {
         "id": "61e3ad46ce44"
       },
       "source": [
         "To train a sentiment analysis model, you provide representative samples of the type of content you want AutoML Natural Language to analyze, each labeled with a value indicating how positive the sentiment is within the content.\n",
         "\n",
-        "The sentiment score is an integer ranging from 0 (relatively negative) to a maximum value of your choice (positive). For example, if you want to identify whether the sentiment is negative, positive, or neutral, you would label the training data with sentiment scores of 0 (negative), 1 (neutral), and 2 (positive).If you want to capture more granularity with five levels of sentiment, you still label documents with the most negative sentiment as 0 and use 4 for the most positive sentiment. The Maximum sentiment score (sentiment_max) for the dataset would be 4."
+        "The sentiment score is an integer ranging from 0 (relatively negative) to a maximum value of your choice (positive). For example, if you want to identify whether the sentiment is negative, positive, or neutral, you would label the training data with sentiment scores of 0 (negative), 1 (neutral), and 2 (positive). If you want to capture more granularity with five levels of sentiment, you still label documents with the most negative sentiment as 0 and use 4 for the most positive sentiment. The Maximum sentiment score (sentiment_max) for the dataset would be 4."
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "59636f66-b8ad-4c18-8750-6f1b5035a75d",
       "metadata": {
         "id": "edcf89a00954"
       },
       "source": [
-        "For this notebook we are selecting subset of the orginal data to train on, which consists extreme positive and negative samples. Here the maximum sentiment would be 1. In <i>ML use</i> column we could provide if it is a TRAIN/VALIDATION/TEST sample or let the Vertex AI randomly assign. \n",
+        "Select a subset of the orginal data to train on that consists of extreme positive and negative samples. Here the maximum sentiment would be 1. In the <i>ML use</i> column you could provide if it is a TRAIN/VALIDATION/TEST sample or let the Vertex AI randomly assign. \n",
         "Each line in a CSV file refers to a single document. The following example shows the general format of a valid CSV file. The ml_use column is optional.\n",
         "\n",
         "\\[ml_use\\],gcs_file_uri|\"inline_text\",sentiment,sentimentMax\n",
@@ -451,18 +444,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "9fca82d5-a63b-470c-84d6-9bb01708b55c",
       "metadata": {
         "id": "245c07c7df7b"
       },
       "source": [
-        "### Selecting subset data"
+        "### Select a subset of the data"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "0253fe82-3fc9-46af-a28a-764d719d94d8",
       "metadata": {
         "id": "e1db0f24d1da"
       },
@@ -475,7 +466,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "6b12e9a1-0444-4068-93cd-ba3d173e7233",
       "metadata": {
         "id": "99f314e5a437"
       },
@@ -490,18 +480,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "525bd8c9-5fd8-4e31-a66c-0ab7ee5a2d87",
       "metadata": {
         "id": "c3e54c1f430a"
       },
       "source": [
-        "### Creating an import csv"
+        "### Create an import csv"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "04332242-a356-4539-9191-ada15e603d1b",
       "metadata": {
         "id": "806303530d77"
       },
@@ -519,18 +507,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "6bc262be-6b18-49dc-bb3a-d1c6323aa1cc",
       "metadata": {
         "id": "453938b7c88b"
       },
       "source": [
-        "## Creating Dataset in Vertex AI\n",
+        "## Create a dataset in Vertex AI\n",
         "<a name=\"section-7\"></a>"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "79f5b072-5fc4-4804-94fa-dfd7c7f281b8",
       "metadata": {
         "id": "061bca976104"
       },
@@ -541,7 +527,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "de42bdeb-4f17-432a-9bf8-cc76316b0fbf",
       "metadata": {
         "id": "e359a68f6295"
       },
@@ -573,7 +558,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "7ece2f5d-e684-4301-a594-75512a32c8b5",
       "metadata": {
         "id": "989313dc7b94"
       },
@@ -588,29 +572,26 @@
     },
     {
       "cell_type": "markdown",
-      "id": "b7bd14d1-5997-440e-a657-717ab7f75607",
       "metadata": {
         "id": "a7c140cb93c0"
       },
       "source": [
-        "## Training the model using Vertex AI\n",
+        "## Train the model using Vertex AI\n",
         "<a name=\"section-8\"></a>"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "1210da4d-1280-4b6f-bb49-c0cfdbab31e3",
       "metadata": {
         "id": "38bc9330bd37"
       },
       "source": [
-        "The following code uses the Vertex AI SDK for Python to train the model on the above created dataset. You can get the dataset id from the Dataset section of Vertex AI in the console or get from the resource name in the dataset object created above. We can specify how the training data is split between the training, validation, and test sets by setting the fraction_split variables."
+        "The following code uses the Vertex AI SDK for Python to train the model on the above created dataset. You can get the dataset id from the Dataset section of Vertex AI in the console or from the resource name in the dataset object created above. You can specify how the training data is split between the training, validation, and test sets by setting the fraction_split variables."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "29279a7b-fd0e-472a-8d60-425c0db773b2",
       "metadata": {
         "id": "bd06f6f67a56"
       },
@@ -658,7 +639,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "3f02a27f-30b9-40fb-a4b8-e896217321af",
       "metadata": {
         "id": "a0a83ba2be4b"
       },
@@ -674,29 +654,26 @@
     },
     {
       "cell_type": "markdown",
-      "id": "af4cd245-8db2-4fbc-a4e7-ed76b5a18719",
       "metadata": {
         "id": "077f319a4218"
       },
       "source": [
-        "## Deploy the Model to the endpoint\n",
+        "## Deploy the model to the endpoint\n",
         "<a name=\"section-9\"></a>\n"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "2a7144bf-ba37-40d4-950a-a9a2bd9708b3",
       "metadata": {
         "id": "cd4463310e5a"
       },
       "source": [
-        "#### create the endpoint"
+        "#### Create the endpoint"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "3b456052-2378-4d83-bcf5-072e0fd67283",
       "metadata": {
         "id": "473ff65e0b88"
       },
@@ -723,7 +700,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "adfddb5e-b4a6-403e-9da6-1f93e7251398",
       "metadata": {
         "id": "54785032708f"
       },
@@ -735,7 +711,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "5404bc6a-fbe5-4f26-83ff-010c2146a024",
       "metadata": {
         "id": "f84df96c9828"
       },
@@ -745,7 +720,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "c3f02b2d-8e5c-490c-8176-1d1b43442981",
       "metadata": {
         "id": "6bf13cc6a68f"
       },
@@ -756,7 +730,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "7207f24c-3fc0-4759-96c1-2d0b29f45bb7",
       "metadata": {
         "id": "7db8d93ea373"
       },
@@ -796,7 +769,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "9d588407-324e-4bf2-9bbd-25dc45f58a38",
       "metadata": {
         "id": "ace75348ce10"
       },
@@ -808,7 +780,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "f970ca16-34ef-47ff-97af-c4b35b97db67",
       "metadata": {
         "id": "9bcd4d7a11de"
       },
@@ -819,18 +790,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a2e6a187-cf73-4072-9373-05d9847ff44d",
       "metadata": {
         "id": "c72060f26336"
       },
       "source": [
-        "After deploying the model to an endpoint use the Vertex AI API to request an online prediction. Filter the data which we haven't used for the training and pick longer reviews to test the model "
+        "After deploying the model to an endpoint use the Vertex AI API to request an online prediction. Filter the data that you haven't used for the training and pick longer reviews to test the model."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "6b69fd2c-d0e0-4d77-b33a-038302d97c2a",
       "metadata": {
         "id": "7fa5e1a01a77"
       },
@@ -847,7 +816,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c1bfbef3-9a3f-46a2-9858-a53b2e63d743",
       "metadata": {
         "id": "817ba5968e22"
       },
@@ -864,7 +832,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "5cac4c12-b4bb-41ef-aeb9-87bfa7071b48",
       "metadata": {
         "id": "3fed98fbb6d7"
       },
@@ -877,18 +844,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "340f3d6a-c350-4846-a040-36db400fdf37",
       "metadata": {
         "id": "963102b04a59"
       },
       "source": [
-        "Here is the prediction results on the positive samples. Model did a good job on predicting positive sentiment for positive reviews. First and last review predictions are false negatives. \n"
+        "Here is the prediction results on the positive samples. The model did a good job on predicting positive sentiment for positive reviews. The first and last review predictions are false negatives. "
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "03d750ea-d1ca-49a5-ae40-ebeded32d680",
       "metadata": {
         "id": "5d7b1d59c0d0"
       },
@@ -900,7 +865,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "45430d7b-62e5-4e8f-be64-f0aece454b6e",
       "metadata": {
         "id": "6fc9dbc3436e"
       },
@@ -911,7 +875,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "f83741a7-0a90-4bbb-869d-c0f60b65782a",
       "metadata": {
         "id": "53830cc82fc5"
       },
@@ -923,29 +886,26 @@
     },
     {
       "cell_type": "markdown",
-      "id": "992a4147-c488-4a7c-827b-bdcbda3a798b",
       "metadata": {
         "id": "aa6a2abc2006"
       },
       "source": [
-        "## Reviews visualisation\n",
+        "## Review visualization\n",
         "<a name=\"section-11\"></a>\n"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "fe396e2f-e3fb-48c9-8aac-f92820644e70",
       "metadata": {
         "id": "f478d63de61a"
       },
       "source": [
-        "Here we are trying to visualise the positive and negative reviews in the data."
+        "Visualize the positive and negative reviews in the data."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "904a2d19-180a-4d99-9f59-1c838fe26275",
       "metadata": {
         "id": "b08c4be897ce"
       },
@@ -960,7 +920,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "d4fd3cbe-b5f3-40f4-a3e0-5c28335d08a6",
       "metadata": {
         "id": "27d61dcee56a"
       },
@@ -971,18 +930,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "e7d4e8e8-3d8a-437f-b010-3a4b8794c241",
       "metadata": {
         "id": "9ddc8e1dfaab"
       },
       "source": [
-        "Creating the word cloud by removing the common words to highlight the words representing positive and negative samples "
+        "Create the word cloud by removing the common words to highlight the words representing positive and negative samples."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "318ace0b-07de-4e67-9d33-112e9af393a7",
       "metadata": {
         "id": "8f48fa9258c3"
       },
@@ -1021,18 +978,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "a442b525-54b6-4794-b1e4-7f53f1cb7e3d",
       "metadata": {
         "id": "09e568ad3526"
       },
       "source": [
-        "Word cloud of negative reviews"
+        "Plot a word cloud of negative reviews."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "3cde242c-fe9a-4144-a6f5-c8bbac321786",
       "metadata": {
         "id": "4fd9bf528bb4"
       },
@@ -1072,18 +1027,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "abc93a13-e675-4381-8b0a-0563ab939017",
       "metadata": {
         "id": "cd2c9686efbc"
       },
       "source": [
-        "Word cloud of positive reviews"
+        "Plot a word cloud of positive reviews."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "887787e6-498d-4194-86aa-51b46efe29b6",
       "metadata": {
         "id": "2fb8c50e991b"
       },
@@ -1121,7 +1074,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "67aebd05-2822-4dc9-86dc-8fb60bbbfeb7",
       "metadata": {
         "id": "c169667d92e8"
       },
@@ -1129,13 +1081,12 @@
         "## Clean up\n",
         "<a name=\"section-12\"></a>\n",
         "\n",
-        "Undeploy the model from endpoint."
+        "Undeploy the model from the endpoint."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "9e1b4484-64b8-43b9-8700-8015ec043714",
       "metadata": {
         "id": "c72329be87c8"
       },
@@ -1147,7 +1098,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "9177d56b-6d09-4e2a-8cb3-40e98b277a79",
       "metadata": {
         "id": "1b8c7af9f513"
       },
@@ -1158,7 +1108,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "755f0d68-b7d8-46b4-978a-15e88084ac84",
       "metadata": {
         "id": "1a08e7cea52d"
       },
@@ -1169,18 +1118,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "6213446a-fd71-4aa8-8c34-7d0777c1e89d",
       "metadata": {
         "id": "aa0be755cb23"
       },
       "source": [
-        "Delete the dataset"
+        "Delete the dataset."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "fbd51fb9-c7f0-4be4-ab51-982902920494",
       "metadata": {
         "id": "42244042a680"
       },
@@ -1191,18 +1138,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "736ce014-e3e4-4757-8030-69046f754868",
       "metadata": {
         "id": "c79a8e124887"
       },
       "source": [
-        "Delete the model"
+        "Delete the model."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c04e5fa3-3f5f-43d3-9dc9-a7c8cf8a1474",
       "metadata": {
         "id": "034a8bcc30de"
       },

notebooks/community/matching_engine/matching_engine_for_indexing.ipynb

@@ -459,7 +459,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil cp gs://cloud-samples-data/ai-platform-unified/matching_engine/glove-100-angular.hdf5 ."
+        "! gsutil cp gs://cloud-samples-data/vertex-ai/matching_engine/glove-100-angular.hdf5 ."
       ]
     },
     {

notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb

@@ -1,877 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ur8xi4C7S06n"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2021 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# You may obtain a copy of the License at\n",
-        "#\n",
-        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
-        "#\n",
-        "# Unless required by applicable law or agreed to in writing, software\n",
-        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-        "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "JAPoU8Sm5E6e"
-      },
-      "source": [
-        "<table align=\"left\">\n",
-        "\n",
-        "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
-        "    </a>\n",
-        "  </td>\n",
-        "</table>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WBFL9LagqmwT"
-      },
-      "source": [
-        "#Vertex AI: Track parameters and metrics for locally trained models"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "tvgnzT1CKxrO"
-      },
-      "source": [
-        "## Overview\n",
-        "\n",
-        "This notebook demonstrates how to track metrics and parameters for ML training jobs and analyze this metadata using Vertex SDK for Python.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "In this notebook, we will train a simple distributed neural network (DNN) model to predict automobile's miles per gallon (MPG) based on automobile information in the [auto-mpg dataset](https://www.kaggle.com/devanshbesain/exploration-and-analysis-auto-mpg).\n",
-        "\n",
-        "### Objective\n",
-        "\n",
-        "In this notebook, you will learn how to use Vertex SDK for Python to:\n",
-        "\n",
-        "    * Track parameters and metrics for a locally trainined model.\n",
-        "    * Extract and perform analysis for all parameters and metrics within an Experiment.\n",
-        "\n",
-        "### Costs \n",
-        "\n",
-        "\n",
-        "This tutorial uses billable components of Google Cloud:\n",
-        "\n",
-        "* Vertex AI\n",
-        "* Cloud Storage\n",
-        "\n",
-        "\n",
-        "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
-        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
-        "to generate a cost estimate based on your projected usage."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ze4-nDLfK4pw"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gCuSR8GkAgzl"
-      },
-      "source": [
-        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
-        "You need the following:\n",
-        "\n",
-        "* The Google Cloud SDK\n",
-        "* Git\n",
-        "* Python 3\n",
-        "* virtualenv\n",
-        "* Jupyter notebook running in a virtual environment with Python 3\n",
-        "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
-        "for meeting these requirements. The following steps provide a condensed set of\n",
-        "instructions:\n",
-        "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
-        "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
-        "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
-        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
-        "\n",
-        "1. To install Jupyter, run `pip install jupyter` on the\n",
-        "command-line in a terminal shell.\n",
-        "\n",
-        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
-        "\n",
-        "1. Open this notebook in the Jupyter Notebook Dashboard."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "i7EUnXsZhAGF"
-      },
-      "source": [
-        "### Install additional packages\n",
-        "\n",
-        "Run the following commands to install the Vertex SDK for Python."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "IaYsrh0Tc17L"
-      },
-      "outputs": [],
-      "source": [
-        "import sys\n",
-        "\n",
-        "if \"google.colab\" in sys.modules:\n",
-        "    USER_FLAG = \"\"\n",
-        "else:\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "wyy5Lbnzg5fi"
-      },
-      "outputs": [],
-      "source": [
-        "!python3 -m pip install {USER_FLAG} google-cloud-aiplatform --upgrade"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "hhq5zEbGg0XX"
-      },
-      "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "EzrelQZ22IZj"
-      },
-      "outputs": [],
-      "source": [
-        "# Automatically restart kernel after installs\n",
-        "import os\n",
-        "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lWEdiXsJg0XY"
-      },
-      "source": [
-        "## Before you begin\n",
-        "\n",
-        "### Select a GPU runtime\n",
-        "\n",
-        "**Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select \"Runtime --> Change runtime type > GPU\"**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "BF1j6f9HApxa"
-      },
-      "source": [
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
-        "\n",
-        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "oM1iC_MfAts1"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output=!gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "riG_qUokg0XZ"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "06571eb4063b"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "697568e92bd6"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dr--iN2kAylZ"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "sBCra4QMA2wR"
-      },
-      "source": [
-        "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n",
-        "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
-        "\n",
-        "2. Click **Create service account**.\n",
-        "\n",
-        "3. In the **Service account name** field, enter a name, and\n",
-        "   click **Create**.\n",
-        "\n",
-        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
-        "into the filter box, and select\n",
-        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
-        "local environment.\n",
-        "\n",
-        "6. Enter the path to your service account key as the\n",
-        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "PyQmSRbKA8r-"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "XoEqT2Y4DJmf"
-      },
-      "source": [
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Y9Uo3tifg1kx"
-      },
-      "source": [
-        "Import required libraries."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "pRUOFELefqf1"
-      },
-      "outputs": [],
-      "source": [
-        "import matplotlib.pyplot as plt\n",
-        "import pandas as pd\n",
-        "from google.cloud import aiplatform\n",
-        "from tensorflow.python.keras import Sequential, layers\n",
-        "from tensorflow.python.keras.utils import data_utils"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "xtXZWmYqJ1bh"
-      },
-      "source": [
-        "Define some constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "JIOrI-hoJ46P"
-      },
-      "outputs": [],
-      "source": [
-        "EXPERIMENT_NAME = \"\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "jWQLXXNVN4Lv"
-      },
-      "source": [
-        "If EXEPERIMENT_NAME is not set, set a default one below:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "Q1QInYWOKsmo"
-      },
-      "outputs": [],
-      "source": [
-        "if EXPERIMENT_NAME == \"\" or EXPERIMENT_NAME is None:\n",
-        "    EXPERIMENT_NAME = \"my-experiment-\" + TIMESTAMP"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Xuny18aMcWDb"
-      },
-      "source": [
-        "## Concepts\n",
-        "\n",
-        "To better understanding how parameters and metrics are stored and organized, we'd like to introduce the following concepts:\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "NThDci5bp0Uw"
-      },
-      "source": [
-        "### Experiment\n",
-        "Experiments describe a context that groups your runs and the artifacts you create into a logical session. For example, in this notebook you create an Experiment and log data to that experiment."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "SAyRR3Ydp4X5"
-      },
-      "source": [
-        "### Run\n",
-        "A run represents a single path/avenue that you executed while performing an experiment. A run includes artifacts that you used as inputs or outputs, and parameters that you used in this execution. An Experiment can contain multiple runs. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "l1YW2pgyegFP"
-      },
-      "source": [
-        "## Getting started tracking parameters and metrics\n",
-        "\n",
-        "You can use the Vertex SDK for Python to track metrics and parameters for models trained locally. \n",
-        "\n",
-        "In the following example, you train a simple distributed neural network (DNN) model to predict automobile's miles per gallon (MPG) based on automobile information in the [auto-mpg dataset](https://www.kaggle.com/devanshbesain/exploration-and-analysis-auto-mpg)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "KPY41M9_AhZU"
-      },
-      "source": [
-        "### Load and process the training dataset"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "bfMQSmRuUuX-"
-      },
-      "source": [
-        "Download and process the dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "RiQuMv4bmpuV"
-      },
-      "outputs": [],
-      "source": [
-        "def read_data(uri):\n",
-        "    dataset_path = data_utils.get_file(\"auto-mpg.data\", uri)\n",
-        "    column_names = [\n",
-        "        \"MPG\",\n",
-        "        \"Cylinders\",\n",
-        "        \"Displacement\",\n",
-        "        \"Horsepower\",\n",
-        "        \"Weight\",\n",
-        "        \"Acceleration\",\n",
-        "        \"Model Year\",\n",
-        "        \"Origin\",\n",
-        "    ]\n",
-        "    raw_dataset = pd.read_csv(\n",
-        "        dataset_path,\n",
-        "        names=column_names,\n",
-        "        na_values=\"?\",\n",
-        "        comment=\"\\t\",\n",
-        "        sep=\" \",\n",
-        "        skipinitialspace=True,\n",
-        "    )\n",
-        "    dataset = raw_dataset.dropna()\n",
-        "    dataset[\"Origin\"] = dataset[\"Origin\"].map(\n",
-        "        lambda x: {1: \"USA\", 2: \"Europe\", 3: \"Japan\"}.get(x)\n",
-        "    )\n",
-        "    dataset = pd.get_dummies(dataset, prefix=\"\", prefix_sep=\"\")\n",
-        "    return dataset\n",
-        "\n",
-        "\n",
-        "dataset = read_data(\n",
-        "    \"http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Y06J7A7yU21t"
-      },
-      "source": [
-        "Split dataset for training and testing."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "p5JBCBKyH-NC"
-      },
-      "outputs": [],
-      "source": [
-        "def train_test_split(dataset, split_frac=0.8, random_state=0):\n",
-        "    train_dataset = dataset.sample(frac=split_frac, random_state=random_state)\n",
-        "    test_dataset = dataset.drop(train_dataset.index)\n",
-        "    train_labels = train_dataset.pop(\"MPG\")\n",
-        "    test_labels = test_dataset.pop(\"MPG\")\n",
-        "\n",
-        "    return train_dataset, test_dataset, train_labels, test_labels\n",
-        "\n",
-        "\n",
-        "train_dataset, test_dataset, train_labels, test_labels = train_test_split(dataset)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "gaNNTFPaU7KT"
-      },
-      "source": [
-        "Normalize the features in the dataset for better model performance."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "VGq5QCoyIEWJ"
-      },
-      "outputs": [],
-      "source": [
-        "def normalize_dataset(train_dataset, test_dataset):\n",
-        "    train_stats = train_dataset.describe()\n",
-        "    train_stats = train_stats.transpose()\n",
-        "\n",
-        "    def norm(x):\n",
-        "        return (x - train_stats[\"mean\"]) / train_stats[\"std\"]\n",
-        "\n",
-        "    normed_train_data = norm(train_dataset)\n",
-        "    normed_test_data = norm(test_dataset)\n",
-        "\n",
-        "    return normed_train_data, normed_test_data\n",
-        "\n",
-        "\n",
-        "normed_train_data, normed_test_data = normalize_dataset(train_dataset, test_dataset)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "UBXUgxgqA_GB"
-      },
-      "source": [
-        "### Define ML model and training function"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "66odBYKrIN4q"
-      },
-      "outputs": [],
-      "source": [
-        "def train(\n",
-        "    train_data,\n",
-        "    train_labels,\n",
-        "    num_units=64,\n",
-        "    activation=\"relu\",\n",
-        "    dropout_rate=0.0,\n",
-        "    validation_split=0.2,\n",
-        "    epochs=1000,\n",
-        "):\n",
-        "\n",
-        "    model = Sequential(\n",
-        "        [\n",
-        "            layers.Dense(\n",
-        "                num_units,\n",
-        "                activation=activation,\n",
-        "                input_shape=[len(train_dataset.keys())],\n",
-        "            ),\n",
-        "            layers.Dropout(rate=dropout_rate),\n",
-        "            layers.Dense(num_units, activation=activation),\n",
-        "            layers.Dense(1),\n",
-        "        ]\n",
-        "    )\n",
-        "\n",
-        "    model.compile(loss=\"mse\", optimizer=\"adam\", metrics=[\"mae\", \"mse\"])\n",
-        "    print(model.summary())\n",
-        "\n",
-        "    history = model.fit(\n",
-        "        train_data, train_labels, epochs=epochs, validation_split=validation_split\n",
-        "    )\n",
-        "\n",
-        "    return model, history"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "O8XJZB3gR8eL"
-      },
-      "source": [
-        "### Initialize the Vertex AI SDK for Python and create an Experiment\n",
-        "\n",
-        "Initialize the *client* for Vertex AI and create an experiment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "o_wnT10RJ7-W"
-      },
-      "outputs": [],
-      "source": [
-        "aiplatform.init(project=PROJECT_ID, location=REGION, experiment=EXPERIMENT_NAME)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "u-iTnzt3B6Z_"
-      },
-      "source": [
-        "### Start several model training runs\n",
-        "\n",
-        "Training parameters and metrics are logged for each run."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "i2wnpu8_7JfV"
-      },
-      "outputs": [],
-      "source": [
-        "parameters = [\n",
-        "    {\"num_units\": 16, \"epochs\": 3, \"dropout_rate\": 0.1},\n",
-        "    {\"num_units\": 16, \"epochs\": 10, \"dropout_rate\": 0.1},\n",
-        "    {\"num_units\": 16, \"epochs\": 10, \"dropout_rate\": 0.2},\n",
-        "    {\"num_units\": 32, \"epochs\": 10, \"dropout_rate\": 0.1},\n",
-        "    {\"num_units\": 32, \"epochs\": 10, \"dropout_rate\": 0.2},\n",
-        "]\n",
-        "\n",
-        "for i, params in enumerate(parameters):\n",
-        "    aiplatform.start_run(run=f\"auto-mpg-local-run-{i}\")\n",
-        "    aiplatform.log_params(params)\n",
-        "    model, history = train(\n",
-        "        normed_train_data,\n",
-        "        train_labels,\n",
-        "        num_units=params[\"num_units\"],\n",
-        "        activation=\"relu\",\n",
-        "        epochs=params[\"epochs\"],\n",
-        "        dropout_rate=params[\"dropout_rate\"],\n",
-        "    )\n",
-        "    aiplatform.log_metrics(\n",
-        "        {metric: values[-1] for metric, values in history.history.items()}\n",
-        "    )\n",
-        "\n",
-        "    loss, mae, mse = model.evaluate(normed_test_data, test_labels, verbose=2)\n",
-        "    aiplatform.log_metrics({\"eval_loss\": loss, \"eval_mae\": mae, \"eval_mse\": mse})"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "jZLrJZTfL7tE"
-      },
-      "source": [
-        "### Extract parameters and metrics into a dataframe for analysis"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "A1PqKxlpOZa2"
-      },
-      "source": [
-        "We can also extract all parameters and metrics associated with any Experiment into a dataframe for further analysis."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "jbRf1WoH_vbY"
-      },
-      "outputs": [],
-      "source": [
-        "experiment_df = aiplatform.get_experiment_df()\n",
-        "experiment_df"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "EYuYgqVCMKU1"
-      },
-      "source": [
-        "### Visualizing an experiment's parameters and metrics"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "r8orCj8iJuO1"
-      },
-      "outputs": [],
-      "source": [
-        "plt.rcParams[\"figure.figsize\"] = [15, 5]\n",
-        "\n",
-        "ax = pd.plotting.parallel_coordinates(\n",
-        "    experiment_df.reset_index(level=0),\n",
-        "    \"run_name\",\n",
-        "    cols=[\n",
-        "        \"param.num_units\",\n",
-        "        \"param.dropout_rate\",\n",
-        "        \"param.epochs\",\n",
-        "        \"metric.loss\",\n",
-        "        \"metric.val_loss\",\n",
-        "        \"metric.eval_loss\",\n",
-        "    ],\n",
-        "    color=[\"blue\", \"green\", \"pink\", \"red\"],\n",
-        ")\n",
-        "ax.set_yscale(\"symlog\")\n",
-        "ax.legend(bbox_to_anchor=(1.0, 0.5))"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WTHvPMweMlP1"
-      },
-      "source": [
-        "## Visualizing experiments in Cloud Console"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "F19_5lw0MqXv"
-      },
-      "source": [
-        "Run the following to get the URL of Vertex AI Experiments for your project.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "GmN9vE9pqqzt"
-      },
-      "outputs": [],
-      "source": [
-        "print(\"Vertex AI Experiments:\")\n",
-        "print(\n",
-        "    f\"https://console.cloud.google.com/ai/platform/experiments/experiments?folder=&organizationId=&project={PROJECT_ID}\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "TpV-iwP9qw9c"
-      },
-      "source": [
-        "## Cleaning up\n",
-        "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial."
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "collapsed_sections": [],
-      "name": "sdk-metric-parameter-tracking-for-locally-trained-models.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/README.md

@@ -12,7 +12,7 @@ The purpose of this set of notebooks and markdown files is to demonstrate Google
 2. [Experimentation](stage2)
 3. [Formalization](stage3)
 4. [Evaluation](stage4)
-5. Deployment
-6. Serving
+5. [Deployment](stage5)
+6. [Serving](stage6)
 7. Monitoring
 8. Continuous Training

notebooks/community/ml_ops/stage1/README.md

@@ -22,7 +22,7 @@ The first stage in MLOps is the collection and preparation for the purpose of de
 - Data is preprocessed for training and evaluation using Dataflow.
 - Data augmentation is performed on-the-fly and is coupled with model feeding.
 
-<img src='stage1.jpg'>
+<img src='stage1v2.png'>
 
 ## Notebooks
 
@@ -76,6 +76,18 @@ The steps performed include:
     - image data
 ```
 
+[Get Started with Data Labeling](get_started_with_data_labeling.ipynb)
+
+```
+The steps performed include:
+
+- Create a Specialist Pool for data labelers.
+- Create a data labeling job.
+- Submit the data labeling job.
+- List data labeling jobs.
+- Cancel a data labeling job.
+```
+
 ### E2E Stage Example
 
 [Stage 1: Data Management](mlops_data_management.ipynb)

notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -34,13 +34,18 @@
         "<table align=\"left\">\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -67,7 +72,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the GSOD dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). The version of the dataset you use only the fields year, month and day to predict the value of mean daily temperature (mean_temp)."
+        "The dataset used for this tutorial is the GSOD dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). In this version of the dataset you consider the fields year, month and day to predict the value of mean daily temperature (mean_temp)."
       ]
     },
     {
@@ -104,7 +109,7 @@
       "source": [
         "### Recommendations\n",
         "\n",
-        "When doing E2E MLOps on Google Cloud, the following best practices with structured (tabular) data in BigQuery:\n",
+        "When doing E2E MLOps on Google Cloud, following are the best practices when dealing with structured (tabular) data in BigQuery:\n",
         "\n",
         "- For AutoML training:\n",
         "  - Create a managed dataset with Vertex AI `TabularDataset`.\n",
@@ -124,7 +129,7 @@
         "        - Within the generator (upstream)\n",
         "        - Within the model (downstream)\n",
         "    - XGBoost model training:\n",
-        "      - Use BigQuery ML builtin XGBoost training.\n",
+        "      - Use BigQuery ML built-in XGBoost training.\n",
         "      - Alternatively, create a DMatrix generator from CSV files extracted from BigQuery table.\n",
         "    - Pytorch model training:\n",
         "        - Extract the BigQuery to a pandas dataframe.\n",
@@ -132,10 +137,19 @@
         "        - Create a DataLoader generator from the pandas dataframe.\n",
         "\n",
         "\n",
-        "- Alternately:\n",
+        "- Alternatively:\n",
         "    - Extract the BigQuery table to CSV files.\n",
         "    - Preprocess the CSV files.\n",
-        "    - Create a tf.data.Dataset generator from the CSV files."
+        "    - Create a tf.data.Dataset generator from the CSV files.\n",
+        "    \n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -146,7 +160,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
@@ -157,40 +171,26 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_xgboost"
-      },
-      "source": [
-        "Install the latest GA version of *XGBoost* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_xgboost"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U xgboost $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the packages\n",
+        "! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install -U xgboost $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q"
       ]
     },
     {
@@ -222,6 +222,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -298,7 +324,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -325,6 +354,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -335,12 +425,7 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you submit a custom training job using the Vertex SDK, you upload a Python package\n",
-        "containing your training code to a Cloud Storage bucket. Vertex AI runs\n",
-        "the code from this package. In this tutorial, Vertex AI also saves the\n",
-        "trained model that results from your job in the same bucket. You can then\n",
-        "create an `Endpoint` resource based on this output in order to serve\n",
-        "online predictions.\n",
+        "When you create a dataset resource using the Vertex SDK, you can provide a Cloud Storage bucket that contains the data. Vertex AI creates the dataset resource from the data. In this tutorial, Vertex AI also creates a dataset resource from your data in the Cloud Storage bucket.\n",
         "\n",
         "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
@@ -353,7 +438,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -364,8 +450,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -385,7 +472,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -405,7 +492,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -414,9 +501,6 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -428,75 +512,12 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_bq"
-      },
-      "source": [
-        "#### Import BigQuery\n",
-        "\n",
-        "Import the BigQuery package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_bq"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
+        "import pandas as pd\n",
+        "import xgboost as xgb\n",
         "from google.cloud import bigquery"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_xgboost"
-      },
-      "source": [
-        "#### Import XGBoost\n",
-        "\n",
-        "Import the XGBoost package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_xgboost"
-      },
-      "outputs": [],
-      "source": [
-        "import xgboost as xgb"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_pandas"
-      },
-      "source": [
-        "#### Import pandas\n",
-        "\n",
-        "Import the pandas package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_pandas"
-      },
-      "outputs": [],
-      "source": [
-        "import pandas as pd"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -516,7 +537,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
       ]
     },
     {
@@ -538,7 +559,7 @@
       },
       "outputs": [],
       "source": [
-        "bqclient = bigquery.Client()"
+        "bqclient = bigquery.Client(project=PROJECT_ID)"
       ]
     },
     {
@@ -549,7 +570,7 @@
       "source": [
         "#### Location of BigQuery training data.\n",
         "\n",
-        "Now set the variable `IMPORT_FILE` to the location of the data table in BigQuery."
+        "Now, set the variable `IMPORT_FILE` to the location of the data table in BigQuery and `BQ_TABLE` with the table id."
       ]
     },
     {
@@ -591,10 +612,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.TabularDataset.create(\n",
+        "dataset = aiplatform.TabularDataset.create(\n",
         "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
         "    bq_source=[IMPORT_FILE],\n",
-        "    labels={\"user_metadata\": BUCKET_NAME[5:]},\n",
+        "    labels={\"user_metadata\": BUCKET_URI[5:]},\n",
         ")\n",
         "\n",
         "label_column = \"mean_temp\"\n",
@@ -610,7 +631,7 @@
       "source": [
         "### Copy the dataset to Cloud Storage\n",
         "\n",
-        "Next, you make a copy of the BigQuery dataset, as a CSV file, to Cloud Storage using the BigQuery extract command.\n",
+        "Next, you make a copy of the BigQuery table as a CSV file, to Cloud Storage using the BigQuery extract command.\n",
         "\n",
         "Learn more about [BigQuery command line interface](https://cloud.google.com/bigquery/docs/reference/bq-cli-reference)."
       ]
@@ -626,9 +647,9 @@
         "comps = BQ_TABLE.split(\".\")\n",
         "BQ_PROJECT_DATASET_TABLE = comps[0] + \":\" + comps[1] + \".\" + comps[2]\n",
         "\n",
-        "! bq --location=us extract --destination_format CSV $BQ_PROJECT_DATASET_TABLE $BUCKET_NAME/mydata*.csv\n",
+        "! bq --location=us extract --destination_format CSV $BQ_PROJECT_DATASET_TABLE $BUCKET_URI/mydata*.csv\n",
         "\n",
-        "IMPORT_FILES = ! gsutil ls $BUCKET_NAME/mydata*.csv\n",
+        "IMPORT_FILES = ! gsutil ls $BUCKET_URI/mydata*.csv\n",
         "\n",
         "print(IMPORT_FILES)\n",
         "\n",
@@ -664,15 +685,12 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    gcs_source = IMPORT_FILES\n",
-        "else:\n",
-        "    gcs_source = [IMPORT_FILE]\n",
+        "gcs_source = IMPORT_FILES\n",
         "\n",
-        "dataset = aip.TabularDataset.create(\n",
+        "dataset = aiplatform.TabularDataset.create(\n",
         "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_source,\n",
-        "    labels={\"user_metadata\": BUCKET_NAME[5:]},\n",
+        "    labels={\"user_metadata\": BUCKET_URI[5:]},\n",
         ")\n",
         "\n",
         "\n",
@@ -694,6 +712,30 @@
         "Learn more about [Creating BigQuery views](https://cloud.google.com/bigquery/docs/views)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7dc142433e50"
+      },
+      "outputs": [],
+      "source": [
+        "# Set dataset name and view name in BigQuery\n",
+        "BQ_MY_DATASET = \"[your-dataset-name]\"\n",
+        "BQ_MY_TABLE = \"[your-view-name]\"\n",
+        "\n",
+        "# Otherwise, use the default names\n",
+        "if (\n",
+        "    BQ_MY_DATASET == \"\"\n",
+        "    or BQ_MY_DATASET is None\n",
+        "    or BQ_MY_DATASET == \"[your-dataset-name]\"\n",
+        "):\n",
+        "    BQ_MY_DATASET = \"mlops_dataset_\" + TIMESTAMP\n",
+        "\n",
+        "if BQ_MY_TABLE == \"\" or BQ_MY_TABLE is None or BQ_MY_TABLE == \"[your-view-name]\":\n",
+        "    BQ_MY_TABLE = \"mlops_view_\" + TIMESTAMP"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -702,8 +744,7 @@
       },
       "outputs": [],
       "source": [
-        "BQ_MY_DATASET = 'mydataset'\n",
-        "BQ_MY_TABLE = 'myview'\n",
+        "# Create the resources\n",
         "! bq --location=US mk -d \\\n",
         "$PROJECT_ID:$BQ_MY_DATASET\n",
         "\n",
@@ -744,8 +785,8 @@
       },
       "outputs": [],
       "source": [
-        "# Download a table.\n",
-        "table = bigquery.TableReference.from_string(\"bigquery-public-data.samples.gsod\")\n",
+        "# Download the table.\n",
+        "table = bigquery.TableReference.from_string(BQ_TABLE)\n",
         "\n",
         "rows = bqclient.list_rows(\n",
         "    table,\n",
@@ -1031,22 +1072,6 @@
         "TABLE_ID = \"gsod\"\n",
         "\n",
         "\n",
-        "def create_bigquery_dataset(dataset_id):\n",
-        "    dataset = bigquery.Dataset(\n",
-        "        bigquery.dataset.DatasetReference(PROJECT_ID, dataset_id)\n",
-        "    )\n",
-        "    dataset.location = \"us\"\n",
-        "\n",
-        "    try:\n",
-        "        dataset = bqclient.create_dataset(dataset)  # API request\n",
-        "        return True\n",
-        "    except Exception as err:\n",
-        "        print(err)\n",
-        "        if err.code != 409:  # http_client.CONFLICT\n",
-        "            raise\n",
-        "    return False\n",
-        "\n",
-        "\n",
         "def load_data_into_bigquery(url, dataset_id, table_id):\n",
         "    create_bigquery_dataset(dataset_id)\n",
         "    dataset = bqclient.dataset(dataset_id)\n",
@@ -1079,13 +1104,11 @@
       "source": [
         "### Read BigQuery table into XGboost DMatrix\n",
         "\n",
-        "Currently, there is no direct data feeding connector between BigQuery and the open source XGBoost.\n",
+        "Currently, there is no direct data feeding connector between BigQuery and the open source XGBoost. The BigQuery ML service has a built-in XGBoost training module.\n",
         "\n",
-        "The BigQuery ML service has XGBoost training builtin.\n",
+        "Alernatively, you extract the data either as a pandas dataframe or as CSV files. The extracted data is then given as an input to a `DMatrix` object when training the model.\n",
         "\n",
-        "Alernatively, you extract the data either as a pandas dataframe or as CSV files. The extracted data is then inputted to a `DMatrix` object when training the model.\n",
-        "\n",
-        "Learn more about [Getting started with builtin XGBoost](https://cloud.google.com/ai-platform/training/docs/algorithms/xgboost-start)"
+        "Learn more about [Getting started with built-in XGBoost](https://cloud.google.com/ai-platform/training/docs/algorithms/xgboost-start)."
       ]
     },
     {
@@ -1096,7 +1119,7 @@
       "source": [
         "### Read pandas table into XGboost DMatrix\n",
         "\n",
-        "Next, you load the pandas dataframe into a `DMatrix` object. XGBoost does not support non-numeric inputs. Any column that is categorical will need to be one-hot encoded prior to loading the dataframe."
+        "Next, you load the pandas dataframe into a `DMatrix` object. XGBoost does not support non-numeric inputs. Any column that is categorical need to be one-hot encoded prior to loading the dataframe."
       ]
     },
     {
@@ -1109,7 +1132,7 @@
       "source": [
         "dataframe[\"station_number\"] = pd.to_numeric(dataframe[\"station_number\"])\n",
         "labels = dataframe[\"mean_temp\"]\n",
-        "data = dataframe.drop(4)\n",
+        "data = dataframe.drop([\"mean_temp\"], axis=1)\n",
         "\n",
         "dtrain = xgb.DMatrix(data, label=labels)"
       ]
@@ -1122,7 +1145,7 @@
       "source": [
         "### Read CSV files into XGboost DMatrix\n",
         "\n",
-        "Currently, there is no Cloud Storage support in XGBoost. If you use CSV files for input, you will need to download them locally."
+        "Currently, there is no Cloud Storage support in XGBoost. If you use CSV files for input, you need to download them locally."
       ]
     },
     {
@@ -1144,87 +1167,42 @@
         "id": "cleanup:mbsdk"
       },
       "source": [
-        "# Cleaning up\n",
+        "# Clean up\n",
         "\n",
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "- Vertex AI Dataset resource\n",
+        "- Cloud Storage Bucket\n",
+        "- BigQuery Dataset\n",
+        "\n",
+        "Set `delete_storage` to _True_ to delete the storage resources used in this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "47ad926d84e8"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "import os\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the temporary BigQuery dataset\n",
+        "! bq rm -r -f $PROJECT_ID:$DATASET_ID\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "delete_storage = False\n",
+        "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
+        "    # Delete the created GCS bucket\n",
+        "    ! gsutil rm -r $BUCKET_URI\n",
+        "    # Delete the created BigQuery datasets\n",
+        "    ! bq rm -r -f $PROJECT_ID:$BQ_MY_DATASET"
       ]
     }
   ],

notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb

@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -139,7 +145,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
@@ -150,20 +156,26 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install --upgrade apache-beam[gcp] $USER_FLAG -q"
       ]
     },
     {
@@ -195,6 +207,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -271,7 +309,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -298,6 +339,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -326,7 +428,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -337,8 +440,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -358,7 +462,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -378,7 +482,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -401,7 +505,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -555,7 +659,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
       ]
     },
     {
@@ -676,6 +780,31 @@
         "dataframe[\"station_number\"] = pd.to_numeric(dataframe[\"station_number\"])"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bqml_create_dataset"
+      },
+      "source": [
+        "### Create BQ dataset resource\n",
+        "\n",
+        "First, you create an empty dataset resource in your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bqml_create_dataset"
+      },
+      "outputs": [],
+      "source": [
+        "BQ_MY_DATASET = 'samples'\n",
+        "BQ_MY_TABLE = 'gsod'\n",
+        "! bq --location=US mk -d \\\n",
+        "$PROJECT_ID:$BQ_MY_DATASET"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -979,7 +1108,7 @@
       },
       "outputs": [],
       "source": [
-        "SCHEMA_LOCATION = BUCKET_NAME + \"/schema.txt\"\n",
+        "SCHEMA_LOCATION = BUCKET_URI + \"/schema.txt\"\n",
         "\n",
         "# When running Apache Beam directly (file is directly accessed)\n",
         "tfdv.write_schema_text(output_path=SCHEMA_LOCATION, schema=schema)\n",
@@ -1124,7 +1253,7 @@
         "            )\n",
         "\n",
         "\n",
-        "EXPORTED_DATA_PREFIX = os.path.join(BUCKET_NAME, \"exported_data\")\n",
+        "EXPORTED_DATA_PREFIX = os.path.join(BUCKET_URI, \"exported_data\")\n",
         "\n",
         "QUERY_STRING = \"SELECT {},{} FROM {} LIMIT 500\".format(\n",
         "    \"CAST(station_number as STRING) AS station_number,year,month,day\",\n",
@@ -1137,7 +1266,7 @@
         "    \"runner\": RUNNER,\n",
         "    \"raw_data_query\": QUERY_STRING,\n",
         "    \"exported_data_prefix\": EXPORTED_DATA_PREFIX,\n",
-        "    \"temp_location\": os.path.join(BUCKET_NAME, \"temp\"),\n",
+        "    \"temp_location\": os.path.join(BUCKET_URI, \"temp\"),\n",
         "    \"project\": PROJECT_ID,\n",
         "    \"region\": REGION,\n",
         "    \"setup_file\": \"./setup.py\",\n",
@@ -1162,17 +1291,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1183,61 +1302,11 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_storage = True\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
+        "    if \"BUCKET_URI\" in globals():\n",
+        "        ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -34,15 +34,21 @@
         "<table align=\"left\">\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
+        "     <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "<img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "   <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>   \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -130,7 +136,17 @@
         "            - Create a tf.data.Dataset generator from the CSV index file.\n",
         "        - If text strings are in text files:\n",
         "            - Using the JSON index file, convert the text files and labels to TFRecords.\n",
-        "            - Create a tf.data.Dataset from the TFRecords."
+        "            - Create a tf.data.Dataset from the TFRecords.\n",
+        "\n",
+        "    \n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -141,7 +157,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -152,20 +168,27 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade db-dtypes $USER_FLAG -q! pip3 install --upgrade future $USER_FLAG -q"
       ]
     },
     {
@@ -197,6 +220,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cb082379ed5b"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -216,7 +263,24 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\"\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Get your Google Cloud project ID from gcloud\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "37c0a68ff20d"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
       ]
     },
     {
@@ -227,18 +291,15 @@
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_gcloud_project_id"
+        "id": "c021ca495967"
       },
       "outputs": [],
       "source": [
@@ -273,7 +334,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -300,6 +364,66 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "927085b84a07"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -328,7 +452,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -339,8 +463,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -360,7 +484,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -380,7 +504,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -392,7 +516,11 @@
         "### Set up variables\n",
         "\n",
         "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
+        "### Import libraries and define constants\n",
+        "\n",
+        "Import the BigQuery package, TensorFlow Data Validation (TFDV) package and TensorFlow Data Validation package into your Python environment. \n",
+        "\n",
+        "Import TensorFlow Transform (TFT) package and pandas into your Python environment."
       ]
     },
     {
@@ -403,97 +531,13 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_bq"
-      },
-      "source": [
-        "#### Import BigQuery\n",
-        "\n",
-        "Import the BigQuery package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_bq"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aip\n",
+        "import pandas as pd\n",
+        "import tensorflow_data_validation as tfdv\n",
+        "import tensorflow_transform as tft\n",
         "from google.cloud import bigquery"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tfdv"
-      },
-      "source": [
-        "#### Import TensorFlow Data Validation\n",
-        "\n",
-        "Import the TensorFlow Data Validation (TFDV) package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_tfdv"
-      },
-      "outputs": [],
-      "source": [
-        "import tensorflow_data_validation as tfdv"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tft"
-      },
-      "source": [
-        "#### Import TensorFlow Transform\n",
-        "\n",
-        "Import the TensorFlow Transform (TFT) package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_tft"
-      },
-      "outputs": [],
-      "source": [
-        "import tensorflow_transform as tft"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_pandas"
-      },
-      "source": [
-        "#### Import pandas\n",
-        "\n",
-        "Import the pandas package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_pandas"
-      },
-      "outputs": [],
-      "source": [
-        "import pandas as pd"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -513,7 +557,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -567,26 +611,13 @@
         "Learn more about [All dataset documentation](https://cloud.google.com/vertex-ai/docs/datasets/datasets)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:flowers,csv,icn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = (\n",
-        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
-        ")"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:image,icn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create an Image Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
         "\n",
@@ -601,6 +632,19 @@
         "Learn more about [ImageDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-image)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:flowers,csv,icn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = (\n",
+        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
+        ")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -618,24 +662,13 @@
         "print(dataset.resource_name)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:hmdb,csv,vcn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = \"gs://automl-video-demo-data/hmdb_split1_5classes_train_inf.csv\""
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:video,vcn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Video Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `VideoDataset` class, which takes the following parameters:\n",
         "\n",
@@ -649,6 +682,17 @@
         "Learn more about [VideoDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-video)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:hmdb,csv,vcn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://automl-video-demo-data/hmdb_split1_5classes_train_inf.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -666,24 +710,13 @@
         "print(dataset.resource_name)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:happydb,csv,tcn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = \"gs://cloud-ml-data/NL-classification/happiness.csv\""
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:text,tcn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Text Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
         "\n",
@@ -698,6 +731,17 @@
         "Learn more about [TextDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-text)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:happydb,csv,tcn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-ml-data/NL-classification/happiness.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -715,6 +759,24 @@
         "print(dataset.resource_name)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "source": [
+        "### Create a Tabular Dataset\n",
+        "\n",
+        "#### CSV input data\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class for CSV input data, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "\n",
+        "Learn more about [TabularDataset from CSV files](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_gcs_sample-python)"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -723,27 +785,50 @@
       },
       "outputs": [],
       "source": [
-        "IMPORT_FILE = \"bq://bigquery-public-data.samples.gsod\"\n",
-        "BQ_TABLE = \"bigquery-public-data.samples.gsod\""
+        "IMPORT_FILE = \"gs://cloud-samples-data/tables/iris_1000.csv\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.TabularDataset.create(\n",
+        "    display_name=\"example\" + \"_\" + TIMESTAMP, gcs_source=[IMPORT_FILE]\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "create_dataset:tabular,bq,lrg,v2"
+        "id": "854dd1e0195c"
       },
       "source": [
-        "### Create the Dataset\n",
+        "#### BigQuery input data\n",
         "\n",
-        "#### CSV input data\n",
-        "\n",
-        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class, which takes the following parameters:\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class for BigQuery table input, which takes the following parameters:\n",
         "\n",
         "- `display_name`: The human readable name for the `Dataset` resource.\n",
-        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
-        "- `labels`: User defined metadata. In this example, you store the location of the Cloud Storage bucket containing the user defined data.\n",
+        "- `bq_source`: A list of one or more BigQuery tables to import the data items into the `Dataset` resource.\n",
         "\n",
-        "Learn more about [TabularDataset from CSV files](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_gcs_sample-python)"
+        "Learn more about [TabularDataset from BigQuery table](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_bigquery_sample-pythonn)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "86343c146300"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"bq://bigquery-public-data.samples.gsod\"\n",
+        "BQ_TABLE = \"bigquery-public-data.samples.gsod\""
       ]
     },
     {
@@ -761,15 +846,63 @@
         "print(dataset.resource_name)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "82e9fe20ce71"
+      },
+      "source": [
+        "#### Dataframe input data\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create_from_dataframe` method for the `TabularDataset` class for pandas dataframe input, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `df_source`: The pandas dataframe to import the data items into the `Dataset` resource.\n",
+        "- `staging_path`: The BigQuery table to store the imported data."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_file:covid,csv,forecast"
+        "id": "3805f945ffdd"
       },
       "outputs": [],
       "source": [
-        "IMPORT_FILE = \"gs://cloud-samples-data/ai-platform/covid/bigquery-public-covid-nyt-us-counties-train.csv\""
+        "# Download the table.\n",
+        "table = bigquery.TableReference.from_string(BQ_TABLE)\n",
+        "\n",
+        "rows = bqclient.list_rows(\n",
+        "    table,\n",
+        "    max_results=10000,\n",
+        "    selected_fields=[\n",
+        "        bigquery.SchemaField(\"station_number\", \"STRING\"),\n",
+        "        bigquery.SchemaField(\"year\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"month\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"day\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"mean_temp\", \"FLOAT\"),\n",
+        "    ],\n",
+        ")\n",
+        "\n",
+        "dataframe = rows.to_dataframe()\n",
+        "print(dataframe.head())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.TabularDataset.create_from_dataframe(\n",
+        "    display_name=\"example\" + \"_\" + TIMESTAMP,\n",
+        "    df_source=dataframe,\n",
+        "    staging_path=f\"bq://{PROJECT_ID}.samples.gsod\",\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
       ]
     },
     {
@@ -778,7 +911,7 @@
         "id": "create_dataset:tabular,forecast,v2"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Time Series Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `TimeSeriesDataset` class, which takes the following parameters:\n",
         "\n",
@@ -789,6 +922,17 @@
         "Learn more about [TimeSeriesDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-tabular)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:covid,csv,forecast"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/ai-platform/covid/bigquery-public-covid-nyt-us-counties-train.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1149,9 +1293,9 @@
         "comps = BQ_TABLE.split(\".\")\n",
         "BQ_PROJECT_DATASET_TABLE = comps[0] + \":\" + comps[1] + \".\" + comps[2]\n",
         "\n",
-        "! bq --location=us extract --destination_format CSV $BQ_PROJECT_DATASET_TABLE $BUCKET_NAME/mydata*.csv\n",
+        "! bq --location=us extract --destination_format CSV $BQ_PROJECT_DATASET_TABLE $BUCKET_URI/mydata*.csv\n",
         "\n",
-        "IMPORT_FILES = ! gsutil ls $BUCKET_NAME/mydata*.csv\n",
+        "IMPORT_FILES = ! gsutil ls $BUCKET_URI/mydata*.csv\n",
         "\n",
         "print(IMPORT_FILES)\n",
         "\n",
@@ -1209,6 +1353,38 @@
         "To create a dataframe from multiple CSV sources, you read each CSV file and concatenate the dataframes together."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bcd2e4e0703b"
+      },
+      "source": [
+        "If you are running this notebook on Colab, run the following cell to install packages fsspec and gcsfs."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "927bd3f92268"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Workbench AI Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        ! pip3 install fsspec\n",
+        "        ! pip3 install gcsfs"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1269,7 +1445,7 @@
       },
       "outputs": [],
       "source": [
-        "EXPORTED_DIR = f\"{BUCKET_NAME}/exported\"\n",
+        "EXPORTED_DIR = f\"{BUCKET_URI}/exported\"\n",
         "exported_files = dataset.export_data(output_dir=EXPORTED_DIR)\n",
         "\n",
         "! gsutil ls $EXPORTED_DIR"
@@ -1498,7 +1674,7 @@
         "    data = f.readlines()\n",
         "\n",
         "# The path to the TFRecord cached file.\n",
-        "GCS_TFRECORD_URI = BUCKET_NAME + \"/flowers.tfrecord\"\n",
+        "GCS_TFRECORD_URI = BUCKET_URI + \"/flowers.tfrecord\"\n",
         "\n",
         "# Create the TFRecord cached file\n",
         "with tf.io.TFRecordWriter(GCS_TFRECORD_URI) as writer:\n",
@@ -1532,14 +1708,7 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "- Bucket"
       ]
     },
     {
@@ -1550,61 +1719,16 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "datasets = aip.TabularDataset.list(filter=f'display_name=\"example_{TIMESTAMP}\"')\n",
+        "for dataset in datasets:\n",
+        "    dataset.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "# Delete the bucket\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb

@@ -0,0 +1,994 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "copyright"
+      },
+      "outputs": [],
+      "source": [
+        "# Copyright 2022 Google LLC\n",
+        "#\n",
+        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+        "# you may not use this file except in compliance with the License.\n",
+        "# You may obtain a copy of the License at\n",
+        "#\n",
+        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+        "#\n",
+        "# Unless required by applicable law or agreed to in writing, software\n",
+        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+        "# See the License for the specific language governing permissions and\n",
+        "# limitations under the License."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4JIDiHvGasba"
+      },
+      "source": [
+        "This notebook was contributed by [Mohammad Al-Ansari](https://github.com/Mansari)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2xDiUNIZINWp"
+      },
+      "source": [
+        "# E2E ML on GCP: MLOps stage 1 : data management: create an unlabelled Vertex AI AutoML text entity extraction dataset from PDFs using Vision API\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+        "      View on GitHub\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb\">\n",
+        "     <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>\n",
+        "<br/><br/><br/>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "H0alLPo_A-LK"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This notebook will create an unlabelled `Vertex AI AutoML` text entity extraction dataset based on a collection of PDF files stored in a Cloud Storage bucket. \n",
+        "\n",
+        "The notebook can be modified to create different types of text datasets including sentiment analysis and classification."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "W4IBLTKOA5nl"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Patent PDF Samples with Extracted Structured Data](https://console.cloud.google.com/marketplace/product/global-patents/labeled-patents) from Google Public Data Sets. \n",
+        "\n",
+        "This dataset includes data extracted from over 300 patent documents issued in the US and EU. The dataset includes links to Cloud Storage blobs for the first page of each patent, in addition to a number of extracted entities. \n",
+        "\n",
+        "The data is published as a [public dataset](https://cloud.google.com/bigquery/public-data) on `BigQuery`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3f8c2f702ccd"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn to use `Vision API` to extract text from PDF files stored on a Cloud Storage bucket. You will then process the results and create an unlabelled `Vertex AI Dataset`, compatible with `AutoML`, for text entity extraction.\n",
+        "\n",
+        "You can then either use Google Cloud console to annotate / label the dataset, or create a labelling job as demonstrated in [this notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb).\n",
+        "\n",
+        "This tutorial uses the following Google Cloud services:\n",
+        "\n",
+        "- `Vision AI`\n",
+        "- `Vertex AI AutoML`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "1. Using `Vision API` to perform Optical Character Recognition (OCR) to extract text from PDF files.\n",
+        "2. Processing the results and saving them to text files.\n",
+        "3. Generating a `Vertex AI Dataset` import file.\n",
+        "4. Creating a new unlabelled text entity extraction `Vertex AI Dataset` resource in `Vertex AI`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CgLDJ419LPJs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vision API\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Vision API pricing](https://cloud.google.com/vision/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "va2g7m9wLTjA"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "If you are using Colab or Vertex AI Workbench Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "\n",
+        "- The Vision API SDK\n",
+        "- The Vertex AI SDK\n",
+        "- The Cloud Storage SDK\n",
+        "- Git\n",
+        "- Python 3\n",
+        "- virtualenv\n",
+        "- Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
+        "\n",
+        "1. [Install and initialize the SDKs](https://cloud.google.com/sdk/docs/).\n",
+        "\n",
+        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "\n",
+        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
+        "\n",
+        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "\n",
+        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "X2tZAmugAe6h"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the packages required for executing this notebook. You can ignore errors for the `pip` dependecy resolver as they do not impact this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "BQOsJ1hZAZu0"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-storage google-cloud-vision google-cloud-aiplatform $USER_FLAG -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "yzvvcmCuAon3"
+      },
+      "source": [
+        "### Restart the kernel\n",
+        "\n",
+        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6qEonzbuAoI_"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Automatically restart kernel after installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "pGbbyN7rAuRM"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### GPU runtime\n",
+        "\n",
+        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vision API, Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=vision.googleapis.com,aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "AE97adtnAzrr"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "nWlzLu5ELxWd"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GB5b27r0LxqE"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "pMJdU1K5xG7D"
+      },
+      "source": [
+        "### Regions\n",
+        "\n",
+        "#### Vision AI\n",
+        "\n",
+        "You can now specify continent-level data storage and Optical Character Regonition (OCR) processing by setting the `VISION_AI_REGION` variable. You can select one of the following options:\n",
+        "\n",
+        "* USA country only: `us`\n",
+        "* The European Union: `eu`\n",
+        "\n",
+        "Learn more about [Vision AI regions for OCR](https://cloud.google.com/vision/docs/pdf#regionalization)\n",
+        "\n",
+        "#### Vertex AI\n",
+        "\n",
+        "You can also change the `VERTEX_AI_REGION` variable, which is used for operations throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "\n",
+        "- Americas: `us-central1`\n",
+        "- Europe: `europe-west4`\n",
+        "- Asia Pacific: `asia-east1`\n",
+        "\n",
+        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "\n",
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5EhEAOK5xIKc"
+      },
+      "outputs": [],
+      "source": [
+        "VISION_AI_REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if VISION_AI_REGION == \"[your-region]\":\n",
+        "    VISION_AI_REGION = \"us\"\n",
+        "\n",
+        "VERTEX_AI_REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if VERTEX_AI_REGION == \"[your-region]\":\n",
+        "    VERTEX_AI_REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "xkgvWoXkxM1r"
+      },
+      "source": [
+        "### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append onto the name of resources which will be created in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gr0HTpQZxNy4"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AA-ns5CcBA9U"
+      },
+      "source": [
+        "### Vertex AI dataset import schema\n",
+        "\n",
+        "This constant tells Vertex AI the schema for importing the dataset. In this tutorial you are going to use the value for text extraction, but you can also change it to any of the values below for other use cases:\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.single_label_classification`\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.multi_label_classification`\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.extraction`\n",
+        "\n",
+        "- \n",
+        "`aiplatform.schema.dataset.ioformat.text.sentiment`\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jnOb6Pp-4w5P"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import aiplatform\n",
+        "\n",
+        "DATASET_IMPORT_SCHEMA = aiplatform.schema.dataset.ioformat.text.extraction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ekbg-G7UA-bK"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench**, your environment is already authenticated. Skip this step. If you receive errors still, you may have to grant the service account that is your Workbench notebook is running under access to the services listed below.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "lCRrULxKBAfa"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "rHB6fbonMMbI"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions. This bucket will be also used to store the output of the Vision API SDK PDF-to-text conversion process.\n",
+        "\n",
+        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZSM5j0nfMOVK"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "i6H2iQX2MP-s"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AOsnYE5cMQX4"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "33RgSjhyMR6C"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $VERTEX_AI_REGION -p $PROJECT_ID $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UpKfi0VfMTwe"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G9dMjMnkMVNt"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "k2qH7YCI0vnG"
+      },
+      "source": [
+        "### Set up variables\n",
+        "\n",
+        "Next, set up some variables used throughout the tutorial.\n",
+        "\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "TB5-_2Xh01NH"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "from google.cloud import aiplatform, storage, vision"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "-v7gY_KABIn8"
+      },
+      "source": [
+        "### Initialize Vision API SDK for Python\n",
+        "\n",
+        "Initialize the `Vision AI` SDK for Python for your project and region."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "DRbf--kWBLpx"
+      },
+      "outputs": [],
+      "source": [
+        "vision_client_options = {\n",
+        "    \"quota_project_id\": PROJECT_ID,\n",
+        "    \"api_endpoint\": f\"{VISION_AI_REGION}-vision.googleapis.com\",\n",
+        "}\n",
+        "vision_client = vision.ImageAnnotatorClient(client_options=vision_client_options)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CA4nNVbBZ25d"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the `Vertex AI` SDK for Python for your project, region and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "awWpNW1vZ6uV"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(\n",
+        "    project=PROJECT_ID, location=VERTEX_AI_REGION, staging_bucket=BUCKET_URI\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "debBBljMDqkM"
+      },
+      "source": [
+        "### Initialize Cloud Storage SDK for Python\n",
+        "\n",
+        "Initialize the `Cloud Storage` SDK for Python for your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ZtzmI9tpDr4e"
+      },
+      "outputs": [],
+      "source": [
+        "storage_client = storage.Client(project=PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "mvD0BxVXMtJe"
+      },
+      "source": [
+        "## Tutorial\n",
+        "\n",
+        "Now you are ready to start creating an unlabelled `Vertex AI Dataset` text entity extraction dataset from PDF files."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EurEFM3GBap9"
+      },
+      "source": [
+        "### Convert PDF files to text using Vision API\n",
+        "\n",
+        "First, you make a `Vision API` request to OCR to text the PDFs from the Patent samples stored in the Cloud Storage bucket.\n",
+        "\n",
+        "*Note:* `Visions API` only allows batches of 100 document submissions at a time."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "uXVPOvjTBeK3"
+      },
+      "outputs": [],
+      "source": [
+        "ORIGIN_BUCKET_NAME = \"gcs-public-data--labeled-patents\"\n",
+        "# You can add a path if needed\n",
+        "ORIGIN_BUCKET_PATH = \"\"\n",
+        "\n",
+        "DESTINATION_BUCKET_NAME = BUCKET_NAME\n",
+        "DESTINATION_BUCKET_PATH = \"ocr-output\"\n",
+        "\n",
+        "gcs_destination_uri = f\"gs://{DESTINATION_BUCKET_NAME}/{DESTINATION_BUCKET_PATH}\"\n",
+        "\n",
+        "# Specify the feature for the Vision API processor\n",
+        "feature = vision.Feature(type_=vision.Feature.Type.DOCUMENT_TEXT_DETECTION)\n",
+        "\n",
+        "# Retrieve a list of all files in the bucket and path\n",
+        "blobs = storage_client.list_blobs(\n",
+        "    ORIGIN_BUCKET_NAME, prefix=ORIGIN_BUCKET_PATH, delimiter=\"/\"\n",
+        ")\n",
+        "\n",
+        "# Create a collection of requests. The SDK requires a separate request per each\n",
+        "# file that we want to extract text from\n",
+        "async_requests = []\n",
+        "\n",
+        "# Visions API only supports processing up to 100 documents at a time\n",
+        "# so we will process the first 100 elements only\n",
+        "sliced_blob_list = list(blobs)[:100]\n",
+        "\n",
+        "# Loop through the source bucket and create a request for each file there\n",
+        "for blob in sliced_blob_list:\n",
+        "    # Build input_config\n",
+        "    # Ensure we are only processing PDF files\n",
+        "    if blob.name.endswith(\".pdf\"):\n",
+        "        gcs_source = vision.GcsSource(uri=f\"gs://{ORIGIN_BUCKET_NAME}/{blob.name}\")\n",
+        "        input_config = vision.InputConfig(\n",
+        "            gcs_source=gcs_source, mime_type=\"application/pdf\"\n",
+        "        )\n",
+        "\n",
+        "        # Build output config\n",
+        "        # Get file name\n",
+        "        file_name = os.path.splitext(os.path.basename(blob.name))[0]\n",
+        "        gcs_destination = vision.GcsDestination(\n",
+        "            uri=f\"{gcs_destination_uri}/{file_name}-\"\n",
+        "        )\n",
+        "        output_config = vision.OutputConfig(gcs_destination=gcs_destination)\n",
+        "\n",
+        "        # Build request object and add to the collection\n",
+        "        async_request = vision.AsyncAnnotateFileRequest(\n",
+        "            features=[feature], input_config=input_config, output_config=output_config\n",
+        "        )\n",
+        "\n",
+        "        async_requests.append(async_request)\n",
+        "\n",
+        "print(f\"Created {len(async_requests)} requests\")\n",
+        "\n",
+        "# Submit the batch OCR job\n",
+        "\n",
+        "operation = vision_client.async_batch_annotate_files(requests=async_requests)\n",
+        "print(\"Submitting the batch OCR job\")\n",
+        "\n",
+        "print(\"Waiting for the operation to finish... this will take a short while\")\n",
+        "\n",
+        "response = operation.result(timeout=420)\n",
+        "\n",
+        "print(\"Completed!\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7b15473e1937"
+      },
+      "source": [
+        "#### Quick peek at extracted annotated JSON files\n",
+        "\n",
+        "Next, you take a peek at the contents of one of the extracted JSON annotated files."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4366442c1373"
+      },
+      "outputs": [],
+      "source": [
+        "json_files = ! gsutil ls {gcs_destination_uri}\n",
+        "\n",
+        "example = json_files[0]\n",
+        "! gsutil cat {example} | head -n 1"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "QWmeHWPIHako"
+      },
+      "source": [
+        "### Process results and build the import file\n",
+        "\n",
+        "The `Vision API` output is in JSON format, and contains detailed text extraction data. You only need the full text output, so you will processs the JSON results, extract the text output, and save it in new text files to be used later in the tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "WDLtiejKHug6"
+      },
+      "outputs": [],
+      "source": [
+        "import json\n",
+        "\n",
+        "print(\"Extracting text from Vision API output and saving it to text files\")\n",
+        "\n",
+        "ocr_blobs = storage_client.list_blobs(\n",
+        "    DESTINATION_BUCKET_NAME, prefix=DESTINATION_BUCKET_PATH\n",
+        ")\n",
+        "\n",
+        "output_bucket = storage_client.bucket(DESTINATION_BUCKET_NAME)\n",
+        "\n",
+        "# begin building the import file content\n",
+        "import_file_entries = []\n",
+        "\n",
+        "for ocr_blob in ocr_blobs:\n",
+        "    # Only process .json files, in case we previously processed files and had .txt files\n",
+        "    if ocr_blob.name.endswith(\".json\"):\n",
+        "        print(f\"Extracting text from {ocr_blob.name}\")\n",
+        "        # read each blob into a stream\n",
+        "        contents = ocr_blob.download_as_string()\n",
+        "        # load as JSON\n",
+        "        json_object = json.loads(contents)\n",
+        "        # extract text\n",
+        "        full_text = \"\"\n",
+        "        for response in json_object[\"responses\"]:\n",
+        "            if response[\"fullTextAnnotation\"]:\n",
+        "                full_text += response[\"fullTextAnnotation\"][\"text\"] + \"\\r\\n\"\n",
+        "\n",
+        "        # save as a blob\n",
+        "        output_blob_name = f\"{ocr_blob.name}.txt\"\n",
+        "        import_file_blob = output_bucket.blob(output_blob_name)\n",
+        "        import_file_blob.upload_from_string(full_text)\n",
+        "\n",
+        "        # create import file listing\n",
+        "        import_file_entry = {\n",
+        "            \"textGcsUri\": f\"gs://{DESTINATION_BUCKET_NAME}/{output_blob_name}\"\n",
+        "        }\n",
+        "\n",
+        "        import_file_entries.append(import_file_entry)\n",
+        "\n",
+        "print(\"Extraction completed!\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0a5aae0eab44"
+      },
+      "source": [
+        "#### Quick peek at extracted text files\n",
+        "\n",
+        "Next, you take a peek at the contents of one of the extracted text files."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "76ce5f57b1ae"
+      },
+      "outputs": [],
+      "source": [
+        "example = import_file_entries[0][\"textGcsUri\"]\n",
+        "\n",
+        "! gsutil cat {example}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hqTLS_AmLWQP"
+      },
+      "source": [
+        "### Generate and save import file to be used in `Vertex AI Dataset` resource\n",
+        "\n",
+        "You will now build the import file that will be used to create the `Vertex AI Dataset` resource."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "_xFvOdQ_LWne"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE_PATH = \"import_file\"\n",
+        "\n",
+        "# Convert import file entries to JSON Lines format\n",
+        "import_file_content = \"\"\n",
+        "for entry in import_file_entries:\n",
+        "    import_file_content += json.dumps(entry) + \"\\n\"\n",
+        "\n",
+        "print(f\"Created import file based on {len(import_file_entries)} annotations\")\n",
+        "\n",
+        "# Upload content to GCS to be used in our next step\n",
+        "gcs_annotation_file_name = f\"{IMPORT_FILE_PATH}/import_file_{TIMESTAMP}.jsonl\"\n",
+        "import_file_blob = output_bucket.blob(gcs_annotation_file_name)\n",
+        "import_file_blob.upload_from_string(import_file_content)\n",
+        "\n",
+        "print(f\"Uploaded import file to {output_bucket.name}/{gcs_annotation_file_name}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6dVjFftOaKdw"
+      },
+      "source": [
+        "### Create an unlabelled `Vertex AI Dataset` resource\n",
+        "\n",
+        "Next, you create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `import_schema_uri`: The data labeling schema for the data items.\n",
+        "\n",
+        "This operation may take ten to twenty minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ciM9HLGCaOTJ"
+      },
+      "outputs": [],
+      "source": [
+        "print(\"Creating dataset ...\")\n",
+        "\n",
+        "dataset = aiplatform.TextDataset.create(\n",
+        "    display_name=\"Text Dataset \" + TIMESTAMP,\n",
+        "    gcs_source=[f\"gs://{output_bucket.name}/{gcs_annotation_file_name}\"],\n",
+        "    import_schema_uri=DATASET_IMPORT_SCHEMA,\n",
+        ")\n",
+        "\n",
+        "print(\"Completed!\")\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2vagHf5T6Jd4"
+      },
+      "source": [
+        "**Congratulations, your dataset is now ready for annotations!**\n",
+        "\n",
+        "You have two options:\n",
+        "\n",
+        "*   Use Google Cloud Console to manually annotate the dataset in `Vertex AI`. Checkout [this link](https://cloud.google.com/vertex-ai/docs/datasets/label-using-console#entity-extraction) for more details on how to do so.\n",
+        "*   Create a labelling job to request data labelling. Check out [this link](https://cloud.google.com/vertex-ai/docs/datasets/data-labeling-job) and [this notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb) for more details and examples.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:migration,new"
+      },
+      "source": [
+        "# Cleaning up\n",
+        "\n",
+        "To clean up all GCP resources used in this project, you can [delete the GCP\n",
+        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "aoJ18d8Y_jAy"
+      },
+      "outputs": [],
+      "source": [
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
+        "\n",
+        "# Delete the dataset using the Vertex AI fully qualified identifier for the dataset\n",
+        "dataset.delete()\n",
+        "\n",
+        "# Delete the bucket created\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
+      ]
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "collapsed_sections": [],
+      "name": "get_started_with_visionapi_and_vertex_datasets.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/community/ml_ops/stage1/mlops_data_management.ipynb

@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/mlops_data_management.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage1/mlops_data_management.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage1/mlops_data_management.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -133,7 +139,20 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "ONCE_ONLY = True\n",
         "if ONCE_ONLY:\n",
         "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
         "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
@@ -178,6 +197,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -254,7 +299,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -281,6 +329,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -309,7 +418,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -320,8 +430,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -341,7 +452,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -361,7 +472,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -516,7 +627,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -757,7 +868,7 @@
         "dataset = aip.TabularDataset.create(\n",
         "    display_name=\"Chicago Taxi\" + \"_\" + TIMESTAMP,\n",
         "    bq_source=[IMPORT_FILE],\n",
-        "    labels={\"user_metadata\": BUCKET_NAME[5:]},\n",
+        "    labels={\"user_metadata\": BUCKET_NAME},\n",
         ")\n",
         "\n",
         "label_column = \"tip_bin\"\n",
@@ -949,9 +1060,9 @@
       },
       "outputs": [],
       "source": [
-        "STATISTICS_SCHEMA = BUCKET_NAME + \"/statistics.jsonl\"\n",
+        "STATISTICS_SCHEMA = BUCKET_URI + \"/statistics.jsonl\"\n",
         "\n",
-        "tfdv.write_stats_text(stats, BUCKET_NAME + \"/statistics.jsonl\")\n",
+        "tfdv.write_stats_text(stats, BUCKET_URI + \"/statistics.jsonl\")\n",
         "\n",
         "with tf.io.gfile.GFile(\n",
         "    \"gs://\" + dataset.labels[\"user_metadata\"] + \"/metadata.jsonl\", \"r\"\n",
@@ -964,7 +1075,7 @@
         ") as f:\n",
         "    json.dump(metadata, f)\n",
         "\n",
-        "!gsutil cat $BUCKET_NAME/metadata.jsonl"
+        "! gsutil cat $BUCKET_URI/metadata.jsonl"
       ]
     },
     {
@@ -1011,7 +1122,7 @@
       },
       "outputs": [],
       "source": [
-        "SCHEMA_LOCATION = BUCKET_NAME + \"/schema.txt\"\n",
+        "SCHEMA_LOCATION = BUCKET_URI + \"/schema.txt\"\n",
         "\n",
         "# When running Apache Beam directly (file is directly accessed)\n",
         "tfdv.write_schema_text(output_path=SCHEMA_LOCATION, schema=schema)\n",
@@ -1049,7 +1160,7 @@
         ") as f:\n",
         "    json.dump(metadata, f)\n",
         "\n",
-        "!gsutil cat $BUCKET_NAME/metadata.jsonl"
+        "! gsutil cat $BUCKET_URI/metadata.jsonl"
       ]
     },
     {
@@ -1372,10 +1483,10 @@
         "            )\n",
         "\n",
         "\n",
-        "EXPORTED_JSONL_PREFIX = os.path.join(BUCKET_NAME, \"exported_data/jsonl\")\n",
-        "EXPORTED_TFREC_PREFIX = os.path.join(BUCKET_NAME, \"exported_data/tfrec\")\n",
-        "TRANSFORMED_DATA_PREFIX = os.path.join(BUCKET_NAME, \"transformed_data\")\n",
-        "TRANSFORM_ARTIFACTS_DIR = os.path.join(BUCKET_NAME, \"transformed_artifacts\")\n",
+        "EXPORTED_JSONL_PREFIX = os.path.join(BUCKET_URI, \"exported_data/jsonl\")\n",
+        "EXPORTED_TFREC_PREFIX = os.path.join(BUCKET_URI, \"exported_data/tfrec\")\n",
+        "TRANSFORMED_DATA_PREFIX = os.path.join(BUCKET_URI, \"transformed_data\")\n",
+        "TRANSFORM_ARTIFACTS_DIR = os.path.join(BUCKET_URI, \"transformed_artifacts\")\n",
         "\n",
         "QUERY_STRING = \"SELECT * FROM {} LIMIT 300000\".format(BQ_TABLE)\n",
         "JOB_NAME = \"chicago\" + TIMESTAMP\n",
@@ -1388,7 +1499,7 @@
         "    \"transform_artifact_dir\": TRANSFORM_ARTIFACTS_DIR,\n",
         "    \"exported_jsonl_prefix\": EXPORTED_JSONL_PREFIX,\n",
         "    \"exported_tfrec_prefix\": EXPORTED_TFREC_PREFIX,\n",
-        "    \"temp_location\": os.path.join(BUCKET_NAME, \"temp\"),\n",
+        "    \"temp_location\": os.path.join(BUCKET_URI, \"temp\"),\n",
         "    \"project\": PROJECT_ID,\n",
         "    \"region\": REGION,\n",
         "    \"setup_file\": \"./setup.py\",\n",
@@ -1459,7 +1570,7 @@
         ") as f:\n",
         "    json.dump(metadata, f)\n",
         "\n",
-        "!gsutil cat $BUCKET_NAME/metadata.jsonl"
+        "! gsutil cat $BUCKET_URI/metadata.jsonl"
       ]
     },
     {
@@ -1473,17 +1584,9 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "*Note:* stage2/mlops_experimentation is dependent on the resources created by this stage1 notebook."
       ]
     },
     {
@@ -1504,8 +1607,8 @@
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "    if \"BUCKET_URI\" in globals():\n",
+        "        ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/README.md

@@ -25,7 +25,11 @@ The second stage in MLOps is experimenting in developing one or more baseline mo
 - Use the What-if-Tool (WIT) to explore how the trained model would make predictions in different scenarios.
 
 
-<img src='stage2.png'>
+<img src='stage2v3.png'>
+<br/>
+<br/>
+<br/>
+<img src='stage2.2v1.png'>
 
 ## Notebooks
 
@@ -115,6 +119,32 @@ The steps performed include:
 - Train a R model using `Vertex AI Trainingh` service with the R-to-Python training package.
 ```
 
+[Get Started with Custom Training Packages (R) and Deployment in R environment](get_started_vertex_training_r_using_r_kernel.ipynb)
+```
+The steps performed include:
+
+- Create a custom R training script
+- Create a custom R serving script
+- Create a custom R deployment (serving) container.
+- Train the model using `Vertex AI` custom training.
+- Create an `Endpoint` resource.
+- Deploy the `Model` resource (trained R model) to the `Endpoint` resource.
+- Make an online prediction.
+```
+
+[Get Started with Custom Training Packages (LightGBM)](get_started_vertex_training_lightgbm.ipynb)
+
+```
+The steps performed include:
+
+- Training using a Python package.
+- Save the model artifacts to Cloud Storage using GCSFuse.
+- Construct a FastAPI prediction server.
+- Construct a Dockerfile deployment image.
+- Test the deployment image locally.
+- Create a `Vertex AI Model` resource.
+```
+
 [Get Started with Distributed Training](get_started_vertex_distributed_training.ipynb)
 
 ```
@@ -153,12 +183,13 @@ The steps performed include:
 ```
 The steps performed include:
 
-- Create a local BQ table in your project.
-- Train a BQML model.
-- Evaluate the BQML model.
-- Export the BQML model as a cloud model.
-- Upload the exported model as a Vertex AI Model resource.
-- Hyperparameter tune a BQML model with Vertex AI Vizier.
+- Create a local BigQuery table in your project
+- Train a BQML model
+- Evaluate the BQML model
+- Export the BQML model as a cloud model
+- Upload the exported model as a `Vertex AI Model` resource
+- Hyperparameter tune a BQML model with `Vertex AI Vizier`
+- Automatically register a BQML model to `Vertex AI Model Registry`
 ```
 
 [Get Started with Vertex Feature Store](get_started_vertex_feature_store.ipynb)
@@ -169,11 +200,66 @@ The steps performed include:
 - Creating a Vertex AI `Featurestore` resource.
     - Creating `EntityType` resources for the `Featurestore` resource.
     - Creating `Feature` resources for each `EntityType` resource.
-- Import feature values (entity data items) into `Featurestore` resource.
+- Import feature values (entity data items) into `Featurestore` resource from Cloud Storage.
+- Import feature values (entity data items) into `Featurestore` resource from pandas DataFrame.
 - Perform online serving from a `Featurestore` resource.
 - Perform batch serving from a `Featurestore` resource.
 ```
 
+[Get Started with Google CMEK Training](get_started_with_cmek_training.ipynb)
+
+```
+The steps performed include:
+
+- Creating a customer managed encryption key.
+- Creating an image dataset with CMEK encryption.
+- Train an AutoML model with CMEK encryption.
+```
+
+[Get Started with TensorFlow Hub models](get_started_with_tfhub_models.ipynb)
+
+```
+The steps performed include:
+
+- Download a TensorFlow Hub prebuilt model.
+- Add the task component as a classifier for the CIFAR-10 dataset.
+- Fine tune locally the model with transfer learning training.
+- Construct a custom training script:
+    - Get training data from TensorFlow Datasets
+    - Get model architecture from TensorFlow Hub
+    - Train then model
+    - Save model artifacts and upload as Vertex AI Model resource.
+```
+
+[Get Started with Vertex AI TabNet builtin algorithm](get_started_with_tabnet.ipynb)
+```
+The steps performed include:
+
+- Get the training data.
+- Configure training parameters for the Vertex AI TabNet container.
+- Train the model using Vertex AI Training using CSV data.
+- Upload the model as a Vertex AI Model resource.
+- Deploy the Vertex AI Model resource to a Vertex AI Endpoint resource.
+- Make a prediction with the deployed model.
+- Hyperparameter tuning the Vertex AI TabNet model.
+- Train the model using Vertex AI Training using BigQuery table.
+```
+
+[Get Started with Vision API and AutoML](get_started_with_visionapi_and_automl.ipynb)
+```
+The steps performed include:
+
+- Preprocess training files using `Vision AI` APIs to extract the text from PDF files.
+- Create a custom import file that includes annotation data based on the sample `BigQuery` dataset.
+- Create a `Vertex AI Dataset` resource.
+- Train the model.
+- View the model evaluation.
+- Deploy the `Vertex AI Model` resource to a serving `Endpoint` resource.
+- Make a prediction.
+- Undeploy the `Model`.
+```
+
+
 ### E2E Stage Example
 
 [Stage 2: Experimentation](mlops_experimentation.ipynb)

notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -65,9 +71,11 @@
         "id": "dataset:flowers,icn"
       },
       "source": [
-        "### Dataset\n",
+        "### Datasets\n",
         "\n",
-        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower an image is from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
+        "#### Image\n",
+        "\n",
+        "The image dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower in a given image from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
       ]
     },
     {
@@ -76,9 +84,9 @@
         "id": "dataset:gsod,lrg"
       },
       "source": [
-        "### Dataset\n",
+        "#### Tabular\n",
         "\n",
-        "The dataset used for this tutorial is the GSOD dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). The version of the dataset you use only the fields year, month and day to predict the value of mean daily temperature (mean_temp)."
+        "The tabular dataset used for this tutorial is the GSOD dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). The version of the dataset you use only the fields year, month and day to predict the value of mean daily temperature (mean_temp)."
       ]
     },
     {
@@ -87,9 +95,20 @@
         "id": "dataset:happydb,tcn"
       },
       "source": [
-        "### Dataset\n",
+        "#### Text\n",
         "\n",
-        "The dataset used for this tutorial is the [Happy Moments dataset](https://www.kaggle.com/ritresearch/happydb) from [Kaggle Datasets](https://www.kaggle.com/ritresearch/happydb). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+        "The text dataset used for this tutorial is the [Happy Moments dataset](https://www.kaggle.com/ritresearch/happydb) from [Kaggle Datasets](https://www.kaggle.com/ritresearch/happydb). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "98eb93ec6faa"
+      },
+      "source": [
+        "#### Video\n",
+        "\n",
+        "The video dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset](https://todo) from [MIT](http://cbcl.mit.edu/publications/ps/Kuehne_etal_iccv11.pdf). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model will predict the start frame where a golf swing begins."
       ]
     },
     {
@@ -108,11 +127,12 @@
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Train an image model.\n",
-        "- Export the image model as an edge model.\n",
-        "- Train a tabular model.\n",
-        "- Export the tabular model as a cloud model.\n",
-        "- Train a text model."
+        "- Train an image model\n",
+        "- Export the image model as an edge model\n",
+        "- Train a tabular model\n",
+        "- Export the tabular model as a cloud model\n",
+        "- Train a text model\n",
+        "- Train a video model"
       ]
     },
     {
@@ -125,9 +145,24 @@
         "\n",
         "When doing E2E MLOps on Google Cloud, the following are best practices for when to use AutoML:\n",
         "\n",
-        "**You have a limited amount of training data**\n",
+        "* **You have a limited amount of training data**\n",
         "\n",
-        "**You want to establish a baseline metric before experimenting with a custom model**"
+        "* **You want to establish a baseline metric before experimenting with a custom model**"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb3451ce8e47"
+      },
+      "source": [
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -138,7 +173,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -149,20 +184,23 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the packages\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-storage $USER_FLAG -q"
       ]
     },
     {
@@ -200,6 +238,23 @@
         "id": "project_id"
       },
       "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
         "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
@@ -270,7 +325,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -297,6 +355,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3ffa6b6c7cdb"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2b72272258fc"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -320,7 +439,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -331,8 +451,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -352,7 +473,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -372,7 +493,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -395,7 +516,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -417,7 +538,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -448,7 +569,7 @@
       "source": [
         "## AutoML image models\n",
         "\n",
-        "AutoML can train the following types of models:\n",
+        "AutoML can train the following types of image models:\n",
         "\n",
         "- classification\n",
         "- objection detection\n",
@@ -504,10 +625,7 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    FILE = IMPORT_FILES[0]\n",
-        "else:\n",
-        "    FILE = IMPORT_FILE\n",
+        "FILE = IMPORT_FILE\n",
         "\n",
         "count = ! gsutil cat $FILE | wc -l\n",
         "print(\"Number of Examples\", int(count[0]))\n",
@@ -545,10 +663,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.ImageDataset.create(\n",
-        "    display_name=\"Happy Moments\" + \"_\" + TIMESTAMP,\n",
+        "dataset = aiplatform.ImageDataset.create(\n",
+        "    display_name=\"flowers_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.image.single_label_classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -593,8 +711,8 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLImageTrainingJob(\n",
-        "    display_name=\"happydb_\" + TIMESTAMP,\n",
+        "dag = aiplatform.AutoMLImageTrainingJob(\n",
+        "    display_name=\"flowers_\" + TIMESTAMP,\n",
         "    prediction_type=\"classification\",\n",
         "    multi_label=False,\n",
         "    model_type=\"MOBILE_TF_LOW_LATENCY_1\",\n",
@@ -612,14 +730,14 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
         "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
         "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
         "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
-        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of milli node-hours (1000 = node-hour).\n",
         "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
@@ -637,7 +755,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"happydb_\" + TIMESTAMP,\n",
+        "    model_display_name=\"flowers_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -653,9 +771,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -666,18 +783,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=happydb_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -721,7 +830,7 @@
       "source": [
         "### Get test item\n",
         "\n",
-        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model -- we just want to demonstrate how to make a prediction."
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used in training the model. You are just looking at how to make a prediction."
       ]
     },
     {
@@ -753,7 +862,7 @@
         "\n",
         "#### Request\n",
         "\n",
-        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 -- which makes the content safe from modification while transmitting binary data over the network.\n",
+        "Since your test item is in a public Cloud Storage bucket in this example, you copy it to your bucket and read the contents of the image using `Cloud Storage SDK`. To pass the test data to the prediction service, you encode the bytes into base64 which makes the content safe from modification while transmitting binary data over the network.\n",
         "\n",
         "The format of each instance is:\n",
         "\n",
@@ -775,32 +884,66 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "predict_request:mbsdk,icn"
+        "id": "1c1d53e89beb"
       },
       "outputs": [],
       "source": [
         "import base64\n",
         "\n",
-        "import tensorflow as tf\n",
+        "from google.cloud import storage\n",
         "\n",
-        "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
-        "    content = f.read()\n",
+        "# Copy the test image to the Cloud storage bucket as \"test.jpg\"\n",
+        "test_image_local = \"{}/test.jpg\".format(BUCKET_URI)\n",
+        "! gsutil cp $test_item $test_image_local\n",
+        "\n",
+        "# Download the test image in bytes format\n",
+        "storage_client = storage.Client(project=PROJECT_ID)\n",
+        "bucket = storage_client.bucket(bucket_name=BUCKET_NAME)\n",
+        "test_content = bucket.get_blob(\"test.jpg\").download_as_bytes()\n",
         "\n",
         "# The format of each instance should conform to the deployed model's prediction input schema.\n",
-        "instances = [{\"content\": base64.b64encode(content).decode(\"utf-8\")}]\n",
+        "instances = [{\"content\": base64.b64encode(test_content).decode(\"utf-8\")}]\n",
         "\n",
         "prediction = endpoint.predict(instances=instances)\n",
         "\n",
         "print(prediction)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3b1b67898533"
+      },
+      "source": [
+        "#### Alternate method using [GFile](https://www.tensorflow.org/api_docs/python/tf/io/gfile/GFile)\n",
+        "\n",
+        "Alternatively, [GFile](https://www.tensorflow.org/api_docs/python/tf/io/gfile/GFile) method from tensorflow-io library can be used to read the data from Cloud storage directly. The following code snippet does the same :\n",
+        "\n",
+        "```\n",
+        "import base64\n",
+        "import tensorflow as tf\n",
+        "\n",
+        "# Read the test file using GFile\n",
+        "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
+        "    content = f.read()\n",
+        "\n",
+        "# The format of each instance should conform to the deployed model's prediction input schema.\n",
+        "instances = [{\"content\": base64.b64encode(content).decode(\"utf-8\")}]\n",
+        "\n",
+        "prediction = endpoint.predict(instances=instances)\n",
+        "\n",
+        "print(prediction)\n",
+        "```\n",
+        "Nevertheless, `tf.io.gfile.GFile` supports multiple file system implementations, including local files, Google Cloud Storage (using a gs:// prefix), and HDFS (using an hdfs:// prefix)."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "undeploy_model:mbsdk"
       },
       "source": [
-        "## Undeploy the model\n",
+        "#### Undeploy the model\n",
         "\n",
         "When you are done doing predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
       ]
@@ -846,7 +989,7 @@
       "outputs": [],
       "source": [
         "response = model.export_model(\n",
-        "    artifact_destination=BUCKET_NAME, export_format_id=\"tflite\", sync=True\n",
+        "    artifact_destination=BUCKET_URI, export_format_id=\"tflite\", sync=True\n",
         ")\n",
         "\n",
         "model_package = response[\"artifactOutputUri\"]"
@@ -987,10 +1130,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.TabularDataset.create(\n",
-        "    display_name=\"Happy Moments\" + \"_\" + TIMESTAMP,\n",
+        "dataset = aiplatform.TabularDataset.create(\n",
+        "    display_name=\"gsod_\" + TIMESTAMP,\n",
         "    bq_source=[IMPORT_FILE],\n",
-        "    labels={\"user_metadata\": BUCKET_NAME[5:]},\n",
+        "    labels={\"user_metadata\": BUCKET_NAME},\n",
         ")\n",
         "\n",
         "label_column = \"mean_temp\"\n",
@@ -1046,9 +1189,7 @@
         "  - regression:\n",
         "    - `minimize-rmse`\n",
         "    - `minimize-mae`\n",
-        "    - `minimize-rmsle`\n",
-        "\n",
-        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+        "    - `minimize-rmsle`"
       ]
     },
     {
@@ -1059,8 +1200,8 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLTabularTrainingJob(\n",
-        "    display_name=\"happydb_\" + TIMESTAMP,\n",
+        "dag = aiplatform.AutoMLTabularTrainingJob(\n",
+        "    display_name=\"gsod_\" + TIMESTAMP,\n",
         "    optimization_prediction_type=\"regression\",\n",
         "    optimization_objective=\"minimize-rmse\",\n",
         "    column_transformations=TRANSFORMATIONS,\n",
@@ -1077,7 +1218,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -1103,7 +1244,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"happydb_\" + TIMESTAMP,\n",
+        "    model_display_name=\"gsod_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -1120,9 +1261,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -1133,18 +1273,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=happydb_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1177,7 +1309,7 @@
         "id": "undeploy_model:mbsdk"
       },
       "source": [
-        "## Undeploy the model\n",
+        "#### Undeploy the model\n",
         "\n",
         "When you are done doing predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
       ]
@@ -1218,7 +1350,7 @@
       "outputs": [],
       "source": [
         "response = model.export_model(\n",
-        "    artifact_destination=BUCKET_NAME, export_format_id=\"tf-saved-model\", sync=True\n",
+        "    artifact_destination=BUCKET_URI, export_format_id=\"tf-saved-model\", sync=True\n",
         ")\n",
         "\n",
         "model_package = response[\"artifactOutputUri\"]"
@@ -1350,10 +1482,7 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    FILE = IMPORT_FILES[0]\n",
-        "else:\n",
-        "    FILE = IMPORT_FILE\n",
+        "FILE = IMPORT_FILE\n",
         "\n",
         "count = ! gsutil cat $FILE | wc -l\n",
         "print(\"Number of Examples\", int(count[0]))\n",
@@ -1391,10 +1520,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.TextDataset.create(\n",
-        "    display_name=\"Happy Moments\" + \"_\" + TIMESTAMP,\n",
+        "dataset = aiplatform.TextDataset.create(\n",
+        "    display_name=\"happydb_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.text.single_label_classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.single_label_classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -1420,9 +1549,7 @@
         "  - `sentiment`: A text sentiment analysis model.\n",
         "  - `extraction`: A text entity extraction model.\n",
         "- `multi_label`: If a classification task, whether single (False) or multi-labeled (True).\n",
-        "- `sentiment_max`: If a sentiment analysis task, the maximum sentiment value.\n",
-        "\n",
-        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+        "- `sentiment_max`: If a sentiment analysis task, the maximum sentiment value.\n"
       ]
     },
     {
@@ -1433,7 +1560,7 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLTextTrainingJob(\n",
+        "dag = aiplatform.AutoMLTextTrainingJob(\n",
         "    display_name=\"happydb_\" + TIMESTAMP,\n",
         "    prediction_type=\"classification\",\n",
         "    multi_label=False,\n",
@@ -1450,7 +1577,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -1487,9 +1614,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -1500,18 +1626,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=happydb_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1542,7 +1660,7 @@
         "id": "undeploy_model:mbsdk"
       },
       "source": [
-        "## Undeploy the model\n",
+        "#### Undeploy the model\n",
         "\n",
         "When you are done doing predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
       ]
@@ -1686,10 +1804,7 @@
       },
       "outputs": [],
       "source": [
-        "if \"IMPORT_FILES\" in globals():\n",
-        "    FILE = IMPORT_FILES[0]\n",
-        "else:\n",
-        "    FILE = IMPORT_FILE\n",
+        "FILE = IMPORT_FILE\n",
         "\n",
         "count = ! gsutil cat $FILE | wc -l\n",
         "print(\"Number of Examples\", int(count[0]))\n",
@@ -1726,10 +1841,10 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.VideoDataset.create(\n",
-        "    display_name=\"Happy Moments\" + \"_\" + TIMESTAMP,\n",
+        "dataset = aiplatform.VideoDataset.create(\n",
+        "    display_name=\"human_motion_\" + TIMESTAMP,\n",
         "    gcs_source=[IMPORT_FILE],\n",
-        "    import_schema_uri=aip.schema.dataset.ioformat.video.classification,\n",
+        "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -1753,9 +1868,7 @@
         "- `prediction_type`: The type task to train the model for.\n",
         "  - `classification`: A video classification model.\n",
         "  - `object_tracking`: A video object tracking model.\n",
-        "  - `action_recognition`: A video action recognition model.\n",
-        "\n",
-        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+        "  - `action_recognition`: A video action recognition model."
       ]
     },
     {
@@ -1766,8 +1879,8 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"happydb_\" + TIMESTAMP,\n",
+        "dag = aiplatform.AutoMLVideoTrainingJob(\n",
+        "    display_name=\"human_motion_\" + TIMESTAMP,\n",
         "    prediction_type=\"classification\",\n",
         ")\n",
         "\n",
@@ -1782,7 +1895,7 @@
       "source": [
         "#### Run the training pipeline\n",
         "\n",
-        "Next, you run the DAG to start the training job by invoking the method `run`, with the following parameters:\n",
+        "Next, you run the created DAG to start the training job by invoking the method `run`, with the following parameters:\n",
         "\n",
         "- `dataset`: The `Dataset` resource to train the model.\n",
         "- `model_display_name`: The human readable name for the trained model.\n",
@@ -1804,7 +1917,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"happydb_\" + TIMESTAMP,\n",
+        "    model_display_name=\"human_motion_\" + TIMESTAMP,\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -1817,9 +1930,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -1830,18 +1942,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=happydb_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1899,16 +2003,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n"
       ]
     },
     {
@@ -1919,66 +2014,11 @@
       },
       "outputs": [],
       "source": [
-        "delete_dataset = True\n",
-        "delete_pipeline = True\n",
-        "delete_model = True\n",
-        "delete_endpoint = True\n",
-        "delete_batchjob = True\n",
-        "delete_customjob = True\n",
-        "delete_hptjob = True\n",
-        "delete_bucket = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "# Delete the dataset using the Vertex fully qualified identifier for the dataset\n",
-        "try:\n",
-        "    if delete_dataset and \"dataset_id\" in globals():\n",
-        "        clients[\"dataset\"].delete_dataset(name=dataset_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the training pipeline using the Vertex fully qualified identifier for the pipeline\n",
-        "try:\n",
-        "    if delete_pipeline and \"pipeline_id\" in globals():\n",
-        "        clients[\"pipeline\"].delete_training_pipeline(name=pipeline_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the model using the Vertex fully qualified identifier for the model\n",
-        "try:\n",
-        "    if delete_model and \"model_to_deploy_id\" in globals():\n",
-        "        clients[\"model\"].delete_model(name=model_to_deploy_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the endpoint using the Vertex fully qualified identifier for the endpoint\n",
-        "try:\n",
-        "    if delete_endpoint and \"endpoint_id\" in globals():\n",
-        "        clients[\"endpoint\"].delete_endpoint(name=endpoint_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the batch job using the Vertex fully qualified identifier for the batch job\n",
-        "try:\n",
-        "    if delete_batchjob and \"batch_job_id\" in globals():\n",
-        "        clients[\"job\"].delete_batch_prediction_job(name=batch_job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the custom job using the Vertex fully qualified identifier for the custom job\n",
-        "try:\n",
-        "    if delete_customjob and \"job_id\" in globals():\n",
-        "        clients[\"job\"].delete_custom_job(name=job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the hyperparameter tuning job using the Vertex fully qualified identifier for the hyperparameter tuning job\n",
-        "try:\n",
-        "    if delete_hptjob and \"hpt_job_id\" in globals():\n",
-        "        clients[\"job\"].delete_hyperparameter_tuning_job(name=hpt_job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -38,9 +38,15 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -67,7 +73,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the Penguins dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). The version of the dataset predicts the species."
+        "The dataset used for this tutorial is the Penguins dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). This version of the dataset is used to predict the species of penguins from the available features like culmen-length, flipper-depth etc."
       ]
     },
     {
@@ -84,16 +90,26 @@
         "\n",
         "- `BigQueryML Training`\n",
         "- `Vertex AI Model resource`\n",
-        "- `Vertex AI Vizier.\n",
+        "- `Vertex AI Vizier`\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a local BQ table in your project.\n",
-        "- Train a BQML model.\n",
-        "- Evaluate the BQML model.\n",
-        "- Export the BQML model as a cloud model.\n",
-        "- Upload the exported model as a Vertex AI Model resource.\n",
-        "- Hyperparameter tune a BQML model with Vertex AI Vizier."
+        "- Create a local BigQuery table in your project\n",
+        "- Train a BQML model\n",
+        "- Evaluate the BQML model\n",
+        "- Export the BQML model as a cloud model\n",
+        "- Upload the exported model as a `Vertex AI Model` resource\n",
+        "- Hyperparameter tune a BQML model with `Vertex AI Vizier`\n",
+        "- Automatically register a BQML model to `Vertex AI Model Registry`\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -104,7 +120,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
@@ -115,20 +131,22 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the packages\n",
+        "! pip3 install --upgrade pyarrow \\\n",
+        "                        google-cloud-aiplatform \\\n",
+        "                        google-cloud-bigquery \\\n",
+        "                        google-cloud-bigquery-storage $USER_FLAG -q"
       ]
     },
     {
@@ -166,6 +184,23 @@
         "id": "project_id"
       },
       "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
         "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
@@ -236,7 +271,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -263,6 +301,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f3bd8c0d0469"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -286,7 +385,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -297,8 +397,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -318,7 +419,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -338,7 +439,55 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
     {
@@ -347,9 +496,6 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -361,28 +507,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_bq"
-      },
-      "source": [
-        "#### Import BigQuery\n",
-        "\n",
-        "Import the BigQuery package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_bq"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
         "from google.cloud import bigquery"
       ]
     },
@@ -392,7 +517,7 @@
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "### Initialize Vertex AI SDK for Python\n",
+        "### Initialize Vertex AI and BigQuery SDKs for Python\n",
         "\n",
         "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
       ]
@@ -405,7 +530,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -414,8 +539,6 @@
         "id": "init_bq"
       },
       "source": [
-        "### Create BigQuery client\n",
-        "\n",
         "Create the BigQuery client."
       ]
     },
@@ -427,7 +550,7 @@
       },
       "outputs": [],
       "source": [
-        "bqclient = bigquery.Client()"
+        "bqclient = bigquery.Client(project=PROJECT_ID)"
       ]
     },
     {
@@ -436,17 +559,17 @@
         "id": "accelerators:prediction,mbsdk"
       },
       "source": [
-        "#### Set hardware accelerators\n",
+        "### Set hardware accelerators\n",
         "\n",
         "You can set hardware accelerators for prediction.\n",
         "\n",
         "Set the variable `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
         "\n",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "    (aiplatform.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
         "\n",
         "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
         "\n",
-        "Learn more [here](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators) hardware accelerator support for your region"
+        "Learn more [here](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators) hardware accelerator support for your region."
       ]
     },
     {
@@ -457,13 +580,15 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_DEPLOY_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    DEPLOY_GPU, DEPLOY_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+        "    DEPLOY_GPU, DEPLOY_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
       ]
     },
     {
@@ -472,7 +597,7 @@
         "id": "container:prediction"
       },
       "source": [
-        "#### Set pre-built containers\n",
+        "### Set pre-built containers\n",
         "\n",
         "Set the pre-built Docker container image for prediction.\n",
         "\n",
@@ -519,11 +644,11 @@
         "id": "machine:prediction"
       },
       "source": [
-        "#### Set machine type\n",
+        "### Set machine type\n",
         "\n",
         "Next, set the machine type to use for prediction.\n",
         "\n",
-        "- Set the variable `DEPLOY_COMPUTE` to configure the compute resources for the VM you will use for prediction.\n",
+        "- Set the variable `DEPLOY_COMPUTE` to configure the compute resources for the VM which is used for prediction.\n",
         " - `machine type`\n",
         "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
         "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
@@ -557,7 +682,7 @@
         "id": "bqml_intro"
       },
       "source": [
-        "## Bigquery ML introduction\n",
+        "## BigQuery ML introduction\n",
         "\n",
         "BigQuery ML (BQML) provides the capability to train ML tabular models, such as classification and regression, in BigQuery using SQL syntax.\n",
         "\n",
@@ -582,9 +707,9 @@
         "id": "bqml_create_dataset"
       },
       "source": [
-        "### Create BQ dataset/model resource\n",
+        "### Create BQ dataset resource\n",
         "\n",
-        "First, you create a empty dataset/model resource in your project."
+        "First, you create an empty dataset resource in your project."
       ]
     },
     {
@@ -659,7 +784,7 @@
         "id": "bqml_eval_model"
       },
       "source": [
-        "### Evaluate the BQML trained model\n",
+        "### Evaluate the trained BQML model\n",
         "\n",
         "Next, retrieve the model evaluation for the trained BQML model.\n",
         "\n",
@@ -694,7 +819,7 @@
       "source": [
         "### Export the model from BQML\n",
         "\n",
-        "The model you trained in BQML is a TensorFlow model. Next, you will export the TensorFlow model artifacts in TF.SavedModel format."
+        "The model you trained in BQML is a TensorFlow model. Next, you export the TensorFlow model artifacts in TF.SavedModel format."
       ]
     },
     {
@@ -705,10 +830,10 @@
       },
       "outputs": [],
       "source": [
-        "param = f\"{PROJECT_ID}:{BQ_DATASET_NAME}.{MODEL_NAME} {BUCKET_NAME}/{MODEL_NAME}\"\n",
+        "param = f\"{PROJECT_ID}:{BQ_DATASET_NAME}.{MODEL_NAME} {BUCKET_URI}/{MODEL_NAME}\"\n",
         "! bq extract -m $param\n",
         "\n",
-        "MODEL_DIR = f\"{BUCKET_NAME}/{BQ_DATASET_NAME}\"\n",
+        "MODEL_DIR = f\"{BUCKET_URI}/{BQ_DATASET_NAME}\"\n",
         "! gsutil ls $MODEL_DIR"
       ]
     },
@@ -718,9 +843,25 @@
         "id": "upload_bqml_model"
       },
       "source": [
-        "## Upload the BQML model to a Model resource\n",
+        "## Upload the BigQuery ML model to a Vertex AI Model resource\n",
         "\n",
-        "Finally, now that you have the BQML model exported as a TF.SavedModel format, you upload the model artifacts to Vertex AI Model resource, in the same way as if you were uploading a custom trained model."
+        "Finally, now that you have the BigQuery ML model exported, you upload the model artifacts to Vertex AI Model resource, in the same way as if you were uploading a custom trained model.\n",
+        "\n",
+        "Below is a partial list of mapping BigQuery ML model types to their corresponding exported model format:\n",
+        "\n",
+        "'LINEAR_REG'<br/>\n",
+        "'LOGISTIC_REG' --> TensorFlow SavedFormat\n",
+        "\n",
+        "'AUTOML_CLASSIFIER'<br/>\n",
+        "'AUTOML_REGRESSOR' --> TensorFlow SavedFormat\n",
+        "\n",
+        "'BOOSTED_TREE_CLASSIFIER'<br/>\n",
+        "'BOOSTED_TREE_REGRESSOR' --> XGBoost format\n",
+        "\n",
+        "'DNN_CLASSIFIER'<br/>\n",
+        "'DNN_REGRESSOR'<br/>\n",
+        "'DNN_LINEAR_COMBINED_CLASSIFIER'<br/>\n",
+        "'DNN_LINEAR_COMBINED_REGRESSOR' --> TensorFlow Estimator"
       ]
     },
     {
@@ -731,7 +872,7 @@
       },
       "outputs": [],
       "source": [
-        "model = aip.Model.upload(\n",
+        "model = aiplatform.Model.upload(\n",
         "    display_name=\"penguins_\" + TIMESTAMP,\n",
         "    artifact_uri=MODEL_DIR,\n",
         "    serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -752,7 +893,7 @@
         "- `deployed_model_display_name`: A human readable name for the deployed model.\n",
         "- `traffic_split`: Percent of traffic at the endpoint that goes to this model, which is specified as a dictionary of one or more key/value pairs.\n",
         "If only one model, then specify as { \"0\": 100 }, where \"0\" refers to this model being uploaded and 100 means 100% of the traffic.\n",
-        "If there are existing models on the endpoint, for which the traffic will be split, then use model_id to specify as { \"0\": percent, model_id: percent, ... }, where model_id is the model id of an existing model to the deployed endpoint. The percents must add up to 100.\n",
+        "If there are existing models on the endpoint, for which the traffic needs to be split, then use model_id to specify as { \"0\": percent, model_id: percent, ... }, where model_id is the model id of an existing model to the deployed endpoint. The percents must add up to 100.\n",
         "- `machine_type`: The type of machine to use for training.\n",
         "- `accelerator_type`: The hardware accelerator type.\n",
         "- `accelerator_count`: The number of accelerators to attach to a worker replica.\n",
@@ -801,7 +942,7 @@
         "id": "undeploy_model:mbsdk"
       },
       "source": [
-        "## Undeploy the model\n",
+        "#### Undeploy the model\n",
         "\n",
         "When you are done doing predictions, you undeploy the model from the `Endpoint` resouce. This deprovisions all compute resources and ends billing for the deployed model."
       ]
@@ -823,9 +964,9 @@
         "id": "model_delete:mbsdk"
       },
       "source": [
-        "#### Delete the model\n",
+        "#### Delete the `Vertex AI Model` resource\n",
         "\n",
-        "The method 'delete()' will delete the model."
+        "The method 'delete()' deletes the model."
       ]
     },
     {
@@ -839,6 +980,32 @@
         "model.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7890ae6f6410"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f0b6163e70c0"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -847,7 +1014,7 @@
       "source": [
         "### Hyperparameter Tune and train a BQML model\n",
         "\n",
-        "Next, you train a BQML tabular classification model with hyperparameter tuning using the Vertex AI Vizier service. The hyperparameter settings are specified in the `OPTIONS` statement as follows:\n",
+        "Next, you train a BQML tabular classification model with hyperparameter tuning using the `Vertex AI Vizier` service. The hyperparameter settings are specified in the `OPTIONS` statement as follows:\n",
         "\n",
         "- `HPARAM_TUNING_ALGORITHM`: The algorithm for selecting the next trial parameters.\n",
         "- `num_trials`: The number of trials.\n",
@@ -902,7 +1069,7 @@
       "source": [
         "### Evaluate the BQML trained model\n",
         "\n",
-        "Next, retrieve the model evaluation for the trained BQML model.\n",
+        "Next, retrieve the model evaluation results for the trained BQML model.\n",
         "\n",
         "Learn more about [The ML.EVALUATE function](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate)."
       ]
@@ -927,6 +1094,32 @@
         "print(results)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3f3cee1236b1"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "957b7d841502"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -976,6 +1169,179 @@
         "print(\"{} created in {}\".format(tblname, job.ended - job.started))"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4def8aaf3398"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "ff5b32618018"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2b4498ca6fea"
+      },
+      "source": [
+        "## Model Registry\n",
+        "\n",
+        "Alternatively, you can implicitly upload your BigQuery ML model as a `Vertex AI Model` resource with exporting and importing the model artifacts. In this method, you add additional options when training the model that tells BigQuery ML to automatically upload and register the trained model as a `Model` resource.\n",
+        "\n",
+        "### Setting permissions to automatically register the model\n",
+        "\n",
+        "You need to set some additional IAM permissions for BigQuery ML to automatically upload and register the model after training. Depending on your service account, the setting of the permissions below may fail. In this case, we recommend executing the permissions in a Cloud Shell.\n",
+        "\n",
+        "Learn more about [Setting permissions for Model Registry](https://cloud.devsite.corp.google.com/bigquery-ml/docs/managing-models-vertex\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "29229f72d13d"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud projects add-iam-policy-binding $PROJECT_ID \\\n",
+        "    --member=serviceAccount:$SERVICE_ACCOUNT --role=roles/aiplatform.admin --condition=None"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c390ee7c11a"
+      },
+      "source": [
+        "### Training and registering the model\n",
+        "\n",
+        "Next, you train the model and automatically register the model to the `Vertex AI Model Registry`, by adding the following parameters as options:\n",
+        "\n",
+        "- `model_registry`: Set to \"vertex_ai\" to indicate automatic registation to `Vertex AI Model Registry`.\n",
+        "- `vertex_ai_model_id`: The human readable display name for the registered model.\n",
+        "- `vertex_ai_model_version_aliases`: Alternate names for the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "57db464f4c42"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_NAME = \"penguins\"\n",
+        "MODEL_QUERY = f\"\"\"\n",
+        "CREATE OR REPLACE MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "OPTIONS(\n",
+        "    model_type='DNN_CLASSIFIER',\n",
+        "    labels = ['species'],\n",
+        "    model_registry=\"vertex_ai\",\n",
+        "    vertex_ai_model_id=\"bqml_model_{TIMESTAMP}\", \n",
+        "    vertex_ai_model_version_aliases=[\"1\"]\n",
+        "    )\n",
+        "AS\n",
+        "SELECT *\n",
+        "FROM `{BQ_TABLE}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)\n",
+        "print(job.errors, job.state)\n",
+        "\n",
+        "while job.running():\n",
+        "    from time import sleep\n",
+        "\n",
+        "    sleep(30)\n",
+        "    print(\"Running ...\")\n",
+        "print(job.errors, job.state)\n",
+        "\n",
+        "tblname = job.ddl_target_table\n",
+        "tblname = \"{}.{}\".format(tblname.dataset_id, tblname.table_id)\n",
+        "print(\"{} created in {}\".format(tblname, job.ended - job.started))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5b4970272040"
+      },
+      "source": [
+        "### Find the model in the `Vertex Model Registry`\n",
+        "\n",
+        "Finally, you can use the `Vertex AI Model` list() method with a filter query to find the automatically registered model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "76c22674ba99"
+      },
+      "outputs": [],
+      "source": [
+        "models = aiplatform.Model.list(filter=\"display_name=bqml_model_\" + TIMESTAMP)\n",
+        "model = models[0]\n",
+        "\n",
+        "print(model.gca_resource)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "48e6ef5d5ffa"
+      },
+      "outputs": [],
+      "source": [
+        "models = aiplatform.Model.list()\n",
+        "for model in models:\n",
+        "    if model.gca_resource.display_name.startswith(\"bqml\"):\n",
+        "        print(model.gca_resource.display_name)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ef61354b1a5f"
+      },
+      "source": [
+        "### Delete the `BigQuery ML` model\n",
+        "\n",
+        "Next, delete the `BigQuery ML` instance of the model."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f6004d1ce59d"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_QUERY = f\"\"\"\n",
+        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
+        "\"\"\"\n",
+        "\n",
+        "job = bqclient.query(MODEL_QUERY)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -987,17 +1353,9 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Set `delete_storage` to `True` to delete the Cloud Storage bucket used in this notebook."
       ]
     },
     {
@@ -1008,61 +1366,23 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the endpoint using the Vertex endpoint object\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the model using the Vertex model object\n",
+        "try:\n",
+        "    model.delete()\n",
+        "except Exception as e:\n",
+        "    print(e)\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the created BigQuery dataset\n",
+        "! bq rm -r -f $PROJECT_ID:$BQ_DATASET_NAME\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "delete_storage = False\n",
+        "if delete_storage or os.getenv(\"IS_TESTING\"):\n",
+        "    # Delete the created GCS bucket\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -32,6 +32,11 @@
         "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Distributed Training\n",
         "\n",
         "<table align=\"left\">\n",
+        "      <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,8 +44,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Distributed Training."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Distributed Training. Please note: There are incompatibilities between Colab and Docker and the Docker section may not work until resolved by the platform."
       ]
     },
     {
@@ -100,6 +106,15 @@
         "id": "recommendation:mlops,stage2,vertex,distributed_training"
       },
       "source": [
+        "### Costs\n",
+        " \n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "Vertex AI\n",
+        "Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), and use the [Pricing Calculator](https://cloud.google.com/products/calculator/),\n",
+        "        to generate a cost estimate based on your projected usage.\n",
         "### Recommendations\n",
         "\n",
         "When doing E2E MLOps on Google Cloud, the following are best practices for when to use Vertex AI Distributed Training:\n",
@@ -126,59 +141,58 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "install_mlops"
+        "id": "XkYpRvOQyVYb"
       },
       "source": [
-        "## Installations\n",
+        "### Install additional packages\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "xs_Kt8RcyXTC"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "restart"
+        "id": "oQhwq1iozAxh"
       },
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "zo3YFZXLzCRJ"
       },
       "outputs": [],
       "source": [
+        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -189,6 +203,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -208,6 +248,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -261,11 +303,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "qohAA9fJulvP"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -283,7 +328,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "8NKwwe7aulvQ"
       },
       "outputs": [],
       "source": [
@@ -292,6 +337,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "poKeKYG8ulvQ"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "MIpJGzF9ulvQ"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Vh6KDXB5ulvQ"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -315,7 +436,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -326,8 +448,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -343,11 +466,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "Moosy2rOulvR"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -363,11 +486,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "56irx2CvulvS"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -408,11 +531,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "wbvYPSTDulvS"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -441,7 +564,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:training,prediction,ngpu,mbsdk"
+        "id": "PryARdnoulvT"
       },
       "outputs": [],
       "source": [
@@ -483,14 +606,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:training,prediction"
+        "id": "LhhUFw2nulvT"
       },
       "outputs": [],
       "source": [
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -551,7 +674,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "machine:training"
+        "id": "vytMaukeulvT"
       },
       "outputs": [],
       "source": [
@@ -613,7 +736,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "mhw34XoOulvU"
       },
       "outputs": [],
       "source": [
@@ -621,7 +744,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -662,7 +785,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_training_package"
+        "id": "IAaZpZyyulvU"
       },
       "outputs": [],
       "source": [
@@ -711,7 +834,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:mirrored,boston"
+        "id": "zKzddzl6ulvV"
       },
       "outputs": [],
       "source": [
@@ -767,6 +890,13 @@
         "    strategy = tf.distribute.MultiWorkerMirroredStrategy()\n",
         "    logging.info(\"Multi-worker Strategy distributed training\")\n",
         "    logging.info('TF_CONFIG = {}'.format(os.environ.get('TF_CONFIG', 'Not found')))\n",
+        "    # Single Machine, multiple TPU devices\n",
+        "elif args.distribute == 'tpu':\n",
+        "    cluster_resolver = tf.distribute.cluster_resolver.TPUClusterResolver(tpu=\"local\")\n",
+        "    tf.config.experimental_connect_to_cluster(cluster_resolver)\n",
+        "    tf.tpu.experimental.initialize_tpu_system(cluster_resolver)\n",
+        "    strategy = tf.distribute.TPUStrategy(cluster_resolver)\n",
+        "    print(\"All devices: \", tf.config.list_logical_devices('TPU'))\n",
         "\n",
         "logging.info('num_replicas_in_sync = {}'.format(strategy.num_replicas_in_sync))\n",
         "\n",
@@ -825,8 +955,11 @@
         "    else:\n",
         "        task_type, task_id = None, None\n",
         "\n",
+        "    if args.distribute==\"tpu\":\n",
+        "        save_locally = tf.saved_model.SaveOptions(experimental_io_device='/job:localhost')\n",
+        "        model.save(args.model_dir, options=save_locally)\n",
         "    # single, mirrored or primary for multiworker\n",
-        "    if _is_chief(task_type, task_id):\n",
+        "    elif _is_chief(task_type, task_id):\n",
         "        model.save(args.model_dir)\n",
         "    # non-primary workers for multi-workers\n",
         "    else:\n",
@@ -860,14 +993,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tarball_training_script"
+        "id": "LFUHioqTulvV"
       },
       "outputs": [],
       "source": [
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -885,11 +1018,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_pp_training_job:mirrored"
+        "id": "LnUX0UkvulvV"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = BUCKET_NAME\n",
+        "MODEL_DIR = BUCKET_URI\n",
         "\n",
         "CMDARGS = [\"--epochs=5\", \"--batch_size=16\", \"--distribute=mirrored\"]\n",
         "\n",
@@ -920,7 +1053,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "iUWHFpPoulvW"
       },
       "outputs": [],
       "source": [
@@ -942,7 +1075,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "model_delete:mbsdk"
+        "id": "-0gqCUTEulvW"
       },
       "outputs": [],
       "source": [
@@ -1027,7 +1160,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "aXvPN8P6ulvX"
       },
       "source": [
         "### Create and run custom training job\n",
@@ -1053,7 +1186,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "kYcFsVSEulvX"
       },
       "outputs": [],
       "source": [
@@ -1061,7 +1194,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -1084,11 +1217,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_pp_training_job:multiworker"
+        "id": "GHRxPU32ulvX"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = BUCKET_NAME\n",
+        "MODEL_DIR = BUCKET_URI\n",
         "\n",
         "CMDARGS = [\"--epochs=5\", \"--batch_size=16\", \"--distribute=multiworker\"]\n",
         "\n",
@@ -1111,7 +1244,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "92D_hbuVulvX"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1123,7 +1256,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "CqrfWkB3ulvX"
       },
       "outputs": [],
       "source": [
@@ -1175,14 +1308,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "write_docker_file:training,multiworker"
+        "id": "pGI2viDAulvY"
       },
       "outputs": [],
       "source": [
         "%%writefile custom/Dockerfile\n",
         "\n",
         "FROM gcr.io/deeplearning-platform-release/tf2-gpu.2-5\n",
-        "WORKDIR /root\n",
         "\n",
         "WORKDIR /\n",
         "\n",
@@ -1208,7 +1340,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "name_container:training"
+        "id": "7P8cdlFtulvY"
       },
       "outputs": [],
       "source": [
@@ -1228,11 +1360,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "build_container:training"
+        "id": "jmw5cakNulvY"
       },
       "outputs": [],
       "source": [
-        "! docker build custom -t $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker build custom -t $TRAIN_IMAGE\n",
+        "else:\n",
+        "    # install docker daemon\n",
+        "    ! apt-get -qq install docker.io"
       ]
     },
     {
@@ -1250,11 +1386,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "test_container:training"
+        "id": "jJGLjU-TulvZ"
       },
       "outputs": [],
       "source": [
-        "! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
+        "if not IS_COLAB:\n",
+        "    ! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
       ]
     },
     {
@@ -1272,11 +1409,42 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "register_container:training"
+        "id": "GAXGjae7ulvZ"
       },
       "outputs": [],
       "source": [
-        "! docker push $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker push $TRAIN_IMAGE"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f50e9c553fb7"
+      },
+      "source": [
+        "*Executes in Colab*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a7e8c98f1e56"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash -s $IS_COLAB $TRAIN_IMAGE\n",
+        "if [ $1 == \"False\" ]; then\n",
+        "  exit 0\n",
+        "fi\n",
+        "set -x\n",
+        "dockerd -b none --iptables=0 -l warn &\n",
+        "for i in $(seq 5); do [ ! -S \"/var/run/docker.sock\" ] && sleep 2 || break; done\n",
+        "docker build custom -t $2\n",
+        "docker run $2 --epochs=5 --model-dir=./\n",
+        "docker push $2\n",
+        "kill $(jobs -p)"
       ]
     },
     {
@@ -1296,13 +1464,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "worker_pool_primary"
+        "id": "CEAnXBzCulvZ"
       },
       "outputs": [],
       "source": [
         "PRIMARY_COMPUTE = \"n2-highcpu-64\"\n",
         "\n",
-        "MODEL_DIR = BUCKET_NAME\n",
+        "MODEL_DIR = BUCKET_URI\n",
         "\n",
         "CMDARGS = [\n",
         "    \"--model-dir=\" + MODEL_DIR,\n",
@@ -1339,7 +1507,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "worker_pool_training"
+        "id": "6dchPSfNulvZ"
       },
       "outputs": [],
       "source": [
@@ -1375,7 +1543,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "m2VgmqEOulva"
       },
       "outputs": [],
       "source": [
@@ -1399,7 +1567,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "hg8vnI_Wulva"
       },
       "outputs": [],
       "source": [
@@ -1413,7 +1581,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "WT76Sc-culva"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1425,7 +1593,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "I_IxVfuDulva"
       },
       "outputs": [],
       "source": [
@@ -1474,7 +1642,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "L8Av8ATVulvb"
       },
       "source": [
         "### Create CustomJob with worker pool specifications\n",
@@ -1490,7 +1658,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "TUWEP1Lmulvb"
       },
       "outputs": [],
       "source": [
@@ -1502,7 +1670,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "_95FH8jeulvb"
       },
       "source": [
         "### Run the CustomJob\n",
@@ -1514,7 +1682,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "IEbrY05Gulvb"
       },
       "outputs": [],
       "source": [
@@ -1528,7 +1696,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "8R2Bnmwmulvb"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1540,7 +1708,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "s1geVE3Lulvb"
       },
       "outputs": [],
       "source": [
@@ -1583,14 +1751,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "docker_write:tpu"
+        "id": "nQVPtknpulvb"
       },
       "outputs": [],
       "source": [
         "%%writefile custom/Dockerfile\n",
         "FROM python:3.8\n",
         "\n",
-        "WORKDIR /root\n",
+        "WORKDIR /\n",
         "\n",
         "# Copies the trainer code to the docker image.\n",
         "COPY trainer /trainer\n",
@@ -1622,11 +1790,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "docker_push:tpu"
+        "id": "J_d_zEXUulvc"
       },
       "outputs": [],
       "source": [
-        "TRAIN_IMAGE = f\"gcr.io/\" + PROJECT_ID + \"/tpu-train:latest\"\n",
+        "TRAIN_IMAGE = \"gcr.io/\" + PROJECT_ID + \"/tpu-train:latest\"\n",
         "\n",
         "os.chdir(\"custom\")\n",
         "! docker build --quiet --tag={TRAIN_IMAGE} .\n",
@@ -1653,7 +1821,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "worker_pool_tpu"
+        "id": "d514eU7lulvc"
       },
       "outputs": [],
       "source": [
@@ -1701,7 +1869,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "RruSqNfrulvc"
       },
       "source": [
         "### Create CustomJob with worker pool specifications\n",
@@ -1717,7 +1885,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job:worker_pool"
+        "id": "2QvSqbbHulvc"
       },
       "outputs": [],
       "source": [
@@ -1729,7 +1897,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "Iw4L3UIfulvd"
       },
       "source": [
         "### Run the CustomJob\n",
@@ -1741,7 +1909,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:multiworker"
+        "id": "zmqCNS78ulvd"
       },
       "outputs": [],
       "source": [
@@ -1755,7 +1923,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "delete_job"
+        "id": "gWZoH9QKulvd"
       },
       "source": [
         "### Delete a custom training job\n",
@@ -1767,7 +1935,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "Lt8BJ4iBulvd"
       },
       "outputs": [],
       "source": [
@@ -1787,13 +1955,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1801,70 +1963,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup"
+        "id": "U98Wzc01ulvd"
       },
       "outputs": [],
       "source": [
-        "delete_dataset = True\n",
-        "delete_pipeline = True\n",
-        "delete_model = True\n",
-        "delete_endpoint = True\n",
-        "delete_batchjob = True\n",
-        "delete_customjob = True\n",
-        "delete_hptjob = True\n",
-        "delete_bucket = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "# Delete the dataset using the Vertex fully qualified identifier for the dataset\n",
-        "try:\n",
-        "    if delete_dataset and \"dataset_id\" in globals():\n",
-        "        clients[\"dataset\"].delete_dataset(name=dataset_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the training pipeline using the Vertex fully qualified identifier for the pipeline\n",
-        "try:\n",
-        "    if delete_pipeline and \"pipeline_id\" in globals():\n",
-        "        clients[\"pipeline\"].delete_training_pipeline(name=pipeline_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the model using the Vertex fully qualified identifier for the model\n",
-        "try:\n",
-        "    if delete_model and \"model_to_deploy_id\" in globals():\n",
-        "        clients[\"model\"].delete_model(name=model_to_deploy_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the endpoint using the Vertex fully qualified identifier for the endpoint\n",
-        "try:\n",
-        "    if delete_endpoint and \"endpoint_id\" in globals():\n",
-        "        clients[\"endpoint\"].delete_endpoint(name=endpoint_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the batch job using the Vertex fully qualified identifier for the batch job\n",
-        "try:\n",
-        "    if delete_batchjob and \"batch_job_id\" in globals():\n",
-        "        clients[\"job\"].delete_batch_prediction_job(name=batch_job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the custom job using the Vertex fully qualified identifier for the custom job\n",
-        "try:\n",
-        "    if delete_customjob and \"job_id\" in globals():\n",
-        "        clients[\"job\"].delete_custom_job(name=job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "# Delete the hyperparameter tuning job using the Vertex fully qualified identifier for the hyperparameter tuning job\n",
-        "try:\n",
-        "    if delete_hptjob and \"hpt_job_id\" in globals():\n",
-        "        clients[\"job\"].delete_hyperparameter_tuning_job(name=hpt_job_id)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Logging and Vertex Experiments\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Logging and Vertex AI Experiments\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -38,9 +38,15 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Logging and Vertex Experiments."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Logging and Vertex AI Experiments."
       ]
     },
     {
@@ -93,7 +99,7 @@
       "source": [
         "### Recommendations\n",
         "\n",
-        "When doing E2E MLOps on Google Cloud, the following best practices for logging data when experimenting or formal training a model.\n",
+        "When doing E2E MLOps on Google Cloud, the following are some of the best practices for logging data when experimenting or formally training a model.\n",
         "\n",
         "#### Python Logging\n",
         "\n",
@@ -105,7 +111,14 @@
         "\n",
         "#### Experiments\n",
         "\n",
-        "Use Vertex AI Experiments in conjunction with logging when doing experiments to compare results for different experiment configurations."
+        "Use Vertex AI Experiments in conjunction with logging when performing experiments to compare results for different experiment configurations.\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -116,7 +129,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
@@ -127,20 +140,20 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-logging $USER_FLAG -q"
       ]
     },
     {
@@ -178,6 +191,24 @@
         "id": "project_id"
       },
       "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, Compute Engine, Cloud Storage and Cloud Logging APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component,logging).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
+        "\n",
         "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
@@ -248,7 +279,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -275,6 +309,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f3bd8c0d0469"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -284,7 +379,7 @@
         "### Set up variables\n",
         "\n",
         "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
+        "### Import libraries"
       ]
     },
     {
@@ -295,29 +390,9 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_logging"
-      },
-      "source": [
-        "#### Import logging\n",
+        "import logging\n",
         "\n",
-        "Import the logging package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_logging"
-      },
-      "outputs": [],
-      "source": [
-        "import logging"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -339,7 +414,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
       ]
     },
     {
@@ -356,9 +431,9 @@
         "- Send log output to console.\n",
         "- Send log output to a file.\n",
         "\n",
-        "### Logging Levels\n",
+        "### Logging Levels in Python Logging\n",
         "\n",
-        "The logging levels in order (from least to highest) are, with each level inclusive of the previous level:\n",
+        "The logging levels in order (from least to highest) and each level inclusive of the previous level are :\n",
         "\n",
         "1. Informational\n",
         "2. Warnings\n",
@@ -398,7 +473,7 @@
       "source": [
         "### Setting logging level\n",
         "\n",
-        "To set the logging level, you get the logging handler using `getLogger()`. You can have multiple logging handles. When `getLogger()` is called w/o arguments it gets the default handler, named ROOT. With the handler, you set the logging level with the method 'setLevel()`."
+        "To set the logging level, you get the logging handler using `getLogger()`. You can have multiple logging handles. When `getLogger()` is called without any arguments, it gets the default handler named ROOT. With the handler, you set the logging level with the method `setLevel()`."
       ]
     },
     {
@@ -445,7 +520,7 @@
       "source": [
         "### Output to a local file\n",
         "\n",
-        "You can preserve your logging output to a file that is local to where the Python script is running with the method `BasicConfig()`, with the following paraneters:\n",
+        "You can preserve your logging output to a file that is local to where the Python script is running with the method `BasicConfig()`, that takes the following parameters:\n",
         "\n",
         "- `filename`: The file path to the local file to write the log output to.\n",
         "- `level`: Sets the level of logging that is written to the logging file.\n",
@@ -482,7 +557,7 @@
         "- Send log output to storage.\n",
         "- Retrieve log output from storage.\n",
         "\n",
-        "### Logging Levels\n",
+        "### Logging Levels in Cloud Logging\n",
         "\n",
         "The logging levels in order (from least to highest) are, with each level inclusive of the previous level:\n",
         "\n",
@@ -517,7 +592,7 @@
         "from google.cloud.logging.handlers import CloudLoggingHandler\n",
         "\n",
         "# Connect to the Cloud Logging service\n",
-        "cl_client = google.cloud.logging.Client()\n",
+        "cl_client = google.cloud.logging.Client(project=PROJECT_ID)\n",
         "handler = CloudLoggingHandler(cl_client, name=\"mylog\")\n",
         "\n",
         "# Create a logger instance and logging level\n",
@@ -539,7 +614,7 @@
       "source": [
         "### Logging output\n",
         "\n",
-        "To log output at specific levels is identical in method, and method names, as in Python logging, except that you use your instance of the cloud logger in place of logging."
+        "Logging output at specific levels is identical to Python logging with respect to method and method names. The only difference is that you use your instance of the cloud logger in place of logging."
       ]
     },
     {
@@ -567,7 +642,7 @@
         "To get the logged output, you:\n",
         "\n",
         "1. Retrieve the log handle to the service.\n",
-        "2. Using the handle call the method `list_entries()`\n",
+        "2. Using the handle, call the method `list_entries()`.\n",
         "3. Iterate through the entries."
       ]
     },
@@ -594,10 +669,10 @@
       "source": [
         "## Logging with Vertex AI Experiments and Vertex AI ML Metadata\n",
         "\n",
-        "You can log results related to training experiments with `Vertex AI Experiments` and `ML Metadata`:\n",
+        "You can log results related to training experiments with `Vertex AI Experiments` and `ML Metadata` including:\n",
         "\n",
         "- Preserve results of an experiment.\n",
-        "- Track multiple runs -- i.e., training runs -- within an experiment.\n",
+        "- Track multiple runs i.e., training runs within an experiment.\n",
         "- Track parameters (configuration) and metrics (results).\n",
         "- Retrieve and display the logged output.\n",
         "\n",
@@ -612,14 +687,29 @@
       "source": [
         "### Create experiment for tracking training related metadata\n",
         "\n",
-        "Setup tracking the parameters (configuration) and metrics (results) for each experiment:\n",
+        "Setup tracking for parameters (configuration) and metrics (results) in each experiment:\n",
         "\n",
-        "- `aip.init()` - Create an experiment instance\n",
-        "- `aip.start_run()` - Track a specific run within the experiment.\n",
+        "- `aiplatform.init()` - Create an experiment instance\n",
+        "- `aiplatform.start_run()` - Track a specific run within the experiment.\n",
         "\n",
         "Learn more about [Introduction to Vertex AI ML Metadata](https://cloud.google.com/vertex-ai/docs/ml-metadata/introduction)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1ed46e349cf2"
+      },
+      "outputs": [],
+      "source": [
+        "# Specify a name for the experiment\n",
+        "EXPERIMENT_NAME = \"[your-experiment-name]\"\n",
+        "\n",
+        "if EXPERIMENT_NAME == \"[your-experiment-name]\":\n",
+        "    EXPERIMENT_NAME = \"example-\" + TIMESTAMP"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -628,9 +718,9 @@
       },
       "outputs": [],
       "source": [
-        "EXPERIMENT_NAME = \"example-\" + TIMESTAMP\n",
-        "aip.init(experiment=EXPERIMENT_NAME)\n",
-        "aip.start_run(\"run-1\")"
+        "# Create experiment\n",
+        "aiplatform.init(experiment=EXPERIMENT_NAME)\n",
+        "aiplatform.start_run(\"run-1\")"
       ]
     },
     {
@@ -641,14 +731,14 @@
       "source": [
         "### Log parameters for the experiment\n",
         "\n",
-        "Typically, an experiment is associated with a specific dataset and model architecture. Within an experiment, you may have multiple training runs, where each run tries a different configuration. As examples:\n",
+        "Typically, an experiment is associated with a specific dataset and a model architecture. Within an experiment, you may have multiple training runs, where each run tries a different configuration. For example:\n",
         "\n",
         "- Dataset split\n",
         "- Dataset sampling and boosting\n",
         "- Depth and width of layers\n",
         "- Hyperparameters\n",
         "\n",
-        "These configuration settings are referred to as parameters, which you store their key/value pair using the method `log_params()`"
+        "These configuration settings are referred to as parameters, which you store as key-value pairs using the method `log_params()`"
       ]
     },
     {
@@ -663,7 +753,7 @@
         "hyperparams[\"epochs\"] = 100\n",
         "hyperparams[\"batch_size\"] = 32\n",
         "hyperparams[\"learning_rate\"] = 0.01\n",
-        "aip.log_params(hyperparams)"
+        "aiplatform.log_params(hyperparams)"
       ]
     },
     {
@@ -674,14 +764,14 @@
       "source": [
         "### Log metrics for the experiment\n",
         "\n",
-        "At the completion, or termination, of a run within an experiment, you can log results that you use to compare runs. As examples:\n",
+        "At the completion or termination of a run within an experiment, you can log results that you use to compare runs. For example:\n",
         "\n",
         "- Evaluation metrics\n",
         "- Hyperparameter search selection\n",
         "- Time to train the model\n",
         "- Early stop trigger\n",
         "\n",
-        "These results settings are referred to as metrics, which you store their key/value pair using the method `log_metrics()`"
+        "These results are referred to as metrics, which you store as key-value pairs using the method `log_metrics()`"
       ]
     },
     {
@@ -695,7 +785,7 @@
         "metrics = {}\n",
         "metrics[\"test_acc\"] = 98.7\n",
         "metrics[\"train_acc\"] = 99.3\n",
-        "aip.log_metrics(metrics)"
+        "aiplatform.log_metrics(metrics)"
       ]
     },
     {
@@ -717,36 +807,11 @@
       },
       "outputs": [],
       "source": [
-        "EXPERIMENT_NAME = \"example\"\n",
-        "\n",
-        "experiment_df = aip.get_experiment_df()\n",
+        "experiment_df = aiplatform.get_experiment_df()\n",
         "experiment_df = experiment_df[experiment_df.experiment_name == EXPERIMENT_NAME]\n",
         "experiment_df.T"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "delete_experiment"
-      },
-      "source": [
-        "### Delete the experiment\n",
-        "\n",
-        "Next, delete the experiment. You will need to get the context via the metadata to delete it."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "delete_experiment"
-      },
-      "outputs": [],
-      "source": [
-        "c = aiplatform.metadata._Context(EXPERIMENT_NAME)\n",
-        "c.delete()"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -760,15 +825,9 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "### Delete the experiment\n",
+        "\n",
+        "Next, delete the experiment. You will need to get the context via the metadata to delete it."
       ]
     },
     {
@@ -779,61 +838,8 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
-        "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "c = aiplatform.metadata._Context(EXPERIMENT_NAME)\n",
+        "c.delete()"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb

@@ -38,11 +38,20 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    \n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "    \n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
+        "    \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -67,9 +76,9 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the Movie Recommendations. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket, in Avro format.\n",
+        "The dataset used for this tutorial is the `Movie Recommendations` dataset. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket, in Avro format.\n",
         "\n",
-        "The dataset predicts whether a persons will watch a movie."
+        "This dataset is used to predict whether a person will watch a movie or not."
       ]
     },
     {
@@ -80,7 +89,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `Vertex AI Feature Store` for when training and prediction with `Vertex AI`.\n",
+        "In this tutorial, you learn how to use `Vertex AI Feature Store` when training and predicting with `Vertex AI`.\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -92,10 +101,28 @@
         "    - Creating `EntityType` resources for the `Featurestore` resource.\n",
         "    - Creating `Feature` resources for each `EntityType` resource.\n",
         "- Import feature values (entity data items) into `Featurestore` resource.\n",
+        "    - From a Cloud Storage location.\n",
+        "    - From a pandas DataFrame.\n",
         "- Perform online serving from a `Featurestore` resource.\n",
         "- Perform batch serving from a `Featurestore` resource."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "81c777b8ad32"
+      },
+      "source": [
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "- BigQuery\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and [BigQuery pricing](https://cloud.google.com/bigquery/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -104,7 +131,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for further running this notebook."
       ]
     },
     {
@@ -115,24 +142,21 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the dependecies\n",
+        "! pip3 install --upgrade google-cloud-aiplatform google-cloud-bigquery pyarrow avro $USER_FLAG -q"
       ]
     },
     {
@@ -164,6 +188,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "project_id"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, Compute Engine, Cloud Storage and Cloud Logging APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component,logging).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -240,7 +288,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -267,15 +318,72 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "29b110b44457"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -287,28 +395,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_bq"
-      },
-      "source": [
-        "#### Import BigQuery\n",
-        "\n",
-        "Import the BigQuery package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_bq"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
         "from google.cloud import bigquery"
       ]
     },
@@ -318,9 +405,7 @@
         "id": "init_bq"
       },
       "source": [
-        "### Create BigQuery client\n",
-        "\n",
-        "Create the BigQuery client."
+        "Initialize Vertex AI and BigQuery clients."
       ]
     },
     {
@@ -331,7 +416,8 @@
       },
       "outputs": [],
       "source": [
-        "bqclient = bigquery.Client()"
+        "aiplatform.init(project=PROJECT_ID)\n",
+        "bqclient = bigquery.Client(project=PROJECT_ID)"
       ]
     },
     {
@@ -348,11 +434,11 @@
         "\n",
         "Now it's time to do a live prediction. You get a transaction from the cash register, but all it has is the credit card number and this transaction. It does not have the enriched data the model needs. During serving, the credit card number is used as an index to Feature Store to get the enriched data needed for the model.\n",
         "\n",
-        "Next problem. Let's say the enriched data the model was trained on was timestamp June 1. This transaction is June 15. Assume that the user has made other transactions between June 1 and 15, and the enriched data has been continuously updated in Feature Store. But the model was trained on June 1st data. FeatureStore knows the version number and serves the June 1 version to the model (not the current June 15); otherwise, if you used June 15 data you have training-serving skew.\n",
+        "On the other hand, let's say the enriched data the model was trained on was timestamped on June 1st. The current transaction is from June 15th. Assume that the user has made other transactions between June 1st and 15th, and the enriched data has been continuously updated in Feature Store. But the model was trained on June 1st data. FeatureStore knows the version number and serves the June 1st version to the model (not the current June 15th). Otherwise, if you used June 15th data, you would have training-serving skew.\n",
         "\n",
-        "Next problem, data drift. Things change, suddenly one day everybody is buying toilet paper! There is a significant change in the distribution of the current stored enriched data from the distribution that the deployed model was trained on. FeatureStore can detect changes/thresholds in distribution changes and trigger a notification for retraining the model.\n",
+        "Another problem here is the data drift. Things change and suddenly one day, everybody is buying toilet paper! There is a significant change in the distribution of existing enriched data from the distribution that the deployed model was trained on. FeatureStore can detect changes/thresholds in distribution changes and trigger a notification for retraining the model.\n",
         "\n",
-        "Learn more about [Vertex AI Feature Store API](https://cloud.google.com/vertex-ai/docs/featurestore)"
+        "Learn more about [Vertex AI Feature Store API](https://cloud.google.com/vertex-ai/docs/featurestore)."
       ]
     },
     {
@@ -367,9 +453,9 @@
         "\n",
         "        Featurestore -> EntityType -> Feature\n",
         "\n",
-        "- `Featurestore`: the place to store your features\n",
+        "- `Featurestore`: the place to store your features.\n",
         "- `EntityType`: under a `Featurestore`, an `EntityType` describes an object to be modeled, real one or virtual one.\n",
-        "- `Feature`: under an `EntityType`, a `Feature` describes an attribute of the `EntityType`\n",
+        "- `Feature`: under an `EntityType`, a `Feature` describes an attribute of the `EntityType`.\n",
         "\n",
         "Learn more about [Vertex AI Feature Store data model](https://cloud.google.com/vertex-ai/docs/featurestore/concepts).\n",
         "\n",
@@ -403,9 +489,9 @@
       "outputs": [],
       "source": [
         "# Represents featurestore resource path.\n",
-        "FEATURESTORE_NAME = \"movies\"\n",
+        "FEATURESTORE_NAME = \"movies_\" + TIMESTAMP\n",
         "\n",
-        "featurestore = aip.Featurestore.create(\n",
+        "featurestore = aiplatform.Featurestore.create(\n",
         "    featurestore_id=FEATURESTORE_NAME,\n",
         "    online_store_fixed_node_count=1,\n",
         "    project=PROJECT_ID,\n",
@@ -434,7 +520,7 @@
       },
       "outputs": [],
       "source": [
-        "for featurestore in aip.Featurestore.list():\n",
+        "for featurestore in aiplatform.Featurestore.list():\n",
         "    print(featurestore)"
       ]
     },
@@ -461,7 +547,7 @@
       },
       "outputs": [],
       "source": [
-        "featurestore = featurestore = aip.Featurestore(\n",
+        "featurestore = featurestore = aiplatform.Featurestore(\n",
         "    featurestore_name=FEATURESTORE_NAME, project=PROJECT_ID, location=REGION\n",
         ")\n",
         "print(featurestore)"
@@ -520,7 +606,7 @@
       "outputs": [],
       "source": [
         "def create_features(featurestore_name, entity_name, features):\n",
-        "    entity_type = aip.EntityType(\n",
+        "    entity_type = aiplatform.EntityType(\n",
         "        entity_type_name=entity_name, featurestore_id=featurestore_name\n",
         "    )\n",
         "\n",
@@ -571,7 +657,7 @@
       },
       "outputs": [],
       "source": [
-        "for featurestore in aip.Featurestore.list():\n",
+        "for featurestore in aiplatform.Featurestore.list():\n",
         "    print(featurestore)"
       ]
     },
@@ -583,7 +669,7 @@
       "source": [
         "### Search `Feature` resources using a filter\n",
         "\n",
-        "You can narrow your search of `Feature` resources using the method `list_features()` and specifying a `filter` filter."
+        "You can narrow your search of `Feature` resources using the method `list_features()` and specifying a `filter` string."
       ]
     },
     {
@@ -635,17 +721,26 @@
       },
       "outputs": [],
       "source": [
-        "features = aip.Feature.search(query=\"value_type=DOUBLE\")\n",
+        "features = aiplatform.Feature.search(query=\"value_type=DOUBLE\")\n",
         "print(\"By data type\")\n",
         "for feature in features:\n",
         "    print(features)\n",
         "\n",
-        "aip.Feature.search(query=\"feature_id=title\")\n",
+        "aiplatform.Feature.search(query=\"feature_id=title\")\n",
         "print(\"By Name\")\n",
         "for feature in features:\n",
         "    print(features)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "277e9884cf37"
+      },
+      "source": [
+        "Define paths to the feature data."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -675,15 +770,15 @@
         "\n",
         "### Data layout\n",
         "\n",
-        "Each imported `EntityType` resource data must have an ID; also, each `EntityType` resource data item can optionally have a timestamp, sepecifying when the feature values were generated.\n",
+        "Each imported `EntityType` resource data must have an ID. Also, each `EntityType` resource data item can optionally have a timestamp, sepecifying when the feature values were generated.\n",
         "\n",
         "When importing, specify the following in your request:\n",
         "\n",
-        "- Data source format: BigQuery Table/Avro/CSV\n",
+        "- Data source format: BigQuery Table/Avro/CSV/Pandas Dataframe\n",
         "- Data source URL\n",
         "- Destination: featurestore/entity types/features to be imported\n",
         "\n",
-        "The feature values for the movies dataset are in Avro format. The Avro schemas are as follows:\n",
+        "The feature values for `Movie Recommendations` dataset are in Avro format. The Avro schemas are as follows:\n",
         "\n",
         "**Users entity**:\n",
         "\n",
@@ -747,7 +842,7 @@
         "}\n",
         "```\n",
         "\n",
-        "### Importing the feature values\n",
+        "### Importing the feature values from Cloud Storage\n",
         "\n",
         "You import the feature values for the `EntityType` resources using the `ingest_from_gcs()` method, with the following parameters:\n",
         "\n",
@@ -755,7 +850,7 @@
         "- `feature_ids`: A list of identifier names for `Feature` resources' data to add to the `EntityType` resource.\n",
         "- `feature_time`: The field corresponding to the timestamp for the features being entered.\n",
         "- `gcs_source_type`: The format of the imported data. Must be CSV or Avro.\n",
-        "- `gcs_source_uris=`: A list of one or more Cloud Storage locations of the imported data files."
+        "- `gcs_source_uris`: A list of one or more Cloud Storage locations of the imported data files."
       ]
     },
     {
@@ -787,6 +882,225 @@
         "print(response)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "featurestore_delete_entities:movies"
+      },
+      "source": [
+        "#### Delete the entity types and corresponding features and feature values\n",
+        "\n",
+        "Now, in preparation to repeat the process of importing feature values but from a dataframe this time, you delete the existing entity types, and the corresponding content."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "featurestore_delete_entities:movies"
+      },
+      "outputs": [],
+      "source": [
+        "entity_type = featurestore.get_entity_type(\"users\")\n",
+        "entity_type.delete(force=True)\n",
+        "entity_type = featurestore.get_entity_type(\"movies\")\n",
+        "entity_type.delete(force=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "featurestore_create:entity_type"
+      },
+      "source": [
+        "## Create entity types for your `Featurestore` resource\n",
+        "\n",
+        "Next, you create the `EntityType` resources again for your `Featurestore` resource using the `create_entity_type()` method, with the following parameters:\n",
+        "\n",
+        "- `entity_type_id`: The name of the `EntityType` resource.\n",
+        "- `description`:  A description of the entity type."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "featurestore_create:entity_type"
+      },
+      "outputs": [],
+      "source": [
+        "for name, description in [(\"users\", \"Users descrip\"), (\"movies\", \"Movies descrip\")]:\n",
+        "    entity_type = featurestore.create_entity_type(\n",
+        "        entity_type_id=name, description=description\n",
+        "    )\n",
+        "    print(entity_type)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "featurestore_create:feature"
+      },
+      "source": [
+        "### Add `Feature` resources for your `EntityType` resources\n",
+        "\n",
+        "Further, you create the `Feature` resources again for each of the `EntityType` resources in your `Featurestore` resource using the `create_feature()` method, with the following parameters:\n",
+        "\n",
+        "- `feature_id`: The name of the `Feature` resource.\n",
+        "- `description`: A description of the feature.\n",
+        "- `value_type`: The data type for the feature."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "featurestore_create:feature,movies"
+      },
+      "outputs": [],
+      "source": [
+        "def create_features(featurestore_name, entity_name, features):\n",
+        "    entity_type = aiplatform.EntityType(\n",
+        "        entity_type_name=entity_name, featurestore_id=featurestore_name\n",
+        "    )\n",
+        "\n",
+        "    for feature in features:\n",
+        "        feature = entity_type.create_feature(\n",
+        "            feature_id=feature[0], description=feature[1], value_type=feature[2]\n",
+        "        )\n",
+        "        print(feature)\n",
+        "\n",
+        "\n",
+        "create_features(\n",
+        "    FEATURESTORE_NAME,\n",
+        "    \"users\",\n",
+        "    [\n",
+        "        (\"age\", \"Age descrip\", \"INT64\"),\n",
+        "        (\"gender\", \"Gender descrip\", \"STRING\"),\n",
+        "        (\"liked_genres\", \"Genres descrip\", \"STRING_ARRAY\"),\n",
+        "    ],\n",
+        ")\n",
+        "\n",
+        "create_features(\n",
+        "    FEATURESTORE_NAME,\n",
+        "    \"movies\",\n",
+        "    [\n",
+        "        (\"title\", \"Title descrip\", \"STRING\"),\n",
+        "        (\"genres\", \"Genres descrip\", \"STRING\"),\n",
+        "        (\"average_rating\", \"Ave descrip\", \"DOUBLE\"),\n",
+        "    ],\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8715a3f719c8"
+      },
+      "source": [
+        "Now, copy the `users` and `movies` data into avro files."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:movies,lbn,df"
+      },
+      "outputs": [],
+      "source": [
+        "GCS_USERS_AVRO_URI = FS_ENTITIES[\"users\"]\n",
+        "GCS_MOVIES_AVRO_URI = FS_ENTITIES[\"movies\"]\n",
+        "\n",
+        "USERS_AVRO_FN = \"users.avro\"\n",
+        "MOVIES_AVRO_FN = \"movies.avro\"\n",
+        "\n",
+        "! gsutil cp $GCS_USERS_AVRO_URI $USERS_AVRO_FN\n",
+        "! gsutil cp $GCS_MOVIES_AVRO_URI $MOVIES_AVRO_FN"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "load_df_from_avro"
+      },
+      "source": [
+        "#### Load Avro Files into pandas DataFrames"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "load_df_from_avro"
+      },
+      "outputs": [],
+      "source": [
+        "from avro.datafile import DataFileReader\n",
+        "from avro.io import DatumReader\n",
+        "\n",
+        "\n",
+        "class AvroReader:\n",
+        "    def __init__(self, data_file):\n",
+        "        self.avro_reader = DataFileReader(open(data_file, \"rb\"), DatumReader())\n",
+        "\n",
+        "    def to_dataframe(self):\n",
+        "        records = [record for record in self.avro_reader]\n",
+        "        return pd.DataFrame.from_records(data=records)\n",
+        "\n",
+        "\n",
+        "import pandas as pd\n",
+        "\n",
+        "users_avro_reader = AvroReader(data_file=USERS_AVRO_FN)\n",
+        "users_source_df = users_avro_reader.to_dataframe()\n",
+        "print(users_source_df)\n",
+        "\n",
+        "movies_avro_reader = AvroReader(data_file=MOVIES_AVRO_FN)\n",
+        "movies_source_df = movies_avro_reader.to_dataframe()\n",
+        "print(movies_source_df)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "featurestore_import:movies,df"
+      },
+      "source": [
+        "### Importing the feature values from DataFrame\n",
+        "\n",
+        "You import the feature values for the `EntityType` resources using the `ingest_from_df()` method, with the following parameters:\n",
+        "\n",
+        "- `entity_id_field`: The identifier name for the parent `EntityType` resource.\n",
+        "- `feature_ids`: A list of identifier names for `Feature` resources' data to add to the `EntityType` resource.\n",
+        "- `feature_time`: The field corresponding to the timestamp for the features being entered.\n",
+        "- `df_source`: The DataFrame containing the imported feature values."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "featurestore_import:movies,df"
+      },
+      "outputs": [],
+      "source": [
+        "entity_type = featurestore.get_entity_type(\"users\")\n",
+        "entity_type.ingest_from_df(\n",
+        "    feature_ids=[\"age\", \"gender\", \"liked_genres\"],\n",
+        "    feature_time=\"update_time\",\n",
+        "    df_source=users_source_df,\n",
+        "    entity_id_field=\"user_id\",\n",
+        ")\n",
+        "\n",
+        "entity_type = featurestore.get_entity_type(\"movies\")\n",
+        "entity_type.ingest_from_df(\n",
+        "    feature_ids=[\"average_rating\", \"title\", \"genres\"],\n",
+        "    feature_time=\"update_time\",\n",
+        "    df_source=movies_source_df,\n",
+        "    entity_id_field=\"movie_id\",\n",
+        ")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -829,7 +1143,7 @@
       "source": [
         "## Batch Serving\n",
         "\n",
-        "The Vertex AI Feature Store batch serving service is optimized for serving large batches of features in real-time with high-throughput, typically for training a model or batch prediction.\n",
+        "The Vertex AI Feature Store's batch serving service is optimized for serving large batches of features in real-time with high throughput, typically for training a model or batch prediction.\n",
         "\n",
         "One can batch serve to the following destinations:\n",
         "\n",
@@ -881,7 +1195,7 @@
         "\n",
         "You batch serve entity data items to a BigQuery table using the `read_serve_to_bq()` method, with the following parameters:\n",
         "\n",
-        "- `bq_destination_output_uri`: The destination BigQuery table to serve the features to.\n",
+        "- `bq_destination_output_uri`: The destination BigQuery table to receive the served features.\n",
         "- `serving_feature_ids`: A dictionary of entity type and corresponding features to serve.\n",
         "- `read_instances_uri`: A Cloud Storage location to read the entity data items from.\n",
         "\n",
@@ -914,6 +1228,7 @@
         "id": "delete_bq_dataset"
       },
       "source": [
+        "## Cleaning up\n",
         "### Delete a BigQuery dataset\n",
         "\n",
         "Use the method `delete_dataset()` to delete a BigQuery dataset along with all its tables, by setting the parameter `delete_contents` to `True`."

notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -29,9 +29,14 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Tensorboard\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Tensorboard\n",
         "\n",
         "<table align=\"left\">\n",
+        "   <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,8 +44,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/notebook_template.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Tensorboard."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Tensorboard."
       ]
     },
     {
@@ -81,6 +87,68 @@
         "- Using Vertex AI TensorBoard with Vertex AI Training."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b132d4ef86d6"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "56cb7f08a9e8"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -89,7 +157,7 @@
       "source": [
         "### Recommendations\n",
         "\n",
-        "When doing E2E MLOps on Google Cloud, the following best practices for visualizing your training with TensorBoard.\n",
+        "When doing E2E MLOps on Google Cloud, the following are the best practices for visualizing your training with TensorBoard.\n",
         "\n",
         "#### Local TensorBoard\n",
         "\n",
@@ -112,31 +180,32 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "020040f91150"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow==2.8 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q"
       ]
     },
     {
@@ -168,6 +237,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -244,7 +339,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -271,6 +369,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2700e693f1b3"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "885395904904"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "eff327d0552b"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -294,7 +468,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -305,8 +479,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -326,7 +500,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -346,7 +520,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -384,9 +558,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -410,7 +591,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -454,7 +635,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -484,13 +665,15 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+        "    TRAIN_GPU, TRAIN_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
       ]
     },
     {
@@ -663,9 +846,9 @@
         "\n",
         "You can upload your TensorBoard logs and share with others using `tensorboard dev` command. Once uploaded, a URL is returned to open up the TensorBoard instance in a brower for visualizing.\n",
         "\n",
-        "*Note:* Your TensorBoard instance is publicly visable.\n",
+        "*Note:* Your TensorBoard instance is publicly visible.\n",
         "\n",
-        "*Note:* In this example, while running within a notebook, the command will freeze since it is waiting for an interactive yes/no input. You can kill the command with a Ctrl C or kernel interupt.\n",
+        "*Note:* This cell is for demonstration purposes and must be ran in a terminal shell. In this example, while running within a notebook, the command will freeze since it is waiting for an interactive yes/no input. You can kill the command with a Ctrl C or kernel interupt.\n",
         "\n",
         "Learn more about [What is TensorBoard.dev](https://tensorboard.dev/)."
       ]
@@ -678,7 +861,7 @@
       },
       "outputs": [],
       "source": [
-        "! tensorboard dev upload --logdir {LOG_DIR} \\\n",
+        "! tensorboard dev upload --logdir logs \\\n",
         "  --name \"Simple experiment with MNIST\" \\\n",
         "  --description \"Training results\" \\\n",
         "  --one_shot"
@@ -706,7 +889,7 @@
       "outputs": [],
       "source": [
         "TENSORBOARD_DISPLAY_NAME = \"example\"\n",
-        "tensorboard = aip.Tensorboard.create(display_name=TENSORBOARD_DISPLAY_NAME)\n",
+        "tensorboard = aiplatform.Tensorboard.create(display_name=TENSORBOARD_DISPLAY_NAME)\n",
         "tensorboard_resource_name = tensorboard.gca_resource.name\n",
         "print(\"TensorBoard resource name:\", tensorboard_resource_name)"
       ]
@@ -746,9 +929,9 @@
         "\n",
         "url = output[1].split(' ')[-1]\n",
         "\n",
-        "print(url)\n",
+        "#print(url)\n",
         "\n",
-        "from IPython.core.display import display, HTML\n",
+        "from IPython.display import display, HTML\n",
         "display(HTML(\"<a href='\" + url + \"'>click here for TensorBoard instance</a>\"))"
       ]
     },
@@ -953,7 +1136,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_example.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_example.tar.gz"
       ]
     },
     {
@@ -985,7 +1168,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomTrainingJob(\n",
+        "job = aiplatform.CustomTrainingJob(\n",
         "    display_name=\"example_\" + TIMESTAMP,\n",
         "    script_path=\"custom/trainer/task.py\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
@@ -1021,7 +1204,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -1143,14 +1326,8 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
         "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
         "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1162,61 +1339,14 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the custom training job\n",
+        "job.delete()\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Training\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -127,7 +133,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook"
       ]
     },
     {
@@ -138,20 +144,20 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -173,8 +179,6 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
         "    # Automatically restart kernel after installs\n",
         "    import IPython\n",
@@ -183,6 +187,36 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### GPU runtime\n",
+        "\n",
+        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -259,7 +293,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -286,6 +323,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -309,7 +407,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -320,8 +419,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -341,7 +441,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -361,7 +461,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -384,7 +484,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -406,7 +506,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -441,7 +541,7 @@
       "source": [
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
@@ -449,7 +549,7 @@
         "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_DEPLOY_GPU\")),\n",
         "    )\n",
         "else:\n",
@@ -484,7 +584,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -602,7 +702,7 @@
         "DISPLAY_NAME = \"boston_\" + TIMESTAMP\n",
         "REQUIREMENTS = [\"tensorflow==2.3\"]\n",
         "\n",
-        "job = aip.CustomTrainingJob(\n",
+        "job = aiplatform.CustomTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
         "    script_path=\"task.py\",\n",
         "    requirements=REQUIREMENTS,\n",
@@ -693,12 +793,12 @@
       "outputs": [],
       "source": [
         "CMDARGS = [\n",
-        "    \"--model-dir=\" + BUCKET_NAME,\n",
+        "    \"--model-dir=\" + BUCKET_URI,\n",
         "]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)\n",
         "\n",
-        "! gsutil cat {BUCKET_NAME}/test.txt"
+        "! gsutil cat {BUCKET_URI}/test.txt"
       ]
     },
     {
@@ -768,9 +868,9 @@
       "source": [
         "DISPLAY_NAME = \"boston_\" + TIMESTAMP\n",
         "\n",
-        "job = aip.CustomPythonPackageTrainingJob(\n",
+        "job = aiplatform.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         ")"
@@ -900,7 +1000,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -922,11 +1022,11 @@
       },
       "outputs": [],
       "source": [
-        "CMDARGS = [\"--model-dir=\" + BUCKET_NAME, \"--epochs=5\"]\n",
+        "CMDARGS = [\"--model-dir=\" + BUCKET_URI, \"--epochs=5\"]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)\n",
         "\n",
-        "! gsutil cat {BUCKET_NAME}/test.txt"
+        "! gsutil cat {BUCKET_URI}/test.txt"
       ]
     },
     {
@@ -1151,7 +1251,11 @@
       },
       "outputs": [],
       "source": [
-        "! docker build custom -t $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker build custom -t $TRAIN_IMAGE\n",
+        "else:\n",
+        "    # install docker daemon\n",
+        "    ! apt-get -qq install docker.io"
       ]
     },
     {
@@ -1173,7 +1277,8 @@
       },
       "outputs": [],
       "source": [
-        "! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
+        "if not IS_COLAB:\n",
+        "    ! docker run $TRAIN_IMAGE --epochs=5 --model-dir=./"
       ]
     },
     {
@@ -1195,7 +1300,38 @@
       },
       "outputs": [],
       "source": [
-        "! docker push $TRAIN_IMAGE"
+        "if not IS_COLAB:\n",
+        "    ! docker push $TRAIN_IMAGE"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f50e9c553fb7"
+      },
+      "source": [
+        "*Executes in Colab*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a7e8c98f1e56"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash -s $IS_COLAB $TRAIN_IMAGE\n",
+        "if [ $1 == \"False\" ]; then\n",
+        "  exit 0\n",
+        "fi\n",
+        "set -x\n",
+        "dockerd -b none --iptables=0 -l warn &\n",
+        "for i in $(seq 5); do [ ! -S \"/var/run/docker.sock\" ] && sleep 2 || break; done\n",
+        "docker build custom -t $2\n",
+        "docker run $2 --epochs=5 --model-dir=./\n",
+        "docker push $2\n",
+        "kill $(jobs -p)"
       ]
     },
     {
@@ -1229,7 +1365,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomContainerTrainingJob(\n",
+        "job = aiplatform.CustomContainerTrainingJob(\n",
         "    display_name=\"boston_\" + TIMESTAMP,\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    command=[\"python3\", \"trainer/task.py\"],\n",
@@ -1257,11 +1393,11 @@
       },
       "outputs": [],
       "source": [
-        "CMDARGS = [\"--model-dir=\" + BUCKET_NAME, \"--epochs=5\"]\n",
+        "CMDARGS = [\"--model-dir=\" + BUCKET_URI, \"--epochs=5\"]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)\n",
         "\n",
-        "! gsutil cat {BUCKET_NAME}/test.txt"
+        "! gsutil cat {BUCKET_URI}/test.txt"
       ]
     },
     {
@@ -1466,7 +1602,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -1496,7 +1632,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2.1\".replace(\".\", \"-\")\n",
+        "    TF = \"2.5\".replace(\".\", \"-\")\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -1551,9 +1687,9 @@
       "source": [
         "DISPLAY_NAME = \"boston_\" + TIMESTAMP\n",
         "\n",
-        "job = aip.CustomPythonPackageTrainingJob(\n",
+        "job = aiplatform.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_boston.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_boston.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -1587,12 +1723,12 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
         "\n",
-        "DIRECT = True\n",
+        "DIRECT = False\n",
         "if DIRECT:\n",
         "    CMDARGS = [\n",
         "        \"--model-dir=\" + MODEL_DIR,\n",
@@ -1758,17 +1894,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1779,61 +1905,24 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
+        "delete_model = True\n",
+        "delete_job = True\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
+        "if delete_model:\n",
         "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
+        "        model.delete()\n",
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
+        "if delete_job:\n",
         "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
+        "        job.delete()\n",
         "    except Exception as e:\n",
         "        print(e)\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -rf {BUCKET_URI}"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb

@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/notebook_template.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -82,8 +88,9 @@
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
-        "- `Vertex AI Training`\n",
-        "- `Vertex AI Model` resource\n",
+        "* `Vertex AI Training`\n",
+        "* `Vertex AI Model` resource\n",
+        "\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -93,6 +100,75 @@
         "- Create a `Vertex AI Model` resource."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "85ee859437ed"
+      },
+      "source": [
+        "## Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5cd61a5dd9db"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7e689ee0bc3c"
+      },
+      "source": [
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -101,7 +177,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
@@ -112,22 +188,22 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install --upgrade cloudml-hypertune $USER_FLAG -q\n",
+        "! pip3 install --upgrade torchvision $USER_FLAG -q"
       ]
     },
     {
@@ -159,6 +235,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "84cd83853240"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -235,7 +337,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -262,6 +367,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -285,7 +451,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -296,8 +462,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -317,7 +483,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -337,7 +503,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -360,7 +526,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aiplatform"
       ]
     },
     {
@@ -382,7 +548,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -412,13 +578,15 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
-        "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
+        "        aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+        "    TRAIN_GPU, TRAIN_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
       ]
     },
     {
@@ -561,6 +729,7 @@
         "# Add package information\n",
         "! touch custom/README.md\n",
         "\n",
+        "# Instructions for installing package into environment of the docker image\n",
         "setup_cfg = \"[egg_info]\\n\\ntag_build =\\n\\ntag_date = 0\"\n",
         "! echo \"$setup_cfg\" > custom/setup.cfg\n",
         "\n",
@@ -891,7 +1060,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_cifar10.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_cifar10.tar.gz"
       ]
     },
     {
@@ -902,7 +1071,7 @@
       "source": [
         "### Make Pytorch container for prediction\n",
         "\n",
-        "Currently, Vertex AI does not have a prefined container for making predictions with a deployed Pytorch model. No problem, you can assemble your own custom container. Typically, one would base the container on the `Torch Server`. For demonstration purpose, you build a placeholder container (not complete) that includes the latest `Torch Server` image, and push it to the `Container Registry`."
+        "Currently, Vertex AI does not have a predefined container for making predictions with a deployed Pytorch model. No problem, you can assemble your own custom container. Typically, one would base the container on the `Torch Server`. For demonstration purpose, you build a placeholder container (not complete) that includes the latest `Torch Server` image, and push it to the `Container Registry`."
       ]
     },
     {
@@ -932,11 +1101,52 @@
       "source": [
         "APP_NAME = \"cifar10\"\n",
         "DEPLOY_IMAGE = f\"gcr.io/{PROJECT_ID}/pytorch_predict_{APP_NAME}\"\n",
-        "print(DEPLOY_IMAGE)\n",
-        "\n",
-        "! docker build --tag=$DEPLOY_IMAGE ./\n",
-        "\n",
-        "! docker push $DEPLOY_IMAGE"
+        "print(DEPLOY_IMAGE)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "85739262f629"
+      },
+      "outputs": [],
+      "source": [
+        "if not IS_COLAB:\n",
+        "    ! docker build --tag=$DEPLOY_IMAGE ./\n",
+        "    ! docker push $DEPLOY_IMAGE\n",
+        "else:\n",
+        "    # install docker daemon\n",
+        "    ! apt-get -qq install docker.io"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f50e9c553fb7"
+      },
+      "source": [
+        "*Executes in Colab*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a7e8c98f1e56"
+      },
+      "outputs": [],
+      "source": [
+        "%%bash -s $IS_COLAB $DEPLOY_IMAGE\n",
+        "if [ $1 == \"False\" ]; then\n",
+        "  exit 0\n",
+        "fi\n",
+        "set -x\n",
+        "dockerd -b none --iptables=0 -l warn &\n",
+        "for i in $(seq 5); do [ ! -S \"/var/run/docker.sock\" ] && sleep 2 || break; done\n",
+        "docker build --tag=$2 ./\n",
+        "docker push $2\n",
+        "kill $(jobs -p)"
       ]
     },
     {
@@ -974,9 +1184,9 @@
       "source": [
         "DISPLAY_NAME = \"cifar10_\" + TIMESTAMP\n",
         "\n",
-        "job = aip.CustomPythonPackageTrainingJob(\n",
+        "job = aiplatform.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_cifar10.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_cifar10.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -1009,7 +1219,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "DIRECT = False\n",
         "if DIRECT:\n",
@@ -1121,7 +1331,7 @@
       "source": [
         "### Delete a custom training job\n",
         "\n",
-        "After a training job is completed, you can delete the training job with the method `delete()`.  Prior to completion, a training job can be canceled with the method `cancel()`."
+        "After a training job is completed, you can delete the training job with the method `delete()`.  Prior to completion, a training job can be cancelled with the method `cancel()`."
       ]
     },
     {
@@ -1148,14 +1358,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
         "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1167,61 +1370,12 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb

@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Training for R\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training for R\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Training for R."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for R. Please note that this notebook should be ran only in R notebook image (e.g., R4.1)."
       ]
     },
     {
@@ -98,6 +104,28 @@
         "- Train a R model using `Vertex AI Trainingh` service with the R-to-Python training package."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -106,33 +134,32 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade rpy2 $USER_FLAG -q"
       ]
     },
     {
@@ -164,6 +191,39 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0e3cab0cc491"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "be929e7b4d76"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -183,6 +243,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -240,7 +302,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -267,6 +331,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3ffa6b6c7cdb"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2b72272258fc"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -277,7 +402,7 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
         "\n",
         "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
@@ -290,7 +415,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -301,8 +426,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -322,7 +447,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -342,7 +467,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -365,6 +490,8 @@
       },
       "outputs": [],
       "source": [
+        "import traceback\n",
+        "\n",
         "import google.cloud.aiplatform as aip"
       ]
     },
@@ -387,7 +514,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -964,14 +1091,17 @@
       },
       "outputs": [],
       "source": [
-        "INSTANCES = [\n",
-        "    {\"sepal_width\": 1, \"sepal_length\": 2, \"petal_width\": 3, \"petal_length\": 1},\n",
-        "    {\"sepal_width\": 4, \"sepal_length\": 2, \"petal_width\": 1, \"petal_length\": 1},\n",
-        "]\n",
+        "try:\n",
+        "    INSTANCES = [\n",
+        "        {\"sepal_width\": 1, \"sepal_length\": 2, \"petal_width\": 3, \"petal_length\": 1},\n",
+        "        {\"sepal_width\": 4, \"sepal_length\": 2, \"petal_width\": 1, \"petal_length\": 1},\n",
+        "    ]\n",
         "\n",
-        "prediction = endpoint.predict(instances=INSTANCES)\n",
+        "    prediction = endpoint.predict(instances=INSTANCES)\n",
         "\n",
-        "print(prediction)"
+        "    print(prediction)\n",
+        "except:\n",
+        "    traceback.print_exc()"
       ]
     },
     {
@@ -1242,7 +1372,7 @@
       },
       "outputs": [],
       "source": [
-        "CMDARGS = [\"--model-dir=\" + BUCKET_NAME]\n",
+        "CMDARGS = [\"--model-dir=\" + BUCKET_URI]\n",
         "\n",
         "job.run(args=CMDARGS, replica_count=1, machine_type=TRAIN_COMPUTE, sync=True)"
       ]
@@ -1282,14 +1412,9 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "- Model (Already deleted in previous cells)\n",
+        "- Endpoint (Already deleted in previous cells)\n",
+        "- Custom Job (Already deleted in previous cells)\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1301,61 +1426,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb

@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb\">\n",
+        "     <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Training for Scikit-Learn."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for scikit-Learn."
       ]
     },
     {
@@ -93,41 +99,101 @@
         "- Create a `Vertex AI Model` resource."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b132d4ef86d6"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "94a148f11da5"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "install_mlops"
       },
       "source": [
-        "## Installations\n",
+        "### Install additional packages\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "78168417490e"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform -q"
       ]
     },
     {
@@ -159,6 +225,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -235,7 +327,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -262,6 +357,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -285,7 +441,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -296,8 +452,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -317,7 +473,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -337,7 +493,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -382,7 +538,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -415,6 +571,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
@@ -517,9 +675,9 @@
         "id": "sklearn_intro"
       },
       "source": [
-        "## Introduction to Scikit-learn training\n",
+        "## Introduction to scikit-learn training\n",
         "\n",
-        "Once you have trained a Scikit-learn model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource. The Scikit-learn package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
+        "Once you have trained a scikit-learn model, you will want to save it at a Cloud Storage location, so it can subsequently be uploaded to a `Vertex AI Model` resource. The Scikit-learn package does not have support to save the model to a Cloud Storage location. Instead, you will do the following steps to save to a Cloud Storage location.\n",
         "\n",
         "1. Save the in-memory model to the local filesystem in pickle format (e.g., model.pkl).\n",
         "2. Create a Cloud Storage storage client.\n",
@@ -783,7 +941,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_newsaggr.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_newsaggr.tar.gz"
       ]
     },
     {
@@ -823,7 +981,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_newsaggr.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_newsaggr.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -857,7 +1015,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "DATASET_URL = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00359/NewsAggregatorDataset.zip\"\n",
         "\n",
         "DIRECT = False\n",
@@ -1002,14 +1160,8 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
+        "\n",
         "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1017,65 +1169,16 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "b413063dfdcf"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb

@@ -29,9 +29,15 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Training for XGBoost\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Training for XGBoost\n",
         "\n",
         "<table align=\"left\">\n",
+        "    <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "    \n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,8 +45,9 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb\">\n",
+        "    <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -56,7 +63,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex Training for XGBoost."
+        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with Vertex AI Training for XGBoost."
       ]
     },
     {
@@ -90,7 +97,21 @@
         "- Training using a Python package.\n",
         "- Report accuracy when hyperparameter tuning.\n",
         "- Save the model artifacts to Cloud Storage using GCSFuse.\n",
-        "- Create a `Vertex AI Model` resource."
+        "- Create a `Vertex AI Model` resource.\n",
+        "\n",
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -101,62 +122,57 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages to execute this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
-      },
-      "outputs": [],
-      "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "restart"
-      },
-      "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "restart"
+        "id": "ncRJ_Dfdox9L"
       },
       "outputs": [],
       "source": [
         "import os\n",
         "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
       ]
     },
     {
@@ -231,11 +247,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "sKBTnvJpox9P"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -253,7 +272,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "JYtXOocrox9Q"
       },
       "outputs": [],
       "source": [
@@ -262,6 +281,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "77c385f0db59"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "NNc5Bf_NpPTq"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -272,7 +352,7 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+        "When you initialize the Vertex AI SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
         "\n",
         "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
@@ -285,7 +365,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -296,8 +376,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -313,11 +393,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "aO4sKJfFox9R"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -333,11 +413,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "yWnghzKFox9S"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -378,11 +458,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "JZg2sszQox9T"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -411,10 +491,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:training,cpu,prediction,cpu,mbsdk"
+        "id": "cQUrG4Mbox9T"
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
@@ -453,7 +535,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:training,prediction,xgboost"
+        "id": "XujRA5ueox9U"
       },
       "outputs": [],
       "source": [
@@ -497,7 +579,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "machine:training"
+        "id": "UMPFgENkox9U"
       },
       "outputs": [],
       "source": [
@@ -561,7 +643,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_training_package:xgboost"
+        "id": "f4wS4eISox9V"
       },
       "outputs": [],
       "source": [
@@ -616,7 +698,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:iris,xgboost"
+        "id": "WiSnFuDoox9W"
       },
       "outputs": [],
       "source": [
@@ -731,14 +813,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tarball_training_script"
+        "id": "dnmdycf6ox9X"
       },
       "outputs": [],
       "source": [
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_iris.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_iris.tar.gz"
       ]
     },
     {
@@ -770,7 +852,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_custom_pp_training_job:mbsdk"
+        "id": "rVEMz1xqox9X"
       },
       "outputs": [],
       "source": [
@@ -778,7 +860,7 @@
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
-        "    python_package_gcs_uri=f\"{BUCKET_NAME}/trainer_iris.tar.gz\",\n",
+        "    python_package_gcs_uri=f\"{BUCKET_URI}/trainer_iris.tar.gz\",\n",
         "    python_module_name=\"trainer.task\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
@@ -809,11 +891,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "prepare_custom_cmdargs:iris,xgboost"
+        "id": "AoUfpBqVox9Y"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "DATASET_DIR = \"gs://cloud-samples-data/ai-platform/iris\"\n",
         "\n",
         "ROUNDS = 20\n",
@@ -858,7 +940,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_custom_job:mbsdk"
+        "id": "JCruQq1aox9Y"
       },
       "outputs": [],
       "source": [
@@ -899,7 +981,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "list_job"
+        "id": "KBM_KLMSox9Y"
       },
       "outputs": [],
       "source": [
@@ -922,7 +1004,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "custom_job_wait:mbsdk"
+        "id": "lHPMHbSyox9Z"
       },
       "outputs": [],
       "source": [
@@ -944,7 +1026,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_job"
+        "id": "tlYg7Sp-ox9Z"
       },
       "outputs": [],
       "source": [
@@ -964,14 +1046,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "- Custom Job (Custome Training job is remove in previous step)\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -979,65 +1054,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "JyWy23gDox9a"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -29,7 +29,7 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex Vizier\n",
+        "# E2E ML on GCP: MLOps stage 2 : experimentation: get started with Vertex AI Vizier\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -39,10 +39,16 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
-        "    </a>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
         "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>           \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -136,31 +142,31 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG"
       ]
     },
     {
@@ -192,6 +198,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -268,7 +300,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -295,6 +329,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -318,7 +413,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -329,8 +424,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -350,7 +445,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -370,7 +465,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -415,7 +510,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -808,7 +903,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -916,7 +1011,7 @@
       "outputs": [],
       "source": [
         "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, JOB_NAME)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
         "    TRAIN_STRATEGY = \"single\"\n",
@@ -948,7 +1043,7 @@
         "        \"disk_spec\": disk_spec,\n",
         "        \"python_package_spec\": {\n",
         "            \"executor_image_uri\": TRAIN_IMAGE,\n",
-        "            \"package_uris\": [BUCKET_NAME + \"/trainer_boston.tar.gz\"],\n",
+        "            \"package_uris\": [BUCKET_URI + \"/trainer_boston.tar.gz\"],\n",
         "            \"python_module\": \"trainer.task\",\n",
         "            \"args\": CMDARGS,\n",
         "        },\n",
@@ -1577,14 +1672,6 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1596,61 +1683,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb

@@ -39,8 +39,14 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -173,6 +179,19 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
         "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\n",
         "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
@@ -220,6 +239,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2721ef0202d9"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -296,7 +341,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -323,6 +370,75 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "648aa9824ac6"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -436,9 +552,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -583,6 +706,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
@@ -1218,7 +1343,7 @@
         "setup_cfg = \"[egg_info]\\n\\ntag_build =\\n\\ntag_date = 0\"\n",
         "! echo \"$setup_cfg\" > custom/setup.cfg\n",
         "\n",
-        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'google-cloud-aiplatform',\\n\\n        'cloudml-hypertune',\\n\\n        'tensorflow_datasets==1.3.0',\\n\\n        'tensorflow_data_validation==1.2',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
+        "setup_py = \"import setuptools\\n\\nsetuptools.setup(\\n\\n    install_requires=[\\n\\n        'google-cloud-aiplatform',\\n\\n        'cloudml-hypertune',\\n\\n        'tensorflow_datasets==1.3.0',\\n\\n        'tensorflow==2.5',\\n\\n    'tensorflow_data_validation==1.2',\\n\\n    ],\\n\\n    packages=setuptools.find_packages())\"\n",
         "! echo \"$setup_py\" > custom/setup.py\n",
         "\n",
         "pkg_info = \"Metadata-Version: 1.0\\n\\nName: Chicago Taxi tabular binary classifier\\n\\nVersion: 0.0.0\\n\\nSummary: Demostration training script\\n\\nHome-page: www.google.com\\n\\nAuthor: Google\\n\\nAuthor-email: cdpe@google.com\\n\\nLicense: Public\\n\\nDescription: Demo\\n\\nPlatform: Vertex AI\"\n",
@@ -3011,9 +3136,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -3024,18 +3148,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=chicago_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {

notebooks/community/ml_ops/stage3/README.md

@@ -27,7 +27,7 @@ The third stage in MLOps is formalization to develop an automated pipeline proce
 - Use early stop procedure in training script to detect failure to achieve training objective.
 - Store the results of the trained model evaluation in Vertex AI ML Metadata.
 
-<img src='stage3.png'>
+<img src='stage3v3.png'>
 
 ## Notebooks
 
@@ -41,6 +41,7 @@ The steps performed include:
 - Building KFP lightweight Python function components.
 - Assembling and compiling KFP components into a pipeline.
 - Executing a KFP pipeline using Vertex AI Pipelines.
+- Loading component and pipeline definitions from a source code repository.
 - Building sequential, parallel, multiple output components.
 - Building control flow into pipelines.
 ```
@@ -65,6 +66,17 @@ The steps performed include:
 - Execute a Vertex AI pipeline.
 ```
 
+[Get Started with Dataproc components](get_started_with_dataproc_pipeline_components.ipynb)
+
+```
+The steps performed include:
+
+- DataprocPySparkBatchOp for PySpark batch workloads.
+- DataprocSparkBatchOp for Spark batch workloads.
+- DataprocSparkSqlBatchOp for running Spark SQL batch workloads.
+- DataprocSparkRBatchOp for running SparkR batch workloads.
+```
+
 [Get Started with Vertex AI AutoML components](get_started_with_automl_pipeline_components.ipynb)
 
 ```
@@ -91,19 +103,6 @@ The steps performed include:
 
 [Get Started with Vertex AI Hyperparameter Tuning components](get_started_with_hpt_pipeline_components.ipynb)
 
-```
-- Construct a pipeline for:
-    - Training BigQuery ML model.
-    - Evaluating the BigQuery ML model.
-    - Exporting the BigQuery ML model.
-    - Importing the BigQuery ML model to a Vertex AI model.
-    - Deploy the Vertex AI model.
-- Execute a Vertex AI pipeline.
-- Make a prediction with the deployed Vertex AI model.
-```
-
-[Get Started with BQML components](get_started_with_bqml_pipeline_components.ipynb)
-
 ```
 The steps performed include:
 
@@ -116,6 +115,67 @@ The steps performed include:
 - Execute a Vertex AI pipeline.
 ```
 
+[Get Started with BQML components](get_started_with_bqml_pipeline_components.ipynb)
+
+```
+The steps performed include:
+
+- Construct a pipeline for:
+    - Training BigQuery ML model.
+    - Evaluating the BigQuery ML model.
+    - Exporting the BigQuery ML model.
+    - Importing the BigQuery ML model to a Vertex AI model.
+    - Deploy the Vertex AI model.
+- Execute a Vertex AI pipeline.
+- Make a prediction with the deployed Vertex AI model.
+```
+
+[Get Started with rapid prototyping with BQML and AutoML components](get_started_with_rapid_prototyping_bqml_automl.ipynb)
+
+
+```
+The steps performed include:
+
+- Creating a BigQuery and Vertex AI training dataset.
+- Training a BigQuery ML and AutoML model.
+- Extracting evaluation metrics from the BigQueryML and AutoML models.
+- Selecting the best trained model.
+- Deploying the best trained model.
+- Testing the deployed model infrastructure.
+```
+
+[Get Started with TFX Pipelines with Vertex AI](get_started_with_tfx_pipeline.ipynb)
+
+```
+The steps performed include:
+
+- Create a TFX e2e pipeline.
+- Execute the pipeline locally.
+- Execute the pipeline on Google Cloud using `Vertex AI Training`
+- Execute the pipeline using `Vertex AI Pipelines`.
+```
+
+[Get Started with machine management](get_started_with_machine_management.ipynb)
+
+```
+The steps performed in this tutorial include:
+
+- Create a custom component with a self-contained training job.
+- Execute pipeline using component-level settings for machine resources
+- Convert the self-contained training componnt into a Vertex AI CustomJob.
+- Execute pipeline using customjob-level settings for machine resources
+```
+
+[Get Started with Apache Airflow and Vertex AI Pipelines](get_started_with_airflow_and_vertex_pipelines.ipynb)
+
+```
+The steps performed in this tutorial include:
+
+- Create Cloud Composer environment.
+- Upload Airflow DAG to Composer environment that performs data processing -- i.e., creates a BigQuery table from a CSV file.
+- Create a Vertex Pipeline that triggers the Airflow DAG.
+- Execute the `Vertex AI Pipeline`.
+```
 
 ### E2E Stage Example
 

notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -38,9 +38,15 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -67,7 +73,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower an image is from a class of five flowers: daisy, dandelion, rose, sunflower, or tulip."
+        "The dataset used for this tutorial is the [Flowers dataset](https://www.tensorflow.org/datasets/catalog/tf_flowers) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of flower in the given image from the five classes of flowers: daisy, dandelion, rose, sunflower, or tulip."
       ]
     },
     {
@@ -94,7 +100,15 @@
         "    - Training a Vertex AI AutoML trained model.\n",
         "    - Test the serving binary with a batch prediction job.\n",
         "    - Deploying a Vertex AI AutoML trained model.\n",
-        "- Execute a Vertex AI pipeline."
+        "- Execute a Vertex AI pipeline.\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -105,7 +119,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the following packages for executing this MLOps notebook."
       ]
     },
     {
@@ -116,22 +130,25 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "    \n",
+        "! pip3 install tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
+        "                        google-cloud-pipeline-components \\\n",
+        "                        google-cloud-logging \\\n",
+        "                        pyarrow \\\n",
+        "                        kfp $USER_FLAG -q"
       ]
     },
     {
@@ -142,7 +159,7 @@
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "Once you've installed the additional packages, you need to restart the notebook kernel so that it can find the packages."
       ]
     },
     {
@@ -163,6 +180,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -239,7 +280,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -266,6 +310,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c38be665ca50"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Notebook Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0953a00668e"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -289,7 +394,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -300,8 +406,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -321,7 +427,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -341,7 +447,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -352,7 +458,7 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
       ]
     },
     {
@@ -379,9 +485,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -393,7 +506,7 @@
       "source": [
         "#### Set service account access for Vertex AI Pipelines\n",
         "\n",
-        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step. You only need to run this step once per service account."
       ]
     },
     {
@@ -404,9 +517,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -415,32 +528,7 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tf"
-      },
-      "source": [
-        "#### Import TensorFlow\n",
-        "\n",
-        "Import the TensorFlow package into your Python environment."
+        "### Import libraries"
       ]
     },
     {
@@ -451,22 +539,14 @@
       },
       "outputs": [],
       "source": [
-        "import tensorflow as tf"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp"
-      },
-      "outputs": [],
-      "source": [
+        "import base64\n",
         "import json\n",
         "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "import tensorflow as tf\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
+        "from kfp.v2.dsl import Artifact, Input, Output, component"
       ]
     },
     {
@@ -488,7 +568,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -528,7 +608,7 @@
         "- Takes as input the region and Model artifacts returned from an AutoML training component.\n",
         "- Create a client interface to the Vertex AI Model service (`metadata[\"resource_name\"]).\n",
         "- Construct the resource ID for the model from the model artifact parameter.\n",
-        "- Retrieve the model evaluation\n",
+        "- Retrieve the model evaluation.\n",
         "- Return the model evaluation as a string."
       ]
     },
@@ -540,11 +620,10 @@
       },
       "outputs": [],
       "source": [
-        "from kfp.v2.dsl import Artifact, Input, Model\n",
-        "\n",
-        "\n",
         "@component(packages_to_install=[\"google-cloud-aiplatform\"])\n",
-        "def evaluateAutoMLModelOp(model: Input[Artifact], region: str) -> str:\n",
+        "def evaluateAutoMLModelOp(\n",
+        "    model: Input[Artifact], region: str, model_evaluation: Output[Artifact]\n",
+        "):\n",
         "    import logging\n",
         "\n",
         "    import google.cloud.aiplatform.gapic as gapic\n",
@@ -557,8 +636,7 @@
         "\n",
         "    model_evaluations = model_service_client.list_model_evaluations(parent=model_id)\n",
         "    model_evaluation = list(model_evaluations)[0]\n",
-        "    logging.info(model_evaluation)\n",
-        "    return str(model_evaluation)"
+        "    logging.info(model_evaluation)"
       ]
     },
     {
@@ -574,7 +652,7 @@
         "1. Use the prebuilt component `ImageDatasetCreateOp` to create a Vertex AI Dataset resource, where:\n",
         "    - The display name for the dataset is passed into the pipeline.\n",
         "    - The import file for the dataset is passed into the pipeline.\n",
-        "    - The component returns the dataset resource as `outputs[\"dataset\"]`\n",
+        "    - The component returns the dataset resource as `outputs[\"dataset\"]`.\n",
         "\n",
         "\n",
         "2. Use the prebuilt component `AutoMLImageTrainingJobRunOp` to train a Vertex AI AutoML Model resource, where:\n",
@@ -593,12 +671,12 @@
         "    - The component returns the endpoint resource as `outputs[\"endpoint\"]`.\n",
         "\n",
         "\n",
-        "5. Use the prebuilt component `ModelDeployOp` to deploy the trained AutoML model to, where:\n",
+        "5. Use the prebuilt component `ModelDeployOp` to deploy the trained AutoML model where:\n",
         "    - The display name for the dataset is passed into the pipeline.\n",
         "    - The model is the output from the `AutoMLTrainingJobRunOp`.\n",
-        "    - The endpoint is the output from the `EndpointCreateOp`\n",
+        "    - The endpoint is the output from the `EndpointCreateOp`.\n",
         "\n",
-        "*Note:* Since each component is executed as a graph node in its own execution context, you pass the parameter `project` for each component op, in constrast to doing a `aip.init(project=project)` if this was a Python script calling the SDK methods directly within the same execution context."
+        "*Note:* Since each component is executed as a graph node in its own execution context, you pass the parameter `project` for each component op, in constrast to doing a `aiplatform.init(project=project)` if this was a Python script calling the SDK methods directly within the same execution context."
       ]
     },
     {
@@ -609,9 +687,7 @@
       },
       "outputs": [],
       "source": [
-        "from google_cloud_pipeline_components import aiplatform as gcc_aip\n",
-        "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/automl_icn_training\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/automl_icn_training\".format(BUCKET_URI)\n",
         "DEPLOY_COMPUTE = \"n1-standard-4\"\n",
         "\n",
         "\n",
@@ -626,12 +702,13 @@
         "    project: str = PROJECT_ID,\n",
         "    region: str = REGION,\n",
         "):\n",
+        "    from google_cloud_pipeline_components import aiplatform as gcc_aip\n",
         "\n",
         "    dataset_op = gcc_aip.ImageDatasetCreateOp(\n",
         "        project=project,\n",
         "        display_name=display_name,\n",
         "        gcs_source=import_file,\n",
-        "        import_schema_uri=aip.schema.dataset.ioformat.image.single_label_classification,\n",
+        "        import_schema_uri=aiplatform.schema.dataset.ioformat.image.single_label_classification,\n",
         "    )\n",
         "\n",
         "    training_op = gcc_aip.AutoMLImageTrainingJobRunOp(\n",
@@ -639,7 +716,6 @@
         "        display_name=display_name,\n",
         "        prediction_type=\"classification\",\n",
         "        model_type=\"CLOUD\",\n",
-        "        base_model=None,\n",
         "        dataset=dataset_op.outputs[\"dataset\"],\n",
         "        model_display_name=display_name,\n",
         "        training_fraction_split=0.6,\n",
@@ -670,11 +746,12 @@
         "        display_name=display_name,\n",
         "    ).after(batch_op)\n",
         "\n",
-        "    deploy_op = gcc_aip.ModelDeployOp(\n",
+        "    _ = gcc_aip.ModelDeployOp(\n",
         "        model=training_op.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        automatic_resources_min_replica_count=1,\n",
         "        automatic_resources_max_replica_count=1,\n",
+        "        traffic_split={\"0\": 100},\n",
         "    )"
       ]
     },
@@ -686,7 +763,7 @@
       "source": [
         "### Get test item(s)\n",
         "\n",
-        "Now do a batch prediction to your Vertex model. You will use arbitrary examples out of the dataset as a test items. Don't be concerned that the examples were likely used in training the model -- we just want to demonstrate how to make a prediction."
+        "In the pipeline, you do a batch prediction on your Vertex model. You will use arbitrary examples from the dataset as test items. Don't be concerned that the examples were likely used while training the model. This step is just to demonstrate how to make a prediction."
       ]
     },
     {
@@ -731,11 +808,11 @@
         "file_1 = test_item_1.split(\"/\")[-1]\n",
         "file_2 = test_item_2.split(\"/\")[-1]\n",
         "\n",
-        "! gsutil cp $test_item_1 $BUCKET_NAME/$file_1\n",
-        "! gsutil cp $test_item_2 $BUCKET_NAME/$file_2\n",
+        "! gsutil cp $test_item_1 $BUCKET_URI/$file_1\n",
+        "! gsutil cp $test_item_2 $BUCKET_URI/$file_2\n",
         "\n",
-        "test_item_1 = BUCKET_NAME + \"/\" + file_1\n",
-        "test_item_2 = BUCKET_NAME + \"/\" + file_2"
+        "test_item_1 = BUCKET_URI + \"/\" + file_1\n",
+        "test_item_2 = BUCKET_URI + \"/\" + file_2"
       ]
     },
     {
@@ -746,14 +823,14 @@
       "source": [
         "### Make the batch input file\n",
         "\n",
-        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can be either CSV or JSONL. You will use JSONL in this tutorial. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains the key/value pairs:\n",
+        "Now make a batch input file, which you will store in your local Cloud Storage bucket. The batch input file can only be in JSONL format. For JSONL file, you make one dictionary entry per line for each data item (instance). The dictionary contains key/value pairs:\n",
         "\n",
         "- `content`: The Cloud Storage path to the image.\n",
         "- `mime_type`: The content type. In our example, it is a `jpeg` file.\n",
         "\n",
         "For example:\n",
         "\n",
-        "                        {'content': '[your-bucket]/file1.jpg', 'mime_type': 'jpeg'}"
+        "    {'content': '[your-bucket]/file1.jpg', 'mime_type': 'jpeg'}"
       ]
     },
     {
@@ -764,11 +841,7 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
-        "import tensorflow as tf\n",
-        "\n",
-        "gcs_input_uri = BUCKET_NAME + \"/test.jsonl\"\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
         "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
         "    data = {\"content\": test_item_1, \"mime_type\": \"image/jpeg\"}\n",
         "    f.write(json.dumps(data) + \"\\n\")\n",
@@ -808,7 +881,7 @@
         "    pipeline_func=pipeline, package_path=\"automl_icn_training.json\"\n",
         ")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"automl_icn_training\",\n",
         "    template_path=\"automl_icn_training.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -878,25 +951,52 @@
         "            + str(TASK_ID)\n",
         "            + \"/gcp_resources\"\n",
         "        )\n",
+        "        EVAL_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
         "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
         "            ! gsutil cat $EXECUTE_OUTPUT\n",
-        "            break\n",
+        "            return EXECUTE_OUTPUT\n",
         "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
         "            ! gsutil cat $GCP_RESOURCES\n",
-        "            break\n",
+        "            return GCP_RESOURCES\n",
+        "        elif tf.io.gfile.exists(EVAL_METRICS):\n",
+        "            ! gsutil cat $EVAL_METRICS\n",
+        "            return EVAL_METRICS\n",
         "\n",
-        "    return EXECUTE_OUTPUT\n",
+        "    return None\n",
         "\n",
         "\n",
-        "print(\"imagedataset-create\")\n",
-        "artifacts = print_pipeline_output(pipeline, \"imagedataset-create\")\n",
+        "print(\"image-dataset-create\")\n",
+        "artifacts = print_pipeline_output(pipeline, \"image-dataset-create\")\n",
         "print(\"\\n\\n\")\n",
-        "print(\"automlimagetrainingjob-run\")\n",
-        "artifacts = print_pipeline_output(pipeline, \"automlimagetrainingjob-run\")\n",
+        "print(\"automl-image-training-job\")\n",
+        "artifacts = print_pipeline_output(pipeline, \"automl-image-training-job\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
+        "print(\"\\n\")\n",
+        "print(model_id)\n",
         "print(\"endpoint-create\")\n",
         "artifacts = print_pipeline_output(pipeline, \"endpoint-create\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "endpoint_id = output[\"artifacts\"][\"endpoint\"][\"artifacts\"][0][\"metadata\"][\n",
+        "    \"resourceName\"\n",
+        "]\n",
+        "print(\"\\n\")\n",
+        "print(endpoint_id)\n",
         "print(\"model-deploy\")\n",
         "artifacts = print_pipeline_output(pipeline, \"model-deploy\")\n",
         "print(\"\\n\\n\")\n",
@@ -912,7 +1012,12 @@
         "    output[\"artifacts\"][\"batchpredictionjob\"][\"artifacts\"][0][\"metadata\"][\n",
         "        \"gcsOutputDirectory\"\n",
         "    ]\n",
-        ")"
+        ")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "batch_job_id = output[\"artifacts\"][\"batchpredictionjob\"][\"artifacts\"][0][\"metadata\"][\n",
+        "    \"resourceName\"\n",
+        "]"
       ]
     },
     {
@@ -940,7 +1045,117 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "endpoint_load:mbsdk"
+      },
+      "source": [
+        "#### Load an endpoint\n",
+        "\n",
+        "The 'Endpoint' initializer will load an endpoint from an endpoint identifier."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "endpoint_load:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint = aiplatform.Endpoint(endpoint_id)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "make_prediction"
+      },
+      "source": [
+        "## Send a online prediction request\n",
+        "\n",
+        "Send a online prediction request to your deployed model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_test_item"
+      },
+      "source": [
+        "### Get test item\n",
+        "\n",
+        "You will use an arbitrary example out of the dataset as a test item. Don't be concerned that the example was likely used while training the model. This step is just to demonstrate how to make a prediction."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "get_test_item:automl,icn,csv"
+      },
+      "outputs": [],
+      "source": [
+        "test_item = !gsutil cat $IMPORT_FILE | head -n1\n",
+        "if len(str(test_item[0]).split(\",\")) == 3:\n",
+        "    _, test_item, test_label = str(test_item[0]).split(\",\")\n",
+        "else:\n",
+        "    test_item, test_label = str(test_item[0]).split(\",\")\n",
+        "\n",
+        "print(test_item, test_label)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "predict_request:mbsdk,icn"
+      },
+      "source": [
+        "### Make the prediction\n",
+        "\n",
+        "Now that your `Model` resource is deployed to an `Endpoint` resource, you can do online predictions by sending prediction requests to the Endpoint resource.\n",
+        "\n",
+        "#### Request\n",
+        "\n",
+        "Since in this example your test item is in a Cloud Storage bucket, you open and read the contents of the image using `tf.io.gfile.Gfile()`. To pass the test data to the prediction service, you encode the bytes into base64 which makes the content safe from modification while transmitting binary data over the network.\n",
+        "\n",
+        "The format of each instance is:\n",
+        "\n",
+        "    { 'content': { 'b64': base64_encoded_bytes } }\n",
+        "\n",
+        "Since the `predict()` method can take multiple items (instances), send your single test item as a list of one test item.\n",
+        "\n",
+        "#### Response\n",
+        "\n",
+        "The response from the `predict()` call is a Python dictionary with the following entries:\n",
+        "\n",
+        "- `ids`: The internal assigned unique identifiers for each prediction request.\n",
+        "- `displayNames`: The class names for each class label.\n",
+        "- `confidences`: The predicted confidence, between 0 and 1, per class label.\n",
+        "- `deployed_model_id`: The Vertex AI identifier for the deployed Model resource which did the predictions."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "predict_request:mbsdk,icn"
+      },
+      "outputs": [],
+      "source": [
+        "with tf.io.gfile.GFile(test_item, \"rb\") as f:\n",
+        "    content = f.read()\n",
+        "\n",
+        "# The format of each instance should conform to the deployed model's prediction input schema.\n",
+        "instances = [{\"content\": base64.b64encode(content).decode(\"utf-8\")}]\n",
+        "\n",
+        "prediction = endpoint.predict(instances=instances)\n",
+        "\n",
+        "print(prediction)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9d347472d5ba"
       },
       "source": [
         "# Cleaning up\n",
@@ -948,17 +1163,40 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "Otherwise, you can delete the individual resources you created in this tutorial.\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "#### Delete the Vertex AI Model, Endpoint and BatchPredictionJob resources\n",
+        "\n",
+        "Undelpoy and delete the Vertex AI Model, Endpoint and BatchPredictionJob resources."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "baa3e1071f7b"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
+        "\n",
+        "model = aiplatform.Model(model_id)\n",
+        "model.delete()\n",
+        "\n",
+        "batch_job = aiplatform.BatchPredictionJob(batch_job_id)\n",
+        "batch_job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a802da1f6fa7"
+      },
+      "source": [
+        "#### Delete the Cloud Storage bucket\n",
+        "\n",
+        "Set `delete_bucket` to *True* to delete the Cloud storage bucket used in this notebook."
       ]
     },
     {
@@ -969,61 +1207,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -93,6 +99,28 @@
         "- Execute a Vertex AI pipeline."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -101,31 +129,33 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -157,6 +187,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -176,6 +230,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -233,7 +289,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -260,6 +318,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "648aa9824ac6"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fc52bba17ee3"
+      },
+      "source": [
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -283,7 +417,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -294,8 +428,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -315,7 +449,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -335,7 +469,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -346,7 +480,9 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below.\n",
+        "\n",
+        "*Note:* The code for automatically finding your service account works on a user-managed Workbench AI noteboook. If you are using a fully-managed notebook or colab, you will need to manually enter your service account."
       ]
     },
     {
@@ -373,9 +509,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -398,9 +541,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -482,7 +625,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -597,7 +740,7 @@
         "    return dataset.column_names\n",
         "\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_bq\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_bq\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -610,9 +753,9 @@
         "):\n",
         "    create_op = create_dataset_bq(bq_table, display_name, project)\n",
         "\n",
-        "    source_op = get_dataset_source(create_op.output)\n",
+        "    _ = get_dataset_source(create_op.output)\n",
         "\n",
-        "    column_names_op = get_column_names(create_op.output)\n",
+        "    _ = get_column_names(create_op.output)\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataset_bq.json\")\n",
@@ -811,7 +954,7 @@
         "    return (stats_file, schema_file)\n",
         "\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_stats\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataset_stats\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -819,7 +962,7 @@
         ")\n",
         "def pipeline(dataset_id: str, label: str, bucket: str):\n",
         "\n",
-        "    stats_op = statistics(dataset_id, label, bucket)\n",
+        "    _ = statistics(dataset_id, label, bucket)\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataset_stats.json\")\n",
@@ -831,7 +974,7 @@
         "    parameter_values={\n",
         "        \"dataset_id\": dataset_id,\n",
         "        \"label\": \"mean_temp\",\n",
-        "        \"bucket\": BUCKET_NAME,\n",
+        "        \"bucket\": BUCKET_URI,\n",
         "    },\n",
         ")\n",
         "\n",
@@ -901,14 +1044,7 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
+        "- Vertex AI dataset\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -920,61 +1056,17 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Create reference to Vertex AI dataset created in pipeline\n",
+        "dataset = aip.TabularDataset(dataset_id)\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# delete Vertex AI dataset\n",
+        "dataset.delete()\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb

@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>  \n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -99,6 +105,28 @@
         "- Make a prediction with the deployed Vertex AI model."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -107,35 +135,35 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the packages required for executing the notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -153,7 +181,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "fIuF_ZjxJ39h"
       },
       "outputs": [],
       "source": [
@@ -167,6 +195,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -186,6 +238,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -239,11 +293,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "c1Rim3ogJ39j"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -261,7 +317,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "hdkr5x2jJ39k"
       },
       "outputs": [],
       "source": [
@@ -270,6 +326,82 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "UG2SHSlTJ39k"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ETQR4H1HJ39k"
+      },
+      "source": [
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9M66jv07J39l"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -293,7 +425,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -304,8 +437,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -321,11 +454,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "V97jQQuiJ39m"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -341,11 +474,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "7PN6kSQtJ39m"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -356,14 +489,16 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below.\n",
+        "\n",
+        "*Note:* The code for automatically finding your service account works on a user-managed Workbench AI noteboook. If you are using a fully-managed notebook, you will need to manually enter your service account."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account"
+        "id": "M4WZi4CDJ39n"
       },
       "outputs": [],
       "source": [
@@ -383,9 +518,17 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        # print(\"shell_output=\", shell_output)\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -404,13 +547,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account:pipelines"
+        "id": "mI3IJONMJ39n"
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -447,8 +590,7 @@
         "import json\n",
         "\n",
         "from kfp import dsl\n",
-        "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
+        "from kfp.v2 import compiler"
       ]
     },
     {
@@ -466,7 +608,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_bq"
+        "id": "r7p4Iv8_J39o"
       },
       "outputs": [],
       "source": [
@@ -488,7 +630,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_tf"
+        "id": "_K5tP8oJJ39p"
       },
       "outputs": [],
       "source": [
@@ -510,11 +652,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk,all"
+        "id": "uAnLpS9cJ39p"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -532,7 +674,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_bq"
+        "id": "I9RloZo9J39p"
       },
       "outputs": [],
       "source": [
@@ -562,7 +704,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:prediction,mbsdk"
+        "id": "1-mE_7kXJ39p"
       },
       "outputs": [],
       "source": [
@@ -595,7 +737,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:prediction"
+        "id": "AmHM8whxJ39q"
       },
       "outputs": [],
       "source": [
@@ -668,11 +810,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bqml_pipeline:tabular"
+        "id": "LvND7iTpJ39r"
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = f\"{BUCKET_NAME}/bq_query\"\n",
+        "PIPELINE_ROOT = f\"{BUCKET_URI}/bq_query\"\n",
         "\n",
         "\n",
         "@dsl.pipeline(name=\"bq-hello-world\", pipeline_root=PIPELINE_ROOT)\n",
@@ -694,6 +836,7 @@
         "    location: str = \"US\",\n",
         "    region: str = \"us-central1\",\n",
         "):\n",
+        "    from google_cloud_pipeline_components.types import artifact_types\n",
         "    from google_cloud_pipeline_components.v1.bigquery import (\n",
         "        BigqueryCreateModelJobOp, BigqueryEvaluateModelJobOp,\n",
         "        BigqueryExportModelJobOp, BigqueryPredictModelJobOp,\n",
@@ -701,6 +844,7 @@
         "    from google_cloud_pipeline_components.v1.endpoint import (EndpointCreateOp,\n",
         "                                                              ModelDeployOp)\n",
         "    from google_cloud_pipeline_components.v1.model import ModelUploadOp\n",
+        "    from kfp.v2.components import importer_node\n",
         "\n",
         "    bq_dataset = BigqueryQueryJobOp(\n",
         "        project=project, location=\"US\", query=f\"CREATE SCHEMA {dataset}\"\n",
@@ -712,11 +856,11 @@
         "        query=f\"CREATE OR REPLACE MODEL {dataset}.{model} OPTIONS (model_type='dnn_classifier', labels=['{label}'], num_trials={num_trials}) AS SELECT * FROM `{bq_table}` WHERE body_mass_g IS NOT NULL AND sex IS NOT NULL\",\n",
         "    ).after(bq_dataset)\n",
         "\n",
-        "    bq_eval = BigqueryEvaluateModelJobOp(\n",
+        "    _ = BigqueryEvaluateModelJobOp(\n",
         "        project=PROJECT_ID, location=\"US\", model=bq_model.outputs[\"model\"]\n",
         "    ).after(bq_model)\n",
         "\n",
-        "    bq_predict = BigqueryPredictModelJobOp(\n",
+        "    _ = BigqueryPredictModelJobOp(\n",
         "        project=project,\n",
         "        location=location,\n",
         "        model=bq_model.outputs[\"model\"],\n",
@@ -738,21 +882,29 @@
         "        model_destination_path=artifact_uri,\n",
         "    ).after(bq_model)\n",
         "\n",
-        "    model_upload = ModelUploadOp(\n",
-        "        display_name=display_name,\n",
+        "    import_unmanaged_model_task = importer_node.importer(\n",
         "        artifact_uri=artifact_uri,\n",
-        "        serving_container_image_uri=deploy_image,\n",
-        "        project=project,\n",
-        "        location=region,\n",
+        "        artifact_class=artifact_types.UnmanagedContainerModel,\n",
+        "        metadata={\n",
+        "            \"containerSpec\": {\n",
+        "                \"imageUri\": DEPLOY_IMAGE,\n",
+        "            },\n",
+        "        },\n",
         "    ).after(bq_export)\n",
         "\n",
+        "    model_upload = ModelUploadOp(\n",
+        "        project=project,\n",
+        "        display_name=display_name,\n",
+        "        unmanaged_container_model=import_unmanaged_model_task.outputs[\"artifact\"],\n",
+        "    ).after(import_unmanaged_model_task)\n",
+        "\n",
         "    endpoint = EndpointCreateOp(\n",
         "        project=project,\n",
         "        location=region,\n",
         "        display_name=display_name,\n",
         "    ).after(model_upload)\n",
         "\n",
-        "    deploy_model = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=model_upload.outputs[\"model\"],\n",
         "        endpoint=endpoint.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=min_replica_count,\n",
@@ -794,11 +946,23 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_pipeline:bqml"
+        "id": "l2FMs74-J39r"
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = BUCKET_NAME + \"/bqmodel\"\n",
+        "# If DEPLOY_GPU is None, keeping gpu as no accelerator and accelerator_count as 0\n",
+        "accelerator_count = 0\n",
+        "if DEPLOY_GPU:\n",
+        "    gpu = DEPLOY_GPU.name\n",
+        "    accelerator_count = 1\n",
+        "else:\n",
+        "    gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"  # Unspecified accelerator type, which means no accelerator.\n",
+        "    accelerator_count = 0\n",
+        "\n",
+        "print(\"gpu=\", gpu)\n",
+        "print(\"accelerator_count=\", accelerator_count)\n",
+        "\n",
+        "MODEL_DIR = BUCKET_URI + \"/bqmodel\"\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"bqml.json\")\n",
         "\n",
@@ -818,8 +982,8 @@
         "        \"machine_type\": \"n1-standard-4\",\n",
         "        \"min_replica_count\": 1,\n",
         "        \"max_replica_count\": 1,\n",
-        "        \"accelerator_type\": DEPLOY_GPU.name,\n",
-        "        \"accelerator_count\": DEPLOY_NGPU,\n",
+        "        \"accelerator_type\": gpu,\n",
+        "        \"accelerator_count\": accelerator_count,\n",
         "        \"project\": PROJECT_ID,\n",
         "        \"location\": \"US\",\n",
         "    },\n",
@@ -844,7 +1008,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "view_pipleline_results:bqml"
+        "id": "2OM8zzJXJ39s"
       },
       "outputs": [],
       "source": [
@@ -881,14 +1045,29 @@
         "            + str(TASK_ID)\n",
         "            + \"/gcp_resources\"\n",
         "        )\n",
+        "        EVAL_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
         "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
         "            ! gsutil cat $EXECUTE_OUTPUT\n",
-        "            break\n",
+        "            return EXECUTE_OUTPUT\n",
         "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
         "            ! gsutil cat $GCP_RESOURCES\n",
-        "            break\n",
+        "            return GCP_RESOURCES\n",
+        "        elif tf.io.gfile.exists(EVAL_METRICS):\n",
+        "            ! gsutil cat $EVAL_METRICS\n",
+        "            return EVAL_METRICS\n",
         "\n",
-        "    return EXECUTE_OUTPUT\n",
+        "    return None\n",
         "\n",
         "\n",
         "print(\"bigquery-query-job\")\n",
@@ -908,6 +1087,9 @@
         "print(\"\\n\\n\")\n",
         "print(\"model-upload\")\n",
         "artifacts = print_pipeline_output(pipeline, \"model-upload\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
         "print(\"\\n\\n\")\n",
         "print(\"endpoint-create\")\n",
         "artifacts = print_pipeline_output(pipeline, \"endpoint-create\")\n",
@@ -940,7 +1122,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_pipeline"
+        "id": "1UTEiNi9J39s"
       },
       "outputs": [],
       "source": [
@@ -962,7 +1144,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "endpoint_load:mbsdk"
+        "id": "gPEt5GMAJ39s"
       },
       "outputs": [],
       "source": [
@@ -1009,7 +1191,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "make_test_items:bqml,penguins"
+        "id": "sesK_MSdJ39t"
       },
       "outputs": [],
       "source": [
@@ -1055,7 +1237,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "endpoint_predict:mbsdk"
+        "id": "u5_cgdKQJ39t"
       },
       "outputs": [],
       "source": [
@@ -1083,15 +1265,41 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete:bqml,penguins"
+        "id": "W0rhdoHmJ39t"
       },
       "outputs": [],
       "source": [
         "try:\n",
-        "    job = bqclient.delete_model(\"bqml_tutorial.penguins_model\")\n",
+        "    job = bqclient.delete_model(f\"{PROJECT_ID}.bqml_tutorial.penguins_model\")\n",
         "except:\n",
         "    pass\n",
-        "job = bqclient.delete_dataset(\"bqml_tutorial\", delete_contents=True)"
+        "job = bqclient.delete_dataset(f\"{PROJECT_ID}.bqml_tutorial\", delete_contents=True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e776f9a3bdc4"
+      },
+      "source": [
+        "#### Delete the Vertex AI Model and Endpoint resources\n",
+        "\n",
+        "Next, undelpoy and delete the Vertex AI Model and Endpoint resources."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "63462e0480f0"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
+        "\n",
+        "model = aip.Model(model_id)\n",
+        "model.delete()"
       ]
     },
     {
@@ -1105,82 +1313,22 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial:"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "ufWUEbnZJ39u"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -33,14 +33,20 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>  \n",
+        "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -94,9 +100,37 @@
         "    - Training a Vertex AI custom trained model.\n",
         "    - Test the serving binary with a batch prediction job.\n",
         "    - Deploying a Vertex AI custom trained model.\n",
+        "- Execute a Vertex AI pipeline.\n",
+        "- Construct a pipeline for:\n",
+        "     - Construct a custom training component.\n",
+        "     - Convert custom training component to CustomTrainingJobOp.\n",
+        "     - Training a Vertex AI custom trained model using the converted component.\n",
+        "    - Deploying a Vertex AI custom trained model.\n",
         "- Execute a Vertex AI pipeline."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0c997d8d92ce"
+      },
+      "source": [
+        "### Costs \n",
+        "\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -105,35 +139,34 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing the notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "1fd00fa70a2a"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -165,6 +198,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -184,6 +241,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
@@ -241,7 +300,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -268,6 +329,81 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "648aa9824ac6"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fc52bba17ee3"
+      },
+      "source": [
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "535223fa4b84"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -291,7 +427,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -302,8 +439,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -323,7 +460,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -343,7 +480,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -381,9 +518,17 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        # print(\"shell_output=\", shell_output)\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -406,9 +551,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -490,7 +635,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -529,7 +674,7 @@
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "    TRAIN_GPU, TRAIN_NGPU = (None, None)\n",
         "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
@@ -1017,7 +1162,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_flowers.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_flowers.tar.gz"
       ]
     },
     {
@@ -1077,9 +1222,20 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_training\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_training\".format(BUCKET_URI)\n",
         "DEPLOY_COMPUTE = \"n1-standard-4\"\n",
         "\n",
+        "# If TRAIN_GPU is None, keeping gpu as no accelerator and accelerator_count as 0\n",
+        "gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"\n",
+        "accelerator_count = 0\n",
+        "\n",
+        "if TRAIN_GPU:\n",
+        "    gpu = TRAIN_GPU.name\n",
+        "    accelerator_count = 1\n",
+        "else:\n",
+        "    gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"  # Unspecified accelerator type, which means no accelerator.\n",
+        "    accelerator_count = 0\n",
+        "\n",
         "\n",
         "@dsl.pipeline(\n",
         "    name=\"flowers-custom-training\",\n",
@@ -1121,8 +1277,8 @@
         "        args=[\"--epochs\", \"50\", \"--image-width\", \"32\", \"--image-height\", \"32\"],\n",
         "        replica_count=1,\n",
         "        machine_type=TRAIN_COMPUTE,\n",
-        "        accelerator_type=TRAIN_GPU.name,\n",
-        "        accelerator_count=TRAIN_NGPU,\n",
+        "        accelerator_type=gpu,\n",
+        "        accelerator_count=accelerator_count,\n",
         "        # Serving - As part of this operation, the model is registered to Vertex AI\n",
         "        model_serving_container_image_uri=DEPLOY_IMAGE,\n",
         "        model_display_name=display_name,\n",
@@ -1148,7 +1304,7 @@
         "        display_name=display_name,\n",
         "    ).after(batch_op)\n",
         "\n",
-        "    deploy_op = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=training_op.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1210,11 +1366,11 @@
         "file_1 = test_item_1.split(\"/\")[-1]\n",
         "file_2 = test_item_2.split(\"/\")[-1]\n",
         "\n",
-        "! gsutil cp $test_item_1 $BUCKET_NAME/$file_1\n",
-        "! gsutil cp $test_item_2 $BUCKET_NAME/$file_2\n",
+        "! gsutil cp $test_item_1 $BUCKET_URI/$file_1\n",
+        "! gsutil cp $test_item_2 $BUCKET_URI/$file_2\n",
         "\n",
-        "test_item_1 = BUCKET_NAME + \"/\" + file_1\n",
-        "test_item_2 = BUCKET_NAME + \"/\" + file_2"
+        "test_item_1 = BUCKET_URI + \"/\" + file_1\n",
+        "test_item_2 = BUCKET_URI + \"/\" + file_2"
       ]
     },
     {
@@ -1243,11 +1399,7 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
-        "import tensorflow as tf\n",
-        "\n",
-        "gcs_input_uri = BUCKET_NAME + \"/test.jsonl\"\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.jsonl\"\n",
         "with tf.io.gfile.GFile(gcs_input_uri, \"w\") as f:\n",
         "    data = {\"content\": test_item_1, \"mime_type\": \"image/jpeg\"}\n",
         "    f.write(json.dumps(data) + \"\\n\")\n",
@@ -1297,7 +1449,7 @@
         "        \"import_file\": IMPORT_FILE,\n",
         "        \"batch_files\": [gcs_input_uri],\n",
         "        \"display_name\": \"flowers\" + TIMESTAMP,\n",
-        "        \"python_package\": f\"{BUCKET_NAME}/trainer_flowers.tar.gz\",\n",
+        "        \"python_package\": f\"{BUCKET_URI}/trainer_flowers.tar.gz\",\n",
         "        \"python_module\": \"trainer.task\",\n",
         "        \"project\": PROJECT_ID,\n",
         "        \"region\": REGION,\n",
@@ -1361,25 +1513,53 @@
         "            + str(TASK_ID)\n",
         "            + \"/gcp_resources\"\n",
         "        )\n",
+        "        EVAL_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
         "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
         "            ! gsutil cat $EXECUTE_OUTPUT\n",
-        "            break\n",
+        "            return EXECUTE_OUTPUT\n",
         "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
         "            ! gsutil cat $GCP_RESOURCES\n",
-        "            break\n",
+        "            return GCP_RESOURCES\n",
+        "        elif tf.io.gfile.exists(EVAL_METRICS):\n",
+        "            ! gsutil cat $EVAL_METRICS\n",
+        "            return EVAL_METRICS\n",
         "\n",
-        "    return EXECUTE_OUTPUT\n",
+        "    return None\n",
         "\n",
         "\n",
-        "print(\"imagedataset-create\")\n",
-        "artifacts = print_pipeline_output(pipeline, \"imagedataset-create\")\n",
+        "print(\"image-dataset-create\")\n",
+        "artifacts = print_pipeline_output(pipeline, \"image-dataset-create\")\n",
+        "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "dataset_id = output[\"artifacts\"][\"dataset\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
         "print(\"\\n\\n\")\n",
         "print(\"custompythonpackagetrainingjob-run\")\n",
         "artifacts = print_pipeline_output(pipeline, \"custompythonpackagetrainingjob-run\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
+        "print(\"\\n\\n\")\n",
         "print(\"endpoint-create\")\n",
         "artifacts = print_pipeline_output(pipeline, \"endpoint-create\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "endpoint_id = output[\"artifacts\"][\"endpoint\"][\"artifacts\"][0][\"metadata\"][\n",
+        "    \"resourceName\"\n",
+        "]\n",
         "print(\"model-deploy\")\n",
         "artifacts = print_pipeline_output(pipeline, \"model-deploy\")\n",
         "print(\"\\n\\n\")\n",
@@ -1392,7 +1572,13 @@
         "    output[\"artifacts\"][\"batchpredictionjob\"][\"artifacts\"][0][\"metadata\"][\n",
         "        \"gcsOutputDirectory\"\n",
         "    ]\n",
-        ")"
+        ")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "batch_job_id = output[\"artifacts\"][\"batchpredictionjob\"][\"artifacts\"][0][\"metadata\"][\n",
+        "    \"resourceName\"\n",
+        "]\n",
+        "print(\"\\n\\n\")"
       ]
     },
     {
@@ -1417,6 +1603,49 @@
         "pipeline.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d614c239d74c"
+      },
+      "source": [
+        "#### Delete the Vertex AI Model, Endpoint and BatchPredictionJob resources\n",
+        "\n",
+        "Next, delete the daatset, undelpoy and delete the Vertex AI Model, Endpoint and BathPredictionJob resources."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "417791a1a7e2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.ImageDataset(dataset_id)\n",
+        "try:\n",
+        "    dataset.delete()\n",
+        "except:\n",
+        "    pass\n",
+        "\n",
+        "\n",
+        "endpoint = aip.Endpoint(endpoint_id)\n",
+        "endpoint.undeploy_all()\n",
+        "try:\n",
+        "    endpoint.delete()\n",
+        "except:\n",
+        "    pass\n",
+        "\n",
+        "model = aip.Model(model_id)\n",
+        "try:\n",
+        "    model.delete()\n",
+        "except:\n",
+        "    pass\n",
+        "\n",
+        "batch_job = aip.BatchPredictionJob(batch_job_id)\n",
+        "batch_job.delete()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1459,7 +1688,6 @@
       "outputs": [],
       "source": [
         "from google_cloud_pipeline_components.v1.custom_job import utils\n",
-        "from kfp.v2.dsl import Artifact\n",
         "\n",
         "\n",
         "@component(\n",
@@ -1616,9 +1844,7 @@
       },
       "outputs": [],
       "source": [
-        "from google_cloud_pipeline_components import aiplatform as gcc_aip\n",
-        "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/custom_cifar10_training\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/custom_cifar10_training\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(name=\"custom-model-training-sample-pipeline\")\n",
@@ -1632,6 +1858,8 @@
         "    location: str = REGION,\n",
         "    deploy_image: str = \"us-docker.pkg.dev/cloud-aiplatform/prediction/tf2-cpu.2-3:latest\",\n",
         "):\n",
+        "    from google_cloud_pipeline_components import aiplatform as gcc_aip\n",
+        "\n",
         "    custom_job_op = custom_job_training_op(\n",
         "        model_dir=model_dir,\n",
         "        lr=lr,\n",
@@ -1657,7 +1885,7 @@
         "        display_name=display_name,\n",
         "    ).after(model_upload_op)\n",
         "\n",
-        "    deploy_op = gcc_aip.ModelDeployOp(\n",
+        "    _ = gcc_aip.ModelDeployOp(\n",
         "        model=model_upload_op.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1735,46 +1963,6 @@
         "PROJECT_NUMBER = pipeline.gca_resource.name.split(\"/\")[1]\n",
         "print(PROJECT_NUMBER)\n",
         "\n",
-        "\n",
-        "def print_pipeline_output(job, output_task_name):\n",
-        "    JOB_ID = job.name\n",
-        "    print(JOB_ID)\n",
-        "    for _ in range(len(job.gca_resource.job_detail.task_details)):\n",
-        "        TASK_ID = job.gca_resource.job_detail.task_details[_].task_id\n",
-        "        EXECUTE_OUTPUT = (\n",
-        "            PIPELINE_ROOT\n",
-        "            + \"/\"\n",
-        "            + PROJECT_NUMBER\n",
-        "            + \"/\"\n",
-        "            + JOB_ID\n",
-        "            + \"/\"\n",
-        "            + output_task_name\n",
-        "            + \"_\"\n",
-        "            + str(TASK_ID)\n",
-        "            + \"/executor_output.json\"\n",
-        "        )\n",
-        "        GCP_RESOURCES = (\n",
-        "            PIPELINE_ROOT\n",
-        "            + \"/\"\n",
-        "            + PROJECT_NUMBER\n",
-        "            + \"/\"\n",
-        "            + JOB_ID\n",
-        "            + \"/\"\n",
-        "            + output_task_name\n",
-        "            + \"_\"\n",
-        "            + str(TASK_ID)\n",
-        "            + \"/gcp_resources\"\n",
-        "        )\n",
-        "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
-        "            ! gsutil cat $EXECUTE_OUTPUT\n",
-        "            break\n",
-        "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
-        "            ! gsutil cat $GCP_RESOURCES\n",
-        "            break\n",
-        "\n",
-        "    return EXECUTE_OUTPUT\n",
-        "\n",
-        "\n",
         "print(\"custom-train-model\")\n",
         "artifacts = print_pipeline_output(pipeline, \"custom-train-model\")\n",
         "print(\"\\n\\n\")\n",
@@ -1784,9 +1972,17 @@
         "print(\"model-upload\")\n",
         "artifacts = print_pipeline_output(pipeline, \"model-upload\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "model_id = output[\"artifacts\"][\"model\"][\"artifacts\"][0][\"metadata\"][\"resourceName\"]\n",
         "print(\"endpoint-create\")\n",
         "artifacts = print_pipeline_output(pipeline, \"endpoint-create\")\n",
         "print(\"\\n\\n\")\n",
+        "output = !gsutil cat $artifacts\n",
+        "output = json.loads(output[0])\n",
+        "endpoint_id = output[\"artifacts\"][\"endpoint\"][\"artifacts\"][0][\"metadata\"][\n",
+        "    \"resourceName\"\n",
+        "]\n",
         "print(\"model-deploy\")\n",
         "artifacts = print_pipeline_output(pipeline, \"model-deploy\")\n",
         "print(\"\\n\\n\")"
@@ -1814,6 +2010,49 @@
         "pipeline.delete()"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "93e69fc8b9e3"
+      },
+      "source": [
+        "#### Delete the Vertex AI Model and Endpoint resource\n",
+        "\n",
+        "Next, undelpoy and delete the Vertex AI Model and Endpoint resources."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c9d18ae084b1"
+      },
+      "source": [
+        "#### Delete the Vertex model and endpoint\n",
+        "\n",
+        "Next, undelpoy and delete the Vertex Model and Endpoint resource."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "dccf71121d0b"
+      },
+      "outputs": [],
+      "source": [
+        "endpoint.undeploy_all()\n",
+        "try:\n",
+        "    endpoint.delete()\n",
+        "except:\n",
+        "    pass\n",
+        "\n",
+        "model = aip.Model(model_id)\n",
+        "try:\n",
+        "    model.delete()\n",
+        "except:\n",
+        "    pass"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1825,17 +2064,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1846,61 +2075,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb

@@ -40,9 +40,17 @@
         "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "<img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> \n",
+        "        Colab logo Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_dataflow_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>   \n",
+        "    \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -101,7 +109,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing the notebook."
       ]
     },
     {
@@ -112,24 +120,25 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q"
       ]
     },
     {
@@ -161,6 +170,30 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "BF1j6f9HApxa"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Dataflow API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,dataflow.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -180,7 +213,24 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\"\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Get your Google Cloud project ID from gcloud\n",
+        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "37c0a68ff20d"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
       ]
     },
     {
@@ -191,22 +241,8 @@
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -237,7 +273,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -264,6 +303,89 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "927085b84a07"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "89788a802687"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "40ed98f5cc48"
+      },
+      "source": [
+        "#### If you are using Colab Notebooks, set the project using gcloud config."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fde1a355f1e9"
+      },
+      "outputs": [],
+      "source": [
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        ! gcloud config set project $PROJECT_ID"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -287,7 +409,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -298,8 +420,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -319,7 +441,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -339,7 +461,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -377,9 +499,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -402,9 +531,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -427,35 +556,12 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp"
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "from kfp import dsl\n",
-        "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_gcpc:dataflow"
-      },
-      "outputs": [],
-      "source": [
+        "import google.cloud.aiplatform as aip\n",
         "from google_cloud_pipeline_components.v1.dataflow import DataflowPythonJobOp\n",
         "from google_cloud_pipeline_components.v1.wait_gcp_resources import \\\n",
-        "    WaitGcpResourcesOp"
+        "    WaitGcpResourcesOp\n",
+        "from kfp import dsl\n",
+        "from kfp.v2 import compiler"
       ]
     },
     {
@@ -477,7 +583,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -673,12 +779,12 @@
       },
       "outputs": [],
       "source": [
-        "GCS_WC_PY = BUCKET_NAME + \"/wc.py\"\n",
+        "GCS_WC_PY = BUCKET_URI + \"/wc.py\"\n",
         "! gsutil cp wc.py $GCS_WC_PY\n",
-        "GCS_REQUIREMENTS_TXT = BUCKET_NAME + \"/requirements.txt\"\n",
+        "GCS_REQUIREMENTS_TXT = BUCKET_URI + \"/requirements.txt\"\n",
         "! gsutil cp requirements.txt $GCS_REQUIREMENTS_TXT\n",
         "\n",
-        "GCS_WC_OUT = BUCKET_NAME + \"/wc_out.txt\""
+        "GCS_WC_OUT = BUCKET_URI + \"/wc_out.txt\""
       ]
     },
     {
@@ -709,9 +815,7 @@
       },
       "outputs": [],
       "source": [
-        "import json\n",
-        "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_wc\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_wc\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(name=\"dataflow-wc\", description=\"Dataflow word count component pipeline\")\n",
@@ -733,9 +837,7 @@
         "        args=args,\n",
         "    )\n",
         "\n",
-        "    dataflow_wait_op = WaitGcpResourcesOp(\n",
-        "        gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"]\n",
-        "    )\n",
+        "    _ = WaitGcpResourcesOp(gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"])\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataflow_wc.json\")\n",
@@ -813,82 +915,80 @@
         "from apache_beam.options.pipeline_options import SetupOptions\n",
         "\n",
         "def run(argv=None):\n",
-        "  \"\"\"Main entry point; defines and runs the wordcount pipeline.\"\"\"\n",
+        "    \"\"\"Main entry point; defines and runs the wordcount pipeline.\"\"\"\n",
         "\n",
-        "  parser = argparse.ArgumentParser()\n",
-        "  parser.add_argument('--bq_table',\n",
+        "    parser = argparse.ArgumentParser()\n",
+        "    parser.add_argument('--bq_table',\n",
         "                      dest='bq_table')\n",
-        "  parser.add_argument('--bucket',\n",
+        "    parser.add_argument('--bucket',\n",
         "                      dest='bucket')\n",
-        "  args, pipeline_args = parser.parse_known_args(argv)\n",
-        "  logging.info(\"ARGS\")\n",
-        "  logging.info(args)\n",
-        "  logging.info(\"PIPELINE ARGS\")\n",
-        "  logging.info(pipeline_args)\n",
-        "  for i in range(0, len(pipeline_args), 2):\n",
+        "    args, pipeline_args = parser.parse_known_args(argv)\n",
+        "    logging.info(\"ARGS\")\n",
+        "    logging.info(args)\n",
+        "    logging.info(\"PIPELINE ARGS\")\n",
+        "    logging.info(pipeline_args)\n",
+        "    for i in range(0, len(pipeline_args), 2):\n",
         "        if \"--temp_location\" == pipeline_args[i]:\n",
         "            temp_location = pipeline_args[i+1]\n",
         "        elif \"--project\" == pipeline_args[i]:\n",
         "            project = pipeline_args[i+1]\n",
         "\n",
-        "  exported_train = args.bucket + '/exported_data/train'\n",
-        "  exported_eval  = args.bucket + '/exported_data/eval'\n",
+        "    exported_train = args.bucket + '/exported_data/train'\n",
+        "    exported_eval  = args.bucket + '/exported_data/eval'\n",
         "\n",
+        "    pipeline_options = PipelineOptions(pipeline_args)\n",
+        "    pipeline_options.view_as(SetupOptions).save_main_session = True\n",
+        "    with beam.Pipeline(options=pipeline_options) as pipeline:\n",
+        "        with tft_beam.Context(temp_location):\n",
+        "            raw_data_query = \"SELECT {0},{1} FROM {2} LIMIT 500\".format(\"CAST(station_number as STRING) AS station_number,year,month,day\",\"mean_temp\", args.bq_table)\n",
         "\n",
-        "  pipeline_options = PipelineOptions(pipeline_args)\n",
-        "  pipeline_options.view_as(SetupOptions).save_main_session = True\n",
-        "  with beam.Pipeline(options=pipeline_options) as pipeline:\n",
-        "    with tft_beam.Context(temp_location):\n",
+        "            def parse_bq_record(bq_record):\n",
+        "                \"\"\"Parses a bq_record to a dictionary.\"\"\"\n",
+        "                output = {}\n",
+        "                for key in bq_record:\n",
+        "                    output[key] = [bq_record[key]]\n",
+        "                return output\n",
         "\n",
-        "        raw_data_query = \"SELECT {0},{1} FROM {2} LIMIT 500\".format(\"CAST(station_number as STRING) AS station_number,year,month,day\",\"mean_temp\", args.bq_table)\n",
+        "            def split_dataset(bq_row, num_partitions, ratio):\n",
+        "                \"\"\"Returns a partition number for a given bq_row.\"\"\"\n",
+        "                import json\n",
         "\n",
-        "        def parse_bq_record(bq_record):\n",
-        "            \"\"\"Parses a bq_record to a dictionary.\"\"\"\n",
-        "            output = {}\n",
-        "            for key in bq_record:\n",
-        "                output[key] = [bq_record[key]]\n",
-        "            return output\n",
+        "                assert num_partitions == len(ratio)\n",
+        "                bucket = sum(map(ord, json.dumps(bq_row))) % sum(ratio)\n",
+        "                total = 0\n",
+        "                for i, part in enumerate(ratio):\n",
+        "                    total += part\n",
+        "                    if bucket < total:\n",
+        "                        return i\n",
+        "                return len(ratio) - 1\n",
         "\n",
-        "        def split_dataset(bq_row, num_partitions, ratio):\n",
-        "            \"\"\"Returns a partition number for a given bq_row.\"\"\"\n",
-        "            import json\n",
-        "\n",
-        "            assert num_partitions == len(ratio)\n",
-        "            bucket = sum(map(ord, json.dumps(bq_row))) % sum(ratio)\n",
-        "            total = 0\n",
-        "            for i, part in enumerate(ratio):\n",
-        "                total += part\n",
-        "                if bucket < total:\n",
-        "                    return i\n",
-        "            return len(ratio) - 1\n",
-        "\n",
-        "        # Read raw BigQuery data.\n",
-        "        raw_train_data, raw_eval_data = (\n",
-        "            pipeline\n",
-        "            | \"Read Raw Data\"\n",
-        "            >> beam.io.ReadFromBigQuery(\n",
-        "                query=raw_data_query,\n",
-        "                project=project,\n",
-        "                use_standard_sql=True,\n",
+        "            # Read raw BigQuery data.\n",
+        "            raw_train_data, raw_eval_data = (\n",
+        "                pipeline\n",
+        "                | \"Read Raw Data\"\n",
+        "                >> beam.io.ReadFromBigQuery(\n",
+        "                    query=raw_data_query,\n",
+        "                    project=project,\n",
+        "                    use_standard_sql=True,\n",
+        "                )\n",
+        "                | \"Parse Data\" >> beam.Map(parse_bq_record)\n",
+        "                | \"Split\" >> beam.Partition(split_dataset, 2, ratio=[8, 2])\n",
         "            )\n",
-        "            | \"Parse Data\" >> beam.Map(parse_bq_record)\n",
-        "            | \"Split\" >> beam.Partition(split_dataset, 2, ratio=[8, 2])\n",
-        "        )\n",
         "\n",
-        "        # Write raw train data to GCS .\n",
-        "        _ = raw_train_data | \"Write Raw Train Data\" >> beam.io.WriteToText(\n",
-        "            file_path_prefix=exported_train, file_name_suffix=\".csv\"\n",
-        "        )\n",
+        "            # Write raw train data to GCS .\n",
+        "            _ = raw_train_data | \"Write Raw Train Data\" >> beam.io.WriteToText(\n",
+        "                file_path_prefix=exported_train, file_name_suffix=\".csv\"\n",
+        "            )\n",
         "\n",
-        "        # Write raw eval data to GCS .\n",
-        "        _ = raw_eval_data | \"Write Raw Eval Data\" >> beam.io.WriteToText(\n",
-        "            file_path_prefix=exported_eval, file_name_suffix=\".csv\"\n",
-        "        )\n",
+        "            # Write raw eval data to GCS .\n",
+        "            _ = raw_eval_data | \"Write Raw Eval Data\" >> beam.io.WriteToText(\n",
+        "                file_path_prefix=exported_eval, file_name_suffix=\".csv\"\n",
+        "            )\n",
         "\n",
         "\n",
         "if __name__ == '__main__':\n",
-        "  logging.getLogger().setLevel(logging.INFO)\n",
-        "  run()"
+        "    logging.getLogger().setLevel(logging.INFO)\n",
+        "    run()"
       ]
     },
     {
@@ -975,11 +1075,11 @@
       },
       "outputs": [],
       "source": [
-        "GCS_SPLIT_PY = BUCKET_NAME + \"/split.py\"\n",
+        "GCS_SPLIT_PY = BUCKET_URI + \"/split.py\"\n",
         "! gsutil cp split.py $GCS_SPLIT_PY\n",
-        "GCS_REQUIREMENTS_TXT = BUCKET_NAME + \"/requirements.txt\"\n",
+        "GCS_REQUIREMENTS_TXT = BUCKET_URI + \"/requirements.txt\"\n",
         "! gsutil cp requirements.txt $GCS_REQUIREMENTS_TXT\n",
-        "GCS_SETUP_PY = BUCKET_NAME + \"/setup.py\"\n",
+        "GCS_SETUP_PY = BUCKET_URI + \"/setup.py\"\n",
         "! gsutil cp setup.py $GCS_SETUP_PY"
       ]
     },
@@ -1036,7 +1136,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_split\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/dataflow_split\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(name=\"dataflow-split\", description=\"Dataflow split dataset\")\n",
@@ -1047,7 +1147,7 @@
         "    staging_dir: str = PIPELINE_ROOT,\n",
         "    args: list = [\n",
         "        \"--bucket\",\n",
-        "        BUCKET_NAME,\n",
+        "        BUCKET_URI,\n",
         "        \"--bq_table\",\n",
         "        BQ_TABLE,\n",
         "        \"--runner\",\n",
@@ -1067,9 +1167,7 @@
         "        args=args,\n",
         "    )\n",
         "\n",
-        "    dataflow_wait_op = WaitGcpResourcesOp(\n",
-        "        gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"]\n",
-        "    )\n",
+        "    _ = WaitGcpResourcesOp(gcp_resources=dataflow_python_op.outputs[\"gcp_resources\"])\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"dataflow_split.json\")\n",
@@ -1083,7 +1181,7 @@
         "\n",
         "pipeline.run()\n",
         "\n",
-        "! gsutil ls {BUCKET_NAME}/exported_data\n",
+        "! gsutil ls {BUCKET_URI}/exported_data\n",
         "\n",
         "! rm -f dataflow_split.json split.py requirements.txt"
       ]
@@ -1124,13 +1222,6 @@
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
         "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1142,61 +1233,11 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Warning: Setting this to true will delete everything in your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb

@@ -32,6 +32,11 @@
         "# E2E ML on GCP: MLOps stage 3 : formalization: get started with Hyperparameter Tuning pipeline components\n",
         "\n",
         "<table align=\"left\">\n",
+        "    <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
         "  <td>\n",
         "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
@@ -39,7 +44,8 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_hpt_pipeline_components.ipynb\">\n",
+        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Google Cloud Notebooks\n",
         "    </a>\n",
         "  </td>\n",
@@ -94,7 +100,20 @@
         "    - If the metrics exceed a specified threshold.\n",
         "      - Get the location of the model artifacts for the best tuned model.\n",
         "      - Upload the model artifacts to a `Vertex AI Model` resource.\n",
-        "- Execute a Vertex AI pipeline."
+        "- Execute a Vertex AI pipeline.\n",
+        "\n",
+        "### Costs \n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -105,35 +124,37 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing the notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_mlops"
+        "id": "LR9HQnyiMoT5"
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG\n",
-        "    ! pip3 install --upgrade python-tabulate $USER_FLAG\n",
-        "    ! pip3 install -U opencv-python-headless==4.5.2.52 $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install -U tensorflow==2.5 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-transform==1.2 $USER_FLAG -q\n",
+        "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q\n",
+        "! pip3 install --upgrade kfp $USER_FLAG -q"
       ]
     },
     {
@@ -151,7 +172,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "VeBfL2pmMoT7"
       },
       "outputs": [],
       "source": [
@@ -165,6 +186,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1df9ff75fa88"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -237,11 +284,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "7iewOt9NMoT8"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -259,7 +309,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "Y-vhpfibMoT9"
       },
       "outputs": [],
       "source": [
@@ -268,6 +318,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-V_6SvMUNUa1"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -291,7 +402,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -302,8 +413,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -319,11 +430,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "2smRgc53MoT-"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -339,11 +450,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "ME1Tr9j_MoT-"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -361,7 +472,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account"
+        "id": "EIivrR-3MoT-"
       },
       "outputs": [],
       "source": [
@@ -381,9 +492,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -402,13 +520,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "set_service_account:pipelines"
+        "id": "mtwsjYnIMoT_"
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -464,7 +582,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_tf"
+        "id": "DtTIHh_KMoUA"
       },
       "outputs": [],
       "source": [
@@ -486,11 +604,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "sUFJPDW0MoUA"
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -519,17 +637,19 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "accelerators:training,prediction,ngpu,mbsdk"
+        "id": "A6dzi4cXMoUA"
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
         "        int(os.getenv(\"IS_TESTING_TRAIN_GPU\")),\n",
         "    )\n",
         "else:\n",
-        "    TRAIN_GPU, TRAIN_NGPU = (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "    TRAIN_GPU, TRAIN_NGPU = (None, None)\n",
         "\n",
         "if os.getenv(\"IS_TESTING_DEPLOY_GPU\"):\n",
         "    DEPLOY_GPU, DEPLOY_NGPU = (\n",
@@ -560,7 +680,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "container:prediction"
+        "id": "gxai072KMoUB"
       },
       "outputs": [],
       "source": [
@@ -616,7 +736,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "machine:training,prediction"
+        "id": "LEYjL1ojMoUB"
       },
       "outputs": [],
       "source": [
@@ -672,7 +792,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_training_package"
+        "id": "UIoZdxPqMoUC"
       },
       "outputs": [],
       "source": [
@@ -735,7 +855,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:dataset,horses_or_humans"
+        "id": "uk4MAGErMoUC"
       },
       "outputs": [],
       "source": [
@@ -872,14 +992,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "tarball_training_script"
+        "id": "bHcLQLGkMoUD"
       },
       "outputs": [],
       "source": [
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_horses_or_humans.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_horses_or_humans.tar.gz"
       ]
     },
     {
@@ -912,7 +1032,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "write_docker_file:training,tf-dlvm"
+        "id": "MaMK4AoBMoUE"
       },
       "outputs": [],
       "source": [
@@ -945,7 +1065,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "name_container:training"
+        "id": "9qVJGXT2MoUE"
       },
       "outputs": [],
       "source": [
@@ -965,7 +1085,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "build_container:training"
+        "id": "7-dkQP8hMoUE"
       },
       "outputs": [],
       "source": [
@@ -987,7 +1107,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "register_container:training"
+        "id": "7-kh6QBLMoUF"
       },
       "outputs": [],
       "source": [
@@ -1017,11 +1137,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_hpt_pipeline:icn"
+        "id": "Epzlh8M-MoUF"
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_tuning\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/custom_icn_tuning\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component(packages_to_install=[\"google-cloud-aiplatform\"])\n",
@@ -1053,9 +1173,11 @@
         "\n",
         "    from google_cloud_pipeline_components.experimental import \\\n",
         "        hyperparameter_tuning_job\n",
+        "    from google_cloud_pipeline_components.types import artifact_types\n",
         "    from google_cloud_pipeline_components.v1.hyperparameter_tuning_job import \\\n",
         "        HyperparameterTuningJobRunOp\n",
         "    from google_cloud_pipeline_components.v1.model import ModelUploadOp\n",
+        "    from kfp.v2.components import importer_node\n",
         "\n",
         "    tuning_op = HyperparameterTuningJobRunOp(\n",
         "        display_name=display_name,\n",
@@ -1087,20 +1209,25 @@
         "        threshold_op.output == \"true\",\n",
         "        name=\"deploy_decision\",\n",
         "    ):\n",
-        "        best_hyperparameters_op = hyperparameter_tuning_job.GetHyperparametersOp(\n",
-        "            trial=best_trial_op.output\n",
-        "        )\n",
+        "        _ = hyperparameter_tuning_job.GetHyperparametersOp(trial=best_trial_op.output)\n",
         "\n",
         "        model_dir_op = model_dir(base_output_directory, best_trial_op.output)\n",
         "\n",
-        "        model_upload_op = ModelUploadOp(\n",
-        "            display_name=display_name,\n",
+        "        import_unmanaged_model_op = importer_node.importer(\n",
         "            artifact_uri=model_dir_op.output,\n",
-        "            serving_container_image_uri=deploy_image,\n",
-        "            labels=labels,\n",
+        "            artifact_class=artifact_types.UnmanagedContainerModel,\n",
+        "            metadata={\n",
+        "                \"containerSpec\": {\n",
+        "                    \"imageUri\": DEPLOY_IMAGE,\n",
+        "                },\n",
+        "            },\n",
+        "        ).after(model_dir_op)\n",
+        "\n",
+        "        _ = ModelUploadOp(\n",
         "            project=project,\n",
-        "            location=region,\n",
-        "        )"
+        "            display_name=display_name,\n",
+        "            unmanaged_container_model=import_unmanaged_model_op.outputs[\"artifact\"],\n",
+        "        ).after(import_unmanaged_model_op)"
       ]
     },
     {
@@ -1130,13 +1257,26 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_hpt_specs"
+        "id": "aEm7RuwMMoUG"
       },
       "outputs": [],
       "source": [
         "from google_cloud_pipeline_components.experimental import \\\n",
         "    hyperparameter_tuning_job\n",
         "\n",
+        "gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"\n",
+        "accelerator_count = 0\n",
+        "\n",
+        "if TRAIN_GPU:\n",
+        "    gpu = TRAIN_GPU.name\n",
+        "    accelerator_count = 1\n",
+        "\n",
+        "else:\n",
+        "    gpu = \"ACCELERATOR_TYPE_UNSPECIFIED\"\n",
+        "    accelerator_count = (\n",
+        "        0  # same problem with accelerator_count, if we keep is as \"None\" its not\n",
+        "    )\n",
+        "\n",
         "CMDARGS = [\n",
         "    \"--epochs=10\",\n",
         "]\n",
@@ -1146,8 +1286,8 @@
         "    {\n",
         "        \"machine_spec\": {\n",
         "            \"machine_type\": TRAIN_COMPUTE,\n",
-        "            \"accelerator_type\": TRAIN_GPU.name,\n",
-        "            \"accelerator_count\": TRAIN_NGPU,\n",
+        "            \"accelerator_type\": gpu,\n",
+        "            \"accelerator_count\": accelerator_count,\n",
         "        },\n",
         "        \"replica_count\": 1,\n",
         "        \"container_spec\": {\"image_uri\": TRAIN_IMAGE, \"args\": CMDARGS},\n",
@@ -1196,7 +1336,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_pipeline:hpt"
+        "id": "42YNp9Y9MoUG"
       },
       "outputs": [],
       "source": [
@@ -1237,7 +1377,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "view_pipleline_results:hpt,horses_or_humans"
+        "id": "4X3jrdX1MoUH"
       },
       "outputs": [],
       "source": [
@@ -1274,14 +1414,29 @@
         "            + str(TASK_ID)\n",
         "            + \"/gcp_resources\"\n",
         "        )\n",
+        "        EVAL_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
         "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
         "            ! gsutil cat $EXECUTE_OUTPUT\n",
-        "            break\n",
+        "            return EXECUTE_OUTPUT\n",
         "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
         "            ! gsutil cat $GCP_RESOURCES\n",
-        "            break\n",
+        "            return GCP_RESOURCES\n",
+        "        elif tf.io.gfile.exists(EVAL_METRICS):\n",
+        "            ! gsutil cat $EVAL_METRICS\n",
+        "            return EVAL_METRICS\n",
         "\n",
-        "    return EXECUTE_OUTPUT\n",
+        "    return None\n",
         "\n",
         "\n",
         "print(\"hyperparameter-tuning-job\")\n",
@@ -1334,7 +1489,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "delete_pipeline"
+        "id": "hS53o3FcMoUH"
       },
       "outputs": [],
       "source": [
@@ -1354,14 +1509,6 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
         "- Cloud Storage Bucket"
       ]
     },
@@ -1369,70 +1516,20 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "laAQFM4aoBm3"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],
   "metadata": {
     "colab": {
+      "collapsed_sections": [],
       "name": "get_started_with_hpt_pipeline_components.ipynb",
       "toc_visible": true
     },

notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -38,9 +38,16 @@
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        "    <td>\n",
+        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb\">\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        </a>\n",
+        "  </td>\n",
+        "    \n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb\">\n",
-        "      Open in Google Cloud Notebooks\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage3/get_started_with_kubeflow_pipelines.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
@@ -67,7 +74,7 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you learn how to use `Kubeflow Pipelines`.\n",
+        "In this tutorial, you learn how to use `Kubeflow Pipelines`(KFP).\n",
         "\n",
         "This tutorial uses the following Google Cloud ML services:\n",
         "\n",
@@ -78,8 +85,17 @@
         "- Building KFP lightweight Python function components.\n",
         "- Assembling and compiling KFP components into a pipeline.\n",
         "- Executing a KFP pipeline using Vertex AI Pipelines.\n",
+        "- Loading component and pipeline definitions from a source code repository.\n",
         "- Building sequential, parallel, multiple output components.\n",
-        "- Building control flow into pipelines."
+        "- Building control flow into pipelines.\n",
+        "\n",
+        "### Costs\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "- Vertex AI\n",
+        "- Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
       ]
     },
     {
@@ -90,7 +106,7 @@
       "source": [
         "## Installations\n",
         "\n",
-        "Install *one time* the packages for executing the MLOps notebooks."
+        "Install the required packages for executing this MLOps notebook."
       ]
     },
     {
@@ -101,20 +117,21 @@
       },
       "outputs": [],
       "source": [
-        "ONCE_ONLY = False\n",
-        "if ONCE_ONLY:\n",
-        "    ! pip3 install -U tensorflow==2.5 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-data-validation==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-transform==1.2 $USER_FLAG\n",
-        "    ! pip3 install -U tensorflow-io==0.18 $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-bigquery $USER_FLAG\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG"
+        "import os\n",
+        "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "    \n",
+        "! pip3 install tensorflow-io==0.18 $USER_FLAG -q\n",
+        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
+        "                        pyarrow \\\n",
+        "                        kfp $USER_FLAG -q"
       ]
     },
     {
@@ -146,6 +163,32 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e56d698e5d52"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -222,7 +265,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -249,6 +295,67 @@
         "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b5627478895e"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "1. **Click Create service account**.\n",
+        "\n",
+        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "49ee8894d674"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = False\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        IS_COLAB = True\n",
+        "        from google.colab import auth as google_auth\n",
+        "\n",
+        "        google_auth.authenticate_user()\n",
+        "\n",
+        "    # If you are running this notebook locally, replace the string below with the\n",
+        "    # path to your service account key and run this cell to authenticate your GCP\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -272,7 +379,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = \"gs://{}\".format(BUCKET_NAME)"
       ]
     },
     {
@@ -283,8 +391,8 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
       ]
     },
     {
@@ -304,7 +412,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -324,7 +432,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -335,7 +443,7 @@
       "source": [
         "#### Service Account\n",
         "\n",
-        "**If you don't know your service account**, try to get your service account using `gcloud` command by executing the second cell below."
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
       ]
     },
     {
@@ -362,9 +470,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -376,7 +491,7 @@
       "source": [
         "#### Set service account access for Vertex AI Pipelines\n",
         "\n",
-        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step -- you only need to run these once per service account."
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step. You only need to run this step once per service account."
       ]
     },
     {
@@ -387,9 +502,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -398,10 +513,7 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
+        "### Import libraries"
       ]
     },
     {
@@ -411,42 +523,11 @@
         "id": "import_aip:mbsdk"
       },
       "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aip"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_tf"
-      },
-      "source": [
-        "#### Import TensorFlow\n",
-        "\n",
-        "Import the TensorFlow package into your Python environment."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_tf"
-      },
-      "outputs": [],
-      "source": [
-        "import tensorflow as tf"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp:namedtuple"
-      },
-      "outputs": [],
       "source": [
         "from typing import NamedTuple\n",
         "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "import tensorflow as tf\n",
         "from kfp import dsl\n",
         "from kfp.v2 import compiler\n",
         "from kfp.v2.dsl import component"
@@ -471,7 +552,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -486,14 +567,14 @@
         "\n",
         "    1. Design the pipeline workflow.\n",
         "    2. Compile the pipeline.\n",
-        "    3. Schedule execution (or run now) the pipeline.\n",
+        "    3. Schedule pipeline execution (or run now).\n",
         "    4. Get the pipeline results.\n",
         "\n",
-        "Pipelines are designed using language specific domain specific language (DSL). Vertex AI Pipelines support both KFP DSL and TFX DSL for designing pipelines.\n",
+        "Pipelines are designed using domain specific language (DSL). Vertex AI Pipelines support both KFP DSL and TFX DSL for designing pipelines.\n",
         "\n",
         "In addition to designing components, you can use a wide variety of pre-built Google Cloud Pipeline Components for Vertex AI services.\n",
         "\n",
-        "Learn more about [Building a pipeline](https://cloud.google.com/vertex-ai/docs/pipelines/build-pipeline)"
+        "Learn more about [Building a pipeline](https://cloud.google.com/vertex-ai/docs/pipelines/build-pipeline)."
       ]
     },
     {
@@ -502,9 +583,9 @@
         "id": "pipelines_intro:helloworld"
       },
       "source": [
-        "## Basic pipeline introduction\n",
+        "## Basic pipeline\n",
         "\n",
-        "This demonstrates the basics of constructing and executing a pipeline. You do the following:\n",
+        "This step demonstrates the basics of constructing and executing a pipeline. You do the following:\n",
         "\n",
         "1. Design a simple Python function based component to output the input string.\n",
         "2. Construct a pipeline that uses the component.\n",
@@ -522,8 +603,8 @@
         "\n",
         "To create a KFP component from a Python function, you add the KFP DSL decorator `@component` to the function. In this example, the decorator takes the following parameters:\n",
         "\n",
-        "- `output_component_file`: (optional) write the component description to a YAML file such that the component is portable.\n",
-        "- `base_image`: (optional): The interpreter for executing the Python function. By default it is Python 3.7"
+        "- `output_component_file`(optional): write the component description to a YAML file such that the component is portable.\n",
+        "- `base_image`(optional): The interpreter for executing the Python function. By default it is Python 3.7"
       ]
     },
     {
@@ -566,7 +647,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -575,7 +656,8 @@
         "    pipeline_root=PIPELINE_ROOT,\n",
         ")\n",
         "def pipeline(text: str = \"hi there\"):\n",
-        "    hello_world_task = hello_world(text)"
+        "    hello_world_task = hello_world(text)\n",
+        "    return hello_world_task"
       ]
     },
     {
@@ -588,7 +670,7 @@
         "\n",
         "Once the design of the pipeline is completed, the next step is to compile it. The pipeline definition is compiled into a JSON formatted file, which is transportable and can be interpreted by both KFP and Vertex AI Pipelines.\n",
         "\n",
-        "You compile the pipeline with the method Compiler().compile(), with the following parameters:\n",
+        "Compile the pipeline with the Compiler().compile() method using the following parameters:\n",
         "\n",
         "- `pipeline_func`: The corresponding DSL function that defines the pipeline.\n",
         "- `package_path`: The JSON file to write the transportable compiled pipeline to."
@@ -615,14 +697,14 @@
       "source": [
         "### Execute the hello world pipeline\n",
         "\n",
-        "Now that the pipeline is compiled, you can execute by:\n",
+        "Now that the pipeline is compiled, you can execute it by:\n",
         "\n",
-        "- Create a Vertex AI PipelineJob, with the following parameters:\n",
+        "- Creating a Vertex AI PipelineJob with the following parameters:\n",
         "    - `display_name`: The human readable name for the job.\n",
-        "    - `template_path`: Thee compiled JSON pipeline definition.\n",
+        "    - `template_path`: The compiled JSON pipeline definition.\n",
         "    - `pipeline_root`: Where to write output artifacts to.\n",
         "\n",
-        "Click on the generated link below `INFO:google.cloud.aiplatform.pipeline_jobs:View Pipeline Job:` to see your run in the Cloud Console."
+        "Click on the generated link below `INFO:google.cloud.aiplatform.pipeline_jobs:View Pipeline Job:` to see your job run in the Cloud Console."
       ]
     },
     {
@@ -633,7 +715,7 @@
       },
       "outputs": [],
       "source": [
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"hello_world\",\n",
         "    template_path=\"hello_world.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -694,14 +776,29 @@
         "            + str(TASK_ID)\n",
         "            + \"/gcp_resources\"\n",
         "        )\n",
+        "        EVAL_METRICS = (\n",
+        "            PIPELINE_ROOT\n",
+        "            + \"/\"\n",
+        "            + PROJECT_NUMBER\n",
+        "            + \"/\"\n",
+        "            + JOB_ID\n",
+        "            + \"/\"\n",
+        "            + output_task_name\n",
+        "            + \"_\"\n",
+        "            + str(TASK_ID)\n",
+        "            + \"/evaluation_metrics\"\n",
+        "        )\n",
         "        if tf.io.gfile.exists(EXECUTE_OUTPUT):\n",
         "            ! gsutil cat $EXECUTE_OUTPUT\n",
-        "            break\n",
+        "            return EXECUTE_OUTPUT\n",
         "        elif tf.io.gfile.exists(GCP_RESOURCES):\n",
         "            ! gsutil cat $GCP_RESOURCES\n",
-        "            break\n",
+        "            return GCP_RESOURCES\n",
+        "        elif tf.io.gfile.exists(EVAL_METRICS):\n",
+        "            ! gsutil cat $EVAL_METRICS\n",
+        "            return EVAL_METRICS\n",
         "\n",
-        "    return EXECUTE_OUTPUT\n",
+        "    return None\n",
         "\n",
         "\n",
         "print_pipeline_output(pipeline, \"hello-world\")"
@@ -715,7 +812,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -741,7 +838,7 @@
         "\n",
         "    hello_world_op = components.load_component_from_file('./hello_world.yaml').\n",
         "\n",
-        "You can also use the load_component_from_url method, if your component YAML file is stored online, such as if in a git repo."
+        "You can also use the `load_component_from_url` method, if your component YAML file is stored online, such as in a git repository."
       ]
     },
     {
@@ -754,7 +851,7 @@
       "source": [
         "from kfp import components\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world-v2\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/hello_world-v2\".format(BUCKET_URI)\n",
         "\n",
         "hello_world_op = components.load_component_from_file(\"./hello_world.yaml\")\n",
         "\n",
@@ -765,12 +862,13 @@
         "    pipeline_root=PIPELINE_ROOT,\n",
         ")\n",
         "def pipeline(text: str = \"hi there\"):\n",
-        "    hellow_world_task = hello_world_op(text)\n",
+        "    hello_world_task = hello_world_op(text)\n",
+        "    return hello_world_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"hello_world-v2.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"hello_world-v2\",\n",
         "    template_path=\"hello_world-v2.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -789,7 +887,74 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "delete_pipeline"
+      },
+      "outputs": [],
+      "source": [
+        "pipeline.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "load_component_pipeline_git:helloworld"
+      },
+      "source": [
+        "### Loading components and pipeline YAML definitions from source control\n",
+        "\n",
+        "By storing the component and pipeline definitions in a source repository, like Github, you can version control your components and pipelines, as follows:\n",
+        "\n",
+        "- Use the method `load_component_from_url()`.\n",
+        "\n",
+        "- Pull the raw file format version from the repo. For github, that will be in the form of:\n",
+        "\n",
+        "    https://raw.githubusercontent.com/....\n",
+        "\n",
+        "- Specify the version of the component/pipeline. For github, that will be the branch."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "load_component_pipeline_git:helloworld"
+      },
+      "outputs": [],
+      "source": [
+        "VERSION = \"main\"\n",
+        "hello_world_op = components.load_component_from_url(\n",
+        "    f\"https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/{VERSION}/notebooks/community/ml_ops/stage3/src/hello_world.yaml\"\n",
+        ")\n",
+        "\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/{VERSION}/notebooks/community/ml_ops/stage3/src/hello_world.json -O hello_git_example.json\n",
+        "\n",
+        "pipeline = aiplatform.PipelineJob(\n",
+        "    display_name=\"hello_world-git\",\n",
+        "    template_path=\"hello_git_example.json\",\n",
+        "    pipeline_root=PIPELINE_ROOT,\n",
+        ")\n",
+        "\n",
+        "pipeline.run()\n",
+        "\n",
+        "! rm -f hello_git_example.json"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "delete_pipeline"
+      },
+      "source": [
+        "### Delete a pipeline job\n",
+        "\n",
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -829,7 +994,7 @@
         "    return np.mean(values)\n",
         "\n",
         "\n",
-        "PIPELINE_ROOT = \"{}/pipeline_root/numpy_mean\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/numpy_mean\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@dsl.pipeline(\n",
@@ -837,11 +1002,12 @@
         ")\n",
         "def pipeline(values: list = [2, 3]):\n",
         "    numpy_task = numpy_mean(values)\n",
+        "    return numpy_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"numpy_mean.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"numpy_mean\",\n",
         "    template_path=\"numpy_mean.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -862,7 +1028,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -897,7 +1063,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/add_div2\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/add_div2\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component(output_component_file=\"add.yaml\", base_image=\"python:3.9\")\n",
@@ -916,11 +1082,12 @@
         "def pipeline(v1: int = 4, v2: int = 5):\n",
         "    add_task = add(v1, v2)\n",
         "    div2_task = div_by_2(add_task.output)\n",
+        "    return div2_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"add_div2.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"add_div2\",\n",
         "    template_path=\"add_div2.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -941,7 +1108,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -963,7 +1130,7 @@
       "source": [
         "### Multiple output pipeline\n",
         "\n",
-        "Next, you design and execute a pipeline where a first component has multiple outputs, which are then used as inputs to the next component. To distinquish between the outputs, when used as inputs to the next component, you do:\n",
+        "Next, you design and execute a pipeline where a first component has multiple outputs, which are then used as inputs to the next component. To distinguish between the outputs, when used as inputs to the next component, you follow:\n",
         "\n",
         "1. Set the function return type to `NamedTuple`.\n",
         "2. In NamedTuple, specify a name and type for each output, in the specified order.\n",
@@ -978,7 +1145,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/multi_output\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/multi_output\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component()\n",
@@ -1012,11 +1179,12 @@
         "        multi_output_task.outputs[\"output_1\"],\n",
         "        multi_output_task.outputs[\"output_2\"],\n",
         "    )\n",
+        "    return concat_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"multi_output.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"multi-output\",\n",
         "    template_path=\"multi_output.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1037,7 +1205,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1059,9 +1227,9 @@
       "source": [
         "## Parallel tasks in component\n",
         "\n",
-        "Next, you design and execute a pipeline with parallel tasks. In this example, one parallel task adds up a list of integers and another substracts them. Note that the compiler knows these two tasks can be ran in parallel, because their input is not dependent on the output of the other task.\n",
+        "Next, you design and execute a pipeline with parallel tasks. In this example, one parallel task adds up a list of integers and another substracts them. Note that the compiler knows these two tasks can be run in parallel, because their input is not dependent on the output of the other task.\n",
         "\n",
-        "Finally, the add task waits on the two parallel tasks to complete, and then adds together the two outputs."
+        "Finally, the `add_int` task waits on the two parallel tasks to complete, and then adds together the two outputs."
       ]
     },
     {
@@ -1072,14 +1240,14 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/parallel\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/parallel\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component()\n",
         "def add_list(values: list) -> int:\n",
         "    ret = 0\n",
         "    for value in values:\n",
-        "        ret += 1\n",
+        "        ret = value + ret\n",
         "    return ret\n",
         "\n",
         "\n",
@@ -1087,12 +1255,12 @@
         "def sub_list(values: list) -> int:\n",
         "    ret = 0\n",
         "    for value in values:\n",
-        "        ret -= 1\n",
+        "        ret = value - ret\n",
         "    return ret\n",
         "\n",
         "\n",
         "@component()\n",
-        "def add(value1: int, value2: int) -> int:\n",
+        "def add_int(value1: int, value2: int) -> int:\n",
         "    return value1 + value2\n",
         "\n",
         "\n",
@@ -1102,12 +1270,13 @@
         "def pipeline(values: list = [1, 2, 3]):\n",
         "    add_list_task = add_list(values)\n",
         "    sub_list_task = sub_list(values)\n",
-        "    add_task = add(add_list_task.output, sub_list_task.output)\n",
+        "    add_task = add_int(add_list_task.output, sub_list_task.output)\n",
+        "    return add_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"parallel.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"parallel\",\n",
         "    template_path=\"parallel.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1128,7 +1297,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1150,7 +1319,7 @@
       "source": [
         "## Control flow in pipeline\n",
         "\n",
-        "While Python control statements, e.g., if/else, for, can be used in a component, they cannot be used in the pipeline function. Each task in the pipeline function runs as a node in a graph. Thus a control flow statement also has to run as a graph node. To support this, KFP provides a set of DSL statements that implement control flow as a graph node."
+        "While Python control statements(e.g., if/else, for) can be used in a component, they cannot be used in a pipeline function. Each task in a pipeline function runs as a node in a graph. Thus a control flow statement also has to run as a graph node. To support this, KFP provides a set of DSL statements that implement control flow as a graph node."
       ]
     },
     {
@@ -1161,7 +1330,7 @@
       "source": [
         "### dsl.ParallelFor\n",
         "\n",
-        "The statement `dsl.ParallelFor()` implements a for loop, where each iteration in the for loop runs in parallel."
+        "The statement `dsl.ParallelFor()` implements a `for` loop, where each iteration in the `for` loop runs in parallel."
       ]
     },
     {
@@ -1172,7 +1341,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/parallel_for\".format(BUCKET_NAME)\n",
+        "PIPELINE_ROOT = \"{}/pipeline_root/parallel_for\".format(BUCKET_URI)\n",
         "\n",
         "\n",
         "@component()\n",
@@ -1194,11 +1363,12 @@
         "    with dsl.ParallelFor(values) as item:\n",
         "        output = double(item).output\n",
         "        echo_task = echo(output)\n",
+        "    return echo_task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"parallel_for.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"parallel-for\",\n",
         "    template_path=\"parallel_for.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1219,7 +1389,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1241,7 +1411,15 @@
       "source": [
         "### dsl.Condition\n",
         "\n",
-        "The statement `dsl.Condition()` implements an `if` statement. There is no support for an `else` or `elif` statement. You use a separate `dsl.Condition()` for each value you want to test for. For example, if the output from a task is `True` or `False`, you will have two `dsl.Condition()` statements, one for True and one for False."
+        "The statement `dsl.Condition()` implements an `if` statement. There is no support for an `else` or `elif` statement. You use a separate `dsl.Condition()` for each value you want to test for. For example, if the output from a task is `1` or `0`, you will have two `dsl.Condition()` statements, one for 1 and one for 0.\n",
+        "\n",
+        "The condition in `dsl.Condition()` is evaluated at run-time, not compile time. As such it is not Python code anymore.  The condition is of type `ConditionOperator`. This operator has three parts:\n",
+        "\n",
+        "1. PipelineParam or task output\n",
+        "2. == or !=\n",
+        "3. string or integer value\n",
+        "\n",
+        "A `dsl.Condition()` can be named using the `name` parameter while defining the condition."
       ]
     },
     {
@@ -1280,11 +1458,12 @@
         "        task = heads()\n",
         "    with dsl.Condition(flip_task.output == 0, name=\"false_clause\"):\n",
         "        task = tails()\n",
+        "    return task\n",
         "\n",
         "\n",
         "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"condition.json\")\n",
         "\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"condition\",\n",
         "    template_path=\"condition.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1305,7 +1484,7 @@
       "source": [
         "### Delete a pipeline job\n",
         "\n",
-        "After a pipeline job is completed, you can delete the pipeline job with the method `delete()`.  Prior to completion, a pipeline job can be canceled with the method `cancel()`."
+        "After a pipeline job is completed, you can delete the pipeline job with the `delete()` method. Prior to completion, a pipeline job can be canceled with the method `cancel()`."
       ]
     },
     {
@@ -1325,16 +1504,14 @@
         "id": "pipeline_errata"
       },
       "source": [
-        "## Errata\n",
-        "\n",
         "### Caching in pipeline components\n",
         "\n",
-        "When running a pipeline with Vertex AI Pipelines, the outcome state of each task is cached. With caching, if the pipeline is ran again, and the compiled definition of the task and state has not changed, the cached output will be used instead of running the task again.\n",
+        "When running a pipeline with Vertex AI Pipelines, the outcome state of each task is cached. With caching, if the pipeline is run again, and the compiled definition of the task and state has not changed, the cached output will be used instead of running the task again.\n",
         "\n",
-        "To override caching, i.e., forceable run the task, you set the parameter `enable_caching` to `False` when creating the Vertex AI Pipeline job.\n",
+        "To override caching, i.e., force run the task, you set the parameter `enable_caching` to `False` when creating the Vertex AI Pipeline job.\n",
         "\n",
         "```\n",
-        "pipeline = aip.PipelineJob(\n",
+        "pipeline = aiplatform.PipelineJob(\n",
         "    display_name=\"example\",\n",
         "    template_path=\"example.json\",\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
@@ -1344,11 +1521,11 @@
         "\n",
         "### Asynchronous execution of pipeline\n",
         "\n",
-        "When running a pipeline with the method `run()`, the pipeline is ran synchronously. To run asynchronously, you use the method `submit()`. Once the job has started, your Python script can continue to execute. Then when you need to block execution using the method `wait()`.\n",
+        "When running a pipeline with the method `run()`, the pipeline is run synchronously. To run asynchronously, you use the method `submit()`. Once the job has started, your Python script can continue to execute. To block execution, you can use the method `wait()`.\n",
         "\n",
         "### Setting machine resources for pipeline steps\n",
         "\n",
-        "By default, Vertex AI Pipelines will automatically find the best matching machine type to run the component. You can override and specify the machine resources on a per component basis, when you invoke the component in a pipeline, as follows:\n",
+        "By default, Vertex AI Pipelines automatically finds the best matching machine type to run the component. You can override and specify the machine resources on a per component basis, when you invoke the component in a pipeline, as follows:\n",
         "\n",
         "```\n",
         "@dsl.pipeline(name='my-pipeline')\n",
@@ -1376,15 +1553,9 @@
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:\n",
         "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "### Cloud Storage Bucket\n",
+        "\n",
+        "Set `delete_bucket` to True to delete the Cloud storage bucket used in this notebook."
       ]
     },
     {
@@ -1395,61 +1566,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.undeploy_all()\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline training job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom training job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],