Merge branch 'main' into mlops_install

* fix: bump gcpc version for bqml arima notebook

* pr fixes

.cloud-build/execute_changed_notebooks_cli.py

@@ -68,6 +68,12 @@ parser.add_argument(
     help="A service account. This is used to inject a variable value into the notebook before running. This is not the account that will run the notebook.",
     required=True,
 )
+parser.add_argument(
+    "--variable_vpc_network",
+    type=str,
+    help="The full VPC network name. See https://cloud.google.com/compute/docs/networks-and-firewalls#networks. Format is projects/{project}/global/networks/{network}, where {project} is a project number, as in '12345', and {network} is network name. See <https://cloud.google.com/compute/docs/reference/rest/v1/networks/insert> for details. This is used to inject a variable value into the notebook before running.",
+    required=False,
+)
 parser.add_argument(
     "--staging_bucket",
     type=str,
@@ -114,10 +120,11 @@ execute_changed_notebooks_helper.process_and_execute_notebooks(
     container_uri=args.container_uri,
     staging_bucket=args.staging_bucket,
     artifacts_bucket=args.artifacts_bucket,
+    should_parallelize=args.should_parallelize,
+    timeout=args.timeout,
     variable_project_id=args.variable_project_id,
     variable_region=args.variable_region,
     variable_service_account=args.variable_service_account,
+    variable_vpc_network=args.variable_vpc_network,
     private_pool_id=args.private_pool_id,
-    should_parallelize=args.should_parallelize,
-    timeout=args.timeout,
 )

.cloud-build/execute_changed_notebooks_helper.py

@@ -17,13 +17,16 @@ import concurrent
 import dataclasses
 import datetime
 import functools
+import json
 import git
 import operator
 import os
 import pathlib
 import re
 import subprocess
+import utils
 from typing import List, Optional
+from utils import util
 
 import execute_notebook_helper
 import execute_notebook_remote
@@ -35,6 +38,7 @@ from utils import NotebookProcessors, util
 
 # A buffer so that workers finish before the orchestrating job
 WORKER_TIMEOUT_BUFFER_IN_SECONDS: int = 60 * 60
+PYTHON_VERSION = "3.9" # Set default python version
 
 
 def format_timedelta(delta: datetime.timedelta) -> str:
@@ -66,8 +70,9 @@ class NotebookExecutionResult:
     log_url: str
     output_uri: str
     build_id: str
+    logs_bucket: str
     error_message: Optional[str]
-    
+
     @property
     def output_uri_web(self) -> Optional[str]:
         if self.output_uri.startswith("gs://"):
@@ -81,6 +86,7 @@ def _process_notebook(
     variable_project_id: str,
     variable_region: str,
     variable_service_account: str,
+    variable_vpc_network: Optional[str],
 ):
     # Read notebook
     with open(notebook_path) as f:
@@ -93,6 +99,7 @@ def _process_notebook(
             "PROJECT_ID": variable_project_id,
             "REGION": variable_region,
             "SERVICE_ACCOUNT": variable_service_account,
+            "VPC_NETWORK": variable_vpc_network,
         },
     )
 
@@ -108,6 +115,33 @@ def _process_notebook(
         nbformat.write(nb, new_file)
 
 
+def _get_notebook_python_version(notebook_path: str) -> str:
+    """
+    Get the python version for running the notebook if it is specified in
+    the notebook.
+    """
+    python_version = PYTHON_VERSION
+
+    # Load the notebook
+    file = open(notebook_path)
+    src = file.read()
+    nb_json = json.loads(src)
+
+    #Iterate over the cells in the ipynb
+    for cell in nb_json['cells']:
+        if cell['cell_type'] == 'markdown':
+            markdown = str.join('', cell['source'])
+
+            # Look for the python version specification pattern
+            re_match = re.search('python version = (\d\.\d)', markdown, flags=re.IGNORECASE)
+            if re_match:
+                # get the version number
+                python_version = re_match.group(1)
+                break
+
+    return python_version
+
+
 def _create_tag(filepath: str) -> str:
     tag = os.path.basename(os.path.normpath(filepath))
     tag = re.sub("[^0-9a-zA-Z_.-]+", "-", tag)
@@ -128,8 +162,9 @@ def process_and_execute_notebook(
     variable_project_id: str,
     variable_region: str,
     variable_service_account: str,
+    variable_vpc_network: Optional[str],
     private_pool_id: Optional[str],
-    deadline: datetime,
+    deadline: datetime.datetime,
     notebook: str,
     should_get_tail_logs: bool = False,
 ) -> NotebookExecutionResult:
@@ -137,6 +172,13 @@ def process_and_execute_notebook(
 
     print(f"Running notebook: {notebook}")
 
+    # Handle empty strings
+    if not variable_vpc_network:
+        variable_vpc_network = None
+
+    if not private_pool_id:
+        private_pool_id = None
+
     # Create paths
     notebook_output_uri = "/".join([artifacts_bucket, pathlib.Path(notebook).name])
 
@@ -150,6 +192,7 @@ def process_and_execute_notebook(
         output_uri=notebook_output_uri,
         log_url="",
         build_id="",
+        logs_bucket="",
         error_message=None,
     )
 
@@ -157,12 +200,17 @@ def process_and_execute_notebook(
     time_start = datetime.datetime.now()
     operation = None
     try:
+        # Get the python version for running the notebook if specified
+        notebook_exec_python_version = _get_notebook_python_version(notebook_path=notebook)
+        print(f"Running notebook with python {notebook_exec_python_version}")
+
         # Pre-process notebook by substituting variable names
         _process_notebook(
             notebook_path=notebook,
             variable_project_id=variable_project_id,
             variable_region=variable_region,
             variable_service_account=variable_service_account,
+            variable_vpc_network=variable_vpc_network,
         )
 
         # Upload the pre-processed code to a GCS bucket
@@ -182,11 +230,13 @@ def process_and_execute_notebook(
             private_pool_id=private_pool_id,
             private_pool_region=variable_region,
             timeout_in_seconds=timeout_in_seconds,
+            python_version=notebook_exec_python_version
         )
 
         operation_metadata = BuildOperationMetadata(mapping=operation.metadata)
         result.build_id = operation_metadata.build.id
         result.log_url = operation_metadata.build.log_url
+        result.logs_bucket = operation_metadata.build.logs_bucket
 
         # Block and wait for the result
         operation_result = operation.result()
@@ -266,8 +316,8 @@ def get_changed_notebooks(
             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_str = subprocess.check_output(["git", "ls-files"] + test_paths)
+        notebooks = notebooks_str.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]
@@ -286,12 +336,13 @@ def process_and_execute_notebooks(
     container_uri: str,
     staging_bucket: str,
     artifacts_bucket: str,
+    should_parallelize: bool,
+    timeout: int,
     variable_project_id: str,
     variable_region: str,
     variable_service_account: str,
-    private_pool_id: Optional[str],
-    should_parallelize: bool,
-    timeout: int,
+    variable_vpc_network: Optional[str] = None,
+    private_pool_id: Optional[str] = None,
 ):
     """
     Run the notebooks that exist under the folders defined in the test_paths_file.
@@ -327,7 +378,7 @@ def process_and_execute_notebooks(
         seconds=max(timeout - WORKER_TIMEOUT_BUFFER_IN_SECONDS, 0)
     )
 
-    if len(notebooks) > 1:
+    if len(notebooks) >= 1:
         notebook_execution_results: List[NotebookExecutionResult] = []
 
         print(f"Found {len(notebooks)} modified notebooks: {notebooks}")
@@ -349,6 +400,7 @@ def process_and_execute_notebooks(
                             variable_project_id,
                             variable_region,
                             variable_service_account,
+                            variable_vpc_network,
                             private_pool_id,
                             deadline,
                         ),
@@ -364,6 +416,7 @@ def process_and_execute_notebooks(
                     variable_project_id=variable_project_id,
                     variable_region=variable_region,
                     variable_service_account=variable_service_account,
+                    variable_vpc_network=variable_vpc_network,
                     private_pool_id=private_pool_id,
                     deadline=deadline,
                     notebook=notebook,
@@ -389,14 +442,47 @@ def process_and_execute_notebooks(
                         format_timedelta(result.duration),
                         result.log_url,
                         result.output_uri,
-                        result.output_uri_web
+                        result.output_uri_web,
+                        result.logs_bucket
                     ]
                     for result in results_sorted
                 ],
-                headers=["build_tag", "status", "duration", "log_url", "output_uri", "output_uri_web"],
+                headers=[
+                    "build_tag",
+                    "status",
+                    "duration",
+                    "log_url",
+                    "output_uri",
+                    "output_uri_web",
+                    "logs_bucket"
+                ],
             )
         )
 
+        if len(notebooks) == 1:
+          print("="*100)
+          print("The notebook execution build log:\n")
+          print("="*100)
+
+          build_id = results_sorted[0].build_id
+          logs_bucket_name = (results_sorted[0].logs_bucket).removeprefix("gs://")
+          log_file_name = f"log-{build_id}.txt"
+
+          log_contents = util.download_blob_into_memory(
+            bucket_name=logs_bucket_name,
+            blob_name=log_file_name,
+            download_as_text=True
+            )
+
+          # Remove extra steps from the log
+          match = re.search("starting Step #4", log_contents, flags=re.IGNORECASE)
+
+          if match is not None:
+            match_index = match.span()[0]
+            print(log_contents[match_index:])
+          else:
+            print(log_contents)
+
         print("\n=== END RESULTS===\n")
 
         total_notebook_duration = functools.reduce(
@@ -412,24 +498,5 @@ def process_and_execute_notebooks(
         # 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,
-            variable_service_account=variable_service_account,
-        )
-
-        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.")

.cloud-build/execute_notebook_helper.py

@@ -26,6 +26,9 @@ from utils import util
 
 # This script is used to execute a notebook and write out the output notebook.
 
+# This is used to force papermill to use this kernel to run the notebook instead of any defined inside the notebook itself
+DEFAULT_KERNEL_NAME = "python3"
+
 
 def execute_notebook(
     notebook_source: str,
@@ -50,14 +53,11 @@ def execute_notebook(
 
     execution_exception = None
 
-
     print("\n=== DOWNLOAD EXECUTED NOTEBOOK ===\n")
-    print(
-                f"Please debug the executed notebook by downloading the executed notebook:"
-            )
+    print(f"Please debug the executed notebook by downloading the executed notebook:")
 
     print("Option 1. Using gsutil. Run the following command in your terminal.")
-    print(f"\tgsutil cp \"{output_file_or_uri}\" .")
+    print(f'\tgsutil cp "{output_file_or_uri}" .')
 
     print("Option 2. Using this link.")
     print(f"\thttps://storage.googleapis.com/{output_file_or_uri[5:]}")
@@ -72,6 +72,7 @@ def execute_notebook(
             output_path=notebook_source,
             progress_bar=should_log_output,
             request_save_on_cell_execute=should_log_output,
+            kernel_name=DEFAULT_KERNEL_NAME,
             log_output=should_log_output,
             stdout_file=sys.stdout if should_log_output else None,
             stderr_file=sys.stderr if should_log_output else None,

.cloud-build/execute_notebook_remote.py

@@ -40,6 +40,7 @@ def execute_notebook_remote(
     private_pool_region: Optional[str],
     tag: Optional[str],
     timeout_in_seconds: Optional[int] = None,
+    python_version: Optional[str] = None
 ) -> operation.Operation:
     """Create and execute a single notebook on Google Cloud Build"""
     # Load build steps from YAML
@@ -50,8 +51,12 @@ def execute_notebook_remote(
         "_PYTHON_IMAGE": container_uri,
         "_NOTEBOOK_GCS_URI": notebook_uri,
         "_NOTEBOOK_OUTPUT_GCS_URI": notebook_output_uri,
+        "_PYTHON_VERSION" : f"python{python_version}"
     }
 
+    if python_version is not None:
+      substitutions["_PYTHON_VERSION"] = "python" + python_version
+
     build = cloudbuild_v1.Build()
 
     options: Optional[client_options.ClientOptions] = None

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

@@ -10,21 +10,21 @@ steps:
     entrypoint: /bin/sh
     args:
     - -c
-    - python3 .cloud-build/CheckPythonVersion.py -q
+    - ${_PYTHON_VERSION} .cloud-build/CheckPythonVersion.py -q
   # Create a virtual environment
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
-    - python3 -m venv workspace/env
+    - ${_PYTHON_VERSION} -m venv workspace/env
   # Install Python dependencies
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
     args:
     - -c
     - . workspace/env/bin/activate &&
-      python3 -m pip -q install -U pip &&
-      python3 -m pip -q install -U -r .cloud-build/requirements.txt
+      python -m pip -q install -U pip &&
+      python -m pip -q install -U -r .cloud-build/requirements.txt
   # Install Python dependencies and run testing script
   - name: ${_PYTHON_IMAGE}
     entrypoint: /bin/sh
@@ -32,7 +32,7 @@ steps:
     - -c
     - |
       . workspace/env/bin/activate &&
-      python3 .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"
+      python .cloud-build/execute_notebook_cli.py --notebook_source "${_NOTEBOOK_GCS_URI}" --output_file_or_uri "${_NOTEBOOK_OUTPUT_GCS_URI}"
     env:
     - 'IS_TESTING=1'
 timeout: 86400s

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

@@ -36,7 +36,7 @@ steps:
     - -c
     - |
       . workspace/env/bin/activate &&
-      python3 .cloud-build/execute_changed_notebooks_cli.py --test_paths_file "${_TEST_PATHS_FILE}" --base_branch "${_FORCED_BASE_BRANCH}" --container_uri ${_PYTHON_IMAGE} --staging_bucket ${_GCS_STAGING_BUCKET}  --artifacts_bucket ${_GCS_STAGING_BUCKET}/executed_notebooks/PR_${_PR_NUMBER}/BUILD_${BUILD_ID} --variable_project_id ${PROJECT_ID} --variable_region ${_GCP_REGION} --variable_service_account ${_GCP_SERVICE_ACCOUNT} `if [ ! -z "${_PRIVATE_POOL_NAME}" ]; then echo "--private_pool_id ${_PRIVATE_POOL_NAME}"; fi`
+      python3 .cloud-build/execute_changed_notebooks_cli.py --test_paths_file "${_TEST_PATHS_FILE}" --base_branch "${_FORCED_BASE_BRANCH}" --container_uri ${_PYTHON_IMAGE} --staging_bucket ${_GCS_STAGING_BUCKET}  --artifacts_bucket ${_GCS_STAGING_BUCKET}/executed_notebooks/PR_${_PR_NUMBER}/BUILD_${BUILD_ID} --variable_project_id ${PROJECT_ID} --variable_region ${_GCP_REGION} --variable_service_account ${_GCP_SERVICE_ACCOUNT} --variable_vpc_network "${_GPC_VPC_NETWORK_NAME}" `if [ ! -z "${_PRIVATE_POOL_NAME}" ]; then echo "--private_pool_id ${_PRIVATE_POOL_NAME}"; fi`
     env:
     - 'IS_TESTING=1'
 timeout: 86400s

.cloud-build/test_notebook_vm.txt

@@ -1,4 +1,6 @@
 notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb
 notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb
 notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb
-notebooks/official/pipelines/metrics_viz_run_compare_kfp.ipynb
+notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb
+notebooks/official/matching_engine/sdk_matching_engine_for_indexing.ipynb
+.cloud-build/tests/python_version_test.ipynb

.cloud-build/test_single_notebook_vm.txt

@@ -1 +1 @@
-notebooks/official/pipelines/metrics_viz_run_compare_kfp.ipynb
+notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb

.cloud-build/tests/python_version_test.ipynb

@@ -0,0 +1,61 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "57a3d44ed8a8"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.7\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 $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI API and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c6516f90311b"
+      },
+      "outputs": [],
+      "source": [
+        "# test if the right python version is being used\n",
+        "import sys\n",
+        "\n",
+        "actual_python_version = f\"{sys.version_info.major}.{sys.version_info.minor}\"\n",
+        "print(f\"Runtime python version: {actual_python_version}\")\n",
+        "\n",
+        "assert actual_python_version == \"3.7\", \"Wrong python version!\""
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "python_version_test.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

.cloud-build/utils/util.py

@@ -3,7 +3,7 @@ import subprocess
 import tarfile
 import uuid
 from datetime import datetime
-from typing import Optional
+from typing import Optional, Union
 
 from google.auth import credentials as auth_credentials
 from google.cloud import storage
@@ -58,3 +58,34 @@ def archive_code_and_upload(staging_bucket: str):
     print(f"Uploaded source code archive to {source_archived_file_gcs}")
 
     return source_archived_file_gcs
+
+
+def download_blob_into_memory(
+  bucket_name: str,
+  blob_name: str,
+  download_as_text: Optional[bool]=False
+) -> Union[bytes, str]:
+    """
+    Downloads a blob into memory as byte or as text if
+    download_as_text is set to True.
+    """
+
+    storage_client = storage.Client()
+
+    bucket = storage_client.bucket(bucket_name)
+
+    # Construct a client side representation of a blob.
+    blob = bucket.blob(blob_name)
+
+    # Download the blob content
+    if download_as_text:
+      contents = blob.download_as_text()
+    else:
+      contents = blob.download_as_bytes()
+
+    print(
+        f"Downloaded storage object {blob_name} from bucket {bucket_name}."
+    )
+
+    return contents
+

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,4 +1,11 @@
-If you are opening a PR for `Official Notebooks` under the [notebooks/official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder, follow this mandatory checklist:
+**REQUIRED:** Add a summary of your PR here, typically including why the change is needed and what was changed. Include any design alternatives for discussion purposes.
+
+<br>
+--- YOUR PR SUMMARY GOES HERE ---
+<br><br><br>
+
+**REQUIRED:** Fill out the below checklists or remove if irrelevant
+1. If you are opening a PR for `Official Notebooks` under the [notebooks/official](https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/main/notebooks/official) folder, follow this mandatory checklist:
 - [ ] 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.
@@ -7,12 +14,15 @@ If you are opening a PR for `Official Notebooks` under the [notebooks/official](
 - [ ] 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.
 
+<br>
 
-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:
+2. 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/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:
+<br>
+
+3. 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/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/linter/Dockerfile

@@ -0,0 +1,20 @@
+# To use this image, run this command with the desired notebook args from the top-level vertex-ai-samples directory:
+# 1. To lint all changed notebooks:
+# docker run -v ${PWD}:/setup/app gcr.io/python-docs-samples-tests/notebook_linter:latest
+# 2. To lint specific notebooks:
+# docker run -v ${PWD}:/setup/app gcr.io/python-docs-samples-tests/notebook_linter:latest notebooks/1.ipynb notebooks/2.ipynb
+
+FROM python:3.10
+
+WORKDIR setup
+
+COPY ./requirements.txt .
+COPY ./run_linter.sh .
+
+# Install dependencies.
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+
+WORKDIR app
+
+ENTRYPOINT ["/setup/run_linter.sh"]

.github/workflows/linter/run_linter.sh

@@ -47,12 +47,22 @@ done
 
 echo "Test mode: $is_test"
 
+# Read in user-provided notebooks
+notebooks=()
+for arg in "$@"; do
+    if [[ $arg == *.ipynb ]]; then
+        notebooks+=("$arg")
+    fi
+done
+
 # Only check notebooks in test folders modified in this pull request.
 # Note: Use process substitution to persist the data in the array
-notebooks=()
-while read -r file || [ -n "$line" ]; do
-    notebooks+=("$file")
-done < <(git diff --name-only main... | grep '\.ipynb$')
+if [ ${#notebooks[@]} -eq 0 ]; then
+    echo "Checking for changed notebooked using git"
+    while read -r file || [ -n "$line" ]; do
+        notebooks+=("$file")
+    done < <(git diff --name-only main... | grep '\.ipynb$')
+fi
 
 problematic_notebooks=()
 if [ ${#notebooks[@]} -gt 0 ]; then

community-content/CODEOWNERS

@@ -1,5 +1,6 @@
 *  @vertex-ai-samples-contributors  @GoogleCloudPlatform/cloudml-samples-owners
 /tf_agents_bandits_movie_recommendation_with_kfp_and_vertex_sdk	@yinghsienwu
+/pytorch_pre_built_images_deployment @googleapis/vertex-prediction-team
 /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

community-content/cpr-examples/timm_serving/.gitignore

@@ -2,4 +2,5 @@ cpr_model_server.py
 entrypoint.py
 state_dict.pth
 config.json
-**/__pycache__
+**/__pycache__
+!testdata/**

community-content/cpr-examples/timm_serving/README.md

@@ -2,7 +2,7 @@
 
 ## About CPR
 
-CPR ([custom prediction routines](https://github.com/googleapis/python-aiplatform/blob/custom-prediction-routine/google/cloud/aiplatform/prediction/README.md)) is a framework designed by Google Cloud developers to make it easier to combine machine learning models with custom preprocessing and postprocessing logic in a real-time serving application. 
+CPR ([custom prediction routines](https://github.com/googleapis/python-aiplatform/blob/main/google/cloud/aiplatform/prediction/README.md)) is a framework designed by Google Cloud developers to make it easier to combine machine learning models with custom preprocessing and postprocessing logic in a real-time serving application. 
 
 ## Using this example
 
@@ -34,6 +34,23 @@ Finally, install the Python modules required to build and run the model server:
 pip install -r requirements.txt
 ```
 
+### Auth
+
+This example uses Google Cloud Storage for hosting model artifacts and Artifact Registry to store the container image. 
+You'll need to authorize yourself before you can interact with these.
+
+First, log in to GCP with application default credentials:
+```sh
+gcloud auth application-default login
+```
+
+Next, if you haven't done so already, set up the [gcloud credential helper](https://cloud.google.com/artifact-registry/docs/docker/authentication)
+for the Artifact Registry region where you intend to host the image.  
+```
+gcloud auth configure-docker <region>-docker.pkg.dev
+```
+
+
 ### Predictor
 
 The `TimmPredictor` class in `timm_serving/predictor.py` implements most of the important logic for the server.

community-content/cpr-examples/timm_serving/config.py

@@ -60,9 +60,9 @@ class CPRConfig(object):
     image: str = "timm_predictor:latest"
     artifact_local_dir: str = ""
     region: str = "us-central1"
-    project_id: str = "samthrasher-experimental"
+    project_id: str = "<your project ID here>"
     repository: str = "cpr-images"
-    artifact_gcs_dir: str = "gs://samthrasher-cpr-example/timm-vit224/"
+    artifact_gcs_dir: str = "gs://<your bucket ID here>/timm-vit224/"
     model_name: str = ""
     endpoint_name: str = ""
     machine_type: str = "n1-standard-2"

community-content/cpr-examples/timm_serving/requirements.txt

@@ -5,4 +5,4 @@ timm==0.5.4
 smart_open==6.0.0
 
 google-cloud-storage>=1.26.0,<2.0.0dev
-google-cloud-aiplatform[prediction] @ git+https://github.com/googleapis/python-aiplatform.git@custom-prediction-routine
+google-cloud-aiplatform[prediction]>=1.16.0

community-content/cpr-examples/timm_serving/test.py

@@ -70,7 +70,10 @@ class PredictorUnitTests(absltest.TestCase):
     def setUp(self):
         super().setUp()
         self.config = CPRConfig()
-        self.config.load()
+        try:
+            self.config.load()
+        except FileNotFoundError:
+            logging.info("No saved config file found, using default values.")
         self.predictor = predictor.TimmPredictor()
 
     def test_load_from_saved_state_dict_ok(self):
@@ -170,7 +173,10 @@ class ServerEndToEndTests(absltest.TestCase):
     def setUp(self):
         super().setUp()
         self.config = CPRConfig()
-        self.config.load()
+        try:
+            self.config.load()
+        except FileNotFoundError:
+            logging.info("No saved config file found, using default values.")
         self.local_model = cpr.LocalModel(
             serving_container_spec=aiplatform.gapic.ModelContainerSpec(
                 image_uri=self.config.image

community-content/cpr-examples/timm_serving/testdata/bad_model_1/state_dict.pth

@@ -0,0 +1 @@
+blah

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_gloo_vertex_training_with_custom_container.ipynb

@@ -1,474 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a6b56b1c7b76"
-      },
-      "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": "c414a395a19b"
-      },
-      "source": [
-        "# PyTorch Image Classification Multi-Node Distributed Data Parallel Training on CPU using Vertex Training with Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b98238e32cf7"
-      },
-      "source": [
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_gloo_vertex_training_with_custom_container.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": "03d216c7f7b1"
-      },
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c5ac73516218"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"YOUR PROJECT ID\"\n",
-        "BUCKET_NAME = \"gs://YOUR BUCKET NAME\"\n",
-        "REGION = \"YOUR REGION\"\n",
-        "SERVICE_ACCOUNT = \"YOUR SERVICE ACCOUNT\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b5ae674177e"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "19a9b3bdd553"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = \"pt-img-cls-multi-node-ddp-cust-cont\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "57bf6f8b4361"
-      },
-      "source": [
-        "## Local Training"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e5d8a3443da0"
-      },
-      "outputs": [],
-      "source": [
-        "! ls trainer"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "07f79309472d"
-      },
-      "outputs": [],
-      "source": [
-        "! cat trainer/requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e16cd8bb7483"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install -r trainer/requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b8a210718c4"
-      },
-      "outputs": [],
-      "source": [
-        "! cat trainer/task.py"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c0c6e7dfb3c6"
-      },
-      "outputs": [],
-      "source": [
-        "%run trainer/task.py --epochs 5 --no-cuda --local-mode"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "31dfdeede587"
-      },
-      "outputs": [],
-      "source": [
-        "! ls ./tmp"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "48d56ec621cc"
-      },
-      "outputs": [],
-      "source": [
-        "! rm -rf ./tmp"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8f3ea1210749"
-      },
-      "source": [
-        "## Vertex Training using Vertex SDK and Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "93002a20a2a6"
-      },
-      "source": [
-        "### Build Custom Container"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4130ce43fd08"
-      },
-      "outputs": [],
-      "source": [
-        "hostname = \"gcr.io\"\n",
-        "image_name = content_name\n",
-        "tag = \"latest\"\n",
-        "\n",
-        "custom_container_image_uri = f\"{hostname}/{PROJECT_ID}/{image_name}:{tag}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "2f1fc5b05240"
-      },
-      "outputs": [],
-      "source": [
-        "! cd trainer && docker build -t $custom_container_image_uri -f Dockerfile ."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b4f274f499ac"
-      },
-      "outputs": [],
-      "source": [
-        "! docker run --rm $custom_container_image_uri --epochs 5 --no-cuda --local-mode"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ee1a0a06d0b4"
-      },
-      "outputs": [],
-      "source": [
-        "! docker push $custom_container_image_uri"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cb763be12fc9"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud container images list --repository $hostname/$PROJECT_ID"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "10c8cc6b3334"
-      },
-      "source": [
-        "### Initialize Vertex SDK"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "1a12348169fa"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install -r requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "42e981cefe41"
-      },
-      "outputs": [],
-      "source": [
-        "from google.cloud import aiplatform\n",
-        "\n",
-        "aiplatform.init(\n",
-        "    project=PROJECT_ID,\n",
-        "    staging_bucket=BUCKET_NAME,\n",
-        "    location=REGION,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "73c92c9298e9"
-      },
-      "source": [
-        "### Create a Vertex Tensorboard Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "bde509558cd5"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = content_name + \"-cpu\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6d7908c0083c"
-      },
-      "outputs": [],
-      "source": [
-        "tensorboard = aiplatform.Tensorboard.create(\n",
-        "    display_name=content_name,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a1f0a4f54037"
-      },
-      "source": [
-        "#### Option: Use a Previously Created Vertex Tensorboard Instance\n",
-        "\n",
-        "```\n",
-        "tensorboard_name = \"Your Tensorboard Resource Name or Tensorboard ID\"\n",
-        "tensorboard = aiplatform.Tensorboard(tensorboard_name=tensorboard_name)\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "a4cac84e04ac"
-      },
-      "source": [
-        "### Run a Vertex SDK CustomContainerTrainingJob"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f92e8fdd44ee"
-      },
-      "outputs": [],
-      "source": [
-        "display_name = content_name\n",
-        "gcs_output_uri_prefix = f\"{BUCKET_NAME}/{display_name}\"\n",
-        "\n",
-        "replica_count = 4\n",
-        "machine_type = \"n1-standard-4\"\n",
-        "\n",
-        "args = [\n",
-        "    \"--backend\",\n",
-        "    \"gloo\",\n",
-        "    \"--no-cuda\",\n",
-        "    \"--batch-size\",\n",
-        "    \"128\",\n",
-        "    \"--epochs\",\n",
-        "    \"25\",\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ae4c57df7e07"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job = aiplatform.CustomContainerTrainingJob(\n",
-        "    display_name=display_name,\n",
-        "    container_uri=custom_container_image_uri,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "35cf3ecdf0df"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job.run(\n",
-        "    args=args,\n",
-        "    base_output_dir=gcs_output_uri_prefix,\n",
-        "    replica_count=replica_count,\n",
-        "    machine_type=machine_type,\n",
-        "    tensorboard=tensorboard.resource_name,\n",
-        "    service_account=SERVICE_ACCOUNT,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "49d10dded73b"
-      },
-      "outputs": [],
-      "source": [
-        "print(f\"Custom Training Job Name: {custom_container_training_job.resource_name}\")\n",
-        "print(f\"GCS Output URI Prefix: {gcs_output_uri_prefix}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "78398f52807b"
-      },
-      "source": [
-        "### Training Output Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fc74422de1d1"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls $gcs_output_uri_prefix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5e99a6a05b10"
-      },
-      "source": [
-        "## Clean Up Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b0c1b3f7466b"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil rm -rf $gcs_output_uri_prefix"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "multi_node_ddp_gloo_vertex_training_with_custom_container.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_nccl_vertex_training_with_custom_container.ipynb

@@ -1,347 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a6b56b1c7b76"
-      },
-      "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": "20a5ea0081d0"
-      },
-      "source": [
-        "# PyTorch Image Classification Multi-Node Distributed Data Parallel Training on GPU using Vertex Training with Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8752d4a255fb"
-      },
-      "source": [
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/community-content/pytorch_image_classification_distributed_data_parallel_training_with_vertex_sdk/multi_node_ddp_nccl_vertex_training_with_custom_container.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": "03d216c7f7b1"
-      },
-      "source": [
-        "## Setup"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c5ac73516218"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"YOUR PROJECT ID\"\n",
-        "BUCKET_NAME = \"gs://YOUR BUCKET NAME\"\n",
-        "REGION = \"YOUR REGION\"\n",
-        "SERVICE_ACCOUNT = \"YOUR SERVICE ACCOUNT\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b5ae674177e"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "19a9b3bdd553"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = \"pt-img-cls-multi-node-ddp-cust-cont\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5307fe28b633"
-      },
-      "source": [
-        "## Vertex Training using Vertex SDK and Custom Container"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "46cb58c7fbf9"
-      },
-      "source": [
-        "### Built Custom Container"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "97e66e9f9bab"
-      },
-      "outputs": [],
-      "source": [
-        "hostname = \"gcr.io\"\n",
-        "image_name = content_name\n",
-        "tag = \"latest\"\n",
-        "\n",
-        "custom_container_image_uri = f\"{hostname}/{PROJECT_ID}/{image_name}:{tag}\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ae9b29c4773f"
-      },
-      "source": [
-        "### Initialize Vertex SDK"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "dc1e84d5dec2"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install -r requirements.txt"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6964be27b98e"
-      },
-      "outputs": [],
-      "source": [
-        "from google.cloud import aiplatform\n",
-        "\n",
-        "aiplatform.init(\n",
-        "    project=PROJECT_ID,\n",
-        "    staging_bucket=BUCKET_NAME,\n",
-        "    location=REGION,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "594a91f438f2"
-      },
-      "source": [
-        "### Create a Vertex Tensorboard Instance"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "93134273261e"
-      },
-      "outputs": [],
-      "source": [
-        "content_name = content_name + \"-gpu\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "c2bd82dbcd9b"
-      },
-      "outputs": [],
-      "source": [
-        "tensorboard = aiplatform.Tensorboard.create(\n",
-        "    display_name=content_name,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ebc593c6472e"
-      },
-      "source": [
-        "#### Option: Use a Previously Created Vertex Tensorboard Instance\n",
-        "\n",
-        "```\n",
-        "tensorboard_name = \"Your Tensorboard Resource Name or Tensorboard ID\"\n",
-        "tensorboard = aiplatform.Tensorboard(tensorboard_name=tensorboard_name)\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "0769e8e34c2f"
-      },
-      "source": [
-        "### Run a Vertex SDK CustomContainerTrainingJob"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "023f33ece826"
-      },
-      "outputs": [],
-      "source": [
-        "display_name = content_name\n",
-        "gcs_output_uri_prefix = f\"{BUCKET_NAME}/{display_name}\"\n",
-        "\n",
-        "replica_count = 1\n",
-        "machine_type = \"n1-standard-4\"\n",
-        "accelerator_count = 4\n",
-        "accelerator_type = \"NVIDIA_TESLA_K80\"\n",
-        "\n",
-        "args = [\n",
-        "    \"--backend\",\n",
-        "    \"nccl\",\n",
-        "    \"--batch-size\",\n",
-        "    \"128\",\n",
-        "    \"--epochs\",\n",
-        "    \"25\",\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "d4b599e726ef"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job = aiplatform.CustomContainerTrainingJob(\n",
-        "    display_name=display_name,\n",
-        "    container_uri=custom_container_image_uri,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "81321e3bdf7f"
-      },
-      "outputs": [],
-      "source": [
-        "custom_container_training_job.run(\n",
-        "    args=args,\n",
-        "    base_output_dir=gcs_output_uri_prefix,\n",
-        "    replica_count=replica_count,\n",
-        "    machine_type=machine_type,\n",
-        "    accelerator_count=accelerator_count,\n",
-        "    accelerator_type=accelerator_type,\n",
-        "    tensorboard=tensorboard.resource_name,\n",
-        "    service_account=SERVICE_ACCOUNT,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "5100712c2c4c"
-      },
-      "outputs": [],
-      "source": [
-        "print(f\"Custom Training Job Name: {custom_container_training_job.resource_name}\")\n",
-        "print(f\"GCS Output URI Prefix: {gcs_output_uri_prefix}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f9b77676e5a6"
-      },
-      "source": [
-        "### Training Output Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0e171ce95ace"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls $gcs_output_uri_prefix"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cf1b74a12b87"
-      },
-      "source": [
-        "## Clean Up Artifact"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a0b15089c341"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil rm -rf $gcs_output_uri_prefix"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "multi_node_ddp_nccl_vertex_training_with_custom_container.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

community-content/pytorch_pre_built_images_deployment/README.md

@@ -0,0 +1,30 @@
+# PyTorch Deployment on Google Cloud: Text Classification
+
+**This is an Experimental release**, covered by the Pre-GA Offerings Terms of your Google Cloud Platform [Terms of Service](https://cloud.google.com/terms).
+
+Experiments are focused on validating a prototype and are not guaranteed to be released. They are not intended for production use or covered by any SLA, support obligation, or deprecation policy and might be subject to backward-incompatible changes.
+
+**Kindly drop us a note before you run any scale tests.**
+
+**Do not hesitate to contact vertexai-prediction-preview-feedback@google.com if you have any questions or run into any issues.**
+
+The projects need to be added to the allowlist in order to deploy PyTorch models using Vertex AI Prediction pre-built PyTorch images. If you are interested in the feature, please send an email to vertexai-prediction-preview-feedback@google.com to provide your project numbers OR project ids.
+
+## Overview
+
+In the PyTorch on Google Cloud series of blog posts, we aim to share how to deploy PyTorch models at scale on [Vertex AI](https://cloud.google.com/vertex-ai).
+
+This tutorial on text classification shows how to deploy a PyTorch based text classification model on [Vertex AI](https://cloud.google.com/vertex-ai/docs/start/client-libraries#python) using Vertex SDK and [`gcloud ai`](https://cloud.google.com/sdk/gcloud/reference/beta/ai).
+
+## Notebooks
+
+| <h4>Notebook</h4> | <h4>Description</h4>                       |
+| :-------- | :------- |
+| [pytorch-text-classification-vertex-ai-deploy.ipynb](./pytorch-text-classification-vertex-ai-deploy.ipynb) | Notebook to show deploying a PyTorch model on Vertex AI |
+
+## Folders
+
+
+| <h4>Folder Name</h4> | <h4>Description</h4>                       |
+| :-------- | :------- |
+| [`predictor`](./predictor) | Folder with custom prediction handler to deploy a PyTorch model to Vertex Prediction. In the [notebook](./pytorch-text-classification-vertex-ai-deploy.ipynb), this folder is used for deploying a PyTorch model on Vertex AI using Vertex Prediction pre-built PyTorch images |

community-content/pytorch_pre_built_images_deployment/predictor/custom_handler.py

@@ -0,0 +1,91 @@
+
+import os
+import json
+import logging
+
+import torch
+from transformers import AutoModelForSequenceClassification, AutoTokenizer
+from ts.torch_handler.base_handler import BaseHandler
+
+logger = logging.getLogger(__name__)
+
+
+class TransformersClassifierHandler(BaseHandler):
+    """
+    The handler takes an input string and returns the classification text 
+    based on the serialized transformers checkpoint.
+    """
+    def __init__(self):
+        super(TransformersClassifierHandler, self).__init__()
+        self.initialized = False
+
+    def initialize(self, ctx):
+        """ Loads the model.pt file and initialized the model object.
+        Instantiates Tokenizer for preprocessor to use
+        Loads labels to name mapping file for post-processing inference response
+        """
+        self.manifest = ctx.manifest
+
+        properties = ctx.system_properties
+        model_dir = properties.get("model_dir")
+        self.device = torch.device("cuda:" + str(properties.get("gpu_id")) if torch.cuda.is_available() else "cpu")
+
+        # Read model serialize/pt file
+        serialized_file = self.manifest["model"]["serializedFile"]
+        model_pt_path = os.path.join(model_dir, serialized_file)
+        if not os.path.isfile(model_pt_path):
+            raise RuntimeError("Missing the model.pt or pytorch_model.bin file")
+        
+        # Load model
+        self.model = AutoModelForSequenceClassification.from_pretrained(model_dir)
+        self.model.to(self.device)
+        self.model.eval()
+        logger.debug('Transformer model from path {0} loaded successfully'.format(model_dir))
+        
+        # Ensure to use the same tokenizer used during training
+        self.tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+
+        # Read the mapping file, index to object name
+        mapping_file_path = os.path.join(model_dir, "index_to_name.json")
+
+        if os.path.isfile(mapping_file_path):
+            with open(mapping_file_path) as f:
+                self.mapping = json.load(f)
+        else:
+            logger.warning('Missing the index_to_name.json file. Inference output will default.')
+            self.mapping = {"0": "Negative",  "1": "Positive"}
+
+        self.initialized = True
+
+    def preprocess(self, data):
+        """ Preprocessing input request by tokenizing
+            Extend with your own preprocessing steps as needed
+        """
+        text = data[0].get("data")
+        if text is None:
+            text = data[0].get("body")
+        sentences = text.decode('utf-8')
+        logger.info("Received text: '%s'", sentences)
+
+        # Tokenize the texts
+        tokenizer_args = ((sentences,))
+        inputs = self.tokenizer(*tokenizer_args,
+                                padding='max_length',
+                                max_length=128,
+                                truncation=True,
+                                return_tensors = "pt")
+        return inputs
+
+    def inference(self, inputs):
+        """ Predict the class of a text using a trained transformer model.
+        """
+        prediction = self.model(inputs['input_ids'].to(self.device))[0].argmax().item()
+
+        if self.mapping:
+            prediction = self.mapping[str(prediction)]
+
+        logger.info("Model predicted: '%s'", prediction)
+        return [prediction]
+
+    def postprocess(self, inference_output):
+        return inference_output

community-content/pytorch_pre_built_images_deployment/predictor/index_to_name.json

@@ -0,0 +1,5 @@
+
+{
+    "0": "Negative", 
+    "1": "Positive"
+}

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

@@ -658,8 +658,8 @@
       },
       "outputs": [],
       "source": [
-        "datasets = load_dataset(\"imdb\")\n",
-        "datasets"
+        "dataset = load_dataset(\"imdb\")\n",
+        "dataset"
       ]
     },
     {
@@ -668,7 +668,7 @@
         "id": "RzfPtOMoIrIu"
       },
       "source": [
-        "The `datasets` object itself is [`DatasetDict`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasetdict), which contains one key for the training, validation and test set."
+        "The `dataset` object itself is [`DatasetDict`](https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasetdict), which contains one key for the training, validation and test set."
       ]
     },
     {
@@ -681,12 +681,12 @@
       "source": [
         "print(\n",
         "    \"Total # of rows in training dataset {} and size {:5.2f} MB\".format(\n",
-        "        datasets[\"train\"].shape[0], datasets[\"train\"].size_in_bytes / (1024 * 1024)\n",
+        "        dataset[\"train\"].shape[0], dataset[\"train\"].size_in_bytes / (1024 * 1024)\n",
         "    )\n",
         ")\n",
         "print(\n",
         "    \"Total # of rows in test dataset {} and size {:5.2f} MB\".format(\n",
-        "        datasets[\"test\"].shape[0], datasets[\"test\"].size_in_bytes / (1024 * 1024)\n",
+        "        dataset[\"test\"].shape[0], dataset[\"test\"].size_in_bytes / (1024 * 1024)\n",
         "    )\n",
         ")"
       ]
@@ -708,7 +708,7 @@
       },
       "outputs": [],
       "source": [
-        "datasets[\"train\"][0]"
+        "dataset[\"train\"][0]"
       ]
     },
     {
@@ -728,7 +728,7 @@
       },
       "outputs": [],
       "source": [
-        "label_list = datasets[\"train\"].unique(\"label\")\n",
+        "label_list = dataset[\"train\"].unique(\"label\")\n",
         "label_list"
       ]
     },
@@ -779,7 +779,7 @@
       },
       "outputs": [],
       "source": [
-        "show_random_elements(datasets[\"train\"])"
+        "show_random_elements(dataset[\"train\"])"
       ]
     },
     {
@@ -883,7 +883,7 @@
       },
       "outputs": [],
       "source": [
-        "example = datasets[\"train\"][4]\n",
+        "example = dataset[\"train\"][4]\n",
         "print(example)"
       ]
     },
@@ -920,7 +920,7 @@
       "source": [
         "# Dataset loading repeated here to make this cell idempotent\n",
         "# Since we are over-writing datasets variable\n",
-        "datasets = load_dataset(\"imdb\")\n",
+        "dataset = load_dataset(\"imdb\")\n",
         "\n",
         "# Mapping labels to ids\n",
         "# NOTE: We can extract this automatically but the `Unique` method of the datasets\n",
@@ -948,7 +948,7 @@
         "\n",
         "\n",
         "# apply preprocessing function to input examples\n",
-        "datasets = datasets.map(preprocess_function, batched=True, load_from_cache_file=True)"
+        "dataset = dataset.map(preprocess_function, batched=True, load_from_cache_file=True)"
       ]
     },
     {
@@ -1091,8 +1091,8 @@
         "trainer = Trainer(\n",
         "    model,\n",
         "    args,\n",
-        "    train_dataset=datasets[\"train\"],\n",
-        "    eval_dataset=datasets[\"test\"],\n",
+        "    train_dataset=dataset[\"train\"],\n",
+        "    eval_dataset=dataset[\"test\"],\n",
         "    data_collator=default_data_collator,\n",
         "    tokenizer=tokenizer,\n",
         "    compute_metrics=compute_metrics,\n",

notebooks/community/CODEOWNERS

@@ -17,6 +17,7 @@
 /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
+/matching_engine/stream_update_for_matching_engine.ipynb @peterping666
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
 /tensorboard @yfang1
 /feature_store @nayaknishant @morgandu
@@ -27,4 +28,6 @@
 /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/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb @inardini
+/notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb @inardini
+/notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb @fhirschmann
+/notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb @fhirschmann

notebooks/community/feature_store/gapic-feature-store.ipynb

@@ -292,6 +292,37 @@
         "    PROJECT_ID = \"python-docs-samples-tests\"  # @param {type:\"string\"}"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d9f118b92c74"
+      },
+      "source": [
+        "#### UUID\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 uuid 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": "3ee72715c0fd"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -478,7 +509,6 @@
         "from google.cloud.aiplatform_v1.types import \\\n",
         "    featurestore_service as featurestore_service_pb2\n",
         "from google.cloud.aiplatform_v1.types import io as io_pb2\n",
-        "from google.protobuf.duration_pb2 import Duration\n",
         "\n",
         "# Create admin_client for CRUD and data_client for reading feature values.\n",
         "admin_client = FeaturestoreServiceClient(client_options={\"api_endpoint\": API_ENDPOINT})\n",
@@ -542,7 +572,7 @@
       },
       "outputs": [],
       "source": [
-        "FEATURESTORE_ID = \"movie_prediction\"\n",
+        "FEATURESTORE_ID = f\"movie_prediction_{UUID}\"\n",
         "try:\n",
         "    create_lro = admin_client.create_featurestore(\n",
         "        featurestore_service_pb2.CreateFeaturestoreRequest(\n",
@@ -567,7 +597,7 @@
         "id": "ag8pCQ7rNjVf"
       },
       "source": [
-        "You can use [GetFeaturestore](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.GetFeaturestore) or [ListFeaturestores](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeaturestores) to check if the Featurestore was successfully created. The following example gets the details of the Featurestore.\n"
+        "You can use [GetFeaturestore](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.GetFeaturestore) or [ListFeaturestores](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.ListFeaturestores) to check if the Featurestore was successfully created. The following example gets the details of the Featurestore.\n"
       ]
     },
     {
@@ -589,7 +619,7 @@
         "id": "018ab19d934f"
       },
       "source": [
-        "Auto scaling is available in v1beta1 since v1.11. Below is the example for the `CreateFeaturestoreRequest` with auto-scaling, use it with `aiplatform_v1beta1.FeaturestoreServiceClient` to create Featurestore:"
+        "Auto scaling is available in v1 since v1.11. Below is the example for the `CreateFeaturestoreRequest` with auto-scaling, use it with `aiplatform_v1.FeaturestoreServiceClient` to create Featurestore:"
       ]
     },
     {
@@ -600,17 +630,17 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore as v1beta1_featurestore_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore as v1_featurestore_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "create_featurestore_request = v1beta1_featurestore_service_pb2.CreateFeaturestoreRequest(\n",
+        "create_featurestore_request = v1_featurestore_service_pb2.CreateFeaturestoreRequest(\n",
         "    parent=BASE_RESOURCE_PATH,\n",
         "    featurestore_id=FEATURESTORE_ID,\n",
-        "    featurestore=v1beta1_featurestore_pb2.Featurestore(\n",
-        "        online_serving_config=v1beta1_featurestore_pb2.Featurestore.OnlineServingConfig(\n",
-        "            scaling=v1beta1_featurestore_pb2.Featurestore.OnlineServingConfig.Scaling(\n",
+        "    featurestore=v1_featurestore_pb2.Featurestore(\n",
+        "        online_serving_config=v1_featurestore_pb2.Featurestore.OnlineServingConfig(\n",
+        "            scaling=v1_featurestore_pb2.Featurestore.OnlineServingConfig.Scaling(\n",
         "                min_node_count=1, max_node_count=5\n",
         "            )\n",
         "        ),\n",
@@ -681,7 +711,7 @@
         "id": "dPkT7KDuEvWv"
       },
       "source": [
-        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1beta1 Python. Import feature analysis is only available through SDK for now."
+        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1 Python. Import feature analysis is only available through SDK for now."
       ]
     },
     {
@@ -692,36 +722,35 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1 import \\\n",
-        "    FeaturestoreServiceClient as v1beta1_FeaturestoreServiceClient\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    entity_type as v1beta1_entity_type_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_monitoring as v1beta1_featurestore_monitoring_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1 import \\\n",
+        "    FeaturestoreServiceClient as v1_FeaturestoreServiceClient\n",
+        "from google.cloud.aiplatform_v1.types import entity_type as v1_entity_type_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_monitoring as v1_featurestore_monitoring_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "v1beta1_admin_client = v1beta1_FeaturestoreServiceClient(\n",
+        "v1_admin_client = v1_FeaturestoreServiceClient(\n",
         "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
         "# Enable import feature analysis for users entity type.\n",
         "# All Features belonging to this EntityType will by default inherit the monitoring config.\n",
-        "v1beta1_admin_client.update_entity_type(\n",
-        "    v1beta1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
-        "        entity_type=v1beta1_entity_type_pb2.EntityType(\n",
+        "v1_admin_client.update_entity_type(\n",
+        "    v1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
+        "        entity_type=v1_entity_type_pb2.EntityType(\n",
         "            name=admin_client.entity_type_path(\n",
         "                PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
         "            ),\n",
-        "            monitoring_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
-        "                import_features_analysis=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis(\n",
-        "                    anomaly_detection_baseline=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.Baseline.LATEST_STATS,\n",
-        "                    state=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.State.ENABLED,\n",
+        "            monitoring_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
+        "                import_features_analysis=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis(\n",
+        "                    anomaly_detection_baseline=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.Baseline.LATEST_STATS,\n",
+        "                    state=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ImportFeaturesAnalysis.State.ENABLED,\n",
         "                ),\n",
-        "                numerical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                numerical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
-        "                categorical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                categorical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
         "            ),\n",
@@ -736,7 +765,7 @@
         "id": "85b1f59fbf6d"
       },
       "source": [
-        "The easiest way to set up snapshot analysis for now is using [console UI](https://console.cloud.google.com/vertex-ai/features). For completeness, below is example to do this using v1beta1 SDK.\n",
+        "The easiest way to set up snapshot analysis for now is using [console UI](https://console.cloud.google.com/vertex-ai/features). For completeness, below is example to do this using v1 SDK.\n",
         "\n",
         "You can view monitoring statistics on [console UI](https://console.cloud.google.com/vertex-ai/features)."
       ]
@@ -749,36 +778,35 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud.aiplatform_v1beta1 import \\\n",
-        "    FeaturestoreServiceClient as v1beta1_FeaturestoreServiceClient\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    entity_type as v1beta1_entity_type_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_monitoring as v1beta1_featurestore_monitoring_pb2\n",
-        "from google.cloud.aiplatform_v1beta1.types import \\\n",
-        "    featurestore_service as v1beta1_featurestore_service_pb2\n",
+        "from google.cloud.aiplatform_v1 import \\\n",
+        "    FeaturestoreServiceClient as v1_FeaturestoreServiceClient\n",
+        "from google.cloud.aiplatform_v1.types import entity_type as v1_entity_type_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_monitoring as v1_featurestore_monitoring_pb2\n",
+        "from google.cloud.aiplatform_v1.types import \\\n",
+        "    featurestore_service as v1_featurestore_service_pb2\n",
         "\n",
-        "v1beta1_admin_client = v1beta1_FeaturestoreServiceClient(\n",
+        "v1_admin_client = v1_FeaturestoreServiceClient(\n",
         "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
         "# Enable snapshot analysis for users entity type.\n",
         "# All Features belonging to this EntityType will by default inherit the monitoring config.\n",
-        "v1beta1_admin_client.update_entity_type(\n",
-        "    v1beta1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
-        "        entity_type=v1beta1_entity_type_pb2.EntityType(\n",
+        "v1_admin_client.update_entity_type(\n",
+        "    v1_featurestore_service_pb2.UpdateEntityTypeRequest(\n",
+        "        entity_type=v1_entity_type_pb2.EntityType(\n",
         "            name=admin_client.entity_type_path(\n",
         "                PROJECT_ID, REGION, FEATURESTORE_ID, \"users\"\n",
         "            ),\n",
-        "            monitoring_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
-        "                snapshot_analysis=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.SnapshotAnalysis(\n",
-        "                    monitoring_interval=Duration(seconds=86400),  # 1 day\n",
+        "            monitoring_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig(\n",
+        "                snapshot_analysis=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.SnapshotAnalysis(\n",
+        "                    monitoring_interval_days=1,  # 1 day\n",
         "                    staleness_days=30,\n",
         "                ),\n",
-        "                numerical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                numerical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
-        "                categorical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                categorical_threshold_config=v1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
         "                    value=0.001,\n",
         "                ),\n",
         "            ),\n",
@@ -891,8 +919,8 @@
       "source": [
         "## Search created features\n",
         "\n",
-        "While the [ListFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.ListFeatures) method allows you to easily view all features of a single\n",
-        "entity type, the [SearchFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#google.cloud.aiplatform.v1beta1.FeaturestoreService.SearchFeatures) method searches across all featurestores\n",
+        "While the [ListFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.ListFeatures) method allows you to easily view all features of a single\n",
+        "entity type, the [SearchFeatures](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#google.cloud.aiplatform.v1.FeaturestoreService.SearchFeatures) method searches across all featurestores\n",
         "and entity types in a given location (such as `us-central1`). This can help you discover features that were created by someone else.\n",
         "\n",
         "You can query based on feature properties including feature ID, entity type ID,\n",
@@ -1206,7 +1234,7 @@
       },
       "source": [
         "The\n",
-        "[Online Serving APIs](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1beta1#featurestoreonlineservingservice)\n",
+        "[Online Serving APIs](https://cloud.google.com/vertex-ai/docs/reference/rpc/google.cloud.aiplatform.v1#featurestoreonlineservingservice)\n",
         "lets you serve feature values for small batches of entities. It's designed for latency-sensitive service, such as online model prediction. For example, for a movie service, you might want to quickly shows movies that the current user would most likely watch by using online predictions."
       ]
     },

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

@@ -1,823 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "d1cc1c1fa076"
-      },
-      "source": [
-        "# Pricing Optimization \n",
-        "## Table of contents\n",
-        "* [Overview](#section-1)\n",
-        "* [Dataset](#section-2)\n",
-        "* [Objective](#section-3)\n",
-        "* [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",
-        "* [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",
-        "## Overview\n",
-        "<a name=\"section-1\"></a>\n",
-        "\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",
-        "\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",
-        "\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 the best prices.\n",
-        "- Clean up.\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",
-        "- 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/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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5ed1f5e85640"
-      },
-      "source": [
-        "## 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,
-      "metadata": {
-        "id": "c3f30148b66d"
-      },
-      "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": "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\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2a1c270c7d34"
-      },
-      "source": [
-        "### Import the required libraries and define constants\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "acc6fac1fa55"
-      },
-      "outputs": [],
-      "source": [
-        "import matplotlib.pyplot as plt\n",
-        "import pandas as pd\n",
-        "import seaborn as sns\n",
-        "from google.cloud import bigquery\n",
-        "from google.cloud.bigquery import Client"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a06006dff8f9"
-      },
-      "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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "016c3d47cc69"
-      },
-      "source": [
-        "## Create a BigQuery dataset\n",
-        "<a name=\"section-5\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "12ccd8d7956e"
-      },
-      "source": [
-        "#@bigquery\n",
-        "-- create a dataset in BigQuery\n",
-        "\n",
-        "CREATE SCHEMA pricing_optimization\n",
-        "OPTIONS(\n",
-        "  location=\"us\"\n",
-        "  )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c106b978a79b"
-      },
-      "source": [
-        "## Load the dataset from Cloud Storage\n",
-        "<a name=\"section-6\"></a>\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "8aeae9da9796"
-      },
-      "outputs": [],
-      "source": [
-        "DATA_LOCATION = \"gs://cloud-samples-data/ai-platform-unified/datasets/tabular/cdm_pricing_large_table.csv\"\n",
-        "df = pd.read_csv(DATA_LOCATION)\n",
-        "print(df.shape)\n",
-        "df.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "7b98d5f09842"
-      },
-      "source": [
-        "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",
-        "- `List_Price_Converged`\n",
-        "- `Invoiced_quantity_in_Pieces`\n",
-        "- `Net_Sales`\n",
-        "\n",
-        "## Data Analysis\n",
-        "<a name=\"section-7\"></a>\n",
-        "\n",
-        "First, explore the data and distributions.\n",
-        "\n",
-        "Select the required columns from the dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "af4b41c5eb1f"
-      },
-      "outputs": [],
-      "source": [
-        "id_col = \"Product_ID\"\n",
-        "date_col = \"Fiscal_Date\"\n",
-        "categ_cols = [\"Customer_Hierarchy\"]\n",
-        "num_cols = [\"List_Price_Converged\", \"Invoiced_quantity_in_Pieces\", \"Net_Sales\"]\n",
-        "\n",
-        "df = df[[id_col, date_col] + categ_cols + num_cols].copy()\n",
-        "df.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3d780043ee5b"
-      },
-      "source": [
-        "Check the column types and null values in the dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f54c445a1288"
-      },
-      "outputs": [],
-      "source": [
-        "df.info()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cd817b414c4d"
-      },
-      "source": [
-        "This data description reveals that there are no null values in the data. Also, the field `Fiscal_Date` which is a date field is loaded as an object type. \n",
-        "\n",
-        "Change the type of the date field to datetime."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "b160fac085c8"
-      },
-      "outputs": [],
-      "source": [
-        "df[\"Fiscal_Date\"] = pd.to_datetime(df[\"Fiscal_Date\"], infer_datetime_format=True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fb4778578064"
-      },
-      "source": [
-        "Plot the distributions for the categorical fields."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "dd0467cd57c3"
-      },
-      "outputs": [],
-      "source": [
-        "for i in categ_cols:\n",
-        "    df[i].value_counts(normalize=True).plot(kind=\"bar\")\n",
-        "    plt.title(i)\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "145deed255e0"
-      },
-      "source": [
-        "Plot the distributions for the numerical fields."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f934137c6d82"
-      },
-      "outputs": [],
-      "source": [
-        "for i in num_cols:\n",
-        "    _, ax = plt.subplots(1, 2, figsize=(10, 4))\n",
-        "    df[i].plot(kind=\"box\", ax=ax[0])\n",
-        "    df[i].plot(kind=\"hist\", ax=ax[1])\n",
-        "    ax[0].set_title(i + \"-Boxplot\")\n",
-        "    ax[1].set_title(i + \"-Histogram\")\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f9b9c2e58380"
-      },
-      "source": [
-        "Check the maximum date and minimum date in Fiscal_Date column."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "2a10aa689f9d"
-      },
-      "outputs": [],
-      "source": [
-        "print(df[\"Fiscal_Date\"].max())\n",
-        "print(df[\"Fiscal_Date\"].min())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "4834f63e2e59"
-      },
-      "source": [
-        "Check the product distribution across each category."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4664877f5304"
-      },
-      "outputs": [],
-      "source": [
-        "grp_cols = [\"Customer_Hierarchy\", \"Product_ID\"]\n",
-        "grp_df = df[grp_cols].groupby(by=grp_cols).count().reset_index()\n",
-        "grp_df.groupby(\"Customer_Hierarchy\").nunique()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "01ed02b9c8fd"
-      },
-      "source": [
-        "Check the percentage changes in the orders based on the percentage changes in the price."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0b2c428cb135"
-      },
-      "outputs": [],
-      "source": [
-        "# aggregate the data\n",
-        "df_aggr = (\n",
-        "    df.groupby([\"Product_ID\", \"List_Price_Converged\"])\n",
-        "    .agg({\"Fiscal_Date\": min, \"Invoiced_quantity_in_Pieces\": sum, \"Net_Sales\": sum})\n",
-        "    .reset_index()\n",
-        ")\n",
-        "# rename the aggregated columns\n",
-        "df_aggr.rename(\n",
-        "    columns={\n",
-        "        \"Fiscal_Date\": \"First_price_date\",\n",
-        "        \"Invoiced_quantity_in_Pieces\": \"Total_ordered_pieces\",\n",
-        "        \"Net_Sales\": \"Total_net_sales\",\n",
-        "    },\n",
-        "    inplace=True,\n",
-        ")\n",
-        "\n",
-        "# sort values chronologically\n",
-        "df_aggr.sort_values(by=[\"Product_ID\", \"First_price_date\"], inplace=True)\n",
-        "df_aggr.reset_index(drop=True, inplace=True)\n",
-        "\n",
-        "# add columns for previous values\n",
-        "df_aggr[\"Previous_List\"] = df_aggr.groupby([\"Product_ID\"])[\n",
-        "    \"List_Price_Converged\"\n",
-        "].shift()\n",
-        "df_aggr[\"Previous_Total_ordered_pieces\"] = df_aggr.groupby([\"Product_ID\"])[\n",
-        "    \"Total_ordered_pieces\"\n",
-        "].shift()\n",
-        "\n",
-        "# average price change across sku's\n",
-        "df_aggr[\"price_change_perc\"] = (\n",
-        "    (df_aggr[\"List_Price_Converged\"] - df_aggr[\"Previous_List\"])\n",
-        "    / df_aggr[\"Previous_List\"].fillna(0)\n",
-        "    * 100\n",
-        ")\n",
-        "df_aggr[\"order_change_perc\"] = (\n",
-        "    (df_aggr[\"Total_ordered_pieces\"] - df_aggr[\"Previous_Total_ordered_pieces\"])\n",
-        "    / df_aggr[\"Previous_Total_ordered_pieces\"].fillna(0)\n",
-        "    * 100\n",
-        ")\n",
-        "\n",
-        "# plot a scatterplot to visualize the changes\n",
-        "sns.scatterplot(\n",
-        "    x=\"price_change_perc\",\n",
-        "    y=\"order_change_perc\",\n",
-        "    data=df_aggr,\n",
-        "    hue=\"Product_ID\",\n",
-        "    legend=False,\n",
-        ")\n",
-        "plt.title(\"Percentage of change in price vs order\")\n",
-        "plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8259e916fe25"
-      },
-      "source": [
-        "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. 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  have the maximum orders."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f5cbc7709c6a"
-      },
-      "outputs": [],
-      "source": [
-        "df_orders = df.groupby([\"Product_ID\", \"Customer_Hierarchy\"], as_index=False)[\n",
-        "    \"Invoiced_quantity_in_Pieces\"\n",
-        "].sum()\n",
-        "df_orders.loc[\n",
-        "    df_orders.groupby(\"Customer_Hierarchy\")[\"Invoiced_quantity_in_Pieces\"].idxmax()\n",
-        "]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fd6d227e513e"
-      },
-      "source": [
-        "From the above result, you can infer the following:\n",
-        "\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 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 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."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2dbc0d64d157"
-      },
-      "source": [
-        "Check the various prices available for these `Product_ID`s."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "acc1dbd2d838"
-      },
-      "outputs": [],
-      "source": [
-        "df_type_food = df[(df[\"Product_ID\"] == \"SKU 62\") & (df[\"Customer_Hierarchy\"] == \"Food\")]\n",
-        "print(\"Food :\")\n",
-        "print(df_type_food[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_manuf = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 17\") & (df[\"Customer_Hierarchy\"] == \"Manufacturing\")\n",
-        "]\n",
-        "print(\"Manufacturing :\")\n",
-        "print(df_type_manuf[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_paper = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 107\") & (df[\"Customer_Hierarchy\"] == \"Paper\")\n",
-        "]\n",
-        "print(\"Paper :\")\n",
-        "print(df_type_paper[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_pub = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 8\") & (df[\"Customer_Hierarchy\"] == \"Publishing\")\n",
-        "]\n",
-        "print(\"Publishing :\")\n",
-        "print(df_type_pub[\"List_Price_Converged\"].value_counts())\n",
-        "df_type_util = df[\n",
-        "    (df[\"Product_ID\"] == \"SKU 140\") & (df[\"Customer_Hierarchy\"] == \"Utilities\")\n",
-        "]\n",
-        "print(\"Utilities :\")\n",
-        "print(df_type_util[\"List_Price_Converged\"].value_counts())"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f023af578c0f"
-      },
-      "source": [
-        "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."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a44771cc4c20"
-      },
-      "outputs": [],
-      "source": [
-        "df_final = pd.concat([df_type_food, df_type_paper, df_type_util])\n",
-        "df_final = (\n",
-        "    df_final[\n",
-        "        [\n",
-        "            \"Product_ID\",\n",
-        "            \"Fiscal_Date\",\n",
-        "            \"Customer_Hierarchy\",\n",
-        "            \"List_Price_Converged\",\n",
-        "            \"Invoiced_quantity_in_Pieces\",\n",
-        "        ]\n",
-        "    ]\n",
-        "    .drop_duplicates()\n",
-        "    .reset_index(drop=True)\n",
-        ")\n",
-        "df_final.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "add5063df368"
-      },
-      "source": [
-        "Save the data to a BigQuery table."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fd82ba56571f"
-      },
-      "outputs": [],
-      "source": [
-        "bq_client = bigquery.Client(project=PROJECT_ID)\n",
-        "\n",
-        "job_config = bigquery.LoadJobConfig(\n",
-        "    # Specify a (partial) schema. All columns are always written to the\n",
-        "    # table. The schema is used to assist in data type definitions.\n",
-        "    schema=[\n",
-        "        bigquery.SchemaField(\"Product_ID\", bigquery.enums.SqlTypeNames.STRING),\n",
-        "        bigquery.SchemaField(\"Fiscal_Date\", bigquery.enums.SqlTypeNames.DATE),\n",
-        "        bigquery.SchemaField(\"List_Price_Converged\", bigquery.enums.SqlTypeNames.FLOAT),\n",
-        "        bigquery.SchemaField(\n",
-        "            \"Invoiced_quantity_in_Pieces\", bigquery.enums.SqlTypeNames.FLOAT\n",
-        "        ),\n",
-        "    ],\n",
-        "    # Optionally, set the write disposition. BigQuery appends loaded rows\n",
-        "    # to an existing table by default, but with WRITE_TRUNCATE write\n",
-        "    # disposition it replaces the table with the loaded data.\n",
-        "    write_disposition=\"WRITE_TRUNCATE\",\n",
-        ")\n",
-        "\n",
-        "# save the dataframe to a table in the created dataset\n",
-        "job = bq_client.load_table_from_dataframe(\n",
-        "    df_final,\n",
-        "    \"{}.{}.{}\".format(PROJECT_ID, DATASET, TRAINING_DATA_TABLE),\n",
-        "    job_config=job_config,\n",
-        ")  # Make an API request.\n",
-        "job.result()  # Wait for the job to complete."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fca77641b03b"
-      },
-      "source": [
-        "# Train the model using BigQuery ML\n",
-        "<a name=\"section-9\"></a>\n",
-        "\n",
-        "Train an [Arima-Plus](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series) model on the data using BigQuery ML."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cded27507891"
-      },
-      "source": [
-        "#@bigquery\n",
-        "create or replace model pricing_optimization.bqml_arima\n",
-        "options\n",
-        " (model_type = 'ARIMA_PLUS',\n",
-        "  time_series_timestamp_col = 'Fiscal_Date',\n",
-        "  time_series_data_col = 'Invoiced_quantity_in_Pieces',\n",
-        "  time_series_id_col = 'ID'\n",
-        " ) as\n",
-        "select\n",
-        " Fiscal_Date,\n",
-        " Concat(Product_ID,\"_\" ,Cast(List_Price_Converged as string)) as ID,\n",
-        " Invoiced_quantity_in_Pieces\n",
-        "from\n",
-        " pricing_optimization.TRAINING_DATA\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "332fd11ff32b"
-      },
-      "source": [
-        "## Generate forecasts from the model\n",
-        "<a name=\"section-10\"></a>\n",
-        "\n",
-        "Predict the sales for the next 30 days for each id and save to a dataframe."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ef926cdbf28e"
-      },
-      "outputs": [],
-      "source": [
-        "client = Client()\n",
-        "\n",
-        "query = '''\n",
-        "DECLARE HORIZON STRING DEFAULT \"30\"; #number of values to forecast\n",
-        "DECLARE CONFIDENCE_LEVEL STRING DEFAULT \"0.90\"; ## required confidence level\n",
-        "\n",
-        "EXECUTE IMMEDIATE format(\"\"\"\n",
-        "    SELECT\n",
-        "      *\n",
-        "    FROM \n",
-        "      ML.FORECAST(MODEL pricing_optimization.bqml_arima, \n",
-        "                  STRUCT(%s AS horizon, \n",
-        "                         %s AS confidence_level)\n",
-        "                 )\n",
-        "    \"\"\",HORIZON,CONFIDENCE_LEVEL)'''\n",
-        "job = client.query(query)\n",
-        "dfforecast = job.to_dataframe()\n",
-        "dfforecast.head()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "608c7de72dae"
-      },
-      "source": [
-        "## Interpret the results to choose the best price\n",
-        "<a name=\"section-11\"></a>\n",
-        "\n",
-        "Calculate average forecast values for the forecast duration."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "e1e193680400"
-      },
-      "outputs": [],
-      "source": [
-        "dfforecast_avg = (\n",
-        "    dfforecast[[\"ID\", \"forecast_value\"]].groupby(\"ID\", as_index=False).mean()\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "5ce395d652a3"
-      },
-      "source": [
-        "Extract the ID and Price fields from the ID field."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "452c56fa58ed"
-      },
-      "outputs": [],
-      "source": [
-        "dfforecast_avg[\"Product_ID\"] = dfforecast_avg[\"ID\"].apply(lambda x: x.split(\"_\")[0])\n",
-        "dfforecast_avg[\"Price\"] = dfforecast_avg[\"ID\"].apply(lambda x: x.split(\"_\")[1])"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3cee67f4028f"
-      },
-      "source": [
-        "Plot the average forecasted sales vs. the price of the product."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fb351c8f383d"
-      },
-      "outputs": [],
-      "source": [
-        "for i in dfforecast_avg[\"Product_ID\"].unique():\n",
-        "    dfforecast_avg[dfforecast_avg[\"Product_ID\"] == i].set_index(\"Price\").sort_values(\n",
-        "        \"forecast_value\"\n",
-        "    ).plot(kind=\"bar\")\n",
-        "    plt.title(\"Price vs. Average Sales for \" + i)\n",
-        "    plt.show()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "67ff3acc74a5"
-      },
-      "source": [
-        "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",
-        "\n",
-        "\n",
-        "## Clean Up\n",
-        "<a name=\"section-12\"></a>\n",
-        "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud 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. The following code deletes the entire dataset."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "d78908b8134d"
-      },
-      "outputs": [],
-      "source": [
-        "# Construct a BigQuery client object.\n",
-        "client = bigquery.Client()\n",
-        "\n",
-        "# TODO(developer): Set model_id to the ID of the model to fetch.\n",
-        "dataset_id = \"{PROJECT}.{DATASET}\".format(PROJECT=PROJECT_ID, DATASET=DATASET)\n",
-        "\n",
-        "# Use the delete_contents parameter to delete a dataset and its contents.\n",
-        "# Use the not_found_ok parameter to not receive an error if the dataset has already been deleted.\n",
-        "client.delete_dataset(\n",
-        "    dataset_id, delete_contents=True, not_found_ok=True\n",
-        ")  # Make an API request.\n",
-        "\n",
-        "print(\"Deleted dataset '{}'.\".format(dataset_id))"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "pricing-optimization.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb

@@ -212,7 +212,7 @@
         "\n",
         "3. [Enable the Vertex AI APIs and Compute Engine APIs.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component)\n",
         "\n",
-        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Google Cloud Notebooks.\n",
+        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Vertex AI Workbench Notebooks.\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",
@@ -374,15 +374,8 @@
         "### 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": "32e1cd21a5d5"
-      },
-      "source": [
+        "authenticated. \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",

notebooks/community/ml_ops/stage1/mlops_data_management.ipynb

@@ -39,18 +39,15 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\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",
-        "<br/><br/><br/>"
+        "<br/><br/><br/>\n",
+        "\n",
+        "*Note: This notebook is not supported for execution in Colab*"
       ]
     },
     {
@@ -169,21 +166,20 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "ONCE_ONLY = True\n",
+        "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\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 google-cloud-bigquery $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade apache-beam[gcp]==2.33.0 $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG -q\n",
-        "    ! pip3 install future $USER_FLAG -q"
+        "    ! pip3 install -U {USER_FLAG} -q tensorflow==2.5 \\\n",
+        "                                     tensorflow-data-validation==1.2 \\\n",
+        "                                     tensorflow-transform==1.2 \\\n",
+        "                                     tensorflow-io==0.18 \n",
+        "    \n",
+        "    ! pip3 install --upgrade {USER_FLAG} -q google-cloud-aiplatform[tensorboard] \\\n",
+        "                                            google-cloud-pipeline-components \\\n",
+        "                                            google-cloud-bigquery \\\n",
+        "                                            google-cloud-logging \\\n",
+        "                                            apache-beam[gcp] \\\n",
+        "                                            pyarrow \\\n",
+        "                                            cloudml-hypertune\n"
       ]
     },
     {
@@ -355,7 +351,7 @@
       "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",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. \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",
@@ -417,7 +413,7 @@
         "\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",
+        "When you submit a custom training job using the Vertex AI 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",

notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb

@@ -149,8 +149,8 @@
       "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",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook.  \n",
         "\n",
         "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
         "You need the following:\n",

notebooks/community/ml_ops/stage2/get_started_vertex_training_lightgbm.ipynb

@@ -138,7 +138,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb

@@ -128,7 +128,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
         "all the requirements to run this notebook. You can skip this step."
       ]
     },

notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb

@@ -127,7 +127,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "**If you are using Colab or Vertex AI Workbench 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",

notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb

@@ -62,7 +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 Vizier."
+        "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 Vizier."
       ]
     },
     {
@@ -84,7 +84,8 @@
         "The steps performed include:\n",
         "\n",
         "- Hyperparameter tuning with Random algorithm.\n",
-        "- Hyperparameter tuning with Vizier (Bayesian) algorithm."
+        "- Hyperparameter tuning with Vizier (Bayesian) algorithm.\n",
+        "- Suggesting trials and updating results for Vizier study"
       ]
     },
     {
@@ -187,7 +188,8 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q"
+        "! pip3 install --upgrade $USER_FLAG -q google-cloud-aiplatform \\\n",
+        "                                       google-vizier==0.0.4"
       ]
     },
     {
@@ -329,25 +331,32 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "timestamp"
+        "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid 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": "timestamp"
+        "id": "4e166d927e36"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -358,7 +367,7 @@
       "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",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. \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",
@@ -446,7 +455,7 @@
       "outputs": [],
       "source": [
         "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID"
       ]
     },
     {
@@ -509,7 +518,8 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aip\n",
+        "from google.cloud.aiplatform.vizier import Study, pyvizier"
       ]
     },
     {
@@ -534,35 +544,6 @@
         "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "aip_constants"
-      },
-      "source": [
-        "#### Vertex AI constants\n",
-        "\n",
-        "Setup up the following constants for Vertex AI:\n",
-        "\n",
-        "- `API_ENDPOINT`: The Vertex AI API service endpoint for `Dataset`, `Model`, `Job`, `Pipeline` and `Endpoint` services.\n",
-        "- `PARENT`: The Vertex AI location root path for `Dataset`, `Model`, `Job`, `Pipeline` and `Endpoint` resources."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "aip_constants"
-      },
-      "outputs": [],
-      "source": [
-        "# API service endpoint\n",
-        "API_ENDPOINT = \"{}-aiplatform.googleapis.com\".format(REGION)\n",
-        "\n",
-        "# Vertex location root path for your dataset, model and endpoint resources\n",
-        "PARENT = \"projects/\" + PROJECT_ID + \"/locations/\" + REGION"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -626,7 +607,7 @@
         "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",
@@ -1031,7 +1012,7 @@
       },
       "outputs": [],
       "source": [
-        "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
+        "JOB_NAME = \"custom_job_\" + UUID\n",
         "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
@@ -1094,9 +1075,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP, worker_pool_specs=worker_pool_spec\n",
-        ")"
+        "job = aip.CustomJob(display_name=\"boston_\" + UUID, worker_pool_specs=worker_pool_spec)"
       ]
     },
     {
@@ -1128,7 +1107,7 @@
         "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
         "\n",
         "hpt_job = aip.HyperparameterTuningJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    custom_job=job,\n",
         "    metric_spec={\n",
         "        \"val_loss\": \"minimize\",\n",
@@ -1309,7 +1288,7 @@
       "outputs": [],
       "source": [
         "job = aip.CustomJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    worker_pool_specs=worker_pool_spec,\n",
         "    base_output_dir=MODEL_DIR,\n",
         ")"
@@ -1344,7 +1323,7 @@
         "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
         "\n",
         "hpt_job = aip.HyperparameterTuningJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    custom_job=job,\n",
         "    metric_spec={\n",
         "        \"val_loss\": \"minimize\",\n",
@@ -1513,22 +1492,25 @@
         "id": "vizier_client"
       },
       "source": [
-        "### Create Vizier client\n",
+        "### Specify the algorithm used to suggest trial parameters\n",
         "\n",
-        "Create a client side connection to the Vertex AI Vizier service."
+        "First, you create a `StudyConfig`, and specify the algorithm to suggest the next trial.\n",
+        "\n",
+        "    GRID_SEARCH: grid search\n",
+        "    RANDOM_SEARCH: random search\n",
+        "    ALGORIGTHM_UNSPECIFIED: Vizier bayesian algorithm"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "vizier_client"
+        "id": "d7dd26490358"
       },
       "outputs": [],
       "source": [
-        "vizier_client = aip.gapic.VizierServiceClient(\n",
-        "    client_options=dict(api_endpoint=API_ENDPOINT)\n",
-        ")"
+        "problem = pyvizier.StudyConfig()\n",
+        "problem.algorithm = pyvizier.Algorithm.RANDOM_SEARCH"
       ]
     },
     {
@@ -1543,7 +1525,15 @@
         "\n",
         "In the following example, the goal is to maximize y = x^2 with x in the range of \\[-10. 10\\]. This example has only one parameter and uses an easily calculated function to help demonstrate how to use Vizier.\n",
         "\n",
-        "First, you will create the study using the `create_study()` method."
+        "First, you specify the metrics to minimize or maximize in the study as a list to the property `metric_information`. Then you specify the parameters to the study using the `add_XXX_params()` method for the corresponding data type:\n",
+        "\n",
+        "    - add_bool_param\n",
+        "    - add_categorical_param\n",
+        "    - add_discrete_param\n",
+        "    - add_float_param\n",
+        "    - add_int_param\n",
+        "\n",
+        "You create the study using the `create_or_load()` method."
       ]
     },
     {
@@ -1554,28 +1544,19 @@
       },
       "outputs": [],
       "source": [
-        "STUDY_DISPLAY_NAME = \"xpow2\" + TIMESTAMP\n",
+        "STUDY_DISPLAY_NAME = \"xpow2\" + UUID\n",
         "\n",
-        "param_x = {\n",
-        "    \"parameter_id\": \"x\",\n",
-        "    \"double_value_spec\": {\"min_value\": -10.0, \"max_value\": 10.0},\n",
-        "}\n",
+        "problem.metric_information.append(\n",
+        "    pyvizier.MetricInformation(name=\"y\", goal=pyvizier.ObjectiveMetricGoal.MAXIMIZE)\n",
+        ")\n",
         "\n",
-        "metric_y = {\"metric_id\": \"y\", \"goal\": \"MAXIMIZE\"}\n",
+        "params = problem.search_space.select_root()\n",
+        "params.add_float_param(\"x\", -10.0, 10.0, scale_type=pyvizier.ScaleType.LINEAR)\n",
         "\n",
-        "study = {\n",
-        "    \"display_name\": STUDY_DISPLAY_NAME,\n",
-        "    \"study_spec\": {\n",
-        "        \"algorithm\": \"RANDOM_SEARCH\",\n",
-        "        \"parameters\": [param_x],\n",
-        "        \"metrics\": [metric_y],\n",
-        "    },\n",
-        "}\n",
+        "study = Study.create_or_load(display_name=STUDY_DISPLAY_NAME, problem=problem)\n",
         "\n",
-        "study = vizier_client.create_study(parent=PARENT, study=study)\n",
         "STUDY_NAME = study.name\n",
-        "\n",
-        "print(STUDY_NAME)"
+        "print(\"STUDY_NAME: {}\".format(STUDY_NAME))"
       ]
     },
     {
@@ -1586,9 +1567,7 @@
       "source": [
         "### Get Vizier study\n",
         "\n",
-        "You can get a study using the method `get_study()`, with the following key/value pairs:\n",
-        "\n",
-        "- `name`: The name of the study."
+        "You can get a study using the method `list()`."
       ]
     },
     {
@@ -1599,9 +1578,8 @@
       },
       "outputs": [],
       "source": [
-        "study = vizier_client.get_study({\"name\": STUDY_NAME})\n",
-        "\n",
-        "print(study)"
+        "studies = Study.list()\n",
+        "print(studies[0].gca_resource)"
       ]
     },
     {
@@ -1612,11 +1590,9 @@
       "source": [
         "### Get suggested trial\n",
         "\n",
-        "Next, query the Vizier service for a suggested trial(s) using the method `suggest_trials`, with the following key/value pairs:\n",
+        "Next, query the Vizier service for a suggested trial(s) using the method `suggest()`, with the following key/value pairs:\n",
         "\n",
-        "- `parent`: The name of the study.\n",
-        "- `suggestion_count`: The number of trials to suggest.\n",
-        "- `client_id`: blah\n",
+        "- `count`: The number of trials to suggest.\n",
         "\n",
         "This call is a long running operation. The method `result()` from the response object will wait until the call has completed."
       ]
@@ -1625,18 +1601,13 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "vizier_suggest_trial"
+        "id": "11ff2c4562cb"
       },
       "outputs": [],
       "source": [
         "SUGGEST_COUNT = 1\n",
-        "CLIENT_ID = \"1001\"\n",
         "\n",
-        "response = vizier_client.suggest_trials(\n",
-        "    {\"parent\": STUDY_NAME, \"suggestion_count\": SUGGEST_COUNT, \"client_id\": CLIENT_ID}\n",
-        ")\n",
-        "\n",
-        "trials = response.result().trials\n",
+        "trials = study.suggest(count=SUGGEST_COUNT)\n",
         "\n",
         "print(trials)\n",
         "\n",
@@ -1679,12 +1650,10 @@
       "source": [
         "RESULT = 0.01\n",
         "\n",
-        "vizier_client.add_trial_measurement(\n",
-        "    {\n",
-        "        \"trial_name\": TRIAL_ID,\n",
-        "        \"measurement\": {\"metrics\": [{\"metric_id\": \"y\", \"value\": RESULT}]},\n",
-        "    }\n",
-        ")"
+        "measurement = pyvizier.Measurement()\n",
+        "measurement.metrics[\"y\"] = RESULT\n",
+        "\n",
+        "trials[0].add_measurement(measurement)"
       ]
     },
     {
@@ -1695,7 +1664,7 @@
       "source": [
         "### Delete the Vizier study\n",
         "\n",
-        "The method 'delete_study()' will delete the study."
+        "The method 'delete()' will delete the study."
       ]
     },
     {
@@ -1706,7 +1675,7 @@
       },
       "outputs": [],
       "source": [
-        "vizier_client.delete_study({\"name\": STUDY_NAME})"
+        "study.delete()"
       ]
     },
     {

notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb

@@ -151,7 +151,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "If you are using Colab or Vertex AI Workbench Notebooks, your environment already meets all the requirements to run this notebook.  \n",
         "\n",
         "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",

notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb

@@ -39,18 +39,15 @@
         "    </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/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",
-        "<br/><br/><br/>"
+        "<br/><br/><br/>\n",
+        "\n",
+        "*Note: This notebook is not supported for execution in Colab*"
       ]
     },
     {
@@ -216,20 +213,18 @@
         "\n",
         "ONCE_ONLY = False\n",
         "if ONCE_ONLY:\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 google-cloud-bigquery $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade google-cloud-logging $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade apache-beam[gcp] $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade pyarrow $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade cloudml-hypertune $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade kfp $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade torchvision $USER_FLAG -q\n",
-        "    ! pip3 install --upgrade rpy2 $USER_FLAG -q"
+        "    ! pip3 install -U {USER_FLAG} -q tensorflow==2.5 \\\n",
+        "                                     tensorflow-data-validation==1.2 \\\n",
+        "                                     tensorflow-transform==1.2 \\\n",
+        "                                     tensorflow-io==0.18 \n",
+        "    \n",
+        "    ! pip3 install --upgrade {USER_FLAG} -q google-cloud-aiplatform[tensorboard] \\\n",
+        "                                            google-cloud-pipeline-components \\\n",
+        "                                            google-cloud-bigquery \\\n",
+        "                                            google-cloud-logging \\\n",
+        "                                            apache-beam[gcp] \\\n",
+        "                                            pyarrow \\\n",
+        "                                            cloudml-hypertune"
       ]
     },
     {
@@ -444,12 +439,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
-        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",

notebooks/community/ml_ops/stage3/get_started_with_rapid_prototyping_bqml_automl.ipynb

@@ -204,7 +204,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "If you are using Colab or Vertex AI Workbench Notebooks, your environment already meets all the requirements to run this notebook.  \n",
         "\n",
         "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",

notebooks/community/ml_ops/stage5/get_started_with_vertex_endpoints.ipynb

@@ -340,7 +340,7 @@
       "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",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. \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",
@@ -376,12 +376,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
-        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -428,8 +427,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"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}\""
       ]
     },
     {
@@ -785,7 +785,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint.gca_resource"
+        "print(endpoint.gca_resource)"
       ]
     },
     {
@@ -908,7 +908,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint.gca_resource.deployed_models[0]"
+        "print(endpoint.gca_resource.deployed_models[0])"
       ]
     },
     {
@@ -1203,12 +1203,10 @@
         "\n",
         "In this pipeline, you create an `Endpoint` resource, and then you deploy a `Model` resource to the `Endpoint` resource. The `Model` resource  to deploy is your existing TFHub model which you previously imported as a `Model` resource. The steps are:\n",
         "\n",
-        "- For pipeline parameters, pass the resource name and resource URI for the existing `Model` resource.\n",
-        "- Use the `importer_node()` component to create a `VertexModel` pipeline artifact for the model.\n",
+        "- For pipeline parameters, pass the resource name for the existing `Model` resource.\n",
+        "- Use the `GetVertexModelOp()` component to create a `VertexModel` pipeline artifact for the model.\n",
         "- Create an `Endpoint` resource.\n",
-        "- Using the `VertexModel` pipeline artifact, deploy the `Model` resource to the `Endpoint` resource.\n",
-        "\n",
-        "*Note:* This example currently blocked by internal issue: b/219835305"
+        "- Using the `VertexModel` pipeline artifact, deploy the `Model` resource to the `Endpoint` resource."
       ]
     },
     {
@@ -1225,20 +1223,6 @@
         "\n",
         "PIPELINE_ROOT = \"{}/pipeline_root/endpoint_example\".format(BUCKET_URI)\n",
         "\n",
-        "# (WORKAROUND  b/219835305)\n",
-        "@component(\n",
-        "    base_image=\"python:3.9\",\n",
-        "    packages_to_install=[\"google-cloud-aiplatform\"],\n",
-        ")\n",
-        "def return_unmanaged_model(\n",
-        "    serving_image: str, artifact_uri: str, resource_name: str, model: Output[Artifact]\n",
-        "):\n",
-        "    model.metadata[\"containerSpec\"] = {\"imageUri\": serving_image}\n",
-        "\n",
-        "    model.metadata[\"resourceName\"] = resource_name\n",
-        "\n",
-        "    model.uri = artifact_uri\n",
-        "\n",
         "\n",
         "@dsl.pipeline(\n",
         "    name=\"create-endpoint-deploy-model\",\n",
@@ -1246,34 +1230,16 @@
         ")\n",
         "def pipeline(\n",
         "    display_name: str,\n",
-        "    resource_uri: str,\n",
         "    resource_name: str,\n",
-        "    # Model properties (WORKAROUND  b/219835305)\n",
-        "    serving_image: str,\n",
-        "    artifact_uri: str,\n",
         "    project: str = PROJECT_ID,\n",
         "    region: str = REGION,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.types import artifact_types\n",
+        "    from google_cloud_pipeline_components.experimental.evaluation import \\\n",
+        "        GetVertexModelOp\n",
         "    from google_cloud_pipeline_components.v1.endpoint import (EndpointCreateOp,\n",
         "                                                              ModelDeployOp)\n",
-        "    from kfp.v2.components import importer_node\n",
         "\n",
-        "    # Desired sequence: blocked by b/219835305\n",
-        "    \"\"\"\n",
-        "    model = importer_node.importer(\n",
-        "        artifact_uri=resource_uri,\n",
-        "        artifact_class=artifact_types.VertexModel,\n",
-        "        metadata={\"resourceName\": resource_name},\n",
-        "    )\n",
-        "    \"\"\"\n",
-        "\n",
-        "    # (WORKAROUND  b/219835305)\n",
-        "    model = return_unmanaged_model(\n",
-        "        serving_image=serving_image,\n",
-        "        artifact_uri=artifact_uri,\n",
-        "        resource_name=resource_name,\n",
-        "    )\n",
+        "    model = GetVertexModelOp(model_resource_name=resource_name)\n",
         "\n",
         "    endpoint_op = EndpointCreateOp(\n",
         "        project=project,\n",
@@ -1281,7 +1247,7 @@
         "        display_name=display_name,\n",
         "    )\n",
         "\n",
-        "    deploy_op = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=model.outputs[\"model\"],\n",
         "        endpoint=endpoint_op.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1310,7 +1276,6 @@
         "\n",
         "- `display_name`: The display name for the generated Vertex AI resources.\n",
         "- `resource_name`: The resource name of the existing `Model` resource.\n",
-        "- `resource_uri`: The resource uri of the existing `Model` resource.\n",
         "- `project`: The project ID.\n",
         "- `region`: The region."
       ]
@@ -1323,10 +1288,6 @@
       },
       "outputs": [],
       "source": [
-        "# Model properties (WORKAROUND  b/219835305)\n",
-        "SERVING_CONTAINER_URI = model.gca_resource.container_spec.image_uri\n",
-        "ARTIFACT_URI = model.gca_resource.artifact_uri\n",
-        "\n",
         "try:\n",
         "    pipeline = aip.PipelineJob(\n",
         "        display_name=\"create-endpoint-deploy-pipeline\",\n",
@@ -1335,11 +1296,6 @@
         "        parameter_values={\n",
         "            \"display_name\": \"create_endpoint_and_deploy_model_\" + TIMESTAMP,\n",
         "            \"resource_name\": model.resource_name,\n",
-        "            \"resource_uri\": \"https://us-central1-aiplatform.googleapis.com/v1/\"\n",
-        "            + model.resource_name,\n",
-        "            # Model properties (WORKAROUND  b/219835305)\n",
-        "            \"serving_image\": SERVING_CONTAINER_URI,\n",
-        "            \"artifact_uri\": ARTIFACT_URI,\n",
         "            \"project\": PROJECT_ID,\n",
         "            \"region\": REGION,\n",
         "        },\n",
@@ -1488,7 +1444,7 @@
         "\n",
         "- For pipeline parameters, pass the resource names and resource URIs for the existing `Model` and `Endpoint` resource.\n",
         "- Use the `importer_node()` component to create a `VertexModel` pipeline artifact for the model.\n",
-        "- Use the `importer_node()` component to create a `VertexEndpoint` pipeline artifact for the endpoint.\n",
+        "- Use the `GetVertexModelOp()` component to create a `VertexModel` pipeline artifact for the model.\n",
         "- Using the `VertexModel` and `VertexEndpoint` pipeline artifacts, deploy the `Model` resource to the `Endpoint` resource.\n",
         "\n",
         "*Note:* This example currently blocked by internal issue: b/219835305"
@@ -1504,6 +1460,7 @@
       "source": [
         "PIPELINE_ROOT = \"{}/pipeline_root/endpoint_example_2\".format(BUCKET_URI)\n",
         "\n",
+        "\n",
         "# (WORKAROUND  b/219835305)\n",
         "@component(\n",
         "    base_image=\"python:3.9\",\n",
@@ -1520,35 +1477,23 @@
         ")\n",
         "def pipeline(\n",
         "    display_name: str,\n",
-        "    model_resource_uri: str,\n",
         "    model_resource_name: str,\n",
         "    endpoint_resource_uri: str,\n",
         "    endpoint_resource_name: str,\n",
-        "    # Model properties (WORKAROUND  b/219835305)\n",
-        "    serving_image: str,\n",
-        "    artifact_uri: str,\n",
         "    project: str = PROJECT_ID,\n",
         "    region: str = REGION,\n",
         "):\n",
-        "    from google_cloud_pipeline_components.types import artifact_types\n",
+        "    from google_cloud_pipeline_components.experimental.evaluation import \\\n",
+        "        GetVertexModelOp\n",
         "    from google_cloud_pipeline_components.v1.endpoint import ModelDeployOp\n",
-        "    from kfp.v2.components import importer_node\n",
         "\n",
         "    # Desired sequence: blocked by b/219835305\n",
         "    \"\"\"\n",
-        "    model = importer_node.importer(\n",
-        "        artifact_uri=resource_uri,\n",
-        "        artifact_class=artifact_types.VertexModel,\n",
-        "        metadata={\"resourceName\": resource_name},\n",
-        "    )\n",
+        "    from kfp.v2.components import importer_node\n",
+        "    from google_cloud_pipeline_components.types import artifact_types\n",
         "    \"\"\"\n",
         "\n",
-        "    # (WORKAROUND  b/219835305)\n",
-        "    model = return_unmanaged_model(\n",
-        "        serving_image=serving_image,\n",
-        "        artifact_uri=artifact_uri,\n",
-        "        resource_name=model_resource_name,\n",
-        "    )\n",
+        "    model = GetVertexModelOp(model_resource_name=model_resource_name)\n",
         "\n",
         "    # Desired sequence: blocked by b/219835305\n",
         "    \"\"\"\n",
@@ -1562,7 +1507,7 @@
         "    # (WORKAROUND  b/219835305)\n",
         "    endpoint = return_unmanaged_endpoint(resource_name=endpoint_resource_name)\n",
         "\n",
-        "    deploy_op = ModelDeployOp(\n",
+        "    _ = ModelDeployOp(\n",
         "        model=model.outputs[\"model\"],\n",
         "        endpoint=endpoint.outputs[\"endpoint\"],\n",
         "        dedicated_resources_min_replica_count=1,\n",
@@ -1591,7 +1536,6 @@
         "\n",
         "- `display_name`: The display name for the generated Vertex AI resources.\n",
         "- `model_resource_name`: The resource name of the existing `Model` resource.\n",
-        "- `model_resource_uri`: The resource uri of the existing `Model` resource.\n",
         "- `endpoint_resource_name`: The resource name of the existing `Endpoint` resource.\n",
         "- `endpoint_resource_uri`: The resource uri of the existing `Endpoint` resource.\n",
         "- `project`: The project ID.\n",
@@ -1614,14 +1558,9 @@
         "        parameter_values={\n",
         "            \"display_name\": \"deploy_model_existing_endpoint_\" + TIMESTAMP,\n",
         "            \"model_resource_name\": model.resource_name,\n",
-        "            \"model_resource_uri\": \"https://us-central1-aiplatform.googleapis.com/v1/\"\n",
-        "            + model.resource_name,\n",
         "            \"endpoint_resource_name\": endpoint.resource_name,\n",
         "            \"endpoint_resource_uri\": \"https://us-central1-aiplatform.googleapis.com/v1/\"\n",
         "            + endpoint.resource_name,\n",
-        "            # Model properties (WORKAROUND  b/219835305)\n",
-        "            \"serving_image\": SERVING_CONTAINER_URI,\n",
-        "            \"artifact_uri\": ARTIFACT_URI,\n",
         "            \"project\": PROJECT_ID,\n",
         "            \"region\": REGION,\n",
         "        },\n",

notebooks/community/ml_ops/stage5/get_started_with_vertex_private_endpoints.ipynb

@@ -385,12 +385,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\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",
-        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -1068,7 +1067,6 @@
         "- `model`: The `Model` resource.\n",
         "- `deployed_model_displayed_name`: The human readable name for the deployed model instance.\n",
         "- `machine_type`: The machine type for each VM instance.\n",
-        "- `traffic_split`: Set to `{}` to indicate no traffic split.\n",
         "\n",
         "Do to the requirements to provision the resource, this may take upto a few minutes."
       ]
@@ -1085,7 +1083,6 @@
         "    model=model,\n",
         "    deployed_model_display_name=\"example_\" + TIMESTAMP,\n",
         "    machine_type=DEPLOY_COMPUTE,\n",
-        "    traffic_split={},  # no traffic split\n",
         ")\n",
         "\n",
         "print(endpoint)"
@@ -1187,62 +1184,6 @@
         "    f.write(json.dumps({\"instances\": [{serving_input: {\"b64\": b64str}}]}))"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "23e995c35fd6"
-      },
-      "source": [
-        "#### Construct the `Private Endpoint` URI\n",
-        "\n",
-        "Next, you construct the URI for the `Private Endpoint`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "97b248b2efb5"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint_id = endpoint.resource_name\n",
-        "\n",
-        "ENDPOINT_URL = ! gcloud beta ai endpoints describe {endpoint_id} \\\n",
-        "  --region={REGION} \\\n",
-        "  --format=\"value(deployedModels.privateEndpoints.predictHttpUri)\"\n",
-        "\n",
-        "private_url = ENDPOINT_URL[1]\n",
-        "print(private_url)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "27605b5f0c3a"
-      },
-      "source": [
-        "### Make the prediction request using curl\n",
-        "\n",
-        "Use `curl` to make the prediction request to the private URI."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6cb568e6bb49"
-      },
-      "outputs": [],
-      "source": [
-        "output = ! curl -X POST -d@instances.json $private_url\n",
-        "\n",
-        "predictions = output[5]\n",
-        "print(predictions)\n",
-        "\n",
-        "! rm test.jpg instances.json"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1251,7 +1192,7 @@
       "source": [
         "### Make the prediction request using SDK\n",
         "\n",
-        "Finally, use the `Vertex AI SDK` to make a prediction request."
+        "Next, use the `Vertex AI SDK` to make a prediction request."
       ]
     },
     {

notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb

@@ -1,879 +0,0 @@
-{
-  "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": "title:generic,gcp"
-      },
-      "source": [
-        "# E2E ML on GCP: MLOps stage 6 : serving: get started with re-importing AutoML tabular models\n",
-        "\n",
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.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://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.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/stage6/get_started_automl_tabular_exported_deploy.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": "overview:mlops"
-      },
-      "source": [
-        "## 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 AutoML Training."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "objective:mlops,stage2,get_started_automl_training"
-      },
-      "source": [
-        "### Objective\n",
-        "\n",
-        "In this tutorial, you learn how to use `AutoML Tabular` for re-importing exported model artifacts as a `Model` resource. This is useful for example, if one wants to move the exported model across projects.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services:\n",
-        "\n",
-        "- `AutoML Tabular`\n",
-        "- `Vertex AI Model` resource\n",
-        "- `Vertex AI Prediction`\n",
-        "\n",
-        "The steps performed include:\n",
-        "\n",
-        "- Importing a pretrained AutoML tabular exported model artifacts, as a `Model` resource.\n",
-        "- Create an `Endpoint` resource.\n",
-        "- Deploy the `Model` resource to the `Endpoint` resource.\n",
-        "- Make a prediction."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:flowers,icn"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "This tutorial uses a pretrained AutoML tabular model with exported model artifacts.\n",
-        "\n",
-        "\n",
-        "The tabular dataset used for the pretrained model 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).\n",
-        "\n",
-        "*Note:* This version of the exported model contains the custom op and requires the model server: us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server"
-      ]
-    },
-    {
-      "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."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_mlops"
-      },
-      "source": [
-        "## Installations\n",
-        "\n",
-        "Install the packages required for executing this notebook."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_mlops"
-      },
-      "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",
-        "# Install the packages\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
-        "! pip3 install --upgrade google-cloud-storage {USER_FLAG} -q"
-      ]
-    },
-    {
-      "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"
-      },
-      "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": "project_id"
-      },
-      "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 $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "56d591439df1"
-      },
-      "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": "set_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "region"
-      },
-      "source": [
-        "#### Region\n",
-        "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "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": "region"
-      },
-      "outputs": [],
-      "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "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 the timestamp onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "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 = \"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": "bucket:mbsdk"
-      },
-      "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 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."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "bucket"
-      },
-      "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": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "create_bucket"
-      },
-      "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": "create_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil mb -l $REGION $BUCKET_URI"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
-    {
-      "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"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aiplatform"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "init_aip:mbsdk"
-      },
-      "source": [
-        "### Initialize Vertex AI SDK for Python\n",
-        "\n",
-        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "init_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "machine:training"
-      },
-      "source": [
-        "#### Set machine type\n",
-        "\n",
-        "Next, set the machine type to use for training.\n",
-        "\n",
-        "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training.\n",
-        " - `machine type`\n",
-        "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
-        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
-        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
-        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
-        "\n",
-        "*Note: The following is not supported for training:*\n",
-        "\n",
-        " - `standard`: 2 vCPUs\n",
-        " - `highcpu`: 2, 4 and 8 vCPUs\n",
-        "\n",
-        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "machine:training"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING_DEPLOY_MACHINE\"):\n",
-        "    MACHINE_TYPE = os.getenv(\"IS_TESTING_DEPLOY_MACHINE\")\n",
-        "else:\n",
-        "    MACHINE_TYPE = \"n1-standard\"\n",
-        "\n",
-        "VCPU = \"4\"\n",
-        "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
-        "print(\"Train machine type\", DEPLOY_COMPUTE)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_file:u_dataset,csv"
-      },
-      "source": [
-        "### Location of pretrained `AutoML Tabular` exported model\n",
-        "\n",
-        "Now set the variable `MODEL_PACKAGE` to the location of the exported model artifacts in Cloud Storage."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:flowers,csv,icn"
-      },
-      "outputs": [],
-      "source": [
-        "MODEL_PACKAGE = \"gs://cloud-samples-data/vertex-ai/tabular-workflows/models/custom_op\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "quick_peek:csv"
-      },
-      "source": [
-        "#### Quick peek at your model package.\n",
-        "\n",
-        "Next, take a look at the contents of the model package for the exported AutoML tabular model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "quick_peek:csv"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls {MODEL_PACKAGE}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "automl_tabular_intro"
-      },
-      "source": [
-        "## AutoML tabular models\n",
-        "\n",
-        "AutoML can train the following types of tabular models:\n",
-        "\n",
-        "- classification\n",
-        "- regression\n",
-        "- forecasting\n",
-        "\n",
-        "A model can be trained for either automatic deployment to the cloud or exported for manual deployment to the cloud. In this tutorial, you use a pretrained exported AutoML tabular model.\n",
-        "\n",
-        "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)\n",
-        "\n",
-        "Learn more about [Exporting AutoML Tabular models](https://cloud.google.com/vertex-ai/docs/export/export-model-tabular)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c10efb34321b"
-      },
-      "source": [
-        "### Set the model server\n",
-        "\n",
-        "Next, you set the pre-built container for the model server. The container will be a version of `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server`. If the model package contains an `environment.json` file, use the container version specified by the key `container_uri`; otherwise, use `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server:latest` "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a5f271de9040"
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "output = !gsutil cat {MODEL_PACKAGE}/environment.json\n",
-        "\n",
-        "MODEL_SERVER = json.loads(output[0])[\"container_uri\"]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e8ce91147c93"
-      },
-      "source": [
-        "### Upload the pretrained exported `AutoML Tabular` model package to a `Vertex AI Model` resource\n",
-        "\n",
-        "Next, you upload the model artifacts for the pretrained exported `AutoML Tabular` model into a `Vertex AI Model` resource, using the `Model.upload()` method with the following parameters:\n",
-        "\n",
-        "- `display_name`: A human readable name for the `Model` resource.\n",
-        "- `artifact_uri`: The Cloud Storage location of the model package.\n",
-        "- `serving_container_image_uri`: The serving container image.\n",
-        "- `serving_container_ports`: The serving port.\n",
-        "\n",
-        "*Note:* When you upload the model artifacts to a `Vertex Model` resource, you specify the corresponding deployment container image."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "7988eae27f80"
-      },
-      "outputs": [],
-      "source": [
-        "model = aiplatform.Model.upload(\n",
-        "    display_name=\"gsod_\" + TIMESTAMP,\n",
-        "    artifact_uri=MODEL_PACKAGE,\n",
-        "    serving_container_image_uri=MODEL_SERVER,\n",
-        "    serving_container_ports=[8080],\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "628de0914ba1"
-      },
-      "source": [
-        "## Creating an `Endpoint` resource\n",
-        "\n",
-        "You create an `Endpoint` resource using the `Endpoint.create()` method. At a minimum, you specify the display name for the endpoint. Optionally, you can specify the project and location (region); otherwise the settings are inherited by the values you set when you initialized the Vertex AI SDK with the `init()` method.\n",
-        "\n",
-        "In this example, the following parameters are specified:\n",
-        "\n",
-        "- `display_name`: A human readable name for the `Endpoint` resource.\n",
-        "- `project`: Your project ID.\n",
-        "- `location`: Your region.\n",
-        "- `labels`: (optional) User defined metadata for the `Endpoint` in the form of key/value pairs.\n",
-        "\n",
-        "This method returns an `Endpoint` object.\n",
-        "\n",
-        "Learn more about [Vertex AI Endpoints](https://cloud.google.com/vertex-ai/docs/predictions/deploy-model-api)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0ea443f9593b"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint = aiplatform.Endpoint.create(\n",
-        "    display_name=\"gsod_\" + TIMESTAMP,\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    labels={\"your_key\": \"your_value\"},\n",
-        ")\n",
-        "\n",
-        "print(endpoint)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ca3fa3f6a894"
-      },
-      "source": [
-        "## Deploying `Model` resources to an `Endpoint` resource.\n",
-        "\n",
-        "You can deploy one of more `Vertex AI Model` resource instances to the same endpoint. Each `Vertex AI Model` resource that is deployed will have its own deployment container for the serving binary. \n",
-        "\n",
-        "*Note:* For this example, you specified the deployment container for the exported AutoML Tabular model in the previous step of uploading the model artifacts to a `Vertex AI Model` resource.\n",
-        "\n",
-        "To deploy, you specify the following additional configuration settings:\n",
-        "\n",
-        "- The machine type.\n",
-        "- The (if any) type and number of GPUs.\n",
-        "- Static, manual or auto-scaling of VM instances.\n",
-        "\n",
-        "In this example, you deploy the model with the minimal amount of specified parameters, as follows:\n",
-        "\n",
-        "- `model`: The `Model` resource.\n",
-        "- `deployed_model_displayed_name`: The human readable name for the deployed model instance.\n",
-        "- `machine_type`: The machine type for each VM instance.\n",
-        "\n",
-        "Do to the requirements to provision the resource, this may take upto a few minutes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4e93b034a72f"
-      },
-      "outputs": [],
-      "source": [
-        "response = endpoint.deploy(\n",
-        "    model=model,\n",
-        "    deployed_model_display_name=\"gsod_\" + TIMESTAMP,\n",
-        "    machine_type=DEPLOY_COMPUTE,\n",
-        ")\n",
-        "\n",
-        "print(response)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f75331c946d5"
-      },
-      "source": [
-        "## Make a prediction\n",
-        "\n",
-        "Finally, you make an online prediction using the `endpoint()` method, with the following parameters:\n",
-        "\n",
-        "- `instances`: The instances to predict.\n",
-        "\n",
-        "The following is the for a prediction request:\n",
-        "\n",
-        "    [ INSTANCE_1, INSTANCE_2, ... ]\n",
-        "    \n",
-        "    INSTANCE : { \"column_1\": value, \"column_2\": value, ... }\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "72683bd9d777"
-      },
-      "outputs": [],
-      "source": [
-        "INSTANCES = [{\"year\": \"2020\", \"month\": \"1\", \"day\": \"23\"}]\n",
-        "\n",
-        "prediction = endpoint.predict(instances=INSTANCES)\n",
-        "print(prediction)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "endpoint_delete:mbsdk"
-      },
-      "source": [
-        "#### Delete the endpoint\n",
-        "\n",
-        "The method 'delete()' will delete the endpoint."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "endpoint_delete:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint.undeploy_all()\n",
-        "endpoint.delete()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "model_delete:mbsdk"
-      },
-      "source": [
-        "#### Delete the model\n",
-        "\n",
-        "The method 'delete()' will delete the model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "model_delete:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "model.delete()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cleanup"
-      },
-      "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.\n",
-        "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cleanup"
-      },
-      "outputs": [],
-      "source": [
-        "# Set this to true only if you'd like to delete your bucket\n",
-        "delete_bucket = False\n",
-        "\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil rm -r $BUCKET_URI"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "get_started_automl_tabular_exported_deploy.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.ipynb

@@ -0,0 +1,898 @@
+{
+ "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": "title:generic,gcp"
+   },
+   "source": [
+    "# E2E ML on GCP: MLOps stage 6 : serving: get started with re-importing AutoML tabular models\n",
+    "\n",
+    "<table align=\"left\">\n",
+    "  <td>\n",
+    "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.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://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_with_tabular_exported_deploy.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/stage6/get_started_automl_with_tabular_exported_deploy.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": "overview:mlops"
+   },
+   "source": [
+    "## 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 AutoML Training."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "objective:mlops,stage2,get_started_automl_training"
+   },
+   "source": [
+    "### Objective\n",
+    "\n",
+    "In this tutorial, you learn how to use `AutoML Tabular` for re-importing exported model artifacts as a `Model` resource. This is useful for example, if one wants to move the exported model across projects.\n",
+    "\n",
+    "This tutorial uses the following Google Cloud ML services:\n",
+    "\n",
+    "- `AutoML Tabular`\n",
+    "- `Vertex AI Model` resource\n",
+    "- `Vertex AI Prediction`\n",
+    "\n",
+    "The steps performed include:\n",
+    "\n",
+    "- Importing a pretrained AutoML tabular exported model artifacts, as a `Model` resource.\n",
+    "- Create an `Endpoint` resource.\n",
+    "- Deploy the `Model` resource to the `Endpoint` resource.\n",
+    "- Make a prediction."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dataset:flowers,icn"
+   },
+   "source": [
+    "### Dataset\n",
+    "\n",
+    "This tutorial uses a pretrained AutoML tabular model with exported model artifacts.\n",
+    "\n",
+    "\n",
+    "The tabular dataset used for the pretrained model 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).\n",
+    "\n",
+    "*Note:* This version of the exported model contains the custom op and requires the model server: us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server"
+   ]
+  },
+  {
+   "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."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "install_mlops"
+   },
+   "source": [
+    "## Installations\n",
+    "\n",
+    "Install the packages required for executing this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "install_mlops"
+   },
+   "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",
+    "# Install the packages\n",
+    "\n",
+    "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+    "! pip3 install --upgrade google-cloud-storage {USER_FLAG} -q"
+   ]
+  },
+  {
+   "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"
+   },
+   "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": "project_id"
+   },
+   "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 $300 free credit towards your compute/storage costs.\n",
+    "\n",
+    "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+    "\n",
+    "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
+    "\n",
+    "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+    "\n",
+    "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+    "Cloud SDK uses the right project for all the commands in this notebook.\n",
+    "\n",
+    "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "56d591439df1"
+   },
+   "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": "set_project_id"
+   },
+   "outputs": [],
+   "source": [
+    "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "autoset_project_id"
+   },
+   "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"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "region"
+   },
+   "source": [
+    "#### Region\n",
+    "\n",
+    "You can also change the `REGION` variable, which is used for operations\n",
+    "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": "region"
+   },
+   "outputs": [],
+   "source": [
+    "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+    "\n",
+    "if REGION == \"[your-region]\":\n",
+    "    REGION = \"us-central1\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "timestamp"
+   },
+   "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 the timestamp onto the name of resources you create in this tutorial."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "timestamp"
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "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 = \"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": "bucket:mbsdk"
+   },
+   "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 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."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "bucket"
+   },
+   "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": "autoset_bucket"
+   },
+   "outputs": [],
+   "source": [
+    "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"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "create_bucket"
+   },
+   "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": "create_bucket"
+   },
+   "outputs": [],
+   "source": [
+    "! gsutil mb -l $REGION $BUCKET_URI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "validate_bucket"
+   },
+   "source": [
+    "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "validate_bucket"
+   },
+   "outputs": [],
+   "source": [
+    "! gsutil ls -al $BUCKET_URI"
+   ]
+  },
+  {
+   "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"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "import_aip:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "import google.cloud.aiplatform as aiplatform"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "init_aip:mbsdk"
+   },
+   "source": [
+    "### Initialize Vertex AI SDK for Python\n",
+    "\n",
+    "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "init_aip:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "machine:training"
+   },
+   "source": [
+    "#### Set machine type\n",
+    "\n",
+    "Next, set the machine type to use for training.\n",
+    "\n",
+    "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training.\n",
+    " - `machine type`\n",
+    "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
+    "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+    "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+    " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+    "\n",
+    "*Note: The following is not supported for training:*\n",
+    "\n",
+    " - `standard`: 2 vCPUs\n",
+    " - `highcpu`: 2, 4 and 8 vCPUs\n",
+    "\n",
+    "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "machine:training"
+   },
+   "outputs": [],
+   "source": [
+    "if os.getenv(\"IS_TESTING_DEPLOY_MACHINE\"):\n",
+    "    MACHINE_TYPE = os.getenv(\"IS_TESTING_DEPLOY_MACHINE\")\n",
+    "else:\n",
+    "    MACHINE_TYPE = \"n1-standard\"\n",
+    "\n",
+    "VCPU = \"4\"\n",
+    "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+    "print(\"Train machine type\", DEPLOY_COMPUTE)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "import_file:u_dataset,csv"
+   },
+   "source": [
+    "### Location of pretrained `AutoML Tabular` exported model\n",
+    "\n",
+    "Now set the variable `MODEL_PACKAGE` to the location of the exported model artifacts in Cloud Storage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "import_file:flowers,csv,icn"
+   },
+   "outputs": [],
+   "source": [
+    "MODEL_PACKAGE = \"gs://cloud-samples-data/vertex-ai/tabular-workflows/models/custom_op\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "quick_peek:csv"
+   },
+   "source": [
+    "#### Quick peek at your model package.\n",
+    "\n",
+    "Next, take a look at the contents of the model package for the exported AutoML tabular model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "quick_peek:csv"
+   },
+   "outputs": [],
+   "source": [
+    "! gsutil ls {MODEL_PACKAGE}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "automl_tabular_intro"
+   },
+   "source": [
+    "## AutoML tabular models\n",
+    "\n",
+    "AutoML can train the following types of tabular models:\n",
+    "\n",
+    "- classification\n",
+    "- regression\n",
+    "- forecasting\n",
+    "\n",
+    "A model can be trained for either automatic deployment to the cloud or exported for manual deployment to the cloud. In this tutorial, you use a pretrained exported AutoML tabular model.\n",
+    "\n",
+    "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)\n",
+    "\n",
+    "Learn more about [Exporting AutoML Tabular models](https://cloud.google.com/vertex-ai/docs/export/export-model-tabular)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "c10efb34321b"
+   },
+   "source": [
+    "### Set the model server\n",
+    "\n",
+    "Next, you set the pre-built container for the model server. The container will be a version of `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server`. If the model package contains an `environment.json` file, use the container version specified by the key `container_uri`; otherwise, use `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server:latest` "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "a5f271de9040"
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "output = !gsutil cat {MODEL_PACKAGE}/environment.json\n",
+    "\n",
+    "MODEL_SERVER = json.loads(output[0])[\"container_uri\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "e8ce91147c93"
+   },
+   "source": [
+    "### Upload the pretrained exported `AutoML Tabular` model package to a `Vertex AI Model` resource\n",
+    "\n",
+    "Next, you upload the model artifacts for the pretrained exported `AutoML Tabular` model into a `Vertex AI Model` resource, using the `Model.upload()` method with the following parameters:\n",
+    "\n",
+    "- `display_name`: A human readable name for the `Model` resource.\n",
+    "- `artifact_uri`: The Cloud Storage location of the model package.\n",
+    "- `serving_container_image_uri`: The serving container image.\n",
+    "- `serving_container_ports`: The serving port.\n",
+    "\n",
+    "*Note:* When you upload the model artifacts to a `Vertex Model` resource, you specify the corresponding deployment container image."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7988eae27f80"
+   },
+   "outputs": [],
+   "source": [
+    "model = aiplatform.Model.upload(\n",
+    "    display_name=\"gsod_\" + TIMESTAMP,\n",
+    "    artifact_uri=MODEL_PACKAGE,\n",
+    "    serving_container_image_uri=MODEL_SERVER,\n",
+    "    serving_container_ports=[8080],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "628de0914ba1"
+   },
+   "source": [
+    "## Creating an `Endpoint` resource\n",
+    "\n",
+    "You create an `Endpoint` resource using the `Endpoint.create()` method. At a minimum, you specify the display name for the endpoint. Optionally, you can specify the project and location (region); otherwise the settings are inherited by the values you set when you initialized the Vertex AI SDK with the `init()` method.\n",
+    "\n",
+    "In this example, the following parameters are specified:\n",
+    "\n",
+    "- `display_name`: A human readable name for the `Endpoint` resource.\n",
+    "- `project`: Your project ID.\n",
+    "- `location`: Your region.\n",
+    "- `labels`: (optional) User defined metadata for the `Endpoint` in the form of key/value pairs.\n",
+    "\n",
+    "This method returns an `Endpoint` object.\n",
+    "\n",
+    "Learn more about [Vertex AI Endpoints](https://cloud.google.com/vertex-ai/docs/predictions/deploy-model-api)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "0ea443f9593b"
+   },
+   "outputs": [],
+   "source": [
+    "endpoint = aiplatform.Endpoint.create(\n",
+    "    display_name=\"gsod_\" + TIMESTAMP,\n",
+    "    project=PROJECT_ID,\n",
+    "    location=REGION,\n",
+    "    labels={\"your_key\": \"your_value\"},\n",
+    ")\n",
+    "\n",
+    "print(endpoint)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ca3fa3f6a894"
+   },
+   "source": [
+    "## Deploying `Model` resources to an `Endpoint` resource.\n",
+    "\n",
+    "You can deploy one of more `Vertex AI Model` resource instances to the same endpoint. Each `Vertex AI Model` resource that is deployed will have its own deployment container for the serving binary. \n",
+    "\n",
+    "*Note:* For this example, you specified the deployment container for the exported AutoML Tabular model in the previous step of uploading the model artifacts to a `Vertex AI Model` resource.\n",
+    "\n",
+    "To deploy, you specify the following additional configuration settings:\n",
+    "\n",
+    "- The machine type.\n",
+    "- The (if any) type and number of GPUs.\n",
+    "- Static, manual or auto-scaling of VM instances.\n",
+    "\n",
+    "In this example, you deploy the model with the minimal amount of specified parameters, as follows:\n",
+    "\n",
+    "- `model`: The `Model` resource.\n",
+    "- `deployed_model_displayed_name`: The human readable name for the deployed model instance.\n",
+    "- `machine_type`: The machine type for each VM instance.\n",
+    "\n",
+    "Do to the requirements to provision the resource, this may take upto a few minutes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "4e93b034a72f"
+   },
+   "outputs": [],
+   "source": [
+    "response = endpoint.deploy(\n",
+    "    model=model,\n",
+    "    deployed_model_display_name=\"gsod_\" + TIMESTAMP,\n",
+    "    machine_type=DEPLOY_COMPUTE,\n",
+    ")\n",
+    "\n",
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "f75331c946d5"
+   },
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "Finally, you make an online prediction using the `endpoint()` method, with the following parameters:\n",
+    "\n",
+    "- `instances`: The instances to predict.\n",
+    "\n",
+    "The following is the for a prediction request:\n",
+    "\n",
+    "    [ INSTANCE_1, INSTANCE_2, ... ]\n",
+    "    \n",
+    "    INSTANCE : { \"column_1\": value, \"column_2\": value, ... }\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "72683bd9d777"
+   },
+   "outputs": [],
+   "source": [
+    "INSTANCES = [{\"year\": \"2020\", \"month\": \"1\", \"day\": \"23\"}]\n",
+    "\n",
+    "prediction = endpoint.predict(instances=INSTANCES)\n",
+    "print(prediction)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "endpoint_delete:mbsdk"
+   },
+   "source": [
+    "#### Delete the endpoint\n",
+    "\n",
+    "The method 'delete()' will delete the endpoint."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "endpoint_delete:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "endpoint.undeploy_all()\n",
+    "endpoint.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "model_delete:mbsdk"
+   },
+   "source": [
+    "#### Delete the model\n",
+    "\n",
+    "The method 'delete()' will delete the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "model_delete:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "model.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "cleanup"
+   },
+   "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.\n",
+    "\n",
+    "Otherwise, you can delete the individual resources you created in this tutorial.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "cleanup"
+   },
+   "outputs": [],
+   "source": [
+    "# Set this to true only if you'd like to delete your bucket\n",
+    "delete_bucket = False\n",
+    "\n",
+    "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+    "    ! gsutil rm -r $BUCKET_URI"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "name": "get_started_automl_tabular_exported_deploy.ipynb",
+   "toc_visible": true
+  },
+  "environment": {
+   "kernel": "python3",
+   "name": "common-cpu.m95",
+   "type": "gcloud",
+   "uri": "gcr.io/deeplearning-platform-release/base-cpu:m95"
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/community/ml_ops/stage6/get_started_with_cpr.ipynb

@@ -169,15 +169,6 @@
         "scikit-learn~=0.24"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "faf22f3af1ce"
-      },
-      "source": [
-        "**The model you deploy will have a different set of dependencies pre-installed than your notebook environment has. You should not assume that because things work in the notebook, they will work in the model. Instead, you will be very explicit about the dependencies for the model by listing them in requirements.txt and then use `pip install` to install the exact same dependencies in the notebook. Please note, of course, that there is a chance that a dependency is missed in requirements.txt that already exists in the notebook. If that's the case, things will run in the notebook, but not in the model. To guard against that, you will test the model locally before deploying to the cloud.**"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,

notebooks/community/ml_ops/stage6/get_started_with_matching_engine_swivel.ipynb

@@ -143,7 +143,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
         "all the requirements to run this notebook. You can skip this step."
       ]
     },
@@ -424,7 +424,7 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
+        "authenticated. "
       ]
     },
     {
@@ -1068,7 +1068,7 @@
         "model = aiplatform.Model.upload(\n",
         "    display_name=\"movies_\" + TIMESTAMP,\n",
         "    artifact_uri=SAVEDMODEL_DIR,\n",
-        "    serving_container_image_uri=DELOY_IMAGE,\n",
+        "    serving_container_image_uri=DEPLOY_IMAGE,\n",
         ")"
       ]
     },
@@ -1355,8 +1355,6 @@
       "source": [
         "QUERY_EMBEDDING_PATH = f\"{BUCKET_URI}/embeddings/train.jsonl\"\n",
         "\n",
-        "import tensorflow as tf\n",
-        "\n",
         "with tf.io.gfile.GFile(QUERY_EMBEDDING_PATH, \"w\") as f:\n",
         "    for i in range(1, 200001):\n",
         "        query = str(i)\n",
@@ -1417,7 +1415,7 @@
         "MAX_NODES = 4\n",
         "\n",
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=f\"batch_predict_swivel\",\n",
+        "    job_display_name=\"batch_predict_swivel\",\n",
         "    gcs_source=[QUERY_EMBEDDING_PATH],\n",
         "    gcs_destination_prefix=f\"{BUCKET_URI}/embeddings/output\",\n",
         "    machine_type=DEPLOY_COMPUTE,\n",

notebooks/community/ml_ops/stage6/get_started_with_matching_engine_twotowers.ipynb

@@ -142,7 +142,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
         "all the requirements to run this notebook. You can skip this step."
       ]
     },
@@ -422,7 +422,7 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
+        "authenticated. "
       ]
     },
     {

notebooks/community/ml_ops/stage6/get_started_with_tf_serving.ipynb

@@ -702,7 +702,7 @@
         "        + f\"/{PRIVATE_REPO}\"\n",
         "        + \"/tf_serving:gpu\"\n",
         "    )\n",
-        "    TF_IMAGE = \"tensorflow/serving:latest-gpu\"\n",
+        "    TF_IMAGE = \"tensorflow/serving:2.5.4-gpu\"\n",
         "else:\n",
         "    DEPLOY_IMAGE = (\n",
         "        f\"{REGION}-docker.pkg.dev/\"\n",
@@ -710,15 +710,15 @@
         "        + f\"/{PRIVATE_REPO}\"\n",
         "        + \"/tf_serving:cpu\"\n",
         "    )\n",
-        "    TF_IMAGE = \"tensorflow/serving:latest\"\n",
+        "    TF_IMAGE = \"tensorflow/serving:2.5.4\"\n",
         "\n",
         "if not IS_COLAB:\n",
         "    if DEPLOY_GPU:\n",
-        "        ! sudo docker pull tensorflow/serving:latest-gpu\n",
+        "        ! sudo docker pull tensorflow/serving:2.5.4-gpu\n",
         "    else:\n",
-        "        ! sudo docker pull tensorflow/serving:latest\n",
+        "        ! sudo docker pull tensorflow/serving:2.5.4\n",
         "\n",
-        "    ! docker tag tensorflow/serving $DEPLOY_IMAGE\n",
+        "    ! docker tag $TF_IMAGE $DEPLOY_IMAGE\n",
         "    ! docker push $DEPLOY_IMAGE\n",
         "else:\n",
         "    # install docker daemon\n",
@@ -1214,6 +1214,20 @@
         "     [1.0,3.0,\"cat1\"],\n",
         "     [2.0,4.0,\"cat2\"]\n",
         "    ]}\n",
+        "    \n",
+        "**BigQuery**\n",
+        "\n",
+        "Each row is converted to a JSON array. For example:\n",
+        "\n",
+        "    [1.0,3.0,\"cat1\"]\n",
+        "    [2.0,4.0,\"cat2\"]\n",
+        "    \n",
+        "The batch server generates the pivot data with the same format. The generated pivot data is then wrapped into a payload request:\n",
+        "\n",
+        "    {\"instances\": [\n",
+        "     [1.0,3.0,\"cat1\"],\n",
+        "     [2.0,4.0,\"cat2\"]\n",
+        "    ]}\n",
         "\n",
         "**TFRecords**\n",
         "\n",
@@ -1420,7 +1434,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = False\n",
+        "delete_bucket = True\n",
         "delete_model = True\n",
         "delete_endpoint = True\n",
         "delete_batch_job = True\n",

notebooks/community/ml_ops/stage6/get_started_with_xai_and_custom_server.ipynb

@@ -134,7 +134,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
         "all the requirements to run this notebook. You can skip this step."
       ]
     },
@@ -395,7 +395,7 @@
       "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",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. \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",

notebooks/community/model_monitoring/batch_prediction_model_monitoring.ipynb

@@ -3,7 +3,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "d3069d95",
       "metadata": {
         "cellView": "form",
         "id": "d3069d95"
@@ -11,7 +10,7 @@
       "outputs": [],
       "source": [
         "# @title Copyright & License (click to expand)\n",
-        "# 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",
@@ -28,7 +27,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "546c53de",
       "metadata": {
         "id": "546c53de"
       },
@@ -46,13 +44,16 @@
         "        <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><td>\n",
+        "    <a href=\"https://console.cloud.google.com/ai-platform/notebooks/deploy-notebook?name=Model%20Monitoring&download_url=https%3A%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fcommunity%2Fmodel_monitoring%2Fbatch_prediction_model_monitoring.ipynb\">\n",
+        "       <img src=\"https://www.gstatic.com/cloud/images/navigation/vertex-ai.svg\" alt=\"Google Cloud Notebooks\">Open in Workbench AI Notebook\n",
+        "    </a>\n",
+        "  </td> \n",
         "</table>"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "53fd1070",
       "metadata": {
         "id": "53fd1070"
       },
@@ -64,7 +65,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "8b26c855",
       "metadata": {
         "id": "8b26c855"
       },
@@ -98,7 +98,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d52ba95b",
       "metadata": {
         "id": "d52ba95b"
       },
@@ -110,7 +109,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "e64fb18a",
       "metadata": {
         "id": "e64fb18a"
       },
@@ -123,7 +121,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "9d839347",
       "metadata": {
         "id": "9d839347"
       },
@@ -142,7 +139,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "738fce1f",
       "metadata": {
         "id": "738fce1f"
       },
@@ -155,7 +151,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "4536fe4e",
       "metadata": {
         "id": "4536fe4e"
       },
@@ -178,14 +173,13 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "# Install Python package dependencies.\n",
-        "! pip3 install -q tensorflow-data-validation $USER_FLAG\n",
-        "! pip3 install -q google-api-core $USER_FLAG\n",
-        "! pip3 install -q google-cloud-aiplatform $USER_FLAG"
+        "! pip3 install -q {USER_FLAG} tensorflow-data-validation \\\n",
+        "                              google-api-core \\\n",
+        "                              google-cloud-aiplatform"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "6e98402b",
       "metadata": {
         "id": "6e98402b"
       },
@@ -198,7 +192,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "9775c9ff",
       "metadata": {
         "id": "9775c9ff"
       },
@@ -217,13 +210,16 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d5737134",
       "metadata": {
         "id": "d5737134"
       },
       "source": [
         "### Set up your Google Cloud project\n",
         "\n",
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.7\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",
@@ -242,7 +238,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "cfb1a1d5",
       "metadata": {
         "id": "cfb1a1d5"
       },
@@ -255,50 +250,33 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cf8535e4",
       "metadata": {
         "id": "cf8535e4"
       },
       "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",
-      "id": "05a2d397",
-      "metadata": {
-        "id": "05a2d397"
-      },
-      "source": [
-        "Otherwise, set your project ID here.\n"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "1c2be4bd",
       "metadata": {
         "id": "1c2be4bd"
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"python-docs-samples-tests\"  # @param {type:\"string\"}"
+        "if PROJECT_ID == \"\" or not PROJECT_ID or PROJECT_ID == \"[your-project-id]\":\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\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,
-      "id": "c129705c",
       "metadata": {
         "id": "c129705c"
       },
@@ -309,32 +287,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "71404c9f",
-      "metadata": {
-        "id": "71404c9f"
-      },
-      "source": [
-        "#### Set your email address\n",
-        "This is used for delivering model monitoring notifications.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "4b1d2b69",
-      "metadata": {
-        "id": "4b1d2b69"
-      },
-      "outputs": [],
-      "source": [
-        "EMAIL_ADDRESS = \"[your-email-address]\"  # @param {type:\"string\"}\n",
-        "if not EMAIL_ADDRESS or EMAIL_ADDRESS == \"[your-email-address]\":\n",
-        "    print(\"EMAIL_ADDRESS not specified, please correct before proceeding.\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "83340af4",
       "metadata": {
         "id": "83340af4"
       },
@@ -356,18 +308,73 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "4814ea21",
       "metadata": {
         "id": "4814ea21"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "06571eb4063b"
+      },
+      "source": [
+        "#### UUID\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 uuid 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": "4e166d927e36"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "71404c9f"
+      },
+      "source": [
+        "#### Set your email address\n",
+        "This is used for delivering model monitoring notifications.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4b1d2b69"
+      },
+      "outputs": [],
+      "source": [
+        "EMAIL_ADDRESS = \"[your-email-address]\"  # @param {type:\"string\"}\n",
+        "if not EMAIL_ADDRESS or EMAIL_ADDRESS == \"[your-email-address]\":\n",
+        "    print(\"EMAIL_ADDRESS not specified, please correct before proceeding.\")"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "20a546c3",
       "metadata": {
         "id": "20a546c3"
       },
@@ -375,16 +382,35 @@
         "### 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",
+        "authenticated.\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"
+        "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,
-      "id": "06c51076",
       "metadata": {
         "id": "06c51076"
       },
@@ -421,73 +447,284 @@
     },
     {
       "cell_type": "markdown",
-      "id": "6b01af18",
       "metadata": {
-        "id": "6b01af18"
+        "id": "bucket:custom"
       },
       "source": [
-        "### Upload the model\n",
+        "### Create a Cloud Storage bucket\n",
         "\n",
-        "The churn propensity model you'll be using in this notebook has been trained in BigQuery ML and exported to a Google Cloud Storage bucket. This illustrates how you can easily export a trained model and move a model from one cloud service to another. \n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "Next, import the model. **If you've already imported your model, you can skip this step.**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "9638ad2c",
-      "metadata": {
-        "id": "9638ad2c"
-      },
-      "source": [
-        "<span id=\"papermill-error-cell\" style=\"color:red; font-family:Helvetica Neue, Helvetica, Arial, sans-serif; font-size:2em;\">Execution using papermill encountered an exception here and stopped:</span>"
+        "Set the name of your Cloud Storage bucket below, which you use in this tutorial to upload the `input schema` for the monitoring service.\n",
+        "\n",
+        "Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "926e3ba8",
       "metadata": {
-        "id": "926e3ba8"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
-        "import json\n",
-        "import time\n",
-        "import re\n",
-        "import tensorflow as tf\n",
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "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": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a0d294ff6d10"
+      },
+      "source": [
+        "### Import libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bd7a633296eb"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
         "import tensorflow_data_validation as tfdv\n",
-        "from tensorflow_data_validation.utils import io_util \n",
-        "from tensorflow_metadata.proto.v0 import statistics_pb2\n",
-        "\n",
-        "MODEL_DISPLAY_NAME=f\"batch_prediction_monitoring_test_model_{datetime.now().strftime('%Y%m%d%H%M%S')}\"\n",
-        "CONTAINER_IMAGE_URI=\"us-docker.pkg.dev/cloud-aiplatform/prediction/tf2-cpu.2-4:latest\"\n",
-        "ARTIFACT_URI=\"gs://mco-mm/churn\"\n",
-        "\n",
-        "output = ! gcloud ai models upload \\\n",
-        "  --region=$REGION \\\n",
-        "  --display-name=$MODEL_DISPLAY_NAME \\\n",
-        "  --artifact-uri=$ARTIFACT_URI \\\n",
-        "  --container-image-uri=$CONTAINER_IMAGE_URI \\\n",
-        "  --format=\"value(model)\"\n",
-        "MODEL_ID = output[1].split(\"/\")[5]\n",
-        "print(f\"Model {MODEL_ID} created.\")"
+        "from tensorflow_data_validation.utils import io_util\n",
+        "from tensorflow_metadata.proto.v0 import statistics_pb2"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "accelerators:training,prediction"
+      },
+      "source": [
+        "#### Set hardware accelerators\n",
+        "\n",
+        "You can set hardware accelerators for prediction (e.g., GPUs) or choose not to use any (CPU). Hardware accelertors lower the latency response for a prediction request. When choosing a hardware accelerators, consider the additional cost trade-off over latency.\n",
+        "\n",
+        "Set the variables `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 Tesla K80 GPUs allocated to each VM, you would specify:\n",
+        "\n",
+        "    (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "\n",
+        "See the [locations where accelerators are available](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators).\n",
+        "\n",
+        "Otherwise specify `(None, None)` to use a container image to run on a CPU."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xd5PLXDTlugv"
+      },
+      "outputs": [],
+      "source": [
+        "GPU = False\n",
+        "if GPU:\n",
+        "    DEPLOY_GPU, DEPLOY_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "else:\n",
+        "    DEPLOY_GPU, DEPLOY_NGPU = (None, None)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "container:training,prediction"
+      },
+      "source": [
+        "#### Set pre-built containers\n",
+        "\n",
+        "Set the pre-built Docker container image for prediction.\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1u1mr18jlugv"
+      },
+      "outputs": [],
+      "source": [
+        "if GPU:\n",
+        "    DEPLOY_VERSION = \"tf2-gpu.2-5\"\n",
+        "else:\n",
+        "    DEPLOY_VERSION = \"tf2-cpu.2-5\"\n",
+        "\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
+        "\n",
+        "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "machine:training,prediction"
+      },
+      "source": [
+        "#### Set machine types\n",
+        "\n",
+        "Next, set the machine types to use for training and prediction.\n",
+        "\n",
+        "- Set the variable `DEPLOY_COMPUTE` to configure your compute resources for prediction.\n",
+        " - `machine type`\n",
+        "     - `n1-standard`: 3.75GB of memory per vCPU\n",
+        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+        "\n",
+        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YAXwbqKKlugv"
+      },
+      "outputs": [],
+      "source": [
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "TRAIN_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Train machine type\", TRAIN_COMPUTE)\n",
+        "\n",
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Deploy machine type\", DEPLOY_COMPUTE)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9bf06cd476e9"
+      },
+      "source": [
+        "### Upload the model artifacts as a `Vertex AI Model` resource\n",
+        "\n",
+        "First, you upload the pre-trained custom tabular model artifacts as a `Vertex AI Model` resource using the `upload()` method, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Model` resource.\n",
+        "- `artifact_uri`: The Cloud Storage location of the model artifacts.\n",
+        "- `serving_container_image`: The serving container image to use when the model is deployed to a `Vertex AI Endpoint` resource.\n",
+        "- `sync`: Whether to wait for the process to complete, or return immediately (async)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0193f247e216"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_ARTIFACT_URI = \"gs://mco-mm/churn\"\n",
+        "\n",
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=\"churn_\" + UUID,\n",
+        "    artifact_uri=MODEL_ARTIFACT_URI,\n",
+        "    serving_container_image_uri=DEPLOY_IMAGE,\n",
+        "    sync=True,\n",
+        ")\n",
+        "\n",
+        "print(model)"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "a4305ddf",
       "metadata": {
         "id": "a4305ddf"
       },
       "source": [
-        "## Submit a batch prediction request with model monitoring enabled"
+        "## Submit a batch prediction request with model monitoring enabled\n"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "053fde99",
       "metadata": {
         "id": "053fde99"
       },
@@ -503,7 +740,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "b832ad31",
       "metadata": {
         "id": "b832ad31"
       },
@@ -511,20 +747,17 @@
       "source": [
         "# Copy files to your projects gs bucket to avoid permission issues.\n",
         "# Ignore any error(s) for bucket already exists.\n",
-        "OUTPUT_GS_PATH = f\"gs://{PROJECT_ID.replace('-', '_')}_bp_mm_output\"\n",
-        "INPUT_GS_PATH = f\"gs://{PROJECT_ID.replace('-', '_')}_bp_mm_input\"\n",
+        "OUTPUT_GS_PATH = f\"{BUCKET_URI}/bp_mm_output\"\n",
+        "INPUT_GS_PATH = f\"{BUCKET_URI}/bp_mm_input\"\n",
         "PUBLIC_TRAINING_DATASET = \"gs://bp_mm_public_data/churn/churn_bp_insample.csv\"\n",
         "TRAINING_DATASET = f\"{INPUT_GS_PATH}/churn_bp_insample.csv\"\n",
         "TRAINING_DATASET_FORMAT = \"csv\"\n",
         "\n",
-        "! gsutil mb -p {PROJECT_ID} -l {REGION} -b on {INPUT_GS_PATH}\n",
-        "! gsutil mb -p {PROJECT_ID} -l {REGION} -b on {OUTPUT_GS_PATH}\n",
         "! gsutil copy $PUBLIC_TRAINING_DATASET $INPUT_GS_PATH"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "34c95126",
       "metadata": {
         "id": "34c95126"
       },
@@ -541,21 +774,18 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "3a54368a",
       "metadata": {
         "id": "3a54368a"
       },
       "outputs": [],
       "source": [
-        "now = datetime.now()\n",
         "INPUT_URI = \"gs://bp_mm_public_data/churn/churn_bp_outsample.jsonl\"\n",
         "OUTPUT_URI = OUTPUT_GS_PATH\n",
         "INSTANCES_FORMAT = \"jsonl\"\n",
         "PREDICTIONS_FORMAT = \"jsonl\"\n",
         "JOB_NAME_PREFIX = \"bp_mm_demo\"\n",
-        "MODEL_NAME = f\"projects/{PROJECT_ID}/locations/{REGION}/models/{MODEL_ID}\"\n",
-        "MACHINE_TYPE = \"n1-standard-8\"\n",
-        "BATCH_PREDICTION_JOB_NAME = JOB_NAME_PREFIX + \"_\" + now.strftime(\"%Y%m%d%H%M%S\")\n",
+        "MODEL_NAME = model.resource_name\n",
+        "BATCH_PREDICTION_JOB_NAME = JOB_NAME_PREFIX + \"_\" + UUID\n",
         "\n",
         "from google.cloud.aiplatform_v1beta1.types import (\n",
         "    BatchDedicatedResources, BatchPredictionJob, GcsDestination, GcsSource,\n",
@@ -573,7 +803,7 @@
         "        gcs_destination=GcsDestination(output_uri_prefix=OUTPUT_URI),\n",
         "    ),\n",
         "    dedicated_resources=BatchDedicatedResources(\n",
-        "        machine_spec=MachineSpec(machine_type=MACHINE_TYPE),\n",
+        "        machine_spec=MachineSpec(machine_type=DEPLOY_COMPUTE),\n",
         "        starting_replica_count=1,\n",
         "        max_replica_count=1,\n",
         "    ),\n",
@@ -604,7 +834,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "cae39778",
       "metadata": {
         "id": "cae39778"
       },
@@ -617,7 +846,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "bcdd4a47",
       "metadata": {
         "id": "bcdd4a47"
       },
@@ -638,7 +866,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "49ec90a0",
       "metadata": {
         "id": "49ec90a0"
       },
@@ -651,7 +878,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c30496b5",
       "metadata": {
         "id": "c30496b5"
       },
@@ -664,7 +890,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "831651c2",
       "metadata": {
         "id": "831651c2"
       },
@@ -684,7 +909,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a705c10b",
       "metadata": {
         "id": "a705c10b"
       },
@@ -695,7 +919,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "2bbdddac",
       "metadata": {
         "id": "2bbdddac"
       },
@@ -708,7 +931,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "f6c674e9",
       "metadata": {
         "id": "f6c674e9"
       },
@@ -746,7 +968,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "233b1266",
       "metadata": {
         "id": "233b1266"
       },
@@ -759,7 +980,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "4e8c00a7",
       "metadata": {
         "id": "4e8c00a7"
       },
@@ -774,7 +994,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "497a0016",
       "metadata": {
         "id": "497a0016"
       },
@@ -790,7 +1009,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "eabc3f81",
       "metadata": {
         "id": "eabc3f81"
       },
@@ -806,7 +1024,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "0aa0219d",
       "metadata": {
         "id": "0aa0219d"
       },

notebooks/community/prediction/custom_prediction_routines/SDK_Custom_Preprocess.ipynb

@@ -673,7 +673,7 @@
         "Before you can deploy your model for serving, Vertex AI needs access to the following files in Cloud Storage:\n",
         "\n",
         "* `model.joblib` (model artifact)\n",
-        "* `preprocessor.pkl` (model artifact)\n",
+        "* `preprocessor.pkl` (preprocessor code)\n",
         "\n",
         "Run the following commands to upload your files:"
       ]

notebooks/community/sdk/SDK_AutoML_Video_Classification.ipynb

@@ -1,496 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "modular-concentration"
-      },
-      "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": "insured-graduation"
-      },
-      "source": [
-        "# Feedback or issues?\n",
-        "\n",
-        "For any feedback or questions, please open an [issue](https://github.com/googleapis/python-aiplatform/issues)."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "pregnant-going"
-      },
-      "source": [
-        "# Vertex SDK for Python: AutoML Video Classification Example\n",
-        "To use this Jupyter notebook, copy the notebook to a Google Cloud Notebooks instance with Tensorflow installed and open it. You can run each step, or cell, and see its results. To run a cell, use Shift+Enter. Jupyter automatically displays the return value of the last line in each cell. For more information about running notebooks in Google Cloud Notebook, see the [Google Cloud Notebook guide](https://cloud.google.com/vertex-ai/docs/general/notebooks).\n",
-        "\n",
-        "\n",
-        "This notebook demonstrate how to create an AutoML Video Classification Model, with a Vertex AI video dataset, and how to serve the model for batch prediction. It will require you provide a bucket where the dataset will be stored.\n",
-        "\n",
-        "Note: you may incur charges for training, prediction, storage or usage of other GCP products in connection with testing this SDK."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "pending-chamber"
-      },
-      "source": [
-        "### Install Vertex SDK for Python\n",
-        "\n",
-        "\n",
-        "After the SDK installation the kernel will be automatically restarted."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "coated-remark"
-      },
-      "outputs": [],
-      "source": [
-        "!pip3 uninstall -y google-cloud-aiplatform\n",
-        "!pip3 install google-cloud-aiplatform\n",
-        "import IPython\n",
-        "\n",
-        "app = IPython.Application.instance()\n",
-        "app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "incorporated-edgar"
-      },
-      "source": [
-        "### Enter Your Project and GCS Bucket\n",
-        "\n",
-        "Enter your Project Id in the cell below. Then run the cell to make sure the Cloud SDK uses the right project for all the commands in this notebook."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "hispanic-macedonia"
-      },
-      "outputs": [],
-      "source": [
-        "MY_PROJECT = \"YOUR PROJECT\"\n",
-        "MY_STAGING_BUCKET = \"gs://YOUR BUCKET\"  # bucket should be in same region as ucaip"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "efovKMU5WW7u"
-      },
-      "outputs": [],
-      "source": [
-        "import sys\n",
-        "\n",
-        "if \"google.colab\" in sys.modules:\n",
-        "    import os\n",
-        "\n",
-        "    from google.colab import auth\n",
-        "\n",
-        "    auth.authenticate_user()\n",
-        "    os.environ[\"GOOGLE_CLOUD_PROJECT\"] = MY_PROJECT"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "historical-consciousness"
-      },
-      "source": [
-        "### Set Your Task Name, and GCS Prefix\n",
-        "\n",
-        "If you want to centeralize all input and output files under the gcs location."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "organizational-salad"
-      },
-      "outputs": [],
-      "source": [
-        "TASK_TYPE = \"mbsdk_automl-video-training\"\n",
-        "PREDICTION_TYPE = \"classification\"\n",
-        "MODEL_TYPE = \"CLOUD\"\n",
-        "\n",
-        "TASK_NAME = f\"{TASK_TYPE}_{PREDICTION_TYPE}\"\n",
-        "BUCKET_NAME = MY_STAGING_BUCKET.split(\"gs://\")[1]\n",
-        "GCS_PREFIX = TASK_NAME\n",
-        "\n",
-        "print(f\"Bucket Name:    {BUCKET_NAME}\")\n",
-        "print(f\"Task Name:      {TASK_NAME}\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "compact-engagement"
-      },
-      "source": [
-        "# HMDB: a large human motion database\n",
-        "We prepared some training data and prediction data for the demo using the [HMDB Dataset](https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database).\n",
-        "\n",
-        "The HMDB Dataset is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/\n",
-        "\n",
-        "For more information about this dataset please visit: https://serre-lab.clps.brown.edu/resource/hmdb-a-large-human-motion-database/"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "SPDHQoFRD-vM"
-      },
-      "outputs": [],
-      "source": [
-        "automl_video_demo_train_data = (\n",
-        "    \"gs://automl-video-demo-data/hmdb_split1_5classes_all.csv\"\n",
-        ")\n",
-        "automl_video_demo_batch_prediction_data = (\n",
-        "    \"gs://automl-video-demo-data/hmdb_split1_predict.jsonl\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "professional-bulletin"
-      },
-      "source": [
-        "### Copy AutoML Video Demo Train Data for Creating Managed Dataset"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "accurate-producer"
-      },
-      "outputs": [],
-      "source": [
-        "gcs_source_train = f\"gs://{BUCKET_NAME}/{TASK_NAME}/data/video_classification.csv\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "sticky-casino"
-      },
-      "outputs": [],
-      "source": [
-        "!gsutil cp $automl_video_demo_train_data $gcs_source_train"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "rough-alert"
-      },
-      "source": [
-        "# Run AutoML Video Training with Managed Video Dataset"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "adaptive-slovakia"
-      },
-      "source": [
-        "## Initialize Vertex SDK for Python\n",
-        "\n",
-        "Initialize the *client* for Vertex AI."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "figured-fellow"
-      },
-      "outputs": [],
-      "source": [
-        "from google.cloud import aiplatform\n",
-        "\n",
-        "aiplatform.init(project=MY_PROJECT, staging_bucket=MY_STAGING_BUCKET)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "pleasant-holmes"
-      },
-      "source": [
-        "## Create a Dataset on Vertex AI\n",
-        "We will now create a Vertex AI video dataset using the previously prepared csv files. Choose one of the options below. "
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Ln-8NdHjTfbH"
-      },
-      "source": [
-        "Option 1: Using MBSDK VideoDataset class"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "uVBfL-0TTjNS"
-      },
-      "outputs": [],
-      "source": [
-        "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=f\"temp-{TASK_NAME}\",\n",
-        "    gcs_source=gcs_source_train,\n",
-        "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
-        "    sync=False,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lXCA_nvHTp_I"
-      },
-      "source": [
-        "Option 2: Using MBSDK Dataset class\n",
-        "```\n",
-        "dataset = aiplatform.Dataset.create(\n",
-        "    display_name=f'temp-{TASK_NAME}',\n",
-        "    metadata_schema_uri=aiplatform.schema.dataset.metadata.video,\n",
-        "    gcs_source=gcs_source_train, \n",
-        "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
-        "    sync=False\n",
-        ")\n",
-        "```"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3x4xuyIbVR_N"
-      },
-      "outputs": [],
-      "source": [
-        "dataset.wait()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "mexican-spending"
-      },
-      "source": [
-        "## Launch a Training Job and Create a Model on Vertex AI"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dynamic-piece"
-      },
-      "source": [
-        "### Config a Training Job"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "continuous-circular"
-      },
-      "outputs": [],
-      "source": [
-        "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=f\"temp-{TASK_NAME}\",\n",
-        "    prediction_type=PREDICTION_TYPE,\n",
-        "    model_type=MODEL_TYPE,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "juvenile-parameter"
-      },
-      "source": [
-        "### Run the Training Job"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "human-carrier"
-      },
-      "outputs": [],
-      "source": [
-        "model = job.run(\n",
-        "    dataset=dataset,\n",
-        "    training_fraction_split=0.8,\n",
-        "    test_fraction_split=0.2,\n",
-        "    model_display_name=f\"temp-{TASK_NAME}\",\n",
-        "    sync=False,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "abstract-textbook"
-      },
-      "outputs": [],
-      "source": [
-        "model.wait()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "noted-usage"
-      },
-      "source": [
-        "# Batch Prediction Job on the Model"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ruled-smith"
-      },
-      "source": [
-        "### Copy AutoML Video Demo Prediction Data for Creating Batch Prediction Job"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "polished-dispatch"
-      },
-      "outputs": [],
-      "source": [
-        "gcs_source_batch_prediction = (\n",
-        "    f\"gs://{BUCKET_NAME}/{TASK_NAME}/data/video_classification_batch_prediction.jsonl\"\n",
-        ")\n",
-        "gcs_destination_prefix_batch_prediction = (\n",
-        "    f\"gs://{BUCKET_NAME}/{TASK_NAME}/batch_prediction\"\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "objective-soldier"
-      },
-      "outputs": [],
-      "source": [
-        "!gsutil cp $automl_video_demo_batch_prediction_data $gcs_source_batch_prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "piano-middle"
-      },
-      "outputs": [],
-      "source": [
-        "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=f\"temp-{TASK_NAME}\",\n",
-        "    gcs_source=gcs_source_batch_prediction,\n",
-        "    gcs_destination_prefix=gcs_destination_prefix_batch_prediction,\n",
-        "    sync=False,\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "visible-scientist"
-      },
-      "outputs": [],
-      "source": [
-        "batch_predict_job.wait()\n",
-        "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
-        "\n",
-        "prediction_results = list()\n",
-        "for blob in bp_iter_outputs:\n",
-        "    if blob.name.split(\"/\")[-1].startswith(\"prediction\"):\n",
-        "        prediction_results.append(blob.name)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "moving-geneva"
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "import tensorflow as tf\n",
-        "\n",
-        "tags = list()\n",
-        "for prediction_result in prediction_results:\n",
-        "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{prediction_result}\"\n",
-        "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
-        "        for line in gfile.readlines():\n",
-        "            line = json.loads(line)\n",
-        "            break\n",
-        "\n",
-        "print(line)"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "collapsed_sections": [],
-      "name": "AI_Platform_(Unified)_SDK_AutoML_Video_Classification.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/sdk/SDK_BigQuery_Custom_Container_Training.ipynb

@@ -23,6 +23,15 @@
         "# limitations under the License."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2d7a1a97d1ee"
+      },
+      "source": [
+        "# Vertex AI: SDK BigQuery Custom Container Training"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -58,18 +67,61 @@
       },
       "source": [
         "###  Overview \n",
-        "To use this Jupyter notebook, copy the notebook to a Google Cloud Notebooks instance and open it. You can run each step, or cell, and see its results. To run a cell, use Shift+Enter. Jupyter automatically displays the return value of the last line in each cell. For more information about running notebooks in Google Cloud Notebook, see the Google Cloud Notebook guide.. \n",
         "\n",
-        "### Objective \n",
+        "This Note book creates a custom container using bigquery dataset it will train container and crete ,train and Deploy the model to perform prediction. \n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "989999fbdab3"
+      },
+      "source": [
+        "### Objective\n",
         "\n",
-        "This notebook demonstrate how to create a Custom Model using Custom Container Training and a Big Query Dataset. It will require you provide a bucket where the dataset will be stored.\n",
+        "In this notebook, you will learn how to use Vertex AI Experiments to \n",
         "\n",
-        "Costs  \n",
-        "This tutorial uses billable components of Google Cloud: \n",
+        "*   Log Pipeline Job\n",
+        "*   Compare different Pipeline Jobs\n",
         "\n",
-        "Vertex AI\n",
-        "Cloud Storage\n",
-        "Learn about Vertex AI  pricing and Cloud Storage pricing, and use the Pricing Calculator to generate a cost estimate based on your projected usage."
+        "The steps covered include:\n",
+        "\n",
+        "* Formalize a training component\n",
+        "* Build a training a Model\n",
+        "* Run several Pipeline jobs and log their results\n",
+        "* Train the model for prediction\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3d29af7e49d8"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [Iris dataset](https://www.tensorflow.org/datasets/catalog/iris) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the type of Iris flower species from a class of three species: setosa, virginica, or versicolor."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e3e924989cce"
+      },
+      "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)  [Bigquery\n",
+        "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."
       ]
     },
     {
@@ -139,10 +191,9 @@
         "id": "xOMNWzTbftDr"
       },
       "source": [
-        "# Install Vertex AI SDK for Python\n",
+        "### Install additional packages\n",
         "\n",
-        "\n",
-        "After the SDK installation the kernel will be automatically restarted."
+        "Install additional package dependencies not installed in your notebook environment, such as XGBoost, AdaNet, or TensorFlow Hub. Use the latest major GA version of each package."
       ]
     },
     {
@@ -161,6 +212,36 @@
         "app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d4f317591f55"
+      },
+      "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": "f731803a16c0"
+      },
+      "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": {
@@ -172,6 +253,17 @@
         "Enter your Project Id in the cell below. Then run the cell to make sure the Cloud SDK uses the right project for all the commands in this notebook."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3c8049930470"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -183,14 +275,11 @@
         "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)\n",
-        "\n",
-        "MY_STAGING_BUCKET = \"gs://YOUR BUCKET\"  # bucket should be in same region as ucaip"
+        "    print(\"Project ID: \", PROJECT_ID)"
       ]
     },
     {
@@ -218,21 +307,14 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "6x6CSodKjMmg"
+        "id": "ZaQd5jNwjP_0"
       },
       "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": "ZaQd5jNwjP_0"
-      },
-      "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\n",
         "when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -296,9 +378,9 @@
         "id": "r2lr6-MVpXLP"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial.\n"
       ]
     },
     {
@@ -309,9 +391,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -343,15 +432,24 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "GF076Vmoioll"
+        "id": "2f6f0f6ec383"
       },
       "outputs": [],
       "source": [
         "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
-        "\n",
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GF076Vmoioll"
+      },
+      "outputs": [],
+      "source": [
         "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID\n",
         "\n",
         "if REGION == \"[your-region]\":\n",
         "    REGION = \"us-central1\""
@@ -403,8 +501,9 @@
         "id": "5T1d5uBoftDw"
       },
       "source": [
-        "# Copy Big Query Iris Dataset\n",
-        "We will make a Big Query dataset and copy Big Query's public iris table to that dataset. For more information about this dataset please visit: https://archive.ics.uci.edu/ml/datasets/iris "
+        "# Copy bigquery iris dataset\n",
+        "\n",
+        "You make a BigQuery dataset and copy BigQuery's public iris table to that dataset. For more information about this dataset please visit: https://archive.ics.uci.edu/ml/datasets/iris "
       ]
     },
     {
@@ -543,6 +642,15 @@
         "### Write the entrypoint script to invoke trainer"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c5cdc477cd73"
+      },
+      "source": [
+        "The entrypoint script train adn validates the data and also compiles the model."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -697,9 +805,9 @@
         "id": "736ddff8408b"
       },
       "source": [
-        "# Create a Managed Tabular Dataset from Big Query Dataset\n",
+        "# Create a managed tabular dataset from bigquery dataset\n",
         "\n",
-        "This section will create a managed Tabular dataset from the iris Big Query table we copied above."
+        "This section create a managed Tabular dataset from the iris BigQuery table we copied above.The param's used are BigQuery's public iris dataset."
       ]
     },
     {
@@ -723,7 +831,7 @@
       "source": [
         "# Launch The Training Job to Create a Model\n",
         "\n",
-        "We will train a model with the container we built above."
+        "We will train a model with the container we built above.To train the model you use the CustomeContanier TrainingJob method with Container Image and Container_uri as parametrs."
       ]
     },
     {
@@ -753,9 +861,9 @@
         "id": "a7fa9b59f919"
       },
       "source": [
-        "# Deploy The Model\n",
+        "# Deploy the model\n",
         "\n",
-        "Deploy your model, then wait until the model FINISHES deployment before proceeding to prediction."
+        "Deploy your model, then wait until the model Finishes deployment before proceeding to prediction.For prediction deploy method takes machine_type as parameter."
       ]
     },
     {
@@ -778,6 +886,15 @@
         "# Make a prediction\n"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e4b04d246ba9"
+      },
+      "source": [
+        "Endpoint predict method publish the prediction based on length and width feature parameters."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -786,9 +903,11 @@
       },
       "outputs": [],
       "source": [
-        "endpoint.predict(\n",
+        "prediction = endpoint.predict(\n",
         "    [{\"sepal_length\": 5.1, \"sepal_width\": 2.5, \"petal_length\": 3.0, \"petal_width\": 1.1}]\n",
-        ")"
+        ")\n",
+        "\n",
+        "print(prediction)"
       ]
     },
     {
@@ -797,12 +916,16 @@
         "id": "MaoIczP8qu--"
       },
       "source": [
-        "## Cleaning up\n",
+        "# 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.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:"
+        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
+        "\n",
+        "- Pipeline\n",
+        "- Endpoint\n",
+        "- Cloud Storage Bucket"
       ]
     },
     {
@@ -813,16 +936,28 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "delete_pipeline = True\n",
+        "delete_endpoint = True\n",
         "\n",
-        "# Delete endpoint resource\n",
-        "! gcloud ai endpoints delete $ENDPOINT_NAME --quiet --region $REGION_NAME\n",
         "\n",
-        "# Delete Cloud Storage objects that were created\n",
-        "! gsutil -m rm -r $JOB_DIR\n",
+        "if delete_pipeline:\n",
+        "    job.delete()\n",
         "\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "! gsutil -m rm -r $BUCKET_URI  "
+        "    if delete_endpoint and \"DISPLAY_NAME\" in globals():\n",
+        "        endpoints = aip.Endpoint.list(\n",
+        "            filter=f\"display_name={DISPLAY_NAME}_endpoint\", order_by=\"create_time\"\n",
+        "        )\n",
+        "        if endpoints:\n",
+        "            endpoint = endpoints[0]\n",
+        "            endpoint.undeploy_all()\n",
+        "            aip.Endpoint.delete(endpoint.resource_name)\n",
+        "            print(\"Deleted endpoint:\", endpoint)\n",
+        "\n",
+        "\n",
+        "# Delete bucket\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -rf {BUCKET_URI}"
       ]
     }
   ],

notebooks/notebook_template.ipynb

@@ -29,6 +29,8 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
+        "# [TODO] Add your H1 title heading here\n",
+        "\n",
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
@@ -80,7 +82,7 @@
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- * {TODO: Add high level bullets for the steps of performed in the notebook}"
+        "- *{TODO: Add high level bullets for the steps of performed in the notebook}*"
       ]
     },
     {
@@ -109,21 +111,24 @@
         "This tutorial uses billable components of Google Cloud:\n",
         "\n",
         "* Vertex AI\n",
+        "* {TODO: BigQyuery}\n",
         "* Cloud Storage\n",
         "\n",
-        "{TODO: Include links to pricing documentation for each product you listed above.}\n",
+        "{TODO: Include links to pricing documentation for each product you listed above.\n",
+        " NOTE: If you use BigQuery or Dataflow, you need to add this to the pricing.\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",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing),\n",
+        "{ TODO: [BigQuery pricing](https://cloud.google.com/bigquery/pricing), }\n",
+        "and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), \n",
+        "and use the [Pricing 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"
+        "id": "gCuSR8GkAgzl"
       },
       "source": [
         "### Set up your local development environment\n",
@@ -132,6 +137,17 @@
         "all the requirements to run this notebook. You can skip this step."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "24743cf4a1e1"
+      },
+      "source": [
+        "**_NOTE_**: This notebook has been tested in the following environment:\n",
+        "\n",
+        "* Python version = 3.9"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -142,10 +158,6 @@
         "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",
@@ -204,7 +216,7 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
-        "# TODO: Add remaining package installs here"
+        "# TODO: Add remaining package installs here. All packages should be on a single pip install to resolve dependencies"
       ]
     },
     {
@@ -237,21 +249,14 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lWEdiXsJg0XY"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "BF1j6f9HApxa"
       },
       "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",
@@ -412,21 +417,14 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "dr--iN2kAylZ"
+        "id": "sBCra4QMA2wR"
       },
       "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": "sBCra4QMA2wR"
-      },
-      "source": [
+        "authenticated. \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",
@@ -481,7 +479,7 @@
         "    # 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 ''"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
       ]
     },
     {
@@ -497,7 +495,7 @@
         "\n",
         "{TODO: Adjust wording in the first paragraph to fit your use case - explain how your tutorial uses the Cloud Storage bucket. The example below shows how Vertex AI uses the bucket for training.}\n",
         "\n",
-        "When you submit a training job using the Cloud SDK, you upload a Python package\n",
+        "When you submit a training job using the Vertex AI 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. Using this model artifact, you can then\n",

notebooks/notebook_template_review.py

@@ -25,7 +25,11 @@ args = parser.parse_args()
 
 if args.errors_codes:
     args.errors_codes = args.errors_codes.split(',')
-    
+    args.errors = True
+
+if args.errors_csv:
+    args.errors = True
+
 def parse_dir(directory):
     entries = os.scandir(directory)
     for entry in entries:
@@ -38,7 +42,7 @@ def parse_dir(directory):
             parse_dir(entry.path)
         elif entry.name.endswith('.ipynb'):
             parse_notebook(entry.path)
-            
+
 def parse_notebook(path):
     with open(path, 'r') as f:
         try:
@@ -52,7 +56,7 @@ def parse_notebook(path):
         # cell 1 is copyright
         nth = 0
         cell, nth = get_cell(path, cells, nth)
-        if not cell['source'][0].startswith('# Copyright'):
+        if not 'Copyright' in cell['source'][0]:
             report_error(path, 0, "missing copyright cell")
             
         # check for notices
@@ -158,6 +162,11 @@ def parse_notebook(path):
             if cell['cell_type'] != 'code':
                 report_error(path, 22, "Installation code section not found")
             else:
+                if cell['source'][0].startswith('! mkdir'):
+                    cell, nth = get_cell(path, cells, nth)
+                if 'requirements.txt' in cell['source'][0]:
+                    cell, nth = get_cell(path, cells, nth)
+                    
                 text = ''
                 for line in cell['source']:
                     text += line
@@ -238,7 +247,7 @@ def parse_notebook(path):
         if cell['source'][0].startswith("### Region"): 
             report_error(path, 34, "Region section not found")
         '''
-                
+
 
 def get_cell(path, cells, nth):
     while empty_cell(path, cells, nth):
@@ -249,15 +258,38 @@ def get_cell(path, cells, nth):
         check_text_cell(path, cell)
     return cell, nth + 1
 
-                
+
 def empty_cell(path, cells, nth):
     if len(cells[nth]['source']) == 0:
         report_error(path, 10, f'empty cell: cell #{nth}')
         return True
     else:
         return False
-    
+
 def check_text_cell(path, cell):
+    
+    branding = {
+        'Vertex SDK': 'Vertex AI SDK',
+        'Vertex Training': 'Vertex AI Training',
+        'Vertex Prediction': 'Vertex AI Prediction',
+        'Vertex Batch Prediction': 'Vertex AI Batch Prediction',
+        'Vertex XAI': 'Vertex Explainable AI',
+        'Vertex Experiments': 'Vertex AI Experiments',
+        'Vertex TensorBoard': 'Vertex AI TensorBoard',
+        'Vertex Pipelines': 'Vertex AI Pipelines',
+        'Vertex Hyperparameter Tuning': 'Vertex AI Hyperparameter Tuning',
+        'Vertex Metadata': 'Vertex ML Metadata',
+        'Vertex AI Metadata': 'Vertex ML Metadata',
+        'Vertex Vizier': 'Vertex AI Vizier',
+        'Vertex Dataset': 'Vertex AI Dataset',
+        'Vertex Model': 'Vertex AI Model',
+        'Vertex Endpoint': 'Vertex AI Endpoint',
+        'Vertex Private Endpoint': 'Vertex AI Private Endpoint',
+        'Tensorflow': 'TensorFlow',
+        'Tensorboard': 'TensorBoard',
+        'Google Cloud Notebooks': 'Vertex AI Workbench Notebooks'
+    }
+    
     for line in cell['source']:
         if 'TODO' in line:
             report_error(path, 14, f'TODO in cell: {line}')
@@ -266,28 +298,9 @@ def check_text_cell(path, cell):
         if 'will' in line.lower() or 'would' in line.lower():
             report_error(path, 16, f'Do not use future tense (e.g., will), replace with present tense: {line}')
             
-        if 'Vertex SDK' in line:
-            report_error(path, 27, f"Branding: Vertex AI SDK: {line}")
-        if 'Vertex Training' in line:
-            report_error(path, 27, f"Branding: Vertex AI Training: {line}")
-        if 'Vertex Prediction' in line:
-            report_error(path, 27, f"Branding: Vertex AI Prediction: {line}")
-        if 'Vertex Batch Prediction' in line:
-            report_error(path, 27, f"Branding: Vertex AI Batch Prediction {line}")
-        if 'Vertex XAI' in line:
-            report_error(path, 27, f"Branding: Vertex Explainable AI: {line}")
-        if 'Vertex Experiments' in line:
-            report_error(path, 27, f"Branding: Vertex AI Experiments: {line}")
-        if 'Vertex TensorBoard' in line:
-            report_error(path, 27, f"Branding: Vertex AI TensorBoard: {line}")
-        if 'Vertex Pipelines' in line:
-            report_error(path, 27, f"Branding: Vertex AI Pipelines: {line}")
-        if 'Vertex Hyperparameter Tuning' in line:
-            report_error(path, 27, f"Branding: Vertex AI Hyperparameter Tuning: {line}")
-        if 'Tensorflow' in line:
-            report_error(path, 27, f"Branding: TensorFlow: {line}")
-        if 'Tensorboard' in line:
-            report_error(path, 27, f"Branding: TensorBoard: {line}")
+        for mistake, brand in branding.items():
+            if mistake in line:
+                report_error(path, 27, f"Branding {brand}: {line}")
 
 
 def check_sentence_case(path, heading):
@@ -298,12 +311,12 @@ def check_sentence_case(path, heading):
     for word in words[1:]:
         word = word.replace(':', '').replace('(', '').replace(')', '')
         if word in ['E2E', 'Vertex', 'AutoML', 'ML', 'AI', 'GCP', 'API', 'R', 'CMEK', 'TFX', 'TFDV', 'SDK',
-                    'VM', 'CPR', 'NVIDIA', 'ID']:
+                    'VM', 'CPR', 'NVIDIA', 'ID', 'DASK']:
             continue
         if word.isupper():
             report_error(path, 3, f"heading is not sentence case: {word}")
-            
-            
+
+
 def report_error(notebook, code, msg):
     if args.errors:
         if args.errors_codes:
@@ -314,7 +327,7 @@ def report_error(notebook, code, msg):
             print(notebook, ',', code)
         else:
             print(f"{notebook}: ERROR ({code}): {msg}")
-            
+
 def parse_objective(path, cell):
     desc = ''
     in_desc = True
@@ -392,7 +405,7 @@ def add_index(path, title, desc, uses, steps):
         
     if args.steps:
         print(steps)
-            
+
 
 if args.notebook_dir:
     if not os.path.isdir(args.notebook_dir):
@@ -406,4 +419,4 @@ elif args.notebook:
     parse_notebook(args.notebook)
 else:
         print("Error: must specify a directory or notebook")
-        exit(1)
+        exit(1)

notebooks/official/CODEOWNERS

@@ -5,17 +5,18 @@
 * @GoogleCloudPlatform/vertex-ai-samples-contributors  @GoogleCloudPlatform/caiis-tw
 
 # matching_engine folder
-/matching_engine @shenzhimo2
+/matching_engine @shenzhimo2 @ivanmkc
 
 /tabnet/tabnet_vertex_tutorial.ipynb @longtle
 
 /migration @andrewferlitsch
-/explainabl_ai   
+/explainabl_ai
 /pipelines @andrewferlitsch
 /ml_metadata @andrewferlitsch
 /model_monitoring @andrewferlitsch
 /tensorboard @zbl94
 
+/bigquery_ml/bqml-online-prediction.ipynb @polong-lin
 /model_monitoring/model_monitoring.ipynb @mco-gh
 /ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb @jialuzh
 /ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb @jialuzh
@@ -28,4 +29,9 @@
 /automl/automl_forecasting_bqml_arima_plus_comparison.ipynb @TheMichaelHu
 /automl/automl_tabular_on_vertex_pipelines.ipynb @helinwang
 /custom/custom_training_tensorboard_profiler.ipynb @itseric
-/workbench/spark/spark_sample_notebook.ipynb @bmiro
+/workbench/spark/spark_sample_notebook.ipynb @bradmiro
+/workbench/spark/spark_ml.ipynb @bradmiro
+/model-registry/bqml-vertexai-model-registry.ipynb @soheilazangeneh
+/workbench/exploratory_data_analysis/explore_data_in_bigquery_with_workbench.ipynb @alokpattani
+/model_evaluation/automl_tabular_classification_model_evaluation.ipynb @soheilazangeneh
+/model_evaluation/automl_tabular_regression_model_evaluation.ipynb @soheilazangeneh

notebooks/official/automl/automl-text-classification.ipynb

@@ -2,7 +2,7 @@
   "cells": [
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 54,
       "metadata": {
         "id": "ur8xi4C7S06n"
       },
@@ -17,12 +17,21 @@
         "#     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",
+        "# distributed under the Lice`nse 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": "0d2298941703"
+      },
+      "source": [
+        "# Vertex AI: Create, train, and deploy an AutoML text classification model"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -43,8 +52,8 @@
         "    </a>\n",
         "  </td>\n",
         " <td>\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/official/automl/automl-text-classification.ipynb\">\n",
-        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\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/official/automl/automl-text-classification.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",
@@ -54,19 +63,20 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "0259a7ce8120"
+        "id": "1adb10a59bc3"
       },
       "source": [
-        "# Vertex AI: Create, train, and deploy an AutoML text classification model\n",
-        "\n",
         "## Overview\n",
         "\n",
-        "This notebook walks you through the major phases of building and using an AutoML text classification model on [Vertex AI](https://cloud.google.com/vertex-ai/docs/). \n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "In this notebook, you use the \"Happy Moments\" sample dataset to train a model. The resulting model classifies happy moments into categores that reflect the causes of happiness. \n",
-        "\n",
+        "This notebook walks you through the major phases of building and using an AutoML text classification model on [Vertex AI](https://cloud.google.com/vertex-ai/docs/). \n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9b9824ae2c91"
+      },
+      "source": [
         "### Objective\n",
         "\n",
         "In this tutorial, you learn how to use `AutoML` to train a text classification model.\n",
@@ -84,8 +94,26 @@
         "* Create an `Endpoint` resource.\n",
         "* Deploy the `Model` resource to the `Endpoint` resource.\n",
         "* Make an online prediction\n",
-        "* Make a batch prediction\n",
+        "* Make a batch prediction"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "f67c62885df4"
+      },
+      "source": [
+        "### Dataset\n",
         "\n",
+        "In this notebook, you use the \"Happy Moments\" sample dataset to train a model. The resulting model classifies happy moments into categores that reflect the causes of happiness. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0259a7ce8120"
+      },
+      "source": [
         "### Costs\n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -173,7 +201,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 55,
       "metadata": {
         "id": "b75757581291"
       },
@@ -188,6 +216,7 @@
         ")\n",
         "\n",
         "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "\n",
         "USER_FLAG = \"\"\n",
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
@@ -208,7 +237,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 56,
       "metadata": {
         "id": "0c0b2427998a"
       },
@@ -254,7 +283,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 1,
       "metadata": {
         "id": "be175254a715"
       },
@@ -311,7 +340,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 4,
       "metadata": {
         "id": "ae43d96c4b1b"
       },
@@ -336,7 +365,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 5,
       "metadata": {
         "id": "953fa6e5ddda"
       },
@@ -424,7 +453,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 6,
       "metadata": {
         "id": "d2de92accb67"
       },
@@ -436,7 +465,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 7,
       "metadata": {
         "id": "5ba09496accc"
       },
@@ -478,7 +507,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 9,
       "metadata": {
         "id": "96ad3d416327"
       },
@@ -498,7 +527,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 10,
       "metadata": {
         "id": "152013538e59"
       },
@@ -521,7 +550,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 11,
       "metadata": {
         "id": "740cd5c67c79"
       },
@@ -551,24 +580,15 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "6caf82e5e84e"
+        "id": "d35b8b6b94ae"
       },
       "outputs": [],
       "source": [
         "# Use a timestamp to ensure unique resources\n",
         "src_uris = \"gs://cloud-ml-data/NL-classification/happiness.csv\"\n",
-        "display_name = f\"e2e-text-dataset-{TIMESTAMP}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "d35b8b6b94ae"
-      },
-      "outputs": [],
-      "source": [
-        "ds = aiplatform.TextDataset.create(\n",
+        "display_name = f\"e2e-text-dataset-{TIMESTAMP}\"\n",
+        "\n",
+        "text_dataset = aiplatform.TextDataset.create(\n",
         "    display_name=display_name,\n",
         "    gcs_source=src_uris,\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.text.single_label_classification,\n",
@@ -582,53 +602,7 @@
         "id": "5b3cc427353a"
       },
       "source": [
-        "## Train your text classification model\n",
-        "\n",
-        "Once your dataset has finished importing data, you are ready to train your model. To do this, you first need the full resource name of your dataset, where the full name has the format `projects/[YOUR_PROJECT]/locations/[YOUR_REGIO)N]/datasets/[YOUR_DATASET_ID]`. If you don't have the resource name handy, you can list all of the datasets in your project using `TextDataset.list()`. \n",
-        "\n",
-        "As shown in the following code block, you can pass in the display name of your dataset in the call to `list()` to filter the results.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "52cf56f1c8a9"
-      },
-      "outputs": [],
-      "source": [
-        "datasets = aiplatform.TextDataset.list(filter=f'display_name=\"{display_name}\"')\n",
-        "print(datasets)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "58df3e02df82"
-      },
-      "source": [
-        "When you create a new model, you need a reference to the `TextDataset` object that corresponds to your dataset. You can use the `ds` variable you created previously when you created the dataset or you can also list all of your datasets to get a reference to your dataset. Each item returned from `TextDataset.list()` is an instance of `TextDataset`.\n",
-        "\n",
-        "The following code block shows how to instantiate a `TextDataset` object using a dataset ID. Note that this code is intentionally verbose for demonstration purposes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "aa667203da03"
-      },
-      "outputs": [],
-      "source": [
-        "# Get the dataset ID if it's not available\n",
-        "dataset_id = \"[your-dataset-id]\"\n",
-        "\n",
-        "if dataset_id == \"[your-dataset-id]\":\n",
-        "    # Use the reference to the new dataset captured when we created it\n",
-        "    dataset_id = ds.resource_name.split(\"/\")[-1]\n",
-        "    print(f\"Dataset ID: {dataset_id}\")\n",
-        "\n",
-        "text_dataset = aiplatform.TextDataset(dataset_id)"
+        "## Train your text classification model\n"
       ]
     },
     {
@@ -653,7 +627,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 16,
       "metadata": {
         "id": "0aa0f01805ea"
       },
@@ -682,8 +656,8 @@
         "model = job.run(\n",
         "    dataset=text_dataset,\n",
         "    model_display_name=model_display_name,\n",
-        "    training_fraction_split=0.7,\n",
-        "    validation_fraction_split=0.2,\n",
+        "    training_fraction_split=0.1,\n",
+        "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
         "    sync=True,\n",
         ")"
@@ -740,39 +714,11 @@
         "deployed_model_display_name = f\"e2e-deployed-text-classification-model-{TIMESTAMP}\"\n",
         "\n",
         "endpoint = model.deploy(\n",
-        "    deployed_model_display_name=deployed_model_display_name, sync=True\n",
+        "    deployed_model_display_name=deployed_model_display_name, \n",
+        "    sync=True\n",
         ")"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "531da446035b"
-      },
-      "source": [
-        "In case you didn't record the name of the new endpoint, you can get a list of all your endpoints as you did before with datasets and models. For each endpoint, you can list the models deployed to that endpoint. To get a reference to the model that you just deployed, you can check the `display_name` of each model deployed to the endpoint against the model you're looking for."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "f61fb44181b4"
-      },
-      "outputs": [],
-      "source": [
-        "endpoints = aiplatform.Endpoint.list()\n",
-        "\n",
-        "endpoint_with_deployed_model = []\n",
-        "\n",
-        "for endpoint_ in endpoints:\n",
-        "    for model in endpoint_.list_models():\n",
-        "        if model.display_name.find(deployed_model_display_name) == 0:\n",
-        "            endpoint_with_deployed_model.append(endpoint_)\n",
-        "\n",
-        "print(endpoint_with_deployed_model)"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -781,7 +727,7 @@
       "source": [
         "## Get online predictions from your model\n",
         "\n",
-        "Now that you have your endpoint's resource name, you can get online predictions from the text classification model. To get the online prediction, you send a prediction request to your endpoint."
+        "Now that you have your endpoint, you can get online predictions from the text classification model. To get the online prediction, you send a prediction request to your endpoint."
       ]
     },
     {
@@ -792,13 +738,6 @@
       },
       "outputs": [],
       "source": [
-        "endpoint_name = \"[your-endpoint-name]\"\n",
-        "if endpoint_name == \"[your-endpoint-name]\":\n",
-        "    endpoint_name = endpoint.resource_name\n",
-        "\n",
-        "print(f\"Endpoint name: {endpoint_name}\")\n",
-        "\n",
-        "endpoint = aiplatform.Endpoint(endpoint_name)\n",
         "content = \"I got a high score on my math final!\"\n",
         "\n",
         "response = endpoint.predict(instances=[{\"content\": content}])\n",
@@ -835,7 +774,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 23,
       "metadata": {
         "id": "e4b838cbcd99"
       },
@@ -858,7 +797,7 @@
         "\n",
         "+ All of your prediction instances as individual files on Google Cloud Storage, as TXT files for your instances\n",
         "+ A JSONL file that lists the URIs of all your prediction instances\n",
-        "+ A Google Cloud Storage bucket to hold the output from batch prediction\n",
+        "+ A Cloud Storage bucket to hold the output from batch prediction\n",
         "\n",
         "For this tutorial, the following cells create a new Storage bucket, upload individual prediction instances as text files to the bucket, and then create the JSONL file with the URIs of your prediction instances."
       ]
@@ -872,16 +811,15 @@
       "outputs": [],
       "source": [
         "# Instantiate the Storage client and create the new bucket\n",
-        "storage = storage.Client()\n",
-        "bucket = storage.bucket(BUCKET_URI)\n",
-        "\n",
+        "# from google.cloud import  storage\n",
+        "storage_client = storage.Client()\n",
+        "bucket = storage_client.bucket(BUCKET_NAME)\n",
         "# Iterate over the prediction instances, creating a new TXT file\n",
         "# for each.\n",
         "input_file_data = []\n",
         "for count, instance in enumerate(instances):\n",
         "    instance_name = f\"input_{count}.txt\"\n",
         "    instance_file_uri = f\"{BUCKET_URI}/{instance_name}\"\n",
-        "\n",
         "    # Add the data to store in the JSONL input file.\n",
         "    tmp_data = {\"content\": instance_file_uri, \"mimeType\": \"text/plain\"}\n",
         "    input_file_data.append(tmp_data)\n",
@@ -901,7 +839,7 @@
         "id": "31c262320610"
       },
       "source": [
-        "Now that you have the bucket with the prediction instances ready, you can send a batch prediction request to Vertex AI. When you send a request to the service, you must provide the URI of your JSONL file and your output bucket, including the `gs://` protocols.\n",
+        "Now that you have the bucket with the prediction instances ready, you can send a batch prediction rhttps://storage.googleapis.com/upload/storage/v1/b/gs://vertex-ai-devaip-20220728004429/o?uploadType=multipartequest to Vertex AI. When you send a request to the service, you must provide the URI of your JSONL file and your output bucket, including the `gs://` protocols.\n",
         "\n",
         "With the Python SDK, you can create a batch prediction job by calling `Model.batch_predict()`."
       ]
@@ -915,15 +853,13 @@
       "outputs": [],
       "source": [
         "job_display_name = \"e2e-text-classification-batch-prediction-job\"\n",
-        "model = aiplatform.Model(model_name=model_name)\n",
-        "\n",
+        "# model = aiplatform.Model(model_name=model.name)\n",
         "batch_prediction_job = model.batch_predict(\n",
         "    job_display_name=job_display_name,\n",
         "    gcs_source=f\"{BUCKET_URI}/{input_file_name}\",\n",
         "    gcs_destination_prefix=f\"{BUCKET_URI}/output\",\n",
         "    sync=True,\n",
         ")\n",
-        "\n",
         "batch_prediction_job_name = batch_prediction_job.resource_name"
       ]
     },
@@ -938,6 +874,15 @@
         "The following code snippet demonstrates how to create an instance of the `BatchPredictionJob` class to review its status. Note that you need the full resource name printed out from the Python SDK for this snippet.\n"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cd014de40e2f"
+      },
+      "source": [
+        "## BatchPredictionJob"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -999,6 +944,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "RESULTS_DIRECTORY = \"prediction_results\"\n",
         "RESULTS_DIRECTORY_FULL = f\"{RESULTS_DIRECTORY}/output\"\n",
         "\n",
@@ -1020,6 +967,15 @@
         "print(f\"Local results folder: {latest_directory}\")"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e375109b7e40"
+      },
+      "source": [
+        "## JsonLines"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1094,9 +1050,9 @@
         "    ! gsutil rm -r $BUCKET_URI\n",
         "\n",
         "batch_job.delete()\n",
-        "\n",
+        "endpoint.undeploy_all()\n",
         "# `force` parameter ensures that models are undeployed before deletion\n",
-        "endpoint.delete(force=True)\n",
+        "endpoint.delete()\n",
         "\n",
         "model.delete()\n",
         "\n",

notebooks/official/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb

@@ -29,7 +29,7 @@
         "id": "title"
       },
       "source": [
-        "# Compare Vertex Forecasting and BQML ARIMA_PLUS\n",
+        "# Compare Vertex AI Forecasting and BigQuery ML ARIMA_PLUS\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -61,18 +61,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "In this tutorial, you will take on the role of a store planner who must determine how much inventory they will need to order for each of their products and stores for November 2019. You will accomplish this by training forecasting models using historical sales data. You will start with a baseline model using [BQML ARIMA_PLUS](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series) and then compare it against a [Vertex Forecasting](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/overview) model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:covid,forecast"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "To demonstrate the tradeoffs between using BQML and Vertex Forecasting, this tutorial will use a synthetic dataset where product sales are dependent on a variety of factors such as advertisements, holidays, and locations. You will see how well a univariate model like ARIMA_PLUS can forecast future sales without knowing information about these factors explicitly, and how well a multivariate model like Vertex Forecasting can perform when these factors are known."
+        "In this tutorial, you take on the role of a store planner who must determine how much inventory they will need to order for each of their products and stores for November 2019. You will accomplish this by training forecasting models using historical sales data. You will start with a baseline model using BigQuery ML (BQML) [ARIMA_PLUS](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create-time-series) and then compare it against a [Vertex AI Forecasting](https://cloud.google.com/vertex-ai/docs/tabular-data/forecasting/overview) model."
       ]
     },
     {
@@ -83,19 +72,30 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an BQML ARIMA_PLUS model using a training [Vertex Pipeline](https://cloud.google.com/vertex-ai/docs/pipelines/introduction) from [Google Cloud Pipeline Components](https://cloud.google.com/vertex-ai/docs/pipelines/components-introduction) (GCPC), and then do a batch prediction using the corresponding prediction pipeline. You then train a Vertex Forecasting model using the same data and compare the evaluation metrics.\n",
+        "In this tutorial, you create an BQML ARIMA_PLUS model using a training [Vertex AI Pipeline](https://cloud.google.com/vertex-ai/docs/pipelines/introduction) from [Google Cloud Pipeline Components](https://cloud.google.com/vertex-ai/docs/pipelines/components-introduction) (GCPC), and then do a batch prediction using the corresponding prediction pipeline. You then train a Vertex AI Forecasting model using the same data and compare the evaluation metrics.\n",
         "\n",
         "The steps performed are:\n",
         "\n",
         "- Train the BQML ARIMA_PLUS model.\n",
         "- View BQML model evaluation.\n",
         "- Make a batch prediction with the BQML model.\n",
-        "- Create a Vertex `Dataset` resource.\n",
-        "- Train the Vertex Forecasting model.\n",
+        "- Create a Vertex AI `Dataset` resource.\n",
+        "- Train the Vertex AI Forecasting model.\n",
         "- View the Model evaluation.\n",
         "- Make a batch prediction with the Model.\n"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:covid,forecast"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "To demonstrate the tradeoffs between using BQML and Vertex AI Forecasting, this tutorial will use a synthetic dataset where product sales are dependent on a variety of factors such as advertisements, holidays, and locations. You will see how well a univariate model like ARIMA_PLUS can forecast future sales without knowing information about these factors explicitly, and how well a multivariate model like Vertex AI Forecasting can perform when these factors are known."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -155,9 +155,9 @@
         "id": "install_aip:mbsdk"
       },
       "source": [
-        "## Install additional packages\n",
+        "## Installation\n",
         "\n",
-        "Install the latest version of the Google Cloud Pipeline Components (GCPC) SDK."
+        "Install the following packages required to execute this notebook."
       ]
     },
     {
@@ -170,13 +170,22 @@
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\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",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "else:\n",
         "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-bigquery[pandas] google-cloud-aiplatform google-cloud-pipeline-components $USER_FLAG"
+        "! (pip3 install --upgrade $USER_FLAG \\\n",
+        "    google-cloud-bigquery[pandas]==2.34.4 \\\n",
+        "    google-cloud-aiplatform==1.16.1 \\\n",
+        "    google-cloud-pipeline-components==1.0.23)"
       ]
     },
     {
@@ -237,7 +246,7 @@
         "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "6. (optional) You may also specify a service account to use to run Vertex Pipelines in the project.\n",
+        "6. (optional) You may also specify a service account to use to run Vertex AI Pipelines in the project.\n",
         "\n",
         "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
@@ -301,7 +310,7 @@
         "#### Region\n",
         "All BigQuery operations (`DATA_REGION`) are set to run in the `US` multi-region. This is required by the ARIMA pipeline because the data you will be using is stored in this region. All destination tables will also be stored in this region.\n",
         "\n",
-        "You may change the `REGION` variable, which is used for Vertex Forecasting operations\n",
+        "You may change the `REGION` variable, which is used for Vertex AI Forecasting operations\n",
         "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",
@@ -321,8 +330,11 @@
       },
       "outputs": [],
       "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
         "DATA_REGION = \"US\"  # @param {type: \"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}"
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -331,9 +343,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -344,9 +356,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -357,7 +376,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated.\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",
@@ -392,8 +411,11 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\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",
@@ -401,10 +423,9 @@
         "\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. Alternatively, you may edit this notebook to authenticate using\n",
-        "    # gcloud.\n",
+        "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
       ]
     },
     {
@@ -417,7 +438,7 @@
         "\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."
       ]
@@ -451,9 +472,9 @@
       "outputs": [],
       "source": [
         "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID\n",
         "\n",
-        "! gsutil ls -b $BUCKET_URI || gsutil mb -l $DATA_REGION $BUCKET_URI"
+        "! gsutil ls -b $BUCKET_URI || gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -511,9 +532,9 @@
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "## Initialize Vertex SDK for Python\n",
+        "## Initialize Vertex AI SDK for Python\n",
         "\n",
-        "Initialize the Vertex SDK for Python for your project and corresponding bucket."
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -555,8 +576,8 @@
       },
       "outputs": [],
       "source": [
-        "arima_dataset_name = f\"forecasting_demo_arima_{TIMESTAMP}\"\n",
-        "vertex_dataset_name = f\"forecasting_demo_vertex_{TIMESTAMP}\"\n",
+        "arima_dataset_name = f\"forecasting_demo_arima_{UUID}\"\n",
+        "vertex_dataset_name = f\"forecasting_demo_vertex_{UUID}\"\n",
         "\n",
         "arima_dataset_path = \".\".join([PROJECT_ID, arima_dataset_name])\n",
         "vertex_dataset_path = \".\".join([PROJECT_ID, vertex_dataset_name])\n",
@@ -789,15 +810,15 @@
         "\n",
         "Now you are ready to start creating your own BQML ARIMA_PLUS model.\n",
         "\n",
-        "Like with Vertex Forecasting, the pipeline you will run will train evaluation models using the training and validation sets and use backtesting to create evaluation metrics on the test set. Finally, a serving model will be produced that uses all available data.\n",
+        "Like with Vertex AI Forecasting, the pipeline you will run will train evaluation models using the training and validation sets and use backtesting to create evaluation metrics on the test set. Finally, a serving model will be produced that uses all available data.\n",
         "\n",
         "**How do you estimate the cost?**\n",
         "\n",
-        "Backtesting will involve training a single BQML model for each period in the test set, so the cost will be a function of the length of the test set. The cost is also multiplied by the number of candidate models trained, which is determined by `max_order`.\n",
+        "Backtesting involves training a single BQML model for each period in the test set, so the cost is a function of the length of the test set after any downsampling done by the windowing strategy. The cost is also multiplied by the number of candidate models trained, which is determined by `max_order`.\n",
         "\n",
-        "According to [BQ pricing](https://cloud.google.com/bigquery-ml/pricing), BQML model creation costs $250 per TB. We'll use a max order of 3, which translates to 20 candidate models when there are multiple time series. Our demo dataset is 3 MB in size, and includes 31 test periods.\n",
+        "According to [BQ pricing](https://cloud.google.com/bigquery-ml/pricing), BQML model creation costs $250 per TB. We'll use a max order of 3, which translates to 20 candidate models when there are multiple time series. Our demo dataset is 3 MB in size, and includes 31 test periods. We window with a stride length of 1, so all periods are used for evaluation.\n",
         "\n",
-        "In this tutorial, the model create stage of the pipeline costs `3 MB * ($250 / 1024^2) * 31 periods * 20 candidates = $0.44`."
+        "In this tutorial, the model create stage of the pipeline costs `3 MB * ($250 / 1024^2) * (31 / 1) periods * 20 candidates = $0.44`."
       ]
     },
     {
@@ -818,47 +839,23 @@
         "\n",
         "- `bigquery_destination_uri`: (optional) BigQuery Dataset URI. Used to export the metrics table and model. If not given, we will create one for the user.\n",
         "- `data_granularity_unit`: Enum used to specify the time granularity (hour, day, week, month, etc).\n",
-        "- `data_source`: JSON for specifying the input data source URI and type. Similar to a Vertex Dataset. Currently supports BigQuery and CSV (in GCS) data sources.\n",
-        "\n",
-        "  It can look like either:\n",
-        "  ```json\n",
-        "  {\n",
-        "    \"big_query_data_source\": {\n",
-        "      \"big_query_table_path\": \"bq://[PROJECT].[DATASET].[TABLE]\"\n",
-        "    }\n",
-        "  }\n",
-        "  ```\n",
-        "  or\n",
-        "  ```json\n",
-        "  {\n",
-        "    \"csv_data_source\": {\n",
-        "      \"csv_filenames\": [ [GCS_PATHS] ],\n",
-        "  }\n",
-        "  ```\n",
+        "- `data_source_csv_filenames` or `data_source_bigquery_table_path`: A URI for either a CSV stored in GCR or a BigQuery table, respectively.\n",
         "- `evaluated_examples_destination_uri\t`: (optional) BigQuery Dataset URI OR Table URI. Used to export the evaluated examples table. Will use bigquery_destination_uri if not provided.\n",
         "- `forecast_horizon`: Integer number of periods to predict.\n",
-        "- `split_spec`: JSON for specifying how data should be split. Supports predefined split and fractional split.\n",
-        "  \n",
-        "  It can look like either:\n",
-        "  ```json\n",
-        "  {\"predefined_split\": {\"key\": \"[SPLIT_COLUMN]\"}}\n",
-        "  ```\n",
-        "  or\n",
-        "  ```json\n",
-        "  {\n",
-        "    \"fraction_split\": {\n",
-        "        \"training_fraction\": 0.8,\n",
-        "        \"validation_fraction\": 0.1,\n",
-        "        \"test_fraction\": 0.1,\n",
-        "    },\n",
-        "  }\n",
-        "  ```\n",
-        "- `target_column_name`: Name of target column.\n",
+        "- A data splitting strategy of either:\n",
+        "  - `predefined_split_key`: A column containing `TRAIN`, `VALIDATE`, or `TEST` to denote the splits for each row.\n",
+        "  -  `training_fraction`, `validation_fraction`, and `test_fraction` to set the fractions to split on chronologically on the time column.\n",
+        "  - `timestamp_split_key` plus the fractions in the previous option to perform fractional splitting on a column other than the time column.\n",
+        "- A windowing strategy of either:\n",
+        "  - `window_column`: A boolean column decides whether or now each row gets considered when calculating the evaluation metrics.\n",
+        "  - `window_stride_length`: Every N rows will be used to compute the evaluation metrics.\n",
+        "  - `window_max_count`: Downsample rows such that only the given number are used to calculate the evaluation metrics.\n",
+        "- `target_column`: Name of target column.\n",
         "- `time_column`: Name of time column.\n",
         "- `time_series_identifier_column`: Name of id column.\n",
         "- `max_order`: Integer between 1 and 5 representing the size of the parameter search space for ARIMA_PLUS. 5 would result in the highest accuracy model, but also the longest training runtime/cost.\n",
         "\n",
-        "The execution of the training pipeline will take around **20 minutes**."
+        "The execution of the training pipeline may take around **20 minutes**."
       ]
     },
     {
@@ -875,31 +872,24 @@
         "forecast_horizon = 30  # @param {type: \"integer\"}\n",
         "data_granularity_unit = \"day\"  # @param {type: \"string\"}\n",
         "split_column = \"split\"  # @param {type: \"string\"}\n",
+        "window_stride_length = 1  # @param {type: \"integer\"}\n",
         "max_order = 3  # @param {type: \"integer\"}\n",
         "override_destination = True  # @param {type: \"boolean\"}\n",
         "\n",
-        "split_spec = {\"predefined_split\": {\"key\": split_column}}\n",
-        "data_source = {\n",
-        "    \"big_query_data_source\": {\n",
-        "        \"big_query_table_path\": TRAINING_DATASET_BQ_PATH,\n",
-        "    },\n",
-        "}\n",
-        "window_config = {\"stride\": 1}\n",
-        "\n",
         "(\n",
         "    train_job_spec_path,\n",
         "    train_parameter_values,\n",
         ") = utils.get_bqml_arima_train_pipeline_and_parameters(\n",
         "    project=PROJECT_ID,\n",
-        "    location=DATA_REGION,\n",
+        "    location=REGION,\n",
         "    time_column=time_column,\n",
         "    time_series_identifier_column=time_series_identifier_column,\n",
-        "    target_column_name=target_column,\n",
+        "    target_column=target_column,\n",
         "    forecast_horizon=forecast_horizon,\n",
         "    data_granularity_unit=data_granularity_unit,\n",
-        "    split_spec=split_spec,\n",
-        "    data_source=data_source,\n",
-        "    window_config=window_config,\n",
+        "    predefined_split_key=split_column,\n",
+        "    data_source_bigquery_table_path=TRAINING_DATASET_BQ_PATH,\n",
+        "    window_stride_length=window_stride_length,\n",
         "    bigquery_destination_uri=arima_dataset_path,\n",
         "    override_destination=override_destination,\n",
         "    max_order=max_order,\n",
@@ -914,9 +904,9 @@
       "source": [
         "### Run the training pipeline\n",
         "\n",
-        "Use the Vertex Python SDK to kick off a training pipeline run. Once the run has started, the following cell will output a link that will allow you to monitor the run. The link should look like this: \n",
+        "Use the Vertex AI Python SDK to kick off a training pipeline run. Once the run has started, the following cell will output a link that will allow you to monitor the run. The link should look like this: \n",
         "\n",
-        "`https://console.cloud.google.com/vertex-ai/locations/[DATA_REGION]/pipelines/runs/[DISPLAY_NAME]`"
+        "`https://console.cloud.google.com/vertex-ai/locations/[REGION]/pipelines/runs/[DISPLAY_NAME]`"
       ]
     },
     {
@@ -928,8 +918,7 @@
       "outputs": [],
       "source": [
         "# The display name should be unique even if this cell is rerun.\n",
-        "now = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
-        "DISPLAY_NAME = f\"forecasting-demo-train-{now}\"\n",
+        "DISPLAY_NAME = f\"forecasting-demo-train-{generate_uuid()}\"\n",
         "\n",
         "job = aiplatform.PipelineJob(\n",
         "    job_id=DISPLAY_NAME,\n",
@@ -1000,27 +989,11 @@
         "Now that your Model resource is trained, you can make a batch prediction using the prediction pipeline, with the following parameters:\n",
         "\n",
         "- `bigquery_destination_uri`: (optional) BigQuery Dataset URI. Used to export the metrics table and model. If not given, we will create one for the user.\n",
-        "- `data_source`: JSON for specifying the input data source URI and type. Similar to a Vertex Dataset. Currently supports BigQuery and CSV (in GCS) data sources.\n",
-        "\n",
-        "  It can look like either:\n",
-        "  ```json\n",
-        "  {\n",
-        "    \"big_query_data_source\": {\n",
-        "      \"big_query_table_path\": \"bq://[PROJECT].[DATASET].[TABLE]\"\n",
-        "    }\n",
-        "  }\n",
-        "  ```\n",
-        "  or\n",
-        "  ```json\n",
-        "  {\n",
-        "    \"csv_data_source\": {\n",
-        "      \"csv_filenames\": [ [GCS_PATHS] ],\n",
-        "  }\n",
-        "  ```\n",
+        "- `data_source_csv_filenames` or `data_source_bigquery_table_path`: A URI for either a CSV stored in GCR or a BigQuery table, respectively.\n",
         "- `generate_explanation`: If True, the predictions table will have some extra xAI columns.\n",
         "- `model_name`: Name of an existing BQML ARIMA_PLUS model to use for predictions.\n",
         "\n",
-        "The execution of the prediction pipeline will take around **5 minutes**."
+        "The execution of the prediction pipeline may take around **5 minutes**."
       ]
     },
     {
@@ -1031,14 +1004,8 @@
       },
       "outputs": [],
       "source": [
-        "data_source = {\n",
-        "    \"big_query_data_source\": {\n",
-        "        \"big_query_table_path\": PREDICTION_DATASET_BQ_PATH,\n",
-        "    },\n",
-        "}\n",
-        "\n",
         "# Get the model name programmatically, you can also find this by looking at the\n",
-        "# execution graph in Vertex Pipelines.\n",
+        "# execution graph in Vertex AI Pipelines.\n",
         "for task_detail in job.gca_resource.job_detail.task_details:\n",
         "    if task_detail.task_name == \"bigquery-create-model-job\":\n",
         "        model_name = task_detail.outputs[\"model\"].artifacts[0].metadata[\"modelId\"]\n",
@@ -1052,9 +1019,9 @@
         "    predict_parameter_values,\n",
         ") = utils.get_bqml_arima_predict_pipeline_and_parameters(\n",
         "    project=PROJECT_ID,\n",
-        "    location=DATA_REGION,\n",
+        "    location=REGION,\n",
         "    model_name=f\"{arima_dataset_path}.{model_name}\",\n",
-        "    data_source=data_source,\n",
+        "    data_source_bigquery_table_path=PREDICTION_DATASET_BQ_PATH,\n",
         "    bigquery_destination_uri=arima_dataset_path,\n",
         ")"
       ]
@@ -1067,9 +1034,9 @@
       "source": [
         "### Run the prediction pipeline\n",
         "\n",
-        "Use the Vertex Python SDK to kick off a prediction pipeline run. Once the run has started, the following cell will output a link that will allow you to monitor the run. The link should look like this: \n",
+        "Use the Vertex AI Python SDK to kick off a prediction pipeline run. Once the run has started, the following cell will output a link that will allow you to monitor the run. The link should look like this: \n",
         "\n",
-        "`https://console.cloud.google.com/vertex-ai/locations/[DATA_REGION]/pipelines/runs/[DISPLAY_NAME]`"
+        "`https://console.cloud.google.com/vertex-ai/locations/[REGION]/pipelines/runs/[DISPLAY_NAME]`"
       ]
     },
     {
@@ -1081,8 +1048,7 @@
       "outputs": [],
       "source": [
         "# The display name should be unique even if this cell is rerun.\n",
-        "now = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
-        "DISPLAY_NAME = f\"forecasting-demo-predict-{now}\"\n",
+        "DISPLAY_NAME = f\"forecasting-demo-predict-{generate_uuid()}\"\n",
         "\n",
         "job = aiplatform.PipelineJob(\n",
         "    job_id=DISPLAY_NAME,\n",
@@ -1114,7 +1080,7 @@
       "outputs": [],
       "source": [
         "# Get the prediction table programmatically, you can also find this by looking at the\n",
-        "# execution graph in Vertex Pipelines.\n",
+        "# execution graph in Vertex AI Pipelines.\n",
         "for task_detail in job.gca_resource.job_detail.task_details:\n",
         "    if task_detail.task_name == \"bigquery-query-job\":\n",
         "        pred_table = (\n",
@@ -1239,7 +1205,7 @@
         "id": "59qKXL9ARO97"
       },
       "source": [
-        "# Compare Against Vertex Forecasting"
+        "# Compare Against Vertex AI Forecasting"
       ]
     },
     {
@@ -1268,7 +1234,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TimeSeriesDataset.create(\n",
-        "    display_name=\"forecasting_demo_train\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"forecasting_demo_train\" + \"_\" + UUID,\n",
         "    bq_source=[TRAINING_DATASET_BQ_PATH],\n",
         ")\n",
         "print(dataset.resource_name)"
@@ -1314,11 +1280,12 @@
         "    \"product\": \"categorical\",\n",
         "    \"holiday\": \"categorical\",\n",
         "}\n",
-        "available_at_forecast_columns = [\n",
+        "available_at_forecast_columns_ = [\n",
         "    \"date\",\n",
         "    \"advertisement\",\n",
         "    \"holiday\",\n",
-        "]  # @param {type: \"raw\"}\n",
+        "]\n",
+        "available_at_forecast_columns = available_at_forecast_columns_  # @param {type: \"raw\"}\n",
         "unavailable_at_forecast_columns = [\"sales\"]  # @param {type: \"raw\"}\n",
         "time_series_attribute_columns = [\"store\", \"product\"]  # @param {type: \"raw\"}\n",
         "context_window = 30  # @param {type: \"integer\"}\n",
@@ -1334,7 +1301,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DISPLAY_NAME = f\"forecasting-demo-model_{TIMESTAMP}\"\n",
+        "MODEL_DISPLAY_NAME = f\"forecasting-demo-model_{UUID}\"\n",
         "\n",
         "training_job = aiplatform.AutoMLForecastingTrainingJob(\n",
         "    display_name=MODEL_DISPLAY_NAME,\n",
@@ -1370,7 +1337,7 @@
         "\n",
         "The `run` method, when completed, returns the `Model` resource.\n",
         "\n",
-        "The execution of the training pipeline will take up to **one hour**. You can learn about the pricing for Vertex Forecasting [here](https://cloud.google.com/vertex-ai/pricing#tabular-data)."
+        "The execution of the training pipeline may take up to **one hour**. You can learn about the pricing for Vertex AI Forecasting [here](https://cloud.google.com/vertex-ai/pricing#tabular-data)."
       ]
     },
     {
@@ -1397,6 +1364,7 @@
         "    budget_milli_node_hours=budget_milli_node_hours,\n",
         "    model_display_name=MODEL_DISPLAY_NAME,\n",
         "    predefined_split_column_name=split_column,\n",
+        "    window_stride_length=window_stride_length,\n",
         ")"
       ]
     },
@@ -1453,7 +1421,7 @@
         "\n",
         "Now that you have backtesting metrics from both models, you can compare the two side-by-side.\n",
         "\n",
-        "Since the sales in this dataset were a function of covariates, we should expect the MAE, RMSE, and MAPE to be lower when using Vertex Forecasting. The BQML ARIMA_PLUS evaluation metrics show the relative impact of including these additional features in a model."
+        "Since the sales in this dataset were a function of covariates, we should expect the MAE, RMSE, and MAPE to be lower when using Vertex AI Forecasting. The BQML ARIMA_PLUS evaluation metrics show the relative impact of including these additional features in a model."
       ]
     },
     {
@@ -1475,7 +1443,7 @@
       "source": [
         "## Send a batch prediction request\n",
         "\n",
-        "The following section shows how you can send a batch prediction to your Vertex Forecasting model in case you want to compare the models at serving time."
+        "The following section shows how you can send a batch prediction to your Vertex AI Forecasting model in case you want to compare the models at serving time."
       ]
     },
     {
@@ -1507,7 +1475,7 @@
       "outputs": [],
       "source": [
         "batch_prediction_job = model.batch_predict(\n",
-        "    job_display_name=f\"forecasting_demo_predictions_{TIMESTAMP}\",\n",
+        "    job_display_name=f\"forecasting_demo_predictions_{UUID}\",\n",
         "    bigquery_source=PREDICTION_DATASET_BQ_PATH,\n",
         "    instances_format=\"bigquery\",\n",
         "    bigquery_destination_prefix=f\"bq://{vertex_dataset_path}\",\n",
@@ -1528,7 +1496,7 @@
         "\n",
         "Next, wait for the batch job to complete. Alternatively, you can set the parameter `sync` to `True` in the `batch_predict()` method to block until the batch prediction job is completed.\n",
         "\n",
-        "The execution of the prediction pipeline will take up to 30 minutes.\n"
+        "The execution of the prediction pipeline may take up to 30 minutes.\n"
       ]
     },
     {
@@ -1595,7 +1563,7 @@
       },
       "outputs": [],
       "source": [
-        "print(\"Click the link below to view Vertex Forecasting predictions:\")\n",
+        "print(\"Click the link below to view Vertex AI Forecasting predictions:\")\n",
         "print(\n",
         "    get_data_studio_link(\n",
         "        batch_prediction_bq_input_uri=actuals_table,\n",
@@ -1613,7 +1581,7 @@
         "id": "cleanup:mbsdk"
       },
       "source": [
-        "## Clean up Vertex and BigQuery resources\n",
+        "## Clean up Vertex AI and BigQuery resources\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",

notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb

@@ -855,6 +855,7 @@
         "    run_distillation=run_distillation,\n",
         "    dataflow_subnetwork=dataflow_subnetwork,\n",
         "    dataflow_use_public_ips=dataflow_use_public_ips,\n",
+        "    export_additional_model_without_custom_ops=export_additional_model_without_custom_ops,\n",
         ")\n",
         "\n",
         "job_id = \"automl-tabular-{}\".format(uuid.uuid4())\n",

notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# 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",
@@ -66,17 +66,6 @@
         "This tutorial demonstrates how to use the Vertex AI SDK to create image object detection models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:salads,iod"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and the corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -101,6 +90,17 @@
         "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:salads,iod"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the Salads category of the [OpenImages dataset](https://www.tensorflow.org/datasets/catalog/open_images_v4) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the bounding box locations and the corresponding type of salad items in an image from a class of five items: salad, seafood, tomato, baked goods, or cheese."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -201,7 +201,7 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
+        "! pip3 install -U --upgrade tensorflow google-cloud-storage $USER_FLAG"
       ]
     },
     {
@@ -213,17 +213,6 @@
         "Install the latest version of *tensorflow* library."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install --upgrade tensorflow $USER_FLAG"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -383,9 +372,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -396,9 +385,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -409,7 +405,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated.\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",
@@ -494,7 +490,7 @@
       "outputs": [],
       "source": [
         "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + UUID"
       ]
     },
     {
@@ -669,7 +665,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.ImageDataset.create(\n",
-        "    display_name=\"Salads\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"Salads\" + \"_\" + UUID,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.image.bounding_box,\n",
         ")\n",
@@ -717,7 +713,7 @@
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLImageTrainingJob(\n",
-        "    display_name=\"salads_\" + TIMESTAMP,\n",
+        "    display_name=\"salads_\" + UUID,\n",
         "    prediction_type=\"object_detection\",\n",
         "    multi_label=False,\n",
         "    model_type=\"CLOUD\",\n",
@@ -760,7 +756,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"salads_\" + TIMESTAMP,\n",
+        "    model_display_name=\"salads_\" + UUID,\n",
         "    training_fraction_split=0.8,\n",
         "    validation_fraction_split=0.1,\n",
         "    test_fraction_split=0.1,\n",
@@ -790,7 +786,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=\"display_name=salads_\" + TIMESTAMP)\n",
+        "models = aiplatform.Model.list(filter=\"display_name=salads_\" + UUID)\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -961,7 +957,7 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"salads_\" + TIMESTAMP,\n",
+        "    job_display_name=\"salads_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    machine_type=\"n1-standard-4\",\n",

notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb

@@ -68,18 +68,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "dataset:covid,forecast"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial a time series dataset containing samples drawn from the Iowa Liquor Retail Sales dataset. Data were made available by the Iowa Department of Commerce. It is provided under the Creative Commons Zero v1.0 Universal license. For more details, see: https://console.cloud.google.com/marketplace/product/iowa-department-of-commerce/iowa-liquor-sales. This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in BigQuery."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "objective:automl,training,batch_prediction"
+        "id": "02b9af111927"
       },
       "source": [
         "### Objective\n",
@@ -97,7 +86,18 @@
         "- Create a `Vertex AI Dataset` resource.\n",
         "- Train an `AutoML` tabular forecasting `Model` resource.\n",
         "- Obtain the evaluation metrics for the `Model` resource.\n",
-        "- Make a batch prediction.\n"
+        "- Make a batch prediction."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:covid,forecast"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is a time series dataset containing samples drawn from the Iowa Liquor Retail Sales dataset. Data is made available by the Iowa Department of Commerce. It is provided under the Creative Commons Zero v1.0 Universal license. For more details, see: https://console.cloud.google.com/marketplace/product/iowa-department-of-commerce/iowa-liquor-sales. This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in BigQuery."
       ]
     },
     {
@@ -128,29 +128,38 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Workbench AI Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "**If you are using Colab or Vertex AI Workbench 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. You need the following:\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
         "\n",
-        "- The Cloud Storage SDK\n",
-        "- Git\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\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 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",
+        "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 SDK](https://cloud.google.com/sdk/docs/).\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
         "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "1. [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",
+        "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",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
         "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "1. 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"
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
       ]
     },
     {
@@ -161,7 +170,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the following packages required to execute this notebook. "
       ]
     },
     {
@@ -175,7 +184,7 @@
         "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_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
         "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
         "    \"/opt/deeplearning/metadata/env_version\"\n",
         ")\n",
@@ -185,8 +194,7 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
-        "! pip3 install --upgrade tensorflow $USER_FLAG -q"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -197,7 +205,7 @@
       "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."
+        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
@@ -208,6 +216,7 @@
       },
       "outputs": [],
       "source": [
+        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -218,34 +227,48 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0e3cab0cc491"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "before_you_begin:nogpu"
       },
       "source": [
-        "## Before you begin\n",
-        "\n",
-        "### GPU runtime\n",
-        "\n",
-        "This tutorial does not require a GPU runtime.\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 $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
         "\n",
-        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1460fd744366"
+      },
+      "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`."
       ]
     },
     {
@@ -294,7 +317,7 @@
         "#### Region\n",
         "\n",
         "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
         "\n",
         "- Americas: `us-central1`\n",
         "- Europe: `europe-west4`\n",
@@ -302,7 +325,7 @@
         "\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)"
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -325,9 +348,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -338,9 +361,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -351,23 +381,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Workbench AI Notebooks**, your environment is already authenticated. Skip this step.\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 when prompted to authenticate your account via oAuth.\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",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\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",
-        "**Click Create service account**.\n",
+        "2. Click **Create service account**.\n",
         "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   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",
+        "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",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "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."
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell.\n"
       ]
     },
     {
@@ -438,9 +476,9 @@
       },
       "outputs": [],
       "source": [
-        "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"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -460,7 +498,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_URI"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
@@ -489,9 +527,6 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -503,7 +538,10 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aiplatform"
+        "import urllib\n",
+        "\n",
+        "import google.cloud.aiplatform as aiplatform\n",
+        "from google.cloud import bigquery"
       ]
     },
     {
@@ -589,7 +627,7 @@
       "outputs": [],
       "source": [
         "dataset = aiplatform.TimeSeriesDataset.create(\n",
-        "    display_name=\"iowa_liquor_sales_train\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"iowa_liquor_sales_train\" + \"_\" + UUID,\n",
         "    bq_source=[TRAINING_DATASET_BQ_PATH],\n",
         ")\n",
         "\n",
@@ -649,7 +687,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DISPLAY_NAME = f\"iowa-liquor-sales-forecast-model_{TIMESTAMP}\"\n",
+        "MODEL_DISPLAY_NAME = f\"iowa-liquor-sales-forecast-model_{UUID}\"\n",
         "\n",
         "training_job = aiplatform.AutoMLForecastingTrainingJob(\n",
         "    display_name=MODEL_DISPLAY_NAME,\n",
@@ -772,11 +810,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "from google.cloud import bigquery\n",
-        "\n",
-        "batch_predict_bq_output_dataset_name = f\"iowa_liquor_sales_predictions_{TIMESTAMP}\"\n",
+        "batch_predict_bq_output_dataset_name = f\"iowa_liquor_sales_predictions_{UUID}\"\n",
         "batch_predict_bq_output_dataset_path = \"{}.{}\".format(\n",
         "    PROJECT_ID, batch_predict_bq_output_dataset_name\n",
         ")\n",
@@ -820,7 +854,7 @@
         ")\n",
         "\n",
         "batch_prediction_job = model.batch_predict(\n",
-        "    job_display_name=f\"iowa_liquor_sales_forecasting_predictions_{TIMESTAMP}\",\n",
+        "    job_display_name=f\"iowa_liquor_sales_forecasting_predictions_{UUID}\",\n",
         "    bigquery_source=PREDICTION_DATASET_BQ_PATH,\n",
         "    instances_format=\"bigquery\",\n",
         "    bigquery_destination_prefix=batch_predict_bq_output_uri_prefix,\n",
@@ -901,8 +935,6 @@
       },
       "outputs": [],
       "source": [
-        "import urllib\n",
-        "\n",
         "tables = client.list_tables(batch_predict_bq_output_dataset_path)\n",
         "\n",
         "prediction_table_id = \"\"\n",
@@ -1012,9 +1044,6 @@
       },
       "outputs": [],
       "source": [
-        "# Set this to true only if you'd like to delete your bucket\n",
-        "delete_bucket = False\n",
-        "\n",
         "# Delete dataset\n",
         "dataset.delete()\n",
         "\n",
@@ -1027,6 +1056,9 @@
         "# Delete batch prediction job\n",
         "batch_prediction_job.delete()\n",
         "\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
+        "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]

notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 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",

notebooks/official/automl/sdk_automl_video_classification_batch.ipynb

@@ -3,6 +3,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "91417fdd",
       "metadata": {
         "id": "copyright"
       },
@@ -25,11 +26,12 @@
     },
     {
       "cell_type": "markdown",
+      "id": "f2902dac",
       "metadata": {
         "id": "title"
       },
       "source": [
-        "# Vertex SDK: AutoML training video classification model for batch prediction\n",
+        "# Vertex AI SDK: AutoML training video classification model for batch prediction\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -55,6 +57,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "42cfbec0",
       "metadata": {
         "id": "overview:automl"
       },
@@ -62,29 +65,25 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to create video classification models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:hmdb,vcn"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset 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.\n"
+        "This tutorial demonstrates how to use the Vertex AI SDK to create video classification models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "90b9b726",
       "metadata": {
         "id": "objective:automl,training,batch_prediction"
       },
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML video classification model from a Python script, and then do a batch prediction using the Vertex SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "In this tutorial, you create an AutoML video classification model from a Python script, and then do a batch prediction using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services and resources:\n",
+        "\n",
+        "- Vertex AI Training\n",
+        "- Vertex AI Models\n",
+        "- Vertex AI Batch Prediction\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -102,6 +101,19 @@
     },
     {
       "cell_type": "markdown",
+      "id": "44940826",
+      "metadata": {
+        "id": "dataset:hmdb,vcn"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the golf swing recognition portion of the [Human Motion dataset from MIT](http://cbcl.mit.edu/publications/ps/Kuehne_etal_iccv11.pdf). The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket. The trained model predicts the start frame where a golf swing begins.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "7183fc01",
       "metadata": {
         "id": "costs"
       },
@@ -122,89 +134,96 @@
     },
     {
       "cell_type": "markdown",
+      "id": "b88c255b-df72-4666-9403-0c96d7e657ca",
       "metadata": {
-        "id": "setup_local"
+        "id": "384b53dfdb54"
       },
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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 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 SDK](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"
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step."
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "8c1be8fc",
+      "metadata": {
+        "id": "setup_local"
+      },
+      "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.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "e131fbee",
       "metadata": {
         "id": "install_aip:mbsdk"
       },
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the latest versions of Vertex AI and Cloud Storage SDK for Python."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "484dcd52-ef9e-4928-b0f2-7940001bbc2e",
       "metadata": {
-        "id": "install_aip:mbsdk"
+        "id": "2abdd254e90f"
       },
       "outputs": [],
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\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",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_storage"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-storage* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_storage"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+        "! pip3 install -U google-cloud-storage {USER_FLAG} -q"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "aa8cefcd",
       "metadata": {
         "id": "restart"
       },
@@ -217,6 +236,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "4f079854",
       "metadata": {
         "id": "restart"
       },
@@ -234,6 +254,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "e96a43b8",
       "metadata": {
         "id": "before_you_begin:nogpu"
       },
@@ -254,19 +275,32 @@
         "\n",
         "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
-        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
         "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these conmmands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "305e7fa5-dcaf-477a-b20d-d9b69ecba381",
+      "metadata": {
+        "id": "1460fd744366"
+      },
+      "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,
+      "id": "ffd7caab-c2f8-41d3-a0e3-d2519f0bcf2c",
       "metadata": {
-        "id": "set_project_id"
+        "id": "cd85f5c794e5"
       },
       "outputs": [],
       "source": [
@@ -276,8 +310,9 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ffb8077b",
       "metadata": {
-        "id": "autoset_project_id"
+        "id": "set_project_id"
       },
       "outputs": [],
       "source": [
@@ -291,6 +326,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "3c30f77a",
       "metadata": {
         "id": "set_gcloud_project_id"
       },
@@ -301,6 +337,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "61221789",
       "metadata": {
         "id": "region"
       },
@@ -322,68 +359,99 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "e05b6148",
       "metadata": {
         "id": "region"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "dab6b689",
       "metadata": {
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "6dac7084",
       "metadata": {
         "id": "timestamp"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "1bd3f05b-f17f-4341-be85-0bdcef3e6f13",
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "79055ac4078d"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud 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",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. Skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "c38fbff8",
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "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",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\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",
-        "**Click Create service account**.\n",
+        "2. Click **Create service account**.\n",
         "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   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",
+        "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",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "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."
+        "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,
+      "id": "8bae9ca0",
       "metadata": {
         "id": "gcp_authenticate"
       },
@@ -397,8 +465,11 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\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",
@@ -413,6 +484,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "bbda1639",
       "metadata": {
         "id": "bucket:mbsdk"
       },
@@ -421,36 +493,42 @@
         "\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 create a model in Vertex AI using the Cloud SDK, you give a Cloud Storage path where the trained model is saved. In this tutorial, you create a batch prediction job using the Vertex AI model. For this purpose, you need to save your test instances to a Cloud Storage bucket and give a destination Cloud Storage path to write the batch predictions.\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."
+        "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
+        "Cloud Storage buckets."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "be69ad8c",
       "metadata": {
         "id": "bucket"
       },
       "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}\""
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "2d0d674c",
       "metadata": {
         "id": "autoset_bucket"
       },
       "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-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "9307a615",
       "metadata": {
         "id": "create_bucket"
       },
@@ -461,16 +539,18 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "709e7b95",
       "metadata": {
         "id": "create_bucket"
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "b52bb2e6",
       "metadata": {
         "id": "validate_bucket"
       },
@@ -481,72 +561,76 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "e86c8b22",
       "metadata": {
         "id": "validate_bucket"
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "cf0222d3",
       "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"
+        "### Import libraries"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 13,
+      "id": "7534d1a5",
       "metadata": {
         "id": "import_aip:mbsdk"
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aiplatform"
+        "from google.cloud import aiplatform"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "15e5e61a",
       "metadata": {
         "id": "init_aip:mbsdk"
       },
       "source": [
-        "## Initialize Vertex SDK for Python\n",
+        "### Initialize Vertex AI SDK for Python\n",
         "\n",
-        "Initialize the Vertex SDK for Python for your project and corresponding bucket."
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "9df9b0b9",
       "metadata": {
         "id": "init_aip:mbsdk"
       },
       "outputs": [],
       "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "866ae45f",
       "metadata": {
         "id": "tutorial_start:automl"
       },
       "source": [
-        "# Tutorial\n",
+        "## Tutorial\n",
         "\n",
         "Now you are ready to start creating your own AutoML video classification model."
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "0adbd455",
       "metadata": {
         "id": "import_file:u_dataset,csv"
       },
@@ -559,6 +643,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ab42c2d4",
       "metadata": {
         "id": "import_file:hmdb,csv,vcn"
       },
@@ -569,6 +654,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "2f7757ea",
       "metadata": {
         "id": "quick_peek:csv"
       },
@@ -583,6 +669,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ea7bac53",
       "metadata": {
         "id": "quick_peek:csv"
       },
@@ -597,6 +684,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "aeadee6e",
       "metadata": {
         "id": "create_dataset:video,vcn"
       },
@@ -614,13 +702,14 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "9c55581d",
       "metadata": {
         "id": "create_dataset:video,vcn"
       },
       "outputs": [],
       "source": [
         "dataset = aiplatform.VideoDataset.create(\n",
-        "    display_name=\"MIT Human Motion\" + \"_\" + TIMESTAMP,\n",
+        "    display_name=\"MIT Human Motion\" + \"_\" + UUID,\n",
         "    gcs_source=[IMPORT_FILE],\n",
         "    import_schema_uri=aiplatform.schema.dataset.ioformat.video.classification,\n",
         ")\n",
@@ -630,6 +719,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "26f09f81",
       "metadata": {
         "id": "create_automl_pipeline:video,vcn"
       },
@@ -652,13 +742,14 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "9f35d88f",
       "metadata": {
         "id": "create_automl_pipeline:video,vcn"
       },
       "outputs": [],
       "source": [
         "job = aiplatform.AutoMLVideoTrainingJob(\n",
-        "    display_name=\"hmdb_\" + TIMESTAMP,\n",
+        "    display_name=\"hmdb_\" + UUID,\n",
         "    prediction_type=\"classification\",\n",
         ")\n",
         "\n",
@@ -667,6 +758,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "6bbaaf5f",
       "metadata": {
         "id": "run_automl_pipeline:video"
       },
@@ -688,6 +780,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "4b3f2c56",
       "metadata": {
         "id": "run_automl_pipeline:video"
       },
@@ -695,7 +788,7 @@
       "source": [
         "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"hmdb_\" + TIMESTAMP,\n",
+        "    model_display_name=\"hmdb_\" + UUID,\n",
         "    training_fraction_split=0.8,\n",
         "    test_fraction_split=0.2,\n",
         ")"
@@ -703,6 +796,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "6d9e9f29",
       "metadata": {
         "id": "evaluate_the_model:mbsdk"
       },
@@ -710,35 +804,38 @@
         "## 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."
+        "You can check the model's evaluation results using the `get_model_evaluation` method of the Vertex AI Model resource.\n",
+        "\n",
+        "Just like Vertex AI datasets, you can either use the reference to the model variable you created when you deployed the model or you can filter from the list of all of the models in your project using the model's display name as given below."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "59a76fa5",
       "metadata": {
         "id": "evaluate_the_model:mbsdk"
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=\"display_name=hmdb_\" + TIMESTAMP)\n",
+        "# Get model resource ID using the display_name\n",
+        "models = aiplatform.Model.list(filter=\"display_name=hmdb_\" + UUID)\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aiplatform.gapic.ModelServiceClient(\n",
-        "    client_options=client_options\n",
-        ")\n",
+        "if len(models) != 0:\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)"
+        "    # Get the model object\n",
+        "    model_rsc_name = models[0].resource_name\n",
+        "    print(\"Model resource name:\", model_rsc_name)\n",
+        "    model = aiplatform.Model(model_rsc_name)\n",
+        "\n",
+        "    # Print the model evaluation\n",
+        "    model_eval = model.get_model_evaluation()\n",
+        "    print(model_eval.to_dict())"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "060d3bae",
       "metadata": {
         "id": "make_prediction"
       },
@@ -750,18 +847,20 @@
     },
     {
       "cell_type": "markdown",
+      "id": "e614b9bf",
       "metadata": {
         "id": "get_test_items:batch_prediction"
       },
       "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."
+        "Now do a batch prediction to your Vertex AI model. You use arbitrary examples from the dataset as a test items. Don't be concerned that the examples were likely used in training the model as this tutorial is just about how to make a batch prediction."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "bae97d10",
       "metadata": {
         "id": "get_test_items:automl,vcn,csv"
       },
@@ -783,13 +882,14 @@
     },
     {
       "cell_type": "markdown",
+      "id": "54138ea2",
       "metadata": {
         "id": "make_batch_file:automl,video"
       },
       "source": [
         "### Make a batch input file\n",
         "\n",
-        "Now make a batch input file, which you 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 video. The dictionary contains the key/value pairs:\n",
+        "Now make a batch input file, which you store in your local Cloud Storage bucket. The batch input file can be either CSV or JSONL. You use JSONL in this tutorial. For JSONL file, you make one dictionary entry per line for each video. The dictionary contains the key/value pairs:\n",
         "\n",
         "- `content`: The Cloud Storage path to the video.\n",
         "- `mimeType`: The content type. In our example, it is a `avi` file.\n",
@@ -800,6 +900,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ce7da5dd",
       "metadata": {
         "id": "make_batch_file:automl,video"
       },
@@ -810,7 +911,7 @@
         "from google.cloud import storage\n",
         "\n",
         "test_filename = \"test.jsonl\"\n",
-        "gcs_input_uri = BUCKET_NAME + \"/\" + test_filename\n",
+        "gcs_input_uri = BUCKET_URI + \"/\" + test_filename\n",
         "\n",
         "data_1 = {\n",
         "    \"content\": test_item_1,\n",
@@ -826,42 +927,66 @@
         "}\n",
         "\n",
         "\n",
-        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_NAME.replace(\"gs://\", \"\"))\n",
+        "bucket = storage.Client(project=PROJECT_ID).bucket(BUCKET_NAME)\n",
         "blob = bucket.blob(blob_name=test_filename)\n",
         "data = json.dumps(data_1) + \"\\n\" + json.dumps(data_2) + \"\\n\"\n",
         "blob.upload_from_string(data)\n",
-        "print(gcs_input_uri)\n",
+        "print(gcs_input_uri)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "5bbefe4a-e05f-4ed7-acf8-a0588757c376",
+      "metadata": {
+        "id": "d56366168ec5"
+      },
+      "source": [
+        "### Check input content\n",
+        "Check the contents of the `test.jsonl`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "a98d1c39-29f2-40c7-8267-91afebb8a440",
+      "metadata": {
+        "id": "378131e21a7e"
+      },
+      "outputs": [],
+      "source": [
         "! gsutil cat $gcs_input_uri"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "105f3bc5",
       "metadata": {
         "id": "batch_request:mbsdk"
       },
       "source": [
         "### Make the batch prediction request\n",
         "\n",
-        "Now that your Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
+        "Now that your Vertex AI Model resource is trained, you can make a batch prediction by invoking the batch_predict() method, with the following parameters:\n",
         "\n",
         "- `job_display_name`: The human readable name for the batch prediction job.\n",
         "- `gcs_source`: A list of one or more batch request input files.\n",
         "- `gcs_destination_prefix`: The Cloud Storage location for storing the batch prediction resuls.\n",
-        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+        "- `sync`: If set to True, the call blocks while waiting for the asynchronous batch job to complete."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "5657e704",
       "metadata": {
         "id": "batch_request:mbsdk"
       },
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"hmdb_\" + TIMESTAMP,\n",
+        "    job_display_name=\"hmdb_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_NAME,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
         "    sync=False,\n",
         ")\n",
         "\n",
@@ -870,6 +995,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "c86ec9ec",
       "metadata": {
         "id": "batch_request_wait:mbsdk"
       },
@@ -882,6 +1008,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "2f108cc8",
       "metadata": {
         "id": "batch_request_wait:mbsdk"
       },
@@ -892,6 +1019,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "63e33110",
       "metadata": {
         "id": "get_batch_prediction:mbsdk,vcn"
       },
@@ -914,6 +1042,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "a76f3f2c",
       "metadata": {
         "id": "get_batch_prediction:mbsdk,vcn"
       },
@@ -928,7 +1057,7 @@
         "\n",
         "for prediction_result in prediction_results:\n",
         "    gfile_name = f\"gs://{bp_iter_outputs.bucket.name}/{prediction_result}\".replace(\n",
-        "        BUCKET_NAME + \"/\", \"\"\n",
+        "        BUCKET_URI + \"/\", \"\"\n",
         "    )\n",
         "    data = bucket.get_blob(gfile_name).download_as_string()\n",
         "    data = json.loads(data)\n",
@@ -937,11 +1066,12 @@
     },
     {
       "cell_type": "markdown",
+      "id": "000413e5",
       "metadata": {
         "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",
@@ -958,6 +1088,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "7761ab4d",
       "metadata": {
         "id": "cleanup:mbsdk"
       },
@@ -979,8 +1110,8 @@
         "batch_predict_job.delete()\n",
         "\n",
         "# Delete the Cloud storage bucket\n",
-        "if delete_bucket is True:\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/bigquery_ml/bqml-online-prediction.ipynb

@@ -32,18 +32,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.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/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.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/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.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",
@@ -63,7 +63,7 @@
         "\n",
         "### Dataset\n",
         "\n",
-        "The dataset, [available publicly on BigQuery](https://console.cloud.google.com/bigquery?project=bigquery-public-data&d=ga4_obfuscated_sample_ecommerce&p=bigquery-public-data&page=dataset), comes from obfuscated [Google Analytics 4 data](https://support.google.com/analytics/answer/10937659) from the [Google Merchandise Store](https://shop.googlemerchandisestore.com/).\n",
+        "The dataset, <a href=\"https://console.cloud.google.com/bigquery?project=bigquery-public-data&d=ga4_obfuscated_sample_ecommerce&p=bigquery-public-data&page=dataset\" target=\"_blank\">available publicly on BigQuery</a>, comes from obfuscated <a href=\"https://support.google.com/analytics/answer/10937659\" target=\"_blank\">Google Analytics 4 data</a> from the <a href=\"https://shop.googlemerchandisestore.com/\" target=\"_blank\">Google Merchandise Store</a>).\n",
         "\n",
         "### Objective\n",
         "\n",
@@ -95,9 +95,9 @@
         "* Vertex AI\n",
         "\n",
         "\n",
-        "Learn about [BigQuery Pricing](https://cloud.google.com/bigquery/pricing), [BigQuery ML pricing](https://cloud.google.com/bigquery-ml/pricing), [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "Learn about <a href=\"https://cloud.google.com/bigquery/pricing\" target=\"_blank\">BigQuery Pricing</a>, <a href=\"https://cloud.google.com/bigquery-ml/pricing\" target=\"_blank\">BigQuery ML pricing</a>, <a href=\"https://cloud.google.com/vertex-ai/pricing\" target=\"_blank\">Vertex AI\n",
+        "pricing</a>, and use the <a href=\"https://cloud.google.com/products/calculator/\" target=\"_blank\">Pricing\n",
+        "Calculator</a>\n",
         "to generate a cost estimate based on your projected usage."
       ]
     },
@@ -128,18 +128,18 @@
         "* 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",
+        "The Google Cloud guide to <a href=\"https://cloud.google.com/python/setup\" target=\"_blank\">Setting up a Python development\n",
+        "environment</a> and the <a href=\"https://jupyter.org/install\" target=\"_blank\">Jupyter\n",
+        "installation guide</a> 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",
+        "1. <a href=\"https://cloud.google.com/sdk/docs/\" target=\"_blank\">Install and initialize the Cloud SDK.</a>\n",
         "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "1. <a href=\"https://cloud.google.com/python/setup#installing_python\" target=\"_blank\">Install Python 3.</a>\n",
         "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "1. <a href=\"https://cloud.google.com/python/setup#installing_and_using_virtualenv\" target=\"_blank\">Install\n",
+        "   virtualenv</a>\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",
@@ -234,13 +234,13 @@
         "\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",
+        "1. <a href=\"https://console.cloud.google.com/cloud-resource-manager\" target=\"_blank\">Select or create a Google Cloud project</a>. 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",
+        "1. <a href=\"https://cloud.google.com/billing/docs/how-to/modify-project\" target=\"_blank\">Make sure that billing is enabled for your project</a>.\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "1. <a href=\"https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com\" target=\"_blank\">Enable the Vertex AI API</a>.\n",
         "\n",
-        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "1. If you are running this notebook locally, you will need to install the <a href=\"https://cloud.google.com/sdk\" target=\"_blank\">Cloud SDK</a>.\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",
@@ -267,7 +267,7 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"YOUR-PROJECT-ID\"\n",
+        "PROJECT_ID = \"[YOUR-PROJECT-ID]\"\n",
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
         "import os\n",
@@ -314,9 +314,9 @@
         "- 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",
+        "You might not be able to 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)."
+        "Learn more about <a href=\"https://cloud.google.com/vertex-ai/docs/general/locations\" target=\"_blank\">Vertex AI regions</a>."
       ]
     },
     {
@@ -339,9 +339,9 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -352,9 +352,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -380,8 +387,7 @@
         "\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",
+        "1. In the Cloud Console, go to the <a href=\"https://console.cloud.google.com/apis/credentials/serviceaccountkey\" target=\"_blank\">**Create service account key** page</a>.\n",
         "\n",
         "2. Click **Create service account**.\n",
         "\n",
@@ -486,7 +492,10 @@
       },
       "outputs": [],
       "source": [
+        "from typing import Union\n",
+        "\n",
         "import google.cloud.aiplatform as vertex_ai\n",
+        "import pandas as pd\n",
         "from google.cloud import bigquery"
       ]
     },
@@ -550,24 +559,17 @@
       "outputs": [],
       "source": [
         "# Wrapper to use BigQuery client to run query/job, return job ID or result as DF\n",
-        "def bq_query(sql):\n",
+        "def run_bq_query(sql: str) -> Union[str, pd.DataFrame]:\n",
         "    \"\"\"\n",
         "    Input: SQL query, as a string, to execute in BigQuery\n",
         "    Returns the query results as a pandas DataFrame, or error, if any\n",
         "    \"\"\"\n",
-        "    # Import Exceptions library to help with dataset error catching\n",
-        "    from google.cloud.exceptions import BadRequest\n",
         "\n",
         "    # Try dry run before executing query to catch any errors\n",
-        "    try:\n",
-        "        job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)\n",
-        "\n",
-        "        bq_client.query(sql, job_config=job_config)\n",
-        "\n",
-        "    except BadRequest as err:\n",
-        "        print(err)\n",
-        "        return\n",
+        "    job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)\n",
+        "    bq_client.query(sql, job_config=job_config)\n",
         "\n",
+        "    # If dry run succeeds without errors, proceed to run query\n",
         "    job_config = bigquery.QueryJobConfig()\n",
         "    client_result = bq_client.query(sql, job_config=job_config)\n",
         "\n",
@@ -589,7 +591,7 @@
         "\n",
         "BigQuery ML (BQML) provides the capability to train ML tabular models, such as classification, regression, forecasting, and matrix factorization, in BigQuery using SQL syntax directly. BigQuery ML uses the scalable infrastructure of BigQuery ML so you don't need to set up additional infrastructure for training or batch serving.\n",
         "\n",
-        "Learn more about [BigQuery ML documentation](https://cloud.google.com/bigquery-ml/docs)."
+        "Learn more about <a href=\"https://cloud.google.com/bigquery-ml/docs\" target=\"_blank\">BigQuery ML documentation</a>."
       ]
     },
     {
@@ -600,9 +602,13 @@
       },
       "outputs": [],
       "source": [
-        "BQ_DATASET_NAME = \"ga4_churnprediction\"\n",
+        "BQ_DATASET_NAME = f\"ga4_churnprediction_{UUID}\"\n",
         "\n",
-        "bq_query(f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\")"
+        "sql_create_dataset = f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\"\n",
+        "\n",
+        "print(sql_create_dataset)\n",
+        "\n",
+        "run_bq_query(sql_create_dataset)"
       ]
     },
     {
@@ -620,7 +626,7 @@
         "id": "49dd00d5fbe5"
       },
       "source": [
-        "Inpect data that has been pre-processed from [Google Analytics 4 data from the Google Merchandise Store](https://support.google.com/analytics/answer/10937659) so that it can be used for classification. For more information on how this data was prepared, read [this blog post](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml).\n",
+        "Inpect data that has been pre-processed from <a href=\"https://support.google.com/analytics/answer/10937659\" target=\"_blank\">Google Analytics 4 data from the Google Merchandise Store</a> so that it can be used for classification. For more information on how this data was prepared, read <a href=\"https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml\" target=\"_blank\">this blog post</a>.\n",
         "\n",
         "As seen below, each row represents a single user, and the columns represent their demographic features, their aggregated behavioral features in the first 24 hours of visiting the Google Merchandise Store, and the label (whether the user churned or returned any time after the first 24 hours)."
       ]
@@ -641,7 +647,7 @@
         "LIMIT\n",
         "    100\n",
         "\"\"\"\n",
-        "bq_query(sql_inspect)"
+        "run_bq_query(sql_inspect)"
       ]
     },
     {
@@ -662,9 +668,9 @@
         "The query below trains a logistic regression model using BigQuery ML. BigQuery resources are used to train the model.\n",
         "\n",
         "In the `OPTIONS` parameter:\n",
-        "* with `model_registry=\"vertex_ai\"`, the BigQuery ML model will automatically be [registered to Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml), which enables you to view all of your registered models and its versions on Google Cloud in one place.\n",
+        "* with `model_registry=\"vertex_ai\"`, the BigQuery ML model will automatically be <a href=\"https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml\" target=\"_blank\">registered to Vertex AI Model Registry</a>, which enables you to view all of your registered models and its versions on Google Cloud in one place.\n",
         "\n",
-        "* `vertex_ai_model_version_aliases allows you to set aliases to help you keep track of your model version ([documentation](https://cloud.google.com/vertex-ai/docs/model-registry/model-alias))."
+        "* `vertex_ai_model_version_aliases allows you to set aliases to help you keep track of your model version (<a href=\"https://cloud.google.com/vertex-ai/docs/model-registry/model-alias\" target=\"_blank\">documentation</a>)."
       ]
     },
     {
@@ -677,7 +683,7 @@
       "source": [
         "# this cell may take ~1 min to run\n",
         "\n",
-        "BQML_MODEL_NAME = \"bqmlmodelchurn\"\n",
+        "BQML_MODEL_NAME = f\"bqml_model_churn_{UUID}\"\n",
         "\n",
         "sql_train_model_bqml = f\"\"\"\n",
         "CREATE OR REPLACE MODEL {BQ_DATASET_NAME}.{BQML_MODEL_NAME}    \n",
@@ -696,7 +702,7 @@
         "\n",
         "print(sql_train_model_bqml)\n",
         "\n",
-        "bq_query(sql_train_model_bqml)"
+        "run_bq_query(sql_train_model_bqml)"
       ]
     },
     {
@@ -714,7 +720,7 @@
         "id": "2aaaae772f67"
       },
       "source": [
-        "With the model created, you can now evaluate the logistic regression model. Behind the scenes, BigQuery ML automatically [split the data](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method), which makes it easier to quickly train and evaluate models."
+        "With the model created, you can now evaluate the logistic regression model. Behind the scenes, BigQuery ML automatically <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method\" target=\"_blank\">split the data</a>, which makes it easier to quickly train and evaluate models."
       ]
     },
     {
@@ -734,7 +740,7 @@
         "\n",
         "print(sql_evaluate_model)\n",
         "\n",
-        "bq_query(sql_evaluate_model)"
+        "run_bq_query(sql_evaluate_model)"
       ]
     },
     {
@@ -745,7 +751,7 @@
       "source": [
         "These metrics help you understand the performance of the model. \n",
         "\n",
-        "There are various metrics for logistic regression and other model types (full list of metrics can be found in the [documentation](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate#mlevaluate_output))."
+        "There are various metrics for logistic regression and other model types (full list of metrics can be found in the <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate#mlevaluate_output\" target=\"_blank\">documentation</a>)."
       ]
     },
     {
@@ -765,7 +771,7 @@
       "source": [
         "Make a batch prediction in BigQuery ML on the original training data to check the probability of churn for each of the users, as seen in the `probability` column, with the predicted label under the `predicted_churn` column.\n",
         "\n",
-        "[ML.EXPLAIN_PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict) has built-in [Explainable AI](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-xai-overview). This allows you to see the top contributing features to each prediction and interpret how it was computed."
+        "<a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict\" target=\"_blank\">ML.EXPLAIN_PREDICT</a> has built-in <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-xai-overview\" target=\"_blank\">Explainable AI</a>. This allows you to see the top contributing features to each prediction and interpret how it was computed."
       ]
     },
     {
@@ -787,7 +793,7 @@
         "\n",
         "print(sql_explain_predict)\n",
         "\n",
-        "bq_query(sql_explain_predict)"
+        "run_bq_query(sql_explain_predict)"
       ]
     },
     {
@@ -796,7 +802,7 @@
         "id": "fa1f96c0f452"
       },
       "source": [
-        "Since the `top_feature_attributions` is a nested column, you can unnest the array ([documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/arrays)) into separate rows for each of the features. In other words, since ML.EXPLAIN_PREDICT provides the top 5 most important features, using `UNNEST` results in 5 rows per prediction:"
+        "Since the `top_feature_attributions` is a nested column, you can unnest the array (<a href=\"https://cloud.google.com/bigquery/docs/reference/standard-sql/arrays\" target=\"_blank\">documentation</a>) into separate rows for each of the features. In other words, since ML.EXPLAIN_PREDICT provides the top 5 most important features, using `UNNEST` results in 5 rows per prediction:"
       ]
     },
     {
@@ -827,7 +833,7 @@
         "\n",
         "print(sql_explain_predict)\n",
         "\n",
-        "bq_query(sql_explain_predict)"
+        "run_bq_query(sql_explain_predict)"
       ]
     },
     {
@@ -847,7 +853,7 @@
       "source": [
         "When the model was trained in BigQuery ML, the line `model_registry=\"vertex_ai\"` registered the model to Vertex AI Model Registry automatically upon completion.\n",
         "\n",
-        "You can view the model on the [Vertex AI Model Registry page](https://console.cloud.google.com/vertex-ai/models), or use the code below to check that it was successfully registered:"
+        "You can view the model on the <a href=\"https://console.cloud.google.com/vertex-ai/models\" target=\"_blank\">Vertex AI Model Registry page</a>, or use the code below to check that it was successfully registered:"
       ]
     },
     {
@@ -858,12 +864,7 @@
       },
       "outputs": [],
       "source": [
-        "print(f\"BQML_MODEL_NAME = {BQML_MODEL_NAME}\")\n",
-        "\n",
-        "models = vertex_ai.Model.list(\n",
-        "    filter=f\"display_name={BQML_MODEL_NAME}\", order_by=\"update_time\"\n",
-        ")\n",
-        "model = models[0]\n",
+        "model = vertex_ai.Model(model_name=BQML_MODEL_NAME)\n",
         "\n",
         "print(model.gca_resource)"
       ]
@@ -883,7 +884,7 @@
         "id": "b6120dcc1ff6"
       },
       "source": [
-        "While BigQuery ML supports batch prediction with [ML.PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-predict) and [ML.EXPLAIN_PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict), BigQuery ML is not suitable for real-time predictions where you need low latency predictions with potentially high frequency of requests.\n",
+        "While BigQuery ML supports batch prediction with <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-predict\" target=\"_blank\">ML.PREDICT</a> and <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict\" target=\"_blank\">ML.EXPLAIN_PREDICT</a>, BigQuery ML is not suitable for real-time predictions where you need low latency predictions with potentially high frequency of requests.\n",
         "\n",
         "In other words, deploying the BigQuery ML model to an endpoint enables you to do online predictions."
       ]
@@ -906,30 +907,6 @@
         "To deploy your model to an endpoint, you will first need to create an endpoint before you deploy the model to it."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3ce73125dff6"
-      },
-      "outputs": [],
-      "source": [
-        "def create_endpoint(\n",
-        "    project: str,\n",
-        "    display_name: str,\n",
-        "    location: str,\n",
-        "):\n",
-        "    endpoint = vertex_ai.Endpoint.create(\n",
-        "        display_name=display_name,\n",
-        "        project=project,\n",
-        "        location=location,\n",
-        "    )\n",
-        "\n",
-        "    print(endpoint.display_name)\n",
-        "    print(endpoint.resource_name)\n",
-        "    return endpoint"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -938,17 +915,16 @@
       },
       "outputs": [],
       "source": [
-        "endpoint_name = f\"{BQML_MODEL_NAME}-{TIMESTAMP}\"\n",
+        "ENDPOINT_NAME = f\"{BQML_MODEL_NAME}-endpoint\"\n",
         "\n",
-        "print(\n",
-        "    f\"\"\"\n",
-        "PROJECT_ID: {PROJECT_ID},\n",
-        "endpoint_name: {endpoint_name}\n",
-        "REGION: {REGION}\n",
-        "\"\"\"\n",
+        "endpoint = vertex_ai.Endpoint.create(\n",
+        "    display_name=ENDPOINT_NAME,\n",
+        "    project=PROJECT_ID,\n",
+        "    location=REGION,\n",
         ")\n",
         "\n",
-        "create_endpoint(PROJECT_ID, endpoint_name, REGION)"
+        "print(endpoint.display_name)\n",
+        "print(endpoint.resource_name)"
       ]
     },
     {
@@ -966,31 +942,7 @@
         "id": "951ed1693f6b"
       },
       "source": [
-        "List the endpoints to make sure it has successfully been created. You can also view your endpoints on the [Vertex AI Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints?project=polong-contentdev)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0a9bad8d9ad4"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint = vertex_ai.Endpoint.list(\n",
-        "    # filter=f'display_name={endpoint_name}', # optional: filter by specific endpoint name\n",
-        "    order_by=\"update_time\"\n",
-        ")\n",
-        "endpoint[-1]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2431a4d28d97"
-      },
-      "source": [
-        "Retrieve the endpoint id so you can use it in the next step."
+        "List the endpoints to make sure it has successfully been created. (You can also view your endpoints on the <a href=\"https://console.cloud.google.com/vertex-ai/endpoints\" target=\"_blank\">Vertex AI Endpoints page</a>)."
       ]
     },
     {
@@ -1001,7 +953,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint[-1].to_dict()"
+        "endpoint.list()"
       ]
     },
     {
@@ -1019,74 +971,19 @@
         "id": "6a90be5b77a2"
       },
       "source": [
-        "With the model, you can now deploy it to an endpoint. "
+        "With the new endpoint, you can now deploy your model."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "af323ea42c5b"
-      },
-      "outputs": [],
-      "source": [
-        "from typing import Dict, Optional, Sequence, Tuple\n",
-        "\n",
-        "\n",
-        "def deploy_model_with_automatic_resources_sample(\n",
-        "    project,\n",
-        "    location,\n",
-        "    model_name: str,\n",
-        "    endpoint: Optional[vertex_ai.Endpoint] = None,\n",
-        "    deployed_model_display_name: Optional[str] = None,\n",
-        "    traffic_percentage: Optional[int] = 0,\n",
-        "    traffic_split: Optional[Dict[str, int]] = None,\n",
-        "    min_replica_count: int = 1,\n",
-        "    max_replica_count: int = 1,\n",
-        "    metadata: Optional[Sequence[Tuple[str, str]]] = (),\n",
-        "    sync: bool = True,\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    model_name: A fully-qualified model resource name or model ID.\n",
-        "          Example: \"projects/123/locations/us-central1/models/456\" or\n",
-        "          \"456\" when project and location are initialized or passed.\n",
-        "    \"\"\"\n",
-        "\n",
-        "    model = vertex_ai.Model(model_name=model_name)\n",
-        "\n",
-        "    model.deploy(\n",
-        "        endpoint=endpoint,\n",
-        "        deployed_model_display_name=deployed_model_display_name,\n",
-        "        traffic_percentage=traffic_percentage,\n",
-        "        traffic_split=traffic_split,\n",
-        "        min_replica_count=min_replica_count,\n",
-        "        max_replica_count=max_replica_count,\n",
-        "        metadata=metadata,\n",
-        "        sync=sync,\n",
-        "    )\n",
-        "\n",
-        "    model.wait()\n",
-        "\n",
-        "    print(model.display_name)\n",
-        "    print(model.resource_name)\n",
-        "    return"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "9e6763369af4"
+        "id": "c70ecc568ee5"
       },
       "outputs": [],
       "source": [
         "# deploying the model to the endpoint may take 10-15 minutes\n",
-        "deploy_model_with_automatic_resources_sample(\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    model_name=BQML_MODEL_NAME,\n",
-        "    endpoint=endpoint[-1],\n",
-        ")"
+        "model.deploy(endpoint=endpoint)"
       ]
     },
     {
@@ -1095,7 +992,7 @@
         "id": "c303d779477b"
       },
       "source": [
-        "You can also check on the status of your model by visiting the [Vertex AI Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints)."
+        "You can also check on the status of your model by visiting the <a href=\"https://console.cloud.google.com/vertex-ai/endpoints\" target=\"_blank\">Vertex AI Endpoints page</a>."
       ]
     },
     {
@@ -1168,35 +1065,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "2c6093ce9f8a"
+        "id": "b4839f31d2f8"
       },
       "outputs": [],
       "source": [
-        "def endpoint_predict_sample(\n",
-        "    project: str, location: str, instances: list, endpoint: str\n",
-        "):\n",
-        "    endpoint = vertex_ai.Endpoint(endpoint)\n",
-        "\n",
-        "    prediction = endpoint.predict(instances=instances)\n",
-        "    return prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0c41fd6eeb6f"
-      },
-      "outputs": [],
-      "source": [
-        "prediction_response = endpoint_predict_sample(\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    instances=df_sample_requests_list,\n",
-        "    endpoint=endpoint[-1].name,\n",
-        ")\n",
-        "\n",
-        "prediction_response"
+        "prediction = endpoint.predict(df_sample_requests_list)\n",
+        "print(prediction)"
       ]
     },
     {
@@ -1216,7 +1090,7 @@
       },
       "outputs": [],
       "source": [
-        "prediction_response.predictions"
+        "prediction.predictions"
       ]
     },
     {
@@ -1227,8 +1101,8 @@
       "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.\n",
+        "To clean up all Google Cloud resources used in this project, you can <a href=\"https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects\" target=\"_blank\">delete the Google Cloud\n",
+        "project</a> you used for the tutorial.\n",
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:"
       ]
@@ -1241,18 +1115,12 @@
       },
       "outputs": [],
       "source": [
-        "# MODEL_ID = model.name\n",
+        "# Undeploy model from endpoint and delete endpoint\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
         "\n",
-        "ENDPOINT_ID = int(endpoint[-1].name)\n",
-        "\n",
-        "# Undeploy model from endpoint\n",
-        "endpoint[-1].undeploy_all()\n",
-        "\n",
-        "# Delete endpoint resource\n",
-        "! gcloud ai endpoints delete $ENDPOINT_ID --quiet --region $REGION\n",
-        "\n",
-        "# Delete BigQuery ML model\n",
-        "! bq rm -f --model $PROJECT_ID\\:$BQ_DATASET_NAME\\.$BQML_MODEL_NAME"
+        "# Delete BigQuery dataset, including the BigQuery ML model\n",
+        "! bq rm -r -f $PROJECT_ID:$BQ_DATASET_NAME"
       ]
     }
   ],

notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb

@@ -33,18 +33,18 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/custom/custom-tabular-bq-managed-dataset.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/custom-tabular-bq-managed-dataset.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/official/custom/custom-tabular-bq-managed-dataset.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/custom-tabular-bq-managed-dataset.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://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/custom-tabular-bq-managed-dataset.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/official/custom/custom-tabular-bq-managed-dataset.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",
@@ -64,17 +64,6 @@
         "This tutorial demonstrates how to use the Vertex AI SDK for Python to train and deploy a custom tabular classification model for online prediction."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:custom,cifar10,icn"
-      },
-      "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). In this version of the dataset, you will use only the fields `culmen_length_mm`, `culmen_depth_mm`, `flipper_length_mm`, `body_mass_g` to predict the penguins species (`species`)."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -83,7 +72,15 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this notebook, you create a custom-trained model from a Python script in a Docker container using the Vertex SDK for Python, and then get a prediction from the deployed model by sending data. Alternatively, you can create custom-trained models using `gcloud` command-line tool, or online using the Cloud Console.\n",
+        "In this notebook, you create a custom-trained model from a Python script in a Docker container using the Vertex AI SDK for Python, and then get a prediction from the deployed model by sending data. Alternatively, you can create custom-trained models using `gcloud` command-line tool, or online using the Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services and resources:\n",
+        "\n",
+        "- BigQuery\n",
+        "- Cloud Storage\n",
+        "- Vertex AI managed Datasets\n",
+        "- Vertex AI Training\n",
+        "- Vertex AI Endpoints\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -94,6 +91,17 @@
         "- Undeploy the `Model` resource."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:custom,cifar10,icn"
+      },
+      "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). For this tutorial, you use only the fields `culmen_length_mm`, `culmen_depth_mm`, `flipper_length_mm`, `body_mass_g` from the dataset to predict the penguins species (`species`)."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -106,14 +114,64 @@
         "\n",
         "* Vertex AI\n",
         "* Cloud Storage\n",
+        "* BigQuery\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",
+        "pricing](https://cloud.google.com/vertex-ai/pricing), [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), [BigQuery pricing](https://cloud.google.com/bigquery/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": "384b53dfdb54"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Vertex AI Workbench 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": {
@@ -122,7 +180,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the latest version of Cloud Storage, Bigquery and Vertex AI SDKs for Python."
       ]
     },
     {
@@ -135,64 +193,22 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\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",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
-        "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "YsxCgt1zlugo"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_storage"
-      },
-      "source": [
-        "Install the latest version of *google-cloud-storage* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "qssss-KSlugo"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} -U google-cloud-storage"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "Z3hYaR6gLEK-"
-      },
-      "source": [
-        "Install the latest version of *google-cloud-bigquery* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "866ffc5cf763"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} -U \"google-cloud-bigquery[all]\""
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "# Install the packages\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform \\\n",
+        "                                    google-cloud-storage \\\n",
+        "                                    google-cloud-bigquery \\\n",
+        "                                    pyarrow -q"
       ]
     },
     {
@@ -224,18 +240,21 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a47846030fef"
+      },
+      "source": [
+        "## Before you begin"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "before_you_begin"
       },
       "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\"\n",
-        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
@@ -244,9 +263,9 @@
         "\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 Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "3. [Enable the following APIs: Vertex AI API, Cloud Resource Manager API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,cloudresourcemanager.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",
+        "4. If you are running this notebook locally, you 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",
@@ -269,40 +288,71 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "autoset_project_id"
+        "id": "3c8049930470"
       },
       "outputs": [],
       "source": [
-        "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": "set_project_id"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "USd_pUT0lugr"
+        "id": "a36c4b991a39"
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "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": "f2e3c0f2cbfb"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a54f9d7c1876"
+      },
+      "source": [
+        "#### Region\n",
+        "\n",
+        "You can also change the `REGION` variable, which is used for operations\n",
+        "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": "3aaadaaf9b30"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -311,9 +361,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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, create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -324,9 +374,28 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of length 8\n",
+        "def generate_uuid():\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=8))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5c0404984792"
+      },
+      "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."
       ]
     },
     {
@@ -335,11 +404,6 @@
         "id": "gcp_authenticate"
       },
       "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Google Cloud 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",
@@ -372,19 +436,19 @@
       },
       "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",
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "import os\n",
+        "import sys\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",
@@ -415,12 +479,7 @@
         "online predictions.\n",
         "\n",
         "Set the name of your Cloud Storage bucket below. It must be unique across all\n",
-        "Cloud Storage buckets.\n",
-        "\n",
-        "You may also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook. Make sure to [choose a region where Vertex AI services are\n",
-        "available](https://cloud.google.com/vertex-ai/docs/general/locations#available_regions). You may\n",
-        "not use a Multi-Regional Storage bucket for training with Vertex AI."
+        "Cloud Storage buckets."
       ]
     },
     {
@@ -431,8 +490,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -443,11 +502,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -467,7 +524,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_URI\n"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
@@ -490,26 +547,13 @@
         "! gsutil ls -al $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_vars"
-      },
-      "source": [
-        "## Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "import_aip"
       },
       "source": [
-        "### Import Vertex AI SDK for Python\n",
-        "\n",
-        "Import the Vertex AI SDK for Python into your Python environment and initialize it."
+        "### Import libraries"
       ]
     },
     {
@@ -525,12 +569,55 @@
         "import sys\n",
         "\n",
         "import numpy as np\n",
-        "from google.cloud import aiplatform, bigquery\n",
-        "from google.cloud.aiplatform import gapic as aip\n",
+        "from google.cloud import aiplatform, bigquery"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "750d53e37094"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
         "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "c9d3ac73dfbc"
+      },
+      "outputs": [],
+      "source": [
+        "# Initialize the Vertex AI SDK\n",
         "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7c163842eabd"
+      },
+      "source": [
+        "### Initialize BigQuery Client\n",
+        "\n",
+        "Initialize the BigQuery Python client for your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fad2ba1ad7c3"
+      },
+      "outputs": [],
+      "source": [
+        "# Set up BigQuery client\n",
+        "bqclient = bigquery.Client(project=PROJECT_ID)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -560,9 +647,9 @@
       },
       "outputs": [],
       "source": [
-        "TRAIN_GPU, TRAIN_NGPU = (aip.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "TRAIN_GPU, TRAIN_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
         "\n",
-        "DEPLOY_GPU, DEPLOY_NGPU = (aip.AcceleratorType.NVIDIA_TESLA_K80, 1)"
+        "DEPLOY_GPU, DEPLOY_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)"
       ]
     },
     {
@@ -657,17 +744,6 @@
         "Pass these summary statistics to the training script to normalize the data before training. Later, during prediction, use these summary statistics again to normalize the testing data."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "890d562c6291"
-      },
-      "outputs": [],
-      "source": [
-        "BQ_SOURCE = \"bq://bigquery-public-data.ml_datasets.penguins\""
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -678,13 +754,15 @@
       "source": [
         "# Calculate mean and std across all rows\n",
         "\n",
+        "# Define the BigQuery source dataset\n",
+        "BQ_SOURCE = \"bq://bigquery-public-data.ml_datasets.penguins\"\n",
+        "\n",
+        "# Define NA values\n",
         "NA_VALUES = [\"NA\", \".\"]\n",
         "\n",
-        "# Set up BigQuery clients\n",
-        "bqclient = bigquery.Client(project=PROJECT_ID)\n",
-        "\n",
-        "\n",
         "# Download a table\n",
+        "\n",
+        "\n",
         "def download_table(bq_table_uri: str):\n",
         "    # Remove bq:// prefix if present\n",
         "    prefix = \"bq://\"\n",
@@ -740,9 +818,9 @@
         "id": "5c7732822757"
       },
       "source": [
-        "## Create a managed tabular dataset from BigQuery dataset\n",
+        "## Create a Vertex AI Tabular Dataset from BigQuery dataset\n",
         "\n",
-        "Your first step in training a model is to create a managed dataset instance."
+        "Your first step in training the model is to create a Vertex AI tabular dataset resource."
       ]
     },
     {
@@ -789,7 +867,7 @@
         "     - `\"single\"`: single device.\n",
         "     - `\"mirror\"`: all GPU devices on a single compute instance.\n",
         "     - `\"multi\"`: all GPU devices on all compute instances.\n",
-        "  - `\"--mean_and_std_json_file=\" + FILE_PATH`: The file on Google Cloud Storage with pre-calculated means and standard deviations."
+        "  - `\"--mean_and_std_json_file=\" + FILE_PATH`: The file on Cloud Storage with pre-calculated means and standard deviations."
       ]
     },
     {
@@ -800,7 +878,7 @@
       },
       "outputs": [],
       "source": [
-        "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
+        "JOB_NAME = \"custom_job_\" + UUID\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
         "    TRAIN_STRATEGY = \"single\"\n",
@@ -829,7 +907,7 @@
         "In the next cell, write the contents of the training script, `task.py`. In summary, the script does the following:\n",
         "\n",
         "- Loads the data from the BigQuery table using the BigQuery Python client library.\n",
-        "- Loads the pre-calculated mean and standard deviation from the Google Cloud Storage bucket.\n",
+        "- Loads the pre-calculated mean and standard deviation from the Cloud Storage bucket.\n",
         "- Builds a model using TF.Keras model API.\n",
         "- Compiles the model (`compile()`).\n",
         "- Sets a training distribution strategy according to the argument `args.distribute`.\n",
@@ -890,7 +968,7 @@
         "\n",
         "    # Construct a client side representation of a blob.\n",
         "    # Note `Bucket.blob` differs from `Bucket.get_blob` as it doesn't retrieve\n",
-        "    # any content from Google Cloud Storage. As we don't need additional data,\n",
+        "    # any content from Cloud Storage. As we don't need additional data,\n",
         "    # using `Bucket.blob` is preferred here.\n",
         "    blob = bucket.blob(source_blob_name)\n",
         "    blob.download_to_filename(destination_file_name)\n",
@@ -915,13 +993,13 @@
         "\n",
         "    Args:\n",
         "        gcs_path (str):\n",
-        "            Required. A full path to a Google Cloud Storage folder or resource.\n",
+        "            Required. A full path to a Cloud Storage folder or resource.\n",
         "            Can optionally include \"gs://\" prefix or end in a trailing slash \"/\".\n",
         "\n",
         "    Returns:\n",
         "        Tuple[str, Optional[str]]\n",
         "            A (bucket, prefix) pair from provided GCS path. If a prefix is not\n",
-        "            present, a None will be returned in its place.\n",
+        "            present, None is returned in its place.\n",
         "    \"\"\"\n",
         "    if gcs_path.startswith(\"gs://\"):\n",
         "        gcs_path = gcs_path[5:]\n",
@@ -999,7 +1077,6 @@
         "\n",
         "\n",
         "df_train = clean_dataframe(df_train)\n",
-        "#     df_validation = clean_dataframe(df_validation)\n",
         "df_validation = clean_dataframe(df_validation)\n",
         "\n",
         "_CATEGORICAL_TYPES = {\n",
@@ -1186,7 +1263,7 @@
         "    model_serving_container_image_uri=DEPLOY_IMAGE,\n",
         ")\n",
         "\n",
-        "MODEL_DISPLAY_NAME = \"penguins-\" + TIMESTAMP\n",
+        "MODEL_DISPLAY_NAME = \"penguins-\" + UUID\n",
         "\n",
         "# Start the training\n",
         "if TRAIN_GPU:\n",
@@ -1220,7 +1297,7 @@
       "source": [
         "### Deploy the model\n",
         "\n",
-        "Before you use your model to make predictions, you must deploy it to an `Endpoint`. You can do this by calling the `deploy` function on the `Model` resource. This will do two things:\n",
+        "Before you use your model to make predictions, you must deploy it to an `Endpoint`. You can do this by calling the `deploy` function on the `Model` resource. This does two things:\n",
         "\n",
         "1. Create an `Endpoint` resource for deploying the `Model` resource to.\n",
         "2. Deploy the `Model` resource to the `Endpoint` resource.\n",
@@ -1231,7 +1308,7 @@
         "- `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 `{ \"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 `{ \"0\": percent, model_id: percent, ... }`, where `model_id` is the ID of an existing `DeployedModel` on the endpoint. The percentages must add up to 100.\n",
+        "   - If there are existing models on the endpoint, for which the traffic is split, then use `model_id` to specify `{ \"0\": percent, model_id: percent, ... }`, where `model_id` is the ID of an existing `DeployedModel` on the endpoint. The percentages 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",
@@ -1252,7 +1329,7 @@
         "\n",
         "### Endpoint\n",
         "\n",
-        "The method will block until the model is deployed and eventually return an `Endpoint` object. If this is the first time a model is deployed to the endpoint, it may take a few additional minutes to complete provisioning of resources."
+        "The `deploy` method waits until the model is deployed and eventually returns an `Endpoint` object. If this is the first time a model is deployed to the endpoint, it may take a few additional minutes to complete provisioning of resources."
       ]
     },
     {
@@ -1263,7 +1340,7 @@
       },
       "outputs": [],
       "source": [
-        "DEPLOYED_NAME = \"penguins_deployed-\" + TIMESTAMP\n",
+        "DEPLOYED_NAME = \"penguins_deployed-\" + UUID\n",
         "\n",
         "TRAFFIC_SPLIT = {\"0\": 100}\n",
         "\n",
@@ -1427,7 +1504,7 @@
         "\n",
         "- `instances`: A list of penguin measurement instances. According to your custom model, each instance should be an array of numbers. You prepared this list in the previous step.\n",
         "\n",
-        "The `predict` function returns a list, where each element in the list corresponds to the an instance in the request. In the output for each prediction, you will see the following:\n",
+        "The `predict` function returns a list, where each element in the list corresponds to the an instance in the request. In the output for each prediction, you see the following:\n",
         "\n",
         "- Confidence level for the prediction (`predictions`), between 0 and 1, for each of the ten classes.\n",
         "\n",
@@ -1508,7 +1585,7 @@
       },
       "outputs": [],
       "source": [
-        "# Warning: Setting this to true will delete everything in your bucket\n",
+        "# Warning: Setting this to true deletes everything in your bucket\n",
         "delete_bucket = False\n",
         "\n",
         "# Delete the training job\n",

notebooks/official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# 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",
@@ -54,13 +54,31 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "d975c5729f18"
       },
       "source": [
         "## Overview\n",
         "\n",
-        "As a Data Scientist, you want to be able to reuse code path (data preprocessing, feature engineering etc...) that others within your team have written to simplify and standardize all the complex data wrangling. \n",
+        "As a Data Scientist, you want to be able to reuse code path (data preprocessing, feature engineering etc...) that others within your team have written to simplify and standardize all the complex data wrangling. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3a0f8061b9c1"
+      },
+      "source": [
+        "### Objective\n",
         "\n",
+        "In this notebook, you learn how to integrate preprocessing code in a Vertex AI experiments. Also you build the experiment lineage lets you record, analyze, debug, and audit metadata and artifacts produced along your ML journey."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
         "### Dataset\n",
         "\n",
         "This dataset is the UCI News Aggregator Data Set which contains 422,937 news collected between March 10th, 2014 and August 10th, 2014. Below are example records from the dataset:\n",
@@ -72,13 +90,15 @@
         "|2  |Fed's Charles Plosser sees high bar for change in pace of tapering   |http://www.livemint.com/Politics/H2EvwJSK2VE6OF7iK1g3PP/Feds-Charles-Plosser-sees-high-bar-for-change-in-pace-of-ta.html   |Livemint         |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.livemint.com   |1394470371207|\n",
         "|3  |US open: Stocks fall after Fed official hints at accelerated tapering|http://www.ifamagazine.com/news/us-open-stocks-fall-after-fed-official-hints-at-accelerated-tapering-294436                |IFA Magazine     |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.ifamagazine.com|1394470371550|\n",
         "|4  |Fed risks falling 'behind the curve', Charles Plosser says           |http://www.ifamagazine.com/news/fed-risks-falling-behind-the-curve-charles-plosser-says-294430                             |IFA Magazine     |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.ifamagazine.com|1394470371793|\n",
-        "|5  |Fed's Plosser: Nasty Weather Has Curbed Job Growth                   |http://www.moneynews.com/Economy/federal-reserve-charles-plosser-weather-job-growth/2014/03/10/id/557011                   |Moneynews        |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.moneynews.com  |1394470372027|\n",
-        "\n",
-        "\n",
-        "### Objective\n",
-        "\n",
-        "In this notebook, you learn how to integrate preprocessing code in a Vertex AI experiments. Also you will build the experiment lineage lets you record, analyze, debug, and audit metadata and artifacts produced along your ML journey.\n",
-        "\n",
+        "|5  |Fed's Plosser: Nasty Weather Has Curbed Job Growth                   |http://www.moneynews.com/Economy/federal-reserve-charles-plosser-weather-job-growth/2014/03/10/id/557011                   |Moneynews        |b       |ddUyU0VZz0BRneMioxUPQVP6sIxvM|www.moneynews.com  |1394470372027|"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5e2eba58ad71"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -150,7 +170,7 @@
       "source": [
         "### Install additional packages\n",
         "\n",
-        "Install additional package dependencies not installed in your notebook environment, such as TensorFlow or Vertex AI SDK. Use the latest major GA version of each package."
+        "Install additional package dependencies not installed in your notebook environment,TensorFlow or Vertex AI SDK. Use the latest major GA version of each package."
       ]
     },
     {
@@ -174,9 +194,8 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip3 install {USER_FLAG} --upgrade fsspec gcsfs joblib -q\n",
-        "! pip3 install {USER_FLAG} --force-reinstall 'google-cloud-aiplatform>=1.15' -q\n",
-        "! pip3 install {USER_FLAG} --upgrade sklearn"
+        "! pip3 install {USER_FLAG} --upgrade joblib fsspec gcsfs scikit-learn -q\n",
+        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform -q"
       ]
     },
     {
@@ -209,21 +228,14 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lWEdiXsJg0XY"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "BF1j6f9HApxa"
       },
       "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",
@@ -232,9 +244,9 @@
         "\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",
+        "1. [Enable APIs](https://console.cloud.google.com/flows/enableapi?apiid=cloudresourcemanager.googleapis.com,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",
+        "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",
@@ -344,9 +356,9 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -357,9 +369,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -371,7 +390,7 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
+        "authenticated."
       ]
     },
     {
@@ -393,9 +412,14 @@
         "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",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type and select\n",
+        "the following role into the filter box:\n",
+        "\n",
+        "    *   Storage Admin\n",
+        "    *   Storage Object Admin\n",
+        "    *   Service Account User\n",
+        "    *   Vertex AI Administrator\n",
+        "\n",
         "\n",
         "5. Click *Create*. A JSON file that contains your key downloads to your\n",
         "local environment.\n",
@@ -480,7 +504,7 @@
       "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_NAME = PROJECT_ID + \"aip-\" + UUID\n",
         "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
@@ -533,17 +557,6 @@
         "### Set project folder"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "AARD6Fsr-DSi"
-      },
-      "outputs": [],
-      "source": [
-        "DATA_PATH = \"data\""
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -552,6 +565,7 @@
       },
       "outputs": [],
       "source": [
+        "DATA_PATH = \"data\"\n",
         "!mkdir -m 777 -p {DATA_PATH}"
       ]
     },
@@ -564,17 +578,6 @@
         "### Get the data"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3V6W2nIo9FtL"
-      },
-      "outputs": [],
-      "source": [
-        "DATASET_URL = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00359/NewsAggregatorDataset.zip\""
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -583,6 +586,7 @@
       },
       "outputs": [],
       "source": [
+        "DATASET_URL = \"https://archive.ics.uci.edu/ml/machine-learning-databases/00359/NewsAggregatorDataset.zip\"\n",
         "!wget --no-parent {DATASET_URL} --directory-prefix={DATA_PATH}\n",
         "!mkdir -m 777 -p {DATA_PATH}/temp {DATA_PATH}/raw\n",
         "!unzip {DATA_PATH}/*.zip -d {DATA_PATH}/temp\n",
@@ -623,10 +627,13 @@
         "logger = logging.getLogger(\"logger\")\n",
         "logging.basicConfig(level=logging.INFO)\n",
         "\n",
+        "import collections\n",
         "import tempfile\n",
         "import time\n",
         "from json import dumps\n",
         "\n",
+        "collections.Iterable = collections.abc.Iterable\n",
+        "\n",
         "# Vertex AI\n",
         "from google.cloud import aiplatform as vertex_ai"
       ]
@@ -655,7 +662,7 @@
         "# Experiments\n",
         "TASK = \"classification\"\n",
         "MODEL_TYPE = \"naivebayes\"\n",
-        "EXPERIMENT_NAME = f\"{TASK}-{MODEL_TYPE}-{TIMESTAMP}\"\n",
+        "EXPERIMENT_NAME = f\"{TASK}-{MODEL_TYPE}-{UUID}\"\n",
         "EXPERIMENT_RUN_NAME = \"run-1\"\n",
         "\n",
         "# Preprocessing\n",
@@ -683,7 +690,7 @@
         "FEATURES = \"title\"\n",
         "TEST_SIZE = 0.2\n",
         "SEED = 8\n",
-        "TRAINED_MODEL_URI = f\"{BUCKET_URI}/deliverables/{TIMESTAMP}\"\n",
+        "TRAINED_MODEL_URI = f\"{BUCKET_URI}/deliverables/{UUID}\"\n",
         "MODEL_NAME = f\"{EXPERIMENT_NAME}-model\""
       ]
     },
@@ -793,7 +800,7 @@
       "source": [
         "#### Create a Dataset Metadata Artifact\n",
         "\n",
-        "First you create the Dataset artifact to track the dataset resource in the Vertex AI ML Metadata and create the experiment lineage."
+        "First you create the Dataset artifact to track the dataset resource in the Vertex ML Metadata and create the experiment lineage."
       ]
     },
     {
@@ -832,7 +839,6 @@
         "Preprocess module\n",
         "\"\"\"\n",
         "\n",
-        "import string\n",
         "\n",
         "import pandas as pd\n",
         "\n",
@@ -862,7 +868,10 @@
       "source": [
         "#### Add the `preprocessing` Execution\n",
         "\n",
-        "You add the preprocessing step to track its execution in the lineage associated to Vertex AI Experiment. "
+        "Vertex AI Experiments supports tracking both executions and artifacts. Executions are steps in an ML workflow that can include but are not limited to data preprocessing, training, and model evaluation. Executions can consume artifacts such as datasets and produce artifacts such as models.\n",
+        "\n",
+        "You add the preprocessing step to track its execution in the lineage associated to Vertex AI Experiment. \n",
+        "For Vertex AI, the parameters are passed inside the message field which we see in the logs. These structures of the logs are predefined."
       ]
     },
     {
@@ -936,7 +945,16 @@
       "source": [
         "#### Create model training module\n",
         "\n",
-        "Below the training module."
+        "Below the training module.\n",
+        "\n",
+        "**get_training_split :** It takes parameters like  x(The data to be split), y(The labels to be split), test_size(The proportion of the data to be reserved for testing) and random_state(The seed used by the random number generator).\n",
+        "This function return training data, testing data , The training labels and The testing labels.\n",
+        "\n",
+        "**get_pipeline :** It return's the model.\n",
+        "\n",
+        "**train_pipeline :** It train the model by using model, training data, training lables and return's the trained model.\n",
+        "\n",
+        "**evaluate_model :** It evaluate the model and return the accuracy of the model.\n"
       ]
     },
     {
@@ -1144,6 +1162,15 @@
         "    exc.assign_output_artifacts([model])"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e595c893de8d"
+      },
+      "source": [
+        "### Stop Experiment run"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1163,7 +1190,7 @@
       "source": [
         "### Visualize Experiment Lineage\n",
         "\n",
-        "Below you will get the link to Vertex AI Metadata UI in the console that will show the experiment lineage."
+        "Below you get the link to Vertex AI Metadata UI in the console that show the experiment lineage."
       ]
     },
     {
@@ -1201,17 +1228,8 @@
       "source": [
         "# Delete experiment\n",
         "exp = vertex_ai.Experiment(EXPERIMENT_NAME)\n",
-        "exp.delete()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "gW8Ddbr8xaKp"
-      },
-      "outputs": [],
-      "source": [
+        "exp.delete()\n",
+        "\n",
         "# Delete model\n",
         "model_list = vertex_ai.Model.list(filter=f'display_name=\"{MODEL_NAME}\"')\n",
         "for model in model_list:\n",
@@ -1223,22 +1241,26 @@
         "        filter=f'display_name=\"{dataset_name}\"'\n",
         "    )\n",
         "    for dataset in dataset_list:\n",
-        "        dataset.delete()"
+        "        dataset.delete()\n",
+        "\n",
+        "# Delete Cloud Storage objects that were created\n",
+        "delete_bucket = True\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_URI\n",
+        "\n",
+        "!rm -Rf {DATA_PATH}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "sx_vKniMq9ZX"
+        "id": "3f00c455b930"
       },
       "outputs": [],
       "source": [
-        "# Delete Cloud Storage objects that were created\n",
-        "delete_bucket = True\n",
-        "\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil -m rm -r $BUCKET_URI"
+        "!rm -Rf {DATA_PATH}"
       ]
     }
   ],

notebooks/official/experiments/comparing_pipeline_runs.ipynb

@@ -3,6 +3,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ed0fca3f",
       "metadata": {
         "id": "ur8xi4C7S06n"
       },
@@ -25,6 +26,17 @@
     },
     {
       "cell_type": "markdown",
+      "id": "6e92def7-b4f0-4100-b981-82972665d19d",
+      "metadata": {
+        "id": "847715f095b5"
+      },
+      "source": [
+        "# Vertex AI: Comparing Pipeline Runs"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ffada1ce",
       "metadata": {
         "id": "JAPoU8Sm5E6e"
       },
@@ -43,7 +55,7 @@
         "    </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/official/experiments/comparing_pipeline_runs.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/official/experiments/comparing_pipeline_runs.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",
@@ -53,19 +65,25 @@
     },
     {
       "cell_type": "markdown",
+      "id": "d118d181",
       "metadata": {
         "id": "tvgnzT1CKxrO"
       },
       "source": [
+        "# Compare pipeline runs with Vertex AI Experiments\n",
+        "\n",
         "## Overview\n",
         "\n",
-        "Depending on the model life cycle of your data science team, you would like to experiment and track training Pipeline runs and its associated parameters. Then, you would to compare runs of these Pipelines to each others in order to figure out which is the best configuration generates the model you will register in the Vertex AI Model Registry.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the [Iris dataset](https://www.tensorflow.org/datasets/catalog/iris) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. 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 Iris flower species from a class of three species: setosa, virginica, or versicolor.\n",
-        "\n",
-        "\n",
+        "Depending on the model life cycle of your data science team, you would like to experiment and track training Pipeline runs and its associated parameters. Then, you would to compare runs of these Pipelines to each others in order to figure out which is the best configuration generates the model you will register in the Vertex AI Model Registry."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b6201ad0-af42-48fd-b03d-403fd235e268",
+      "metadata": {
+        "id": "d220917f1302"
+      },
+      "source": [
         "### Objective\n",
         "\n",
         "In this notebook, you will learn how to use Vertex AI Experiments to \n",
@@ -78,9 +96,28 @@
         "* Formalize a training component\n",
         "* Build a training pipeline\n",
         "* Run several Pipeline jobs and log their results\n",
-        "* Compare different Pipeline jobs\n",
-        "\n",
+        "* Compare different Pipeline jobs"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "cffa7608-f550-4913-8f88-30cbcd525685",
+      "metadata": {
+        "id": "263933842022"
+      },
+      "source": [
+        "### Dataset\n",
         "\n",
+        "The dataset used for this tutorial is the [Iris dataset](https://www.tensorflow.org/datasets/catalog/iris) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). This dataset does not require any feature engineering. 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 Iris flower species from a class of three species: setosa, virginica, or versicolor.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b46c0eb6-e65d-4b28-b17d-dc9bf9b08120",
+      "metadata": {
+        "id": "de76bb18c85b"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -97,22 +134,16 @@
     },
     {
       "cell_type": "markdown",
+      "id": "ee1e6851",
       "metadata": {
-        "id": "ze4-nDLfK4pw"
+        "id": "gCuSR8GkAgzl"
       },
       "source": [
         "### Set up your local development environment\n",
         "\n",
         "**If you are using Colab or Vertex AI Workbench 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": [
+        "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",
@@ -146,6 +177,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "97e5b386",
       "metadata": {
         "id": "i7EUnXsZhAGF"
       },
@@ -158,6 +190,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "5b01540f",
       "metadata": {
         "id": "2b4ef9b72d43"
       },
@@ -176,13 +209,13 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "!pip3 install {USER_FLAG} --force-reinstall git+https://github.com/sasha-gitg/python-aiplatform@main -q\n",
-        "!pip3 install {USER_FLAG} google-cloud-aiplatform[metadata] -q\n",
-        "!pip3 install {USER_FLAG} kfp -q"
+        "!pip3 install {USER_FLAG} --force-reinstall 'google-cloud-aiplatform>=1.15' -q --no-warn-conflicts\n",
+        "!pip3 install {USER_FLAG} kfp -q --no-warn-conflicts"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "c6806ee8",
       "metadata": {
         "id": "hhq5zEbGg0XX"
       },
@@ -195,6 +228,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "584f0887",
       "metadata": {
         "id": "EzrelQZ22IZj"
       },
@@ -213,6 +247,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "bb098c06",
       "metadata": {
         "id": "lWEdiXsJg0XY"
       },
@@ -222,6 +257,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "3706598b",
       "metadata": {
         "id": "BF1j6f9HApxa"
       },
@@ -234,7 +270,7 @@
         "\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",
+        "1. [Enable APIs](https://console.cloud.google.com/flows/enableapi?apiid=cloudresourcemanager.googleapis.com,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",
@@ -246,6 +282,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "c7f6a1ea",
       "metadata": {
         "id": "WReHDGG5g0XY"
       },
@@ -258,6 +295,19 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "6984e874-ae15-4094-9c5b-8d12661645c9",
+      "metadata": {
+        "id": "3c8049930470"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "ebaef2f9",
       "metadata": {
         "id": "oM1iC_MfAts1"
       },
@@ -265,17 +315,28 @@
       "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",
+        "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)"
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "d9745b2b-cd37-4a1c-aae7-4cd75a3c126c",
+      "metadata": {
+        "id": "f2e3c0f2cbfb"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "fff3c4af",
       "metadata": {
         "id": "qJYoRfYng0XZ"
       },
@@ -286,17 +347,19 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "89a05131",
       "metadata": {
         "id": "riG_qUokg0XZ"
       },
       "outputs": [],
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "    PROJECT_ID = \"python-docs-samples-tests\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "9aa4ad5f",
       "metadata": {
         "id": "2aa333eca058"
       },
@@ -318,6 +381,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "244d416e",
       "metadata": {
         "id": "d8b34ef9a3d0"
       },
@@ -331,46 +395,49 @@
     },
     {
       "cell_type": "markdown",
+      "id": "eed6c3ba",
       "metadata": {
-        "id": "06571eb4063b"
+        "id": "126548a06aa1"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial.\n"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "6ef7c7b1",
       "metadata": {
-        "id": "697568e92bd6"
+        "id": "e660b8504e63"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "5763da2c",
       "metadata": {
-        "id": "dr--iN2kAylZ"
+        "id": "sBCra4QMA2wR"
       },
       "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": "sBCra4QMA2wR"
-      },
-      "source": [
+        "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",
@@ -384,9 +451,14 @@
         "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",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type and select\n",
+        "the following role into the filter box:\n",
+        "\n",
+        "    *   Storage Admin\n",
+        "    *   Storage Object Admin\n",
+        "    *   Service Account User\n",
+        "    *   Vertex AI Administrator\n",
+        "\n",
         "\n",
         "5. Click *Create*. A JSON file that contains your key downloads to your\n",
         "local environment.\n",
@@ -398,6 +470,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "85b826d2",
       "metadata": {
         "id": "PyQmSRbKA8r-"
       },
@@ -412,16 +485,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "\n",
-        "IS_COLAB = False\n",
-        "\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",
-        "\n",
-        "        IS_COLAB = True\n",
-        "\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -429,14 +497,13 @@
         "    # 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",
-        "\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "\n",
         "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "3d31b8b8",
       "metadata": {
         "id": "zgPO1eR3CYjk"
       },
@@ -453,6 +520,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "95a18950",
       "metadata": {
         "id": "MzGDU7TWdts_"
       },
@@ -465,18 +533,20 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "379d758a",
       "metadata": {
         "id": "cf221059d072"
       },
       "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_NAME = PROJECT_ID + \"aip-\" + UUID\n",
         "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "50b86adc",
       "metadata": {
         "id": "-EcIXiGsCePi"
       },
@@ -487,6 +557,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "564ce38f",
       "metadata": {
         "id": "NIq7R4HZCfIc"
       },
@@ -497,6 +568,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "a4324d2e",
       "metadata": {
         "id": "ucvCsknMCims"
       },
@@ -507,6 +579,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "df030498-f6e7-4e45-96f4-0d36590865aa",
       "metadata": {
         "id": "vhOb7YnwClBb"
       },
@@ -517,6 +590,88 @@
     },
     {
       "cell_type": "markdown",
+      "id": "49d12f54",
+      "metadata": {
+        "id": "b7e24e522bee"
+      },
+      "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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "8da829a1",
+      "metadata": {
+        "id": "77b01a1fdbb4"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "f2c8c41d",
+      "metadata": {
+        "id": "121d7ca29426"
+      },
+      "outputs": [],
+      "source": [
+        "import sys\n",
+        "\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "\n",
+        "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)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f0552e61",
+      "metadata": {
+        "id": "aa175e2960ac"
+      },
+      "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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "abbfcad3",
+      "metadata": {
+        "id": "f88cb0488c08"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2689f52b",
       "metadata": {
         "id": "fXUqOdIaLbjf"
       },
@@ -527,27 +682,20 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "754e5f7b",
       "metadata": {
         "id": "9fYX14c0LfmU"
       },
       "outputs": [],
       "source": [
-        "DATASET_URI = \"gs://cloud-samples-data/ai-platform/iris\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "z5WFzPetLl3Y"
-      },
-      "outputs": [],
-      "source": [
+        "DATASET_URI = \"gs://cloud-samples-data/ai-platform/iris\"\n",
+        "\n",
         "!gsutil cp -r $DATASET_URI $BUCKET_URI"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "231e5499",
       "metadata": {
         "id": "XoEqT2Y4DJmf"
       },
@@ -558,6 +706,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "884b2d31",
       "metadata": {
         "id": "pRUOFELefqf1"
       },
@@ -576,12 +725,14 @@
         "import kfp.v2.dsl as dsl\n",
         "# Vertex AI\n",
         "from google.cloud import aiplatform as vertex_ai\n",
+        "from google.cloud.aiplatform_v1.types.pipeline_state import PipelineState\n",
         "from kfp.v2.dsl import Metrics, Model, Output, component"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "20e96b6b",
       "metadata": {
         "id": "OAY0QKZD8qNP"
       },
@@ -590,9 +741,10 @@
         "# Experiments\n",
         "TASK = \"classification\"\n",
         "MODEL_TYPE = \"xgboost\"\n",
-        "EXPERIMENT_NAME = f\"{PROJECT_ID}-{TASK}-{MODEL_TYPE}-{TIMESTAMP}\"\n",
+        "EXPERIMENT_NAME = f\"{PROJECT_ID}-{TASK}-{MODEL_TYPE}-{UUID}\"\n",
         "\n",
         "# Pipeline\n",
+        "PIPELINE_TEMPLATE_FILE = \"pipeline.json\"\n",
         "PIPELINE_URI = f\"{BUCKET_URI}/pipelines\"\n",
         "TRAIN_URI = f\"{BUCKET_URI}/iris/iris_data.csv\"\n",
         "LABEL_URI = f\"{BUCKET_URI}/iris/iris_target.csv\"\n",
@@ -601,6 +753,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "3fb7c387",
       "metadata": {
         "id": "inR70nh38PeK"
       },
@@ -613,6 +766,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "6eb614be",
       "metadata": {
         "id": "Nz0nasrh8T3c"
       },
@@ -623,6 +777,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "01448e2a",
       "metadata": {
         "id": "container:training,prediction,xgboost"
       },
@@ -641,6 +796,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ece742dc",
       "metadata": {
         "id": "XujRA5ueox9U"
       },
@@ -653,6 +809,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "32a2397a",
       "metadata": {
         "id": "t1NLYz1R-KWv"
       },
@@ -662,18 +819,20 @@
     },
     {
       "cell_type": "markdown",
+      "id": "64570881",
       "metadata": {
         "id": "jnfKxpj0-Z0H"
       },
       "source": [
         "Before you start running your pipeline experiments, you have to formalize your training as pipeline component.\n",
         "\n",
-        "To do that, you will use the `kfp.v2.dsl.component` decorator to convert your training task into a pipeline component. "
+        "To do that, you build the pipeline by using the `kfp.v2.dsl.component` decorator to convert your training task into a pipeline component. "
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "f612dbf2",
       "metadata": {
         "id": "jv_-vU46_eFN"
       },
@@ -812,25 +971,20 @@
     },
     {
       "cell_type": "markdown",
+      "id": "bf048b2a",
       "metadata": {
         "id": "U1UiTZhkVoFM"
       },
       "source": [
-        "## Build a pipeline"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "7ABYbPz5UmJQ"
-      },
-      "source": [
-        "### Define your workflow using Kubeflow Pipelines DSL package"
+        "## Build a pipeline\n",
+        "\n",
+        "Below code will perform creating pipelineJob in associated project."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "7684850a",
       "metadata": {
         "id": "9Gfr6pNLU-dB"
       },
@@ -853,6 +1007,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "cb6cae0b",
       "metadata": {
         "id": "RkfZ7qVAVjBO"
       },
@@ -863,6 +1018,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "c6b9ec3f",
       "metadata": {
         "id": "oYlLBGUSVibG"
       },
@@ -873,6 +1029,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "cc940f17",
       "metadata": {
         "id": "95vG4-zPWc0B"
       },
@@ -882,6 +1039,7 @@
     },
     {
       "cell_type": "markdown",
+      "id": "bb2b2eb4",
       "metadata": {
         "id": "ZNb6kZ2l5t-O"
       },
@@ -894,6 +1052,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "77314a6f",
       "metadata": {
         "id": "XPy0Jc8xXgpa"
       },
@@ -911,6 +1070,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "aee97ebf",
       "metadata": {
         "id": "G0hm1no_WY8o"
       },
@@ -920,7 +1080,7 @@
         "\n",
         "    job = vertex_ai.PipelineJob(\n",
         "        display_name=f\"{EXPERIMENT_NAME}-pipeline-run-{i}\",\n",
-        "        template_path=\"pipeline.json\",\n",
+        "        template_path=PIPELINE_TEMPLATE_FILE,\n",
         "        pipeline_root=PIPELINE_URI,\n",
         "        parameter_values={\n",
         "            \"train_uri\": TRAIN_URI,\n",
@@ -934,11 +1094,12 @@
     },
     {
       "cell_type": "markdown",
+      "id": "0ca08588",
       "metadata": {
         "id": "O8TV4q535c2M"
       },
       "source": [
-        "### Check Pipeline run states\n",
+        "### Check Pipeline run states\n",
         "\n",
         "Vertex AI SDK provides you `get_experiment_df` method to monitor the status of pipeline runs. You can use it either to return parameters and metrics of the Pipeline Runs in the Vertex AI Experiment or in combination with `get` method of `PipelineJob` to return the pipeline job in Vertex AI Pipeline.\n"
       ]
@@ -946,6 +1107,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "a65f2574",
       "metadata": {
         "id": "dlCEJKfH5xR7"
       },
@@ -955,9 +1117,20 @@
         "vertex_ai.get_experiment_df(EXPERIMENT_NAME)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "id": "f605666a-9f2a-479f-9948-6f2f29e4e76b",
+      "metadata": {
+        "id": "98c022ca36b4"
+      },
+      "source": [
+        "The pipeline runs in the Vertex AI Experiment will be monitored based on pipeline run status."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "dc6661c5",
       "metadata": {
         "id": "FA9W85vs7LLD"
       },
@@ -965,7 +1138,7 @@
       "source": [
         "while True:\n",
         "    pipeline_experiments_df = vertex_ai.get_experiment_df(EXPERIMENT_NAME)\n",
-        "    if all(\n",
+        "    if any(\n",
         "        pipeline_state != \"COMPLETE\" for pipeline_state in pipeline_experiments_df.state\n",
         "    ):\n",
         "        print(\"Pipeline runs are still running...\")\n",
@@ -984,6 +1157,7 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "ef041ba2",
       "metadata": {
         "id": "ISsK9Msi-Kqs"
       },
@@ -992,12 +1166,13 @@
         "# Get the PipelineJob resource using the experiment run name\n",
         "pipeline_experiments_df = vertex_ai.get_experiment_df(EXPERIMENT_NAME)\n",
         "job = vertex_ai.PipelineJob.get(pipeline_experiments_df.run_name[0])\n",
-        "print(job.resource_name)\n",
-        "print(job._dashboard_uri())"
+        "print(\"Pipeline job name: \", job.resource_name)\n",
+        "print(\"Pipeline Run UI link: \", job._dashboard_uri())"
       ]
     },
     {
       "cell_type": "markdown",
+      "id": "02a718ab",
       "metadata": {
         "id": "TpV-iwP9qw9c"
       },
@@ -1013,42 +1188,36 @@
     {
       "cell_type": "code",
       "execution_count": null,
+      "id": "e90fb0b1",
       "metadata": {
         "id": "6xbYQn5t5Noe"
       },
       "outputs": [],
       "source": [
         "# Delete the pipeline\n",
-        "for i in range(0, len(runs)):\n",
-        "    pipeline_job = vertex_ai.PipelineJob.get(pipeline_experiments_df.run_name[i])\n",
-        "    pipeline_job.delete()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "eRC5iZOh_I8B"
-      },
-      "outputs": [],
-      "source": [
+        "while True:\n",
+        "    for i in range(0, len(runs)):\n",
+        "        pipeline_job = vertex_ai.PipelineJob.get(pipeline_experiments_df.run_name[i])\n",
+        "        if pipeline_job.state != PipelineState.PIPELINE_STATE_SUCCEEDED:\n",
+        "            print(\"Pipeline job is still running...\")\n",
+        "            time.sleep(60)\n",
+        "        else:\n",
+        "            print(\"Pipeline job is complete.\")\n",
+        "            pipeline_job.delete()\n",
+        "    break\n",
+        "\n",
         "# Delete experiment\n",
         "exp = vertex_ai.Experiment(EXPERIMENT_NAME)\n",
-        "exp.delete()"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "sx_vKniMq9ZX"
-      },
-      "outputs": [],
-      "source": [
-        "delete_bucket = False\n",
+        "exp.delete()\n",
         "\n",
+        "# Delete bucket\n",
+        "delete_bucket = False\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil rm -rf {BUCKET_URI}"
+        "    ! gsutil rm -rf {BUCKET_URI}\n",
+        "\n",
+        "# Remove local files\n",
+        "\n",
+        "!rm {PIPELINE_TEMPLATE_FILE}"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb

@@ -29,7 +29,7 @@
         "id": "title"
       },
       "source": [
-        "# Vertex SDK: AutoML training tabular binary classification model for batch explanation\n",
+        "# Vertex AI SDK: AutoML training tabular binary classification model for batch explanation\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
@@ -65,17 +65,6 @@
         "This tutorial demonstrates how to use the Vertex AI SDK to create tabular binary classification models and do batch prediction with explanation using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:bank,lbn"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the [Bank Marketing](https://pantheon.corp.google.com/storage/browser/_details/cloud-ml-tables-data/bank-marketing.csv) . This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -108,6 +97,17 @@
         "* Batch Prediction Service: Does a queued (batch) prediction for the entire set of instances in the background and stores the results in a Cloud Storage bucket when ready."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7a4881cf39a4"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the Bank Marketing. This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -136,7 +136,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Vertex Workbench Notebook, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "If you are using Colab or Vertex AI Workbench Notebook, 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",
@@ -322,7 +322,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -331,9 +334,8 @@
         "id": "timestamp"
       },
       "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 the timestamp onto the name of resources you create in this tutorial."
+        "#### UUID\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 uuid for each instance session, and append the uuid onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -344,9 +346,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of length 8\n",
+        "def generate_uuid():\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=8))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -357,7 +366,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Workbench AI Notebooks**, your environment is already\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",
@@ -440,7 +449,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
         "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
@@ -453,7 +462,7 @@
       "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_NAME = PROJECT_ID + \"aip-\" + UUID\n",
         "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
@@ -583,7 +592,7 @@
       "source": [
         "#### Quick peek at your data\n",
         "\n",
-        "You will use a version of the Bank Marketing dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
+        "You use a version of the Bank Marketing dataset that is stored in a public Cloud Storage bucket, using a CSV index file.\n",
         "\n",
         "Start by doing a quick peek at the data. You count the number of examples by counting the number of rows in the CSV index file  (`wc -l`) and then peek at the first few rows.\n",
         "\n",
@@ -637,7 +646,7 @@
       "outputs": [],
       "source": [
         "dataset = aip.TabularDataset.create(\n",
-        "    display_name=\"Bank Marketing\" + \"_\" + TIMESTAMP, gcs_source=[IMPORT_FILE]\n",
+        "    display_name=\"Bank Marketing\" + \"_\" + UUID, gcs_source=[IMPORT_FILE]\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -688,7 +697,7 @@
       "outputs": [],
       "source": [
         "dag = aip.AutoMLTabularTrainingJob(\n",
-        "    display_name=\"bank_\" + TIMESTAMP,\n",
+        "    display_name=\"bank_\" + UUID,\n",
         "    optimization_prediction_type=\"classification\",\n",
         "    optimization_objective=\"minimize-log-loss\",\n",
         ")\n",
@@ -730,7 +739,7 @@
       "source": [
         "model = dag.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"bank_\" + TIMESTAMP,\n",
+        "    model_display_name=\"bank_\" + UUID,\n",
         "    training_fraction_split=0.6,\n",
         "    validation_fraction_split=0.2,\n",
         "    test_fraction_split=0.2,\n",
@@ -784,7 +793,7 @@
       "source": [
         "### Make test items\n",
         "\n",
-        "You will use synthetic data as a test data items. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
+        "You use synthetic data as a test data items. Don't be concerned that we are using synthetic data."
       ]
     },
     {
@@ -852,11 +861,11 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"bank_\" + TIMESTAMP,\n",
+        "    job_display_name=\"bank_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
         "    instances_format=\"csv\",\n",
-        "    predictions_format=\"csv\",\n",
+        "    predictions_format=\"jsonl\",\n",
         "    generate_explanation=True,\n",
         "    sync=False,\n",
         ")\n",
@@ -952,6 +961,7 @@
         "# Set this to true only if you'd like to delete your bucket\n",
         "delete_bucket = False\n",
         "\n",
+        "dataset.delete()\n",
         "model.delete()\n",
         "batch_predict_job.delete()\n",
         "\n",

notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb

@@ -29,22 +29,22 @@
         "id": "title"
       },
       "source": [
-        "# Vertex SDK: Custom training image classification model for batch prediction with explainabilty\n",
+        "# Vertex AI SDK: Custom training image classification model for batch prediction with explainabilty\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_custom_image_classification_batch_explain.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.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/official/automl/sdk_custom_image_classification_batch_explain.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.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/tree/main/notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb\">\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/official/explainable_ai/sdk_custom_image_classification_batch_explain.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",
@@ -65,17 +65,6 @@
         "This tutorial demonstrates how to use the Vertex AI SDK to train and deploy a custom image classification model for batch prediction with explanation."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:custom,cifar10,icn"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "The dataset used for this tutorial is the [CIFAR10 dataset](https://www.tensorflow.org/datasets/catalog/cifar10) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you will use is built into TensorFlow. The trained model predicts which type of class an image is from ten classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -91,7 +80,7 @@
         "- `Vertex AI Training`\n",
         "- `Vertex AI Batch Prediction`\n",
         "- `Vertex Explainable AI`\n",
-        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Models`\n",
         "\n",
         "The steps performed include:\n",
         "\n",
@@ -102,6 +91,17 @@
         "- Make a batch prediction with explanations."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "dataset:custom,cifar10,icn"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [CIFAR10 dataset](https://www.tensorflow.org/datasets/catalog/cifar10) from [TensorFlow Datasets](https://www.tensorflow.org/datasets/catalog/overview). The version of the dataset you use in this notebook is built into TensorFlow. The trained model predicts the class of the provided input image from 10 classes namely airplane, automobile, bird, cat, deer, dog, frog, horse, ship and truck."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -190,11 +190,11 @@
         "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
         "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q\n",
         "! pip3 install --upgrade tensorflow $USER_FLAG -q\n",
+        "! pip3 install --upgrade opencv-python-headless $USER_FLAG -q\n",
         "\n",
         "if os.getenv(\"IS_TESTING\"):\n",
         "    ! apt-get update && apt-get install -y python3-opencv-headless\n",
-        "    ! apt-get install -y libgl1-mesa-dev\n",
-        "    ! pip3 install --upgrade opencv-python-headless $USER_FLAG"
+        "    ! apt-get install -y libgl1-mesa-dev"
       ]
     },
     {
@@ -256,6 +256,17 @@
         "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5aee4379e8e5"
+      },
+      "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,
@@ -321,7 +332,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -330,9 +344,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -343,9 +357,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of length 8\n",
+        "def generate_uuid():\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=8))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -426,7 +447,7 @@
         "\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."
       ]
@@ -439,7 +460,7 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
         "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
@@ -452,7 +473,7 @@
       "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_NAME = PROJECT_ID + \"aip-\" + UUID\n",
         "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
@@ -516,7 +537,7 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "from google.cloud import aiplatform"
       ]
     },
     {
@@ -538,7 +559,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -560,7 +581,7 @@
         "\n",
         "Learn more [here](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators) hardware accelerator support for your region\n",
         "\n",
-        "*Note*: TF releases before 2.3 for GPU support will fail to load the custom model in this tutorial. It is a known issue and fixed in TF 2.3 -- which is caused by static graph ops that are generated in the serving function. If you encounter this issue on your own custom models, use a container image for TF 2.3 with GPU support."
+        "*Note*: TF releases before 2.3 for GPU support fail to load the custom model in this tutorial. It is a known issue and is fixed in TF 2.3 -- which is caused by static graph ops that are generated in the serving function. If you encounter this issue on your own custom models, use a container image for TF 2.3 with GPU support."
       ]
     },
     {
@@ -573,7 +594,7 @@
       "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",
@@ -581,7 +602,7 @@
         "\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",
@@ -659,7 +680,7 @@
         "\n",
         "Next, set the machine type to use for training and prediction.\n",
         "\n",
-        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training and prediction.\n",
+        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you're going to use for for training and prediction.\n",
         " - `machine type`\n",
         "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
         "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
@@ -722,7 +743,7 @@
         "\n",
         "#### Package layout\n",
         "\n",
-        "Before you start the training, you will look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
+        "Before you start the training, you look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
         "\n",
         "- PKG-INFO\n",
         "- README.md\n",
@@ -738,7 +759,7 @@
         "\n",
         "#### Package Assembly\n",
         "\n",
-        "In the following cells, you will assemble the training package."
+        "In the following cells, you create the training package."
       ]
     },
     {
@@ -952,8 +973,8 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomTrainingJob(\n",
-        "    display_name=\"cifar10_\" + TIMESTAMP,\n",
+        "job = aiplatform.CustomTrainingJob(\n",
+        "    display_name=\"cifar10_\" + UUID,\n",
         "    script_path=\"custom/trainer/task.py\",\n",
         "    container_uri=TRAIN_IMAGE,\n",
         "    requirements=[\"gcsfs==0.7.1\", \"tensorflow-datasets==4.4\"],\n",
@@ -988,7 +1009,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, UUID)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -1094,9 +1115,9 @@
         "\n",
         "### Load evaluation data\n",
         "\n",
-        "You will load the CIFAR10 test (holdout) data from `tf.keras.datasets`, using the method `load_data()`. This returns the dataset as a tuple of two elements. The first element is the training data and the second is the test data. Each element is also a tuple of two elements: the image data, and the corresponding labels.\n",
+        "Load the CIFAR10 test (holdout) data from `tf.keras.datasets`, using the method `load_data()`. This returns the dataset as a tuple of two elements. The first element is the training data and the second is the test data. Each element is also a tuple of two elements: the image data, and the corresponding labels.\n",
         "\n",
-        "You don't need the training data, and hence why we loaded it as `(_, _)`.\n",
+        "You don't need the training data, and hence why it was loaded into `(_, _)`.\n",
         "\n",
         "Before you can run the data through evaluation, you need to preprocess it:\n",
         "\n",
@@ -1104,7 +1125,7 @@
         "1. Normalize (rescale) the pixel data by dividing each pixel by 255. This replaces each single byte integer pixel with a 32-bit floating point number between 0 and 1.\n",
         "\n",
         "`y_test`:<br/>\n",
-        "2. The labels are currently scalar (sparse). If you look back at the `compile()` step in the `trainer/task.py` script, you will find that it was compiled for sparse labels. So we don't need to do anything more."
+        "2. The labels are currently scalar (sparse). At the `compile()` step in the `trainer/task.py` script, it can be noticed that it was compiled for sparse labels already."
       ]
     },
     {
@@ -1238,7 +1259,7 @@
         "\n",
         "You can get the signatures of your model's input and output layers by reloading the model into memory, and querying it for the signatures corresponding to each layer.\n",
         "\n",
-        "When making a prediction request, you need to route the request to the serving function instead of the model, so you need to know the input layer name of the serving function -- which you will use later when you make a prediction request.\n",
+        "When making a prediction request, you need to route the request to the serving function instead of the model, so you need to know the input layer name of the serving function -- which you use later when you make a prediction request.\n",
         "\n",
         "You also need to know the name of the serving function's input and output layer for constructing the explanation metadata -- which is discussed subsequently."
       ]
@@ -1295,7 +1316,7 @@
         "\n",
         "Parameters:\n",
         "\n",
-        "- `path_count`: This is the number of paths over the features that will be processed by the algorithm. An exact approximation of the Shapley values requires M! paths, where M is the number of features. For the CIFAR10 dataset, this would be 784 (28*28).\n",
+        "- `path_count`: The number of paths over the features that are processed by the algorithm. An exact approximation of the Shapley values requires M! paths, where M is the number of features. For the CIFAR10 dataset, this would be 784 (28*28).\n",
         "\n",
         "For any non-trival number of features, this is too compute expensive. You can reduce the number of paths over the features to M * `path_count`.\n",
         "\n",
@@ -1323,7 +1344,7 @@
         "\n",
         "- `step_count`: This is the number of steps to approximate the remaining sum. The more steps, the more accurate the integral approximation. The general rule of thumb is 50 steps, but as you increase so does the compute time.\n",
         "\n",
-        "In the next code cell, set the variable `XAI` to which explainabilty algorithm you will use on your custom model."
+        "In the next code cell, set the variable `XAI` to which explainabilty algorithm you want to use on your custom model."
       ]
     },
     {
@@ -1343,7 +1364,7 @@
         "elif XAI == \"xrai\":\n",
         "    PARAMETERS = {\"xrai_attribution\": {\"step_count\": 50}}\n",
         "\n",
-        "parameters = aip.explain.ExplanationParameters(PARAMETERS)"
+        "parameters = aiplatform.explain.ExplanationParameters(PARAMETERS)"
       ]
     },
     {
@@ -1422,10 +1443,10 @@
         "\n",
         "OUTPUT_METADATA = {\"output_tensor_name\": serving_output}\n",
         "\n",
-        "input_metadata = aip.explain.ExplanationMetadata.InputMetadata(INPUT_METADATA)\n",
-        "output_metadata = aip.explain.ExplanationMetadata.OutputMetadata(OUTPUT_METADATA)\n",
+        "input_metadata = aiplatform.explain.ExplanationMetadata.InputMetadata(INPUT_METADATA)\n",
+        "output_metadata = aiplatform.explain.ExplanationMetadata.OutputMetadata(OUTPUT_METADATA)\n",
         "\n",
-        "metadata = aip.explain.ExplanationMetadata(\n",
+        "metadata = aiplatform.explain.ExplanationMetadata(\n",
         "    inputs={\"image\": input_metadata}, outputs={\"class\": output_metadata}\n",
         ")"
       ]
@@ -1458,8 +1479,8 @@
       },
       "outputs": [],
       "source": [
-        "model = aip.Model.upload(\n",
-        "    display_name=\"cifar10_\" + TIMESTAMP,\n",
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=\"cifar10_\" + UUID,\n",
         "    artifact_uri=MODEL_DIR,\n",
         "    serving_container_image_uri=DEPLOY_IMAGE,\n",
         "    explanation_parameters=parameters,\n",
@@ -1478,7 +1499,7 @@
       "source": [
         "### Get test items\n",
         "\n",
-        "You will use examples out of the test (holdout) portion of the dataset as a test items."
+        "Use examples from the test (holdout) portion of the dataset as a test items."
       ]
     },
     {
@@ -1532,7 +1553,7 @@
       "source": [
         "### Copy test item(s)\n",
         "\n",
-        "For the batch prediction, you will copy the test items over to your Cloud Storage bucket."
+        "For the batch prediction, copy the test items over to your Cloud Storage bucket."
       ]
     },
     {
@@ -1543,11 +1564,11 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil cp tmp1.jpg $BUCKET_NAME/tmp1.jpg\n",
-        "! gsutil cp tmp2.jpg $BUCKET_NAME/tmp2.jpg\n",
+        "! gsutil cp tmp1.jpg $BUCKET_URI/tmp1.jpg\n",
+        "! gsutil cp tmp2.jpg $BUCKET_URI/tmp2.jpg\n",
         "\n",
-        "test_item_1 = BUCKET_NAME + \"/tmp1.jpg\"\n",
-        "test_item_2 = BUCKET_NAME + \"/tmp2.jpg\""
+        "test_item_1 = BUCKET_URI + \"/tmp1.jpg\"\n",
+        "test_item_2 = BUCKET_URI + \"/tmp2.jpg\""
       ]
     },
     {
@@ -1558,7 +1579,7 @@
       "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 only be in JSONL format. 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 is then stored to your 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 the key/value pairs:\n",
         "\n",
         "- `input_name`: the name of the input layer of the underlying model.\n",
         "- `'b64'`: A key that indicates the content is base64 encoded.\n",
@@ -1568,7 +1589,7 @@
         "\n",
         "                        {serving_input: {'b64': content}}\n",
         "\n",
-        "To pass the image data to the prediction service you encode the bytes into base64 -- which makes the content safe from modification when transmitting binary data over the network.\n",
+        "To pass the image data to the prediction service you encode the bytes into base64. It makes the content safe from modification when transmitting binary data over the network.\n",
         "\n",
         "- `tf.io.read_file`: Read the compressed JPG images into memory as raw bytes.\n",
         "- `base64.b64encode`: Encode the raw bytes into a base64 encoded string."
@@ -1585,7 +1606,7 @@
         "import base64\n",
         "import json\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",
         "    bytes = tf.io.read_file(test_item_1)\n",
         "    b64str = base64.b64encode(bytes.numpy()).decode(\"utf-8\")\n",
@@ -1613,7 +1634,7 @@
         "- `instances_format`: The format for the input instances, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
         "- `predictions_format`: The format for the output predictions, either 'csv' or 'jsonl'. Defaults to 'jsonl'.\n",
         "- `machine_type`: The type of machine to use for training.\n",
-        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+        "- `sync`: Whether to execute the job synchronously. If False, the job executes in concurrent Future and any downstream object gets immediately returned and synced when the Future has completed."
       ]
     },
     {
@@ -1628,9 +1649,9 @@
         "MAX_NODES = 1\n",
         "\n",
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"cifar10_\" + TIMESTAMP,\n",
+        "    job_display_name=\"cifar10_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_NAME,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
         "    instances_format=\"jsonl\",\n",
         "    model_parameters=None,\n",
         "    machine_type=DEPLOY_COMPUTE,\n",
@@ -1717,7 +1738,9 @@
         "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."
+        "Otherwise, you can delete the individual resources you created in this tutorial. \n",
+        "\n",
+        "Set `delete_bucket` to **True** to delete the Cloud Storage bucket."
       ]
     },
     {
@@ -1735,7 +1758,7 @@
         "\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/feature_store/sdk-feature-store.ipynb

@@ -29,18 +29,22 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
+        "# Online and Batch predictions using Vertex AI Feature Store\n",
+        "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/feature_store/sdk-feature-store.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/feature_store/sdk-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",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/feature_store/sdk-feature-store.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/feature_store/sdk-feature-store.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",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/notebook_template.ipynb\">\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/official/feature_store/sdk-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",
@@ -51,19 +55,22 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "c4aaea3bab5e"
       },
       "source": [
         "## Overview\n",
         "\n",
         "This notebook introduces Vertex AI Feature Store, a managed cloud service for machine learning engineers and data scientists to store, serve, manage and share machine learning features at a large scale.\n",
         "\n",
-        "This notebook assumes that you understand basic Google Cloud concepts such as [Project](https://cloud.google.com/storage/docs/projects), [Storage](https://cloud.google.com/storage) and [Vertex AI](https://cloud.google.com/vertex-ai/docs). Some machine learning knowledge is also helpful but not required.\n",
-        "\n",
-        "### Dataset\n",
-        "\n",
-        "This notebook uses a movie recommendation dataset as an example throughout all the sessions. The task is to train a model to predict if a user is going to watch a movie and serve this model online. \n",
-        "\n",
+        "This notebook assumes that you understand basic Google Cloud concepts such as [Project](https://cloud.google.com/storage/docs/projects), [Storage](https://cloud.google.com/storage) and [Vertex AI](https://cloud.google.com/vertex-ai/docs). Some machine learning knowledge is also helpful but not required.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "71779c8088bf"
+      },
+      "source": [
         "### Objective\n",
         "\n",
         "In this notebook, you will learn how to use `Vertex AI Feature Store` to import feature data, and to access the feature data for both online serving and offline tasks, such as training.\n",
@@ -72,15 +79,31 @@
         "\n",
         "- `Vertex AI Feature Store`\n",
         "\n",
-        "\n",
-        "\n",
         "The steps performed include:\n",
         "\n",
         "- Create featurestore, entity type, and feature resources.\n",
         "- Import feature data into `Vertex AI Feature Store` resource.\n",
         "- Serve online prediction requests using the imported features.\n",
-        "- Access imported features in offline jobs, such as training jobs.\n",
+        "- Access imported features in offline jobs, such as training jobs."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "55e01a856f57"
+      },
+      "source": [
+        "### Dataset\n",
         "\n",
+        "This notebook uses a movie recommendation dataset as an example throughout all the sessions. The task is to train a model to predict if a user is going to watch a movie and serve this model online."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -262,7 +285,15 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "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)"
       ]
     },
     {
@@ -275,10 +306,7 @@
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
         "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\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)"
+        "print(\"Project ID: \", PROJECT_ID)"
       ]
     },
     {
@@ -320,7 +348,9 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -329,9 +359,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\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 the timestamp onto the name of resources you create in this tutorial."
+        "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 uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -342,9 +372,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -356,7 +393,7 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
+        "authenticated."
       ]
     },
     {
@@ -441,7 +478,7 @@
       "source": [
         "from google.cloud.aiplatform import Feature, Featurestore\n",
         "\n",
-        "FEATURESTORE_ID = \"movie_prediction\"\n",
+        "FEATURESTORE_ID = \"movie_prediction\" + UUID\n",
         "INPUT_CSV_FILE = \"gs://cloud-samples-data-us-central1/vertex-ai/feature-store/datasets/movie_prediction.csv\"\n",
         "ONLINE_STORE_FIXED_NODE_COUNT = 1"
       ]
@@ -785,7 +822,7 @@
       "source": [
         "## Import Feature Values\n",
         "\n",
-        "You need to import feature values before you can use them for online/offline serving. In this step, you learn how to import feature values by ingesting the values from GCS (Google Cloud Storage). You can also import feature values from BigQuery or a Pandas dataframe.\n"
+        "You need to import feature values before you can use them for online/offline serving. In this step, you learn how to import feature values by ingesting the values from Cloud Storage. You can also import feature values from BigQuery or a Pandas dataframe.\n"
       ]
     },
     {
@@ -988,7 +1025,7 @@
       "source": [
         "### Read one entity per request\n",
         "\n",
-        "With the Python SDK, it is easy to read feature values of one entity. By default, the SDK will return the  latest value of each feature, meaning the feature values with the most recent  timestamp.\n",
+        "With the Vertex AI SDK, it is easy to read feature values of one entity. By default, the SDK will return the  latest value of each feature, meaning the feature values with the most recent  timestamp.\n",
         "\n",
         "To read feature values, specify the entity type ID and features to read. By default all the features of an entity type will be selected. The response will output and display the selected entity type ID and the selected feature values as a Pandas dataframe."
       ]

notebooks/official/matching_engine/intro-swivel.ipynb

@@ -214,7 +214,7 @@
         "if not os.getenv(\"IS_TESTING\"):\n",
         "    # Automatically restart kernel after installs\n",
         "    import IPython\n",
-        "    \n",
+        "\n",
         "    app = IPython.Application.instance()\n",
         "    app.kernel.do_shutdown(True)"
       ]
@@ -675,6 +675,18 @@
         "!./swivel_template_configuration.sh -pipeline_suffix {YOUR_PIPELINE_SUFFIX} -project_number {PROJECT_NUMBER} -project_id {PROJECT_ID} -machine_type {MACHINE_TYPE} -accelerator_count {ACCELERATOR_COUNT} -accelerator_type {ACCELERATOR_TYPE} -pipeline_root {BUCKET}"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1cacea95d68c"
+      },
+      "outputs": [],
+      "source": [
+        "! sed \"s:\\t:    :g\" swivel_pipeline_basic.json >tmp.json\n",
+        "! mv tmp.json swivel_pipeline_basic.json"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -765,19 +777,15 @@
         "# Instantiate PipelineJob object\n",
         "pl = aiplatform.PipelineJob(\n",
         "    display_name=YOUR_PIPELINE_SUFFIX,\n",
-        "\n",
         "    # Whether or not to enable caching\n",
         "    # True = always cache pipeline step result\n",
         "    # False = never cache pipeline step result\n",
         "    # None = defer to cache option for each pipeline component in the pipeline definition\n",
         "    enable_caching=False,\n",
-        "\n",
         "    # Local or GCS path to a compiled pipeline definition\n",
         "    template_path=\"swivel_pipeline_basic.json\",\n",
-        "\n",
         "    # Dictionary containing input parameters for your pipeline\n",
         "    parameter_values=PARAMETER_VALUES,\n",
-        "\n",
         "    # GCS path to act as the pipeline root\n",
         "    pipeline_root=PIPELINE_ROOT,\n",
         ")\n",