update: touchups

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

* Linted notebook

* Removed TODOs

* Updates per PR comments

* Revered to multiple imports per line

.cloud-build/cleanup/cleanup.py

@@ -1,9 +1,13 @@
 from typing import List
+from ratemate import RateLimit
+from resource_cleanup_manager import (
+    DatasetResourceCleanupManager,
+    ModelResourceCleanupManager,
+    EndpointResourceCleanupManager,
+    ResourceCleanupManager,
+)
 
-from resource_cleanup_manager import (DatasetResourceCleanupManager,
-                                      EndpointResourceCleanupManager,
-                                      ModelResourceCleanupManager,
-                                      ResourceCleanupManager)
+rate_limit = RateLimit(max_count=25, per=60, greedy=False)
 
 
 def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: bool):
@@ -14,17 +18,18 @@ def run_cleanup_managers(managers: List[ResourceCleanupManager], is_dry_run: boo
         resources = manager.list()
         print(f"Found {len(resources)} {type_name}'s")
         for resource in resources:
-            if not manager.is_deletable(resource):
-                continue
+            try:
+                if not manager.is_deletable(resource):
+                    continue
 
-            if is_dry_run:
-                resource_name = manager.resource_name(resource)
-                print(f"Will delete '{type_name}': {resource_name}")
-            else:
-                try:
+                if is_dry_run:
+                    resource_name = manager.resource_name(resource)
+                    print(f"Will delete '{type_name}': {resource_name}")
+                else:
+                    rate_limit.wait()  # wait before deleting
                     manager.delete(resource)
-                except Exception as exception:
-                    print(exception)
+            except Exception as exception:
+                print(exception)
 
         print("")
 
@@ -38,7 +43,7 @@ if is_dry_run:
 managers = [
     DatasetResourceCleanupManager(),
     EndpointResourceCleanupManager(),
-    ModelResourceCleanupManager(),
+    ModelResourceCleanupManager(),  # ModelResourceCleanupManager must follow EndpointResourceCleanupManager due to deployed models blocking model deletion.
 ]
 
 run_cleanup_managers(managers=managers, is_dry_run=is_dry_run)

.cloud-build/cleanup/resource_cleanup_manager.py

@@ -1,5 +1,5 @@
 import abc
-from typing import Any
+from typing import Any, Type
 
 from google.cloud import aiplatform
 from google.cloud.aiplatform import base
@@ -41,7 +41,7 @@ class ResourceCleanupManager(abc.ABC):
         # Check that it wasn't created too recently, to prevent race conditions
         if time_difference <= RESOURCE_UPDATE_BUFFER_IN_SECONDS:
             print(
-                f"Skipping '{resource}' due update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
+                f"Skipping '{resource}' due to update_time being '{time_difference}', which is less than '{RESOURCE_UPDATE_BUFFER_IN_SECONDS}'."
             )
             return False
 
@@ -51,7 +51,7 @@ class ResourceCleanupManager(abc.ABC):
 class VertexAIResourceCleanupManager(ResourceCleanupManager):
     @property
     @abc.abstractmethod
-    def vertex_ai_resource(self) -> base.VertexAiResourceNounWithFutureManager:
+    def vertex_ai_resource(self) -> Type[base.VertexAiResourceNounWithFutureManager]:
         pass
 
     @property
@@ -61,7 +61,9 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
     def list(self) -> Any:
         return self.vertex_ai_resource.list()
 
-    def resource_name(self, resource: Any) -> str:
+    def resource_name(
+        self, resource: Type[base.VertexAiResourceNounWithFutureManager]
+    ) -> str:
         return resource.display_name
 
     def delete(self, resource):
@@ -75,12 +77,33 @@ class VertexAIResourceCleanupManager(ResourceCleanupManager):
 
 class DatasetResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.datasets._Dataset
+    dataset_types = [
+        aiplatform.ImageDataset,
+        aiplatform.TabularDataset,
+        aiplatform.TextDataset,
+        aiplatform.TimeSeriesDataset,
+        aiplatform.VideoDataset,
+    ]
+
+    def list(self) -> Any:
+        return [
+            dataset
+            for dataset_type in self.dataset_types
+            for dataset in dataset_type.list()
+        ]
 
 
 class EndpointResourceCleanupManager(VertexAIResourceCleanupManager):
     vertex_ai_resource = aiplatform.Endpoint
 
     def delete(self, resource):
+        # TODO: Remove this once https://github.com/googleapis/python-aiplatform/issues/1441 is fixed
+        resource._sync_gca_resource()
+        for deployed_model_id in [
+            models.id for models in resource._gca_resource.deployed_models
+        ]:
+            resource._undeploy(deployed_model_id=deployed_model_id)
+
         resource.delete(force=True)
 
 

.cloud-build/execute_changed_notebooks_helper.py

@@ -17,6 +17,7 @@ import concurrent
 import dataclasses
 import datetime
 import functools
+import git
 import operator
 import os
 import pathlib
@@ -24,6 +25,7 @@ import re
 import subprocess
 from typing import List, Optional
 
+import execute_notebook_helper
 import execute_notebook_remote
 import nbformat
 from google.cloud.devtools.cloudbuild_v1.types import BuildOperationMetadata
@@ -231,20 +233,39 @@ def get_changed_notebooks(
 
     # Find notebooks
     notebooks = []
+
+    # Instantiate GitPython objects
+    repo = git.Repo(os.getcwd())
+    index = repo.index
+
     if base_branch:
-        print(f"Looking for notebooks that changed from branch: {base_branch}")
-        notebooks = subprocess.check_output(
-            ["git", "diff", "--name-only", f"origin/{base_branch}..."] + test_paths
-        )
+        # Get the point at which this branch branches off from main
+        branching_commits = repo.merge_base("HEAD", f"origin/{base_branch}")
+
+        if len(branching_commits) > 0:
+            branching_commit = branching_commits[0]
+            print(f"Looking for notebooks that changed from branch: {branching_commit}")
+
+            notebooks = [
+                diff.b_path
+                for diff in index.diff(branching_commit, paths=test_paths)
+                if diff.b_path is not None
+            ]
+        else:
+            notebooks = []
     else:
         print(f"Looking for all notebooks.")
         notebooks = subprocess.check_output(["git", "ls-files"] + test_paths)
 
-    notebooks = notebooks.decode("utf-8").split("\n")
     notebooks = [notebook for notebook in notebooks if notebook.endswith(".ipynb")]
     notebooks = [notebook for notebook in notebooks if len(notebook) > 0]
     notebooks = [notebook for notebook in notebooks if pathlib.Path(notebook).exists()]
 
+    if len(notebooks) > 0:
+        print(f"Found {len(notebooks)} notebooks:")
+        for notebook in notebooks:
+            print(f"\t{notebook}")
+
     return notebooks
 
 
@@ -287,14 +308,15 @@ def process_and_execute_notebooks(
         timeout (str):
             Required. Timeout string according to https://cloud.google.com/build/docs/build-config-file-schema#timeout.
     """
-    notebook_execution_results: List[NotebookExecutionResult] = []
 
     # Calculate deadline
     deadline = datetime.datetime.now() + datetime.timedelta(
         seconds=max(timeout - WORKER_TIMEOUT_BUFFER_IN_SECONDS, 0)
     )
 
-    if len(notebooks) > 0:
+    if len(notebooks) > 1:
+        notebook_execution_results: List[NotebookExecutionResult] = []
+
         print(f"Found {len(notebooks)} modified notebooks: {notebooks}")
 
         if should_parallelize and len(notebooks) > 1:
@@ -333,43 +355,64 @@ def process_and_execute_notebooks(
                 )
                 for notebook in notebooks
             ]
+
+        print("\n=== RESULTS ===\n")
+
+        results_sorted = sorted(
+            notebook_execution_results,
+            key=lambda result: result.is_pass,
+            reverse=True,
+        )
+
+        # Print results
+        print(
+            tabulate(
+                [
+                    [
+                        result.name,
+                        "PASSED" if result.is_pass else "FAILED",
+                        format_timedelta(result.duration),
+                        result.log_url,
+                        result.output_uri,
+                    ]
+                    for result in results_sorted
+                ],
+                headers=["build_tag", "status", "duration", "log_url", "output_url"],
+            )
+        )
+
+        print("\n=== END RESULTS===\n")
+
+        total_notebook_duration = functools.reduce(
+            operator.add,
+            [datetime.timedelta(seconds=0)]
+            + [result.duration for result in results_sorted],
+        )
+
+        print(
+            f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}"
+        )
+
+        # Raise error if any notebooks failed
+        if not all([result.is_pass for result in results_sorted]):
+            raise RuntimeError("Notebook failures detected. See logs for details")
+
+    elif len(notebooks) == 1:
+        notebook = notebooks[0]
+
+        # Pre-process notebook by substituting variable names
+        _process_notebook(
+            notebook_path=notebook,
+            variable_project_id=variable_project_id,
+            variable_region=variable_region,
+        )
+
+        execute_notebook_helper.execute_notebook(
+            notebook_source=notebook,
+            output_file_or_uri="/".join(
+                [artifacts_bucket, pathlib.Path(notebook).name]
+            ),
+            should_log_output=True,
+        )
     else:
         print("No notebooks modified in this pull request.")
-
-    print("\n=== RESULTS ===\n")
-
-    results_sorted = sorted(
-        notebook_execution_results,
-        key=lambda result: result.is_pass,
-        reverse=True,
-    )
-
-    # Print results
-    print(
-        tabulate(
-            [
-                [
-                    result.name,
-                    "PASSED" if result.is_pass else "FAILED",
-                    format_timedelta(result.duration),
-                    result.log_url,
-                ]
-                for result in results_sorted
-            ],
-            headers=["build_tag", "status", "duration", "log_url"],
-        )
-    )
-
-    print("\n=== END RESULTS===\n")
-
-    total_notebook_duration = functools.reduce(
-        operator.add,
-        [datetime.timedelta(seconds=0)]
-        + [result.duration for result in results_sorted],
-    )
-
-    print(f"Cumulative notebook duration: {format_timedelta(total_notebook_duration)}")
-
-    # Raise error if any notebooks failed
-    if not all([result.is_pass for result in results_sorted]):
-        raise RuntimeError("Notebook failures detected. See logs for details")

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

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

.cloud-build/requirements.txt

@@ -10,3 +10,4 @@ google-cloud-aiplatform
 google-cloud-storage
 google-cloud-build
 ratemate
+GitPython

.cloud-build/test_folders.txt

@@ -1,3 +1,2 @@
 notebooks/official
 notebooks/notebook_template.ipynb
-notebooks/community/ml_ops

.github/workflows/ci.yaml

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

.github/workflows/linter/requirements.txt

@@ -3,7 +3,8 @@ ipython
 jupyter
 nbconvert
 black==22.3.0
-pyupgrade==2.31.1
+pyupgrade==2.34.0
 isort==5.10.1
 flake8==4.0.1
 nbqa==1.3.1
+

CONTRIBUTING.md

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

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

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

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

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

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

@@ -1,5 +1,5 @@
 dataclasses==0.6
 google-cloud-aiplatform==1.8.1
-tensorflow==2.5.3
+tensorflow==2.7.2
 pillow==9.0.1
 tf-agents==0.8.0

community-content/tf_keras_image_classification_distributed_multi_worker_with_vertex_sdk/trainer/requirements.txt

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

community-content/tf_keras_text_classification_distributed_single_worker_gpus_with_gcloud_local_run_and_vertex_sdk/trainer/requirements.txt

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

notebooks/README.md

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

notebooks/community/CODEOWNERS

@@ -12,6 +12,7 @@
 /managed_notebooks/
 /sdk/SDK_FBProphet_Forecasting_Online.ipynb @brianchunkang
 /pipelines/google_cloud_pipeline_components_TPU_model_train_upload_deploy.ipynb @brianchunkang
+/explainable_ai/SDK_Custom_Container_XAI.ipynb @brianchunkang
 /matching_engine/sdk_matching_engine_for_indexing.ipynb @ivanmkc
 /matching_engine/matching_engine_for_indexing.ipynb @yinghsienwu
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
@@ -20,4 +21,6 @@
 /vertex_endpoints/tf_hub_obj_detection/deploy_tfhub_object_detection_on_vertex_endpoints.ipynb @entrpn
 /vertex_endpoints/nvidia-triton/nvidia-triton-custom-container-prediction.ipynb @RajeshThallam
 /vertex_endpoints/optimized_tensorflow_runtime @vlasenkoalexey
-/notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
+/notebooks/community/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/feature_store/mobile_gaming/mobile_gaming_feature_store.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/main/notebooks/notebook_template.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/vertex-ai-samples/blob/main/notebooks/community/feature_store/mobile_gaming/mobile_gaming_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/notebook_template.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/feature_store/mobile_gaming/mobile_gaming_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",
         "  </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/notebook_template.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/community/feature_store/mobile_gaming/mobile_gaming_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",
@@ -54,52 +54,52 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "7FZeBEwdXS4d"
+        "id": "tvgnzT1CKxrO"
       },
       "source": [
         "## Overview\n",
-        "\n",
-        "Imagine you are a member of the Data Science team working on the same Mobile Gaming application reported in the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml) blog post. \n",
-        "\n",
-        "Business wants to use that information in real-time to take immediate intervention actions in-game to prevent churn. In particular, for each player, they want to provide gaming incentives like new items or bonus packs depending on the customer demographic,  behavioral information and the resulting propensity of return. \n",
-        "\n",
-        "Last year, Google Cloud announced Vertex AI, a managed machine learning (ML) platform that allows data science teams to accelerate the deployment and maintenance of ML models. One of the platform building blocks is Vertex AI Feature store which provides a managed service for low latency scalable feature serving. Also it is a centralized feature repository with easy APIs to search & discover features and feature monitoring capabilities to track drift and other quality issues. \n",
-        "\n",
-        "In this notebook, we will show how the role of Vertex AI Feature Store in a ready to production scenario when the user's activities within the first 24 hours of last engagment and the gaming platform would consume in order to improver UX. Below you can find the high level picture of the system\n",
-        "\n",
+        " \n",
+        "Imagine you are a member of the Data Science team working on the same Mobile Gaming application reported in the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml) blog post.\n",
+        " \n",
+        "Business wants to use that information in real-time to take immediate intervention actions in-game to prevent churn. In particular, for each player, they want to provide gaming incentives like new items or bonus packs depending on the customer demographic,  behavioral information and the resulting propensity of return.\n",
+        " \n",
+        "Last year, Google Cloud announced Vertex AI, a managed machine learning (ML) platform that allows data science teams to accelerate the deployment and maintenance of ML models. One of the platform building blocks is Vertex AI Feature store which provides a managed service for low latency scalable feature serving. Also it is a centralized feature repository with easy APIs to search & discover features and feature monitoring capabilities to track drift and other quality issues.\n",
+        " \n",
+        "In this notebook, we will show how the role of Vertex AI Feature Store in a ready to production scenario when the user's activities within the first 24 hours of last engagement and the gaming platform would consume in order to improve UX. Below you can find the high level picture of the system\n",
+        " \n",
         "<img src=\"./assets/mobile_gaming_architecture_1.png\">\n",
-        "\n",
-        "\n",
+        " \n",
+        " \n",
         "### Dataset\n",
-        "\n",
+        " \n",
         "The dataset is the public sample export data from an actual mobile game app called \"Flood It!\" (Android, iOS)\n",
-        "\n",
+        " \n",
         "### Objective\n",
-        "\n",
+        " \n",
         "In the following notebook, you will learn how Vertex AI Feature store\n",
-        "\n",
-        "1.   Provide a centralized feature repository with easy APIs to search & discover features and fetch them for training/serving. \n",
-        "\n",
-        "2.   Simplify deployments of models for Online Prediction, via low latency scalable feature serving.\n",
-        "\n",
-        "3.   Mitigate training serving skew and data leakage by performing point in time lookups to fetch historical data for training.\n",
-        "\n",
+        " \n",
+        "1.  Provide a centralized feature repository with easy APIs to search & discover features and fetch them for training/serving.\n",
+        " \n",
+        "2.  Simplify deployments of models for Online Prediction, via low latency scalable feature serving.\n",
+        " \n",
+        "3.  Mitigate training serving skew and data leakage by performing point in time lookups to fetch historical data for training.\n",
+        " \n",
         "**Notice that we assume that already know how to set up a Vertex AI Feature store. In case you are not, please check out [this detailed notebook](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/feature_store/gapic-feature-store.ipynb).**\n",
-        "\n",
-        "\n",
-        "### Costs \n",
-        "\n",
+        " \n",
+        " \n",
+        "### Costs\n",
+        " \n",
         "This tutorial uses billable components of Google Cloud:\n",
-        "\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) 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."
+        "to generate a cost estimate based on your projected usage.\n"
       ]
     },
     {
@@ -110,7 +110,7 @@
       "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."
       ]
     },
@@ -159,7 +159,7 @@
       "source": [
         "### Install additional packages\n",
         "\n",
-        "Install additional package dependencies not installed in your notebook environment, such as {XGBoost, AdaNet, or TensorFlow Hub TODO: Replace with relevant packages for the tutorial}. Use the latest major GA version of each package."
+        "Install additional package dependencies not installed in your notebook environment, such as XGBoost. Use the latest major GA version of each package."
       ]
     },
     {
@@ -172,12 +172,15 @@
       "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",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\""
       ]
     },
@@ -185,11 +188,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "SzEo6DeE2GOP"
+        "id": "_vr6BYED_5my"
       },
       "outputs": [],
       "source": [
-        "! pip3 install {USER_FLAG} --upgrade pip\n",
+        "! pip3 install {USER_FLAG} --upgrade pip -q\n",
         "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform==1.11.0 -q --no-warn-conflicts\n",
         "! pip3 install {USER_FLAG} git+https://github.com/googleapis/python-aiplatform.git@main # For features monitoring\n",
         "! pip3 install {USER_FLAG} --upgrade google-cloud-bigquery==2.24.0 -q --no-warn-conflicts\n",
@@ -249,7 +252,7 @@
         "\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 and Compute Engine API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component). \n",
+        "1. [Enable the APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,notebooks.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",
@@ -307,18 +310,76 @@
       "outputs": [],
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"\"  # @param {type:\"string\"}"
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "dEjRdjxBuDsi"
+        "id": "set_gcloud_project_id"
       },
       "outputs": [],
       "source": [
-        "!gcloud config set project $PROJECT_ID #change it"
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "23988890fef6"
+      },
+      "source": [
+        "#### Get your project number (Optional)\n",
+        "\n",
+        "Now that the project ID is set, you get your corresponding project number."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "2d6950574e1d"
+      },
+      "outputs": [],
+      "source": [
+        "shell_output = ! gcloud projects list --filter=\"PROJECT_ID:'{PROJECT_ID}'\" --format='value(PROJECT_NUMBER)'\n",
+        "PROJECT_NUMBER = shell_output[0]\n",
+        "print(\"Project Number:\", PROJECT_NUMBER)"
+      ]
+    },
+    {
+      "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": "jIcZV7-C2RrX"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -353,7 +414,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
         "authenticated. Skip this step."
       ]
     },
@@ -376,9 +437,13 @@
         "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 and add the following roles:\n",
+        "   - BigQuery Admin\n",
+        "   - Storage Admin\n",
+        "   - Storage Object Admin\n",
+        "   - Vertex AI Administrator\n",
+        "   - Vertex AI Feature Store Admin\n",
+        "\n",
         "\n",
         "5. Click *Create*. A JSON file that contains your key downloads to your\n",
         "local environment.\n",
@@ -395,19 +460,19 @@
       },
       "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",
@@ -447,8 +512,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -459,11 +524,9 @@
       },
       "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-\" + TIMESTAMP\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -486,26 +549,6 @@
         "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "994afa65eaa2"
-      },
-      "source": [
-        "Run the following cell to grant access to your Cloud Storage resources from Vertex AI Feature store"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "psP1rPU9TRnX"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil uniformbucketlevelaccess set on $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -526,6 +569,78 @@
         "! gsutil ls -al $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account (Optional)\n",
+        "\n",
+        "If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "MQVV9haf2Rra"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    else:  # 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",
+      "metadata": {
+        "id": "set_service_account:pipelines"
+      },
+      "source": [
+        "#### Set service account access\n",
+        "\n",
+        "Run the following commands to grant your service account access. You only need to run this step once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "U4UpQThc2Rrb"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -541,13 +656,22 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "G3G2BXqswb_J"
+        "id": "8615339fa4ca"
       },
       "outputs": [],
       "source": [
         "BQ_DATASET = \"Mobile_Gaming\"  # @param {type:\"string\"}\n",
-        "LOCATION = \"US\"\n",
-        "\n",
+        "LOCATION = \"US\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "G3G2BXqswb_J"
+      },
+      "outputs": [],
+      "source": [
         "!bq mk --location=$LOCATION --dataset $PROJECT_ID:$BQ_DATASET"
       ]
     },
@@ -600,12 +724,9 @@
       "outputs": [],
       "source": [
         "# Data Engineering and Feature Engineering\n",
-        "TODAY = \"2018-10-03\"\n",
-        "TOMORROW = \"2018-10-04\"\n",
+        "TODAY = \"2022-06-16\"\n",
         "LABEL_TABLE = f\"label_table_{TODAY}\".replace(\"-\", \"\")\n",
-        "FEATURES_TABLE = \"wide_features_table\"  # @param {type:\"string\"}\n",
-        "FEATURES_TABLE_TODAY = f\"wide_features_table_{TODAY}\".replace(\"-\", \"\")\n",
-        "FEATURES_TABLE_TOMORROW = f\"wide_features_table_{TOMORROW}\".replace(\"-\", \"\")\n",
+        "FEATURES_TABLE = f\"wide_features_table_{TODAY}\"  # @param {type:\"string\"}\n",
         "FEATURESTORE_ID = \"mobile_gaming\"  # @param {type:\"string\"}\n",
         "ENTITY_TYPE_ID = \"user\"\n",
         "\n",
@@ -947,13 +1068,37 @@
         "You will cover those steps in details below."
       ]
     },
+    {
+      "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": "poLJ0fV52Rrc"
+      },
+      "outputs": [],
+      "source": [
+        "vertex_ai.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "4ffd54e97270"
       },
       "source": [
-        "## Initiate clients"
+        "### Initialize BigQuery SDK for Python\n",
+        "\n",
+        "Initialize the BigQuery AI SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -964,55 +1109,53 @@
       },
       "outputs": [],
       "source": [
-        "bq_client = bigquery.Client(project=PROJECT_ID, location=LOCATION)\n",
-        "vertex_ai.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
+        "bq_client = bigquery.Client(project=PROJECT_ID, location=LOCATION)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "zmMWIpCwsET9"
+        "id": "WnUQO2IHC9pZ"
       },
       "source": [
         "## Identify users and build your features\n",
-        "\n",
-        "This section we will static features we want to fetch from Vertex AI Feature Store. In particular, we will cover the following steps:\n",
-        "\n",
+        " \n",
+        "This section we will have static features we want to fetch from Vertex AI Feature Store. In particular, we will cover the following steps:\n",
+        " \n",
         "1. Identify users, process demographic features and process behavioral features within the last 24 hours using **BigQuery**\n",
-        "\n",
+        " \n",
         "2. Set up the feature store\n",
-        "\n",
+        " \n",
         "3. Register features using **Vertex AI Feature Store** and the SDK.\n",
-        "\n",
-        "Below you have a picture that shows the process. \n",
-        "\n",
+        " \n",
+        "Below you have a picture that shows the process.\n",
+        " \n",
         "<img src=\"./assets/feature_store_ingestion_2.png\">\n",
-        "\n",
-        "\n",
-        "\n",
-        "The original dataset contains raw event data we cannot ingest in the feature store as they are. We need to pre-process the raw data in order to get user features. \n",
-        "\n",
-        "**Notice we simulate those transformations in different point of time (today and tomorrow).**\n"
+        " \n",
+        " \n",
+        "The original dataset contains raw event data we cannot ingest in the feature store as they are. We need to pre-process the raw data in order to get user features.\n",
+        " \n",
+        "**Notice we simulate those transformations in different points of time (today and tomorrow).**\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "8avYy5QOv02s"
+        "id": "e9zIrwhpDF2q"
       },
       "source": [
         "### Label, Demographic and Behavioral Transformations\n",
-        "\n",
-        "This section is based on the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml?utm_source=linkedin&utm_medium=unpaidsoc&utm_campaign=FY21-Q2-Google-Cloud-Tech-Blog&utm_content=google-analytics-4&utm_term=-) blog article by Minhaz Kazi and Polong Lin. \n",
-        "\n",
-        "You will adapt it in order to turn a batch churn prediction (using features within the first 24h user of first engagment) in a real-time churn prediction (using features within the first 24h user of last engagment)."
+        " \n",
+        "This section is based on the [Churn prediction for game developers using Google Analytics 4 (GA4) and BigQuery ML](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml?utm_source=linkedin&utm_medium=unpaidsoc&utm_campaign=FY21-Q2-Google-Cloud-Tech-Blog&utm_content=google-analytics-4&utm_term=-) blog article by Minhaz Kazi and Polong Lin.\n",
+        " \n",
+        "You will adapt it to turn a batch churn prediction (using features within the first 24h user of first engagement) into a real-time churn prediction (using features within the first 6h user of last engagement).\n"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "YO28RAITh6L-"
+        "id": "RQX5m8UiC_px"
       },
       "outputs": [],
       "source": [
@@ -1039,27 +1182,27 @@
         "  SELECT\n",
         "    event_timestamp,\n",
         "    user_pseudo_id,\n",
-        "    SUM(IF(event_name = 'user_engagement', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'user_engagement', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_user_engagement,\n",
-        "    SUM(IF(event_name = 'level_start_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_start_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_start_quickplay,\n",
-        "    SUM(IF(event_name = 'level_end_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_end_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_end_quickplay,\n",
-        "    SUM(IF(event_name = 'level_complete_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_complete_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_complete_quickplay,\n",
-        "    SUM(IF(event_name = 'level_reset_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'level_reset_quickplay', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_level_reset_quickplay,\n",
-        "    SUM(IF(event_name = 'post_score', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'post_score', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_post_score,\n",
-        "    SUM(IF(event_name = 'spend_virtual_currency', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'spend_virtual_currency', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_spend_virtual_currency,\n",
-        "    SUM(IF(event_name = 'ad_reward', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'ad_reward', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_ad_reward,\n",
-        "    SUM(IF(event_name = 'challenge_a_friend', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'challenge_a_friend', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_challenge_a_friend,\n",
-        "    SUM(IF(event_name = 'completed_5_levels', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'completed_5_levels', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_completed_5_levels,\n",
-        "    SUM(IF(event_name = 'use_extra_steps', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 86400000000 PRECEDING\n",
+        "    SUM(IF(event_name = 'use_extra_steps', 1, 0)) OVER (PARTITION BY user_pseudo_id ORDER BY event_timestamp ASC RANGE BETWEEN 21600000000 PRECEDING\n",
         "      AND CURRENT ROW ) AS cnt_use_extra_steps,\n",
         "  FROM (\n",
         "    SELECT\n",
@@ -1071,7 +1214,7 @@
         "\n",
         "SELECT\n",
         "    -- PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', CONCAT('{TODAY}', ' ', STRING(TIME_TRUNC(CURRENT_TIME(), SECOND))), 'UTC') as timestamp,\n",
-        "    PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(beh.event_timestamp))) AS timestamp,\n",
+        "    TIMESTAMP_ADD(PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(beh.event_timestamp))), INTERVAL 1351 DAY) AS timestamp,\n",
         "    dem.*,\n",
         "    CAST(IFNULL(beh.cnt_user_engagement, 0) AS FLOAT64)  AS cnt_user_engagement,\n",
         "    CAST(IFNULL(beh.cnt_level_start_quickplay, 0) AS FLOAT64) AS cnt_level_start_quickplay,\n",
@@ -1097,7 +1240,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "Z6CjIOmDsET-"
+        "id": "oGYxLCSnD068"
       },
       "outputs": [],
       "source": [
@@ -1107,31 +1250,31 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "Lx__2-assET-"
+        "id": "xQLIlsTCD_nk"
       },
       "source": [
         "## Create a Vertex AI Feature store and ingest your features\n",
-        "\n",
-        "Now you have the wide table of features. It is time to ingest them into the feature store. \n",
-        "\n",
+        " \n",
+        "Now you have a wide table of features. It is time to ingest them into the feature store.\n",
+        " \n",
         "Before to moving on, you may have a question: **Why do I need a feature store**\n",
         "in this scenario at that point?\n",
-        "\n",
-        "One of the reason would be to make those features accessable across team by calculating once and reuse them many times. And in order to make it possible you need also be able to monitor those features over time to guarantee freshness and in case have a new feature engineerign run to refresh them. \n",
-        "\n",
-        "If it is not your case, I will give even more reasons about why you should consider feature store in the following sections. Just keep following me for now.\n",
-        "\n",
-        "One of the most important thing is related to its data model. As you can see in the picture below, Vertex AI Feature Store organizes resources hierarchically in the following order: `Featurestore -> EntityType -> Feature`. You must create these resources before you can ingest data into Vertex AI Feature Store.\n",
-        "\n",
+        " \n",
+        "One of the reasons would be to make those features accessible across teams by calculating once and reuse them many times. And in order to make it possible you need also be able to monitor those features over time to guarantee freshness and in case have a new feature engineering run to refresh them.\n",
+        " \n",
+        "If it is not your case, I will give even more reasons about why you should consider a feature store in the following sections. Just keep following me for now.\n",
+        " \n",
+        "One of the most important things is related to its data model. As you can see in the picture below, Vertex AI Feature Store organizes resources hierarchically in the following order: `Featurestore -> EntityType -> Feature`. You must create these resources before you can ingest data into Vertex AI Feature Store.\n",
+        " \n",
         "<img src=\"./assets/feature_store_data_model_3.png\">\n",
-        "\n",
-        "In our case we are going to create **mobile_gaming** featurestore resource containing **user** entity type and all its associated **features** such as country or the number of times a user challenged a friend (cnt_challenge_a_friend)."
+        " \n",
+        "In our case we are going to create **mobile_gaming** featurestore resource containing **user** entity type and all its associated **features** such as country or the number of times a user challenged a friend (cnt_challenge_a_friend).\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "8dNlxda2sET_"
+        "id": "VR7BJEozED_Q"
       },
       "source": [
         "### Create featurestore, ```mobile_gaming```\n",
@@ -1143,7 +1286,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "t2en8I7TSe4b"
+        "id": "vUFqtYU-EDTR"
       },
       "outputs": [],
       "source": [
@@ -1164,7 +1307,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "rN-vlvPUsET_"
+        "id": "mUlCwfdpEHJG"
       },
       "source": [
         "### Create the ```User``` entity type and its features\n",
@@ -1176,7 +1319,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "CbZ2RQ5XbuRq"
+        "id": "PnCU1wBND3W7"
       },
       "outputs": [],
       "source": [
@@ -1194,7 +1337,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "B2PIAprPmnhB"
+        "id": "bT9LXzu1EOvW"
       },
       "source": [
         "### Set Feature Monitoring\n",
@@ -1208,7 +1351,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "N6im2c3ymiwC"
+        "id": "8WBlYUkOERaI"
       },
       "outputs": [],
       "source": [
@@ -1231,7 +1374,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gp9xaLQXn0CS"
+        "id": "92X4-7PFETj5"
       },
       "outputs": [],
       "source": [
@@ -1254,18 +1397,18 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ustwKOMle8Qp"
+        "id": "hxAuZjt3EWFo"
       },
       "source": [
         "### Create features\n",
         "\n",
-        "In order to ingest features, you need to provide feature configuration and create them as featurestore resources.\n"
+        "In order to ingest features, you need to provide feature configuration and create them as featurestore resources."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ijeZCTKIfCRL"
+        "id": "hRXO2I5VEYwt"
       },
       "source": [
         "#### Create Feature configuration\n",
@@ -1278,7 +1421,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "vX_uYmjUgd9x"
+        "id": "K26NEYZIEbvE"
       },
       "outputs": [],
       "source": [
@@ -1359,7 +1502,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ErkruXPJkPuy"
+        "id": "FjzMd1XbEfdo"
       },
       "source": [
         "#### Create features using `batch_create_features` method\n",
@@ -1371,7 +1514,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "ZsCAO_IfsEUC"
+        "id": "nqlgCDI9pbCD"
       },
       "outputs": [],
       "source": [
@@ -1388,19 +1531,19 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "9WisJk18qqgs"
+        "id": "7zpFV7wAppkC"
       },
       "source": [
         "### Search features\n",
         "\n",
-        "Vertex AI Feature store supports serching capabilities. Below you have a simple example that show how to filter a feature based on its name. "
+        "Vertex AI Feature store supports searching capabilities. Below you have a simple example that shows how to filter a feature based on its name. "
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "JzqyarMZqvZS"
+        "id": "BJXYLLOfppCL"
       },
       "outputs": [],
       "source": [
@@ -1412,7 +1555,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "ugtBfW5gsEUD"
+        "id": "is9C_6-QpxG3"
       },
       "source": [
         "## Ingest features \n",
@@ -1447,7 +1590,7 @@
         "        entity_id_field=ENTITY_ID_FIELD,\n",
         "        disable_online_serving=False,\n",
         "        worker_count=10,\n",
-        "        sync=True,\n",
+        "        sync=False,\n",
         "    )\n",
         "except RuntimeError as error:\n",
         "    print(error)"
@@ -1456,7 +1599,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "3Yv8MenWXrRX"
+        "id": "8lCMpDPGp-oQ"
       },
       "source": [
         "# Train and deploy a real-time churn ML model using Vertex AI Training and Endpoints\n",
@@ -1467,34 +1610,34 @@
         "\n",
         "<img src=\"./assets/train_model_4.png\">\n",
         "\n",
-        "Let's dive into each step of this process.\n"
+        "Let's dive into each step of this process."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "saZZ3zWKX1YK"
+        "id": "VMrvnuyjqGfY"
       },
       "source": [
-        "## Fetch training data with point-in-time query using BigQuery and Vertex AI Feature store  \n",
-        "\n",
-        "As we mentioned above, in real time churn prediction, it is so important defining the label you want to predict with your model. \n",
-        "\n",
-        "Let's assume that you decide to predict the churn probability over the last 24 hr. So now you have your label. Next step is to define your training sample. But let's think about that for a second. \n",
-        "\n",
-        "In that churn real time system, you have a high volume of transactions you could use to calculate those features which keep floating and are collected constantly over time. It implies that you always get fresh data to reconstruct features. And depending on when you decide to calculate one feature or another you can end up with a set of features that are not aligned in time. \n",
-        "\n",
+        "## Fetch training data with point-in-time query using BigQuery and Vertex AI Feature store \n",
+        " \n",
+        "As we mentioned above, in real time churn prediction, it is so important defining the label you want to predict with your model.\n",
+        " \n",
+        "Let's assume that you decide to predict the churn probability over the next hour. So now you have your label. Next step is to define your training sample. But let's think about that for a second.\n",
+        " \n",
+        "In that churn real time system, you have a high volume of transactions you could use to calculate those features which keep floating and are collected constantly over time. It implies that you always get fresh data to reconstruct features. And depending on when you decide to calculate one feature or another you can end up with a set of features that are not aligned in time.\n",
+        " \n",
         "When you have labels available, it would be incredibly difficult to say which set of features contains the most up to date historical information associated with the label you want to predict. And, when you are not able to guarantee that, the performance of your model would be badly affected because you serve no representative features of the data and the label from the field when it goes live. So you need a way to get the most updated features you calculated over time before the label becomes available in order to avoid this informational skew.\n",
-        "\n",
-        "**With the Vertex AI Feature store, you can fetch feature values corresponding to a particular timestamp thanks to point-in-time lookup capability.** In our case, it would be the timestamp associated to the label you want to predict with your model. In this way, you will avoid data leakage and you will get the most updated features to train your model. \n",
-        "\n",
-        "Let's see how to do that. \n"
+        " \n",
+        "**With the Vertex AI Feature store, you can fetch feature values corresponding to a particular timestamp thanks to point-in-time lookup capability.** In our case, it would be the timestamp associated with the label you want to predict with your model. In this way, you will avoid data leakage and you will get the most updated features to train your model.\n",
+        " \n",
+        "Let's see how to do that.\n"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "YHNbIHqFcQiM"
+        "id": "RE_Pvmu-qdDt"
       },
       "source": [
         "### Define query for reading instances at a specific point in time\n",
@@ -1506,7 +1649,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "DGUm0bYqhVV4"
+        "id": "bUDVw7l-qF2x"
       },
       "outputs": [],
       "source": [
@@ -1518,13 +1661,13 @@
         "  # get training threshold ----------------------------------------------------------------------------------\n",
         "  get_training_threshold AS (\n",
         "  SELECT\n",
-        "    (MAX(event_timestamp) - 86400000000) AS training_thrs\n",
+        "    (MAX(event_timestamp) - 10800000000) AS training_thrs\n",
         "  FROM\n",
         "    `firebase-public-project.analytics_153293282.events_*`\n",
         "  WHERE\n",
         "    event_name=\"user_engagement\"\n",
         "    AND\n",
-        "    PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))) < '{TODAY}'),\n",
+        "    TIMESTAMP_ADD(PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))), INTERVAL 1351 DAY) < '{TODAY}'),\n",
         "\n",
         "  # query to create label -----------------------------------------------------------------------------------\n",
         "  get_label AS (\n",
@@ -1549,7 +1692,7 @@
         "    WHERE\n",
         "      event_name=\"user_engagement\"\n",
         "    AND\n",
-        "    PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))) < '{TODAY}'\n",
+        "    TIMESTAMP_ADD(PARSE_TIMESTAMP('%Y-%m-%d %H:%M:%S', FORMAT_TIMESTAMP('%Y-%m-%d %H:%M:%S', TIMESTAMP_MICROS(event_timestamp))), INTERVAL 1351 DAY) < '{TODAY}'\n",
         "    GROUP BY\n",
         "      user_pseudo_id )\n",
         "  GROUP BY\n",
@@ -1669,7 +1812,7 @@
       "source": [
         "!mkdir -m 777 -p trainer data/ingest data/raw model config\n",
         "!gsutil -m cp -r $GCS_DESTINATION_OUTPUT_URI/*.csv data/ingest\n",
-        "!head -n 1000 data/ingest/*.csv > data/raw/sample.csv"
+        "!head -n 2000 data/ingest/*.csv > data/raw/sample.csv"
       ]
     },
     {
@@ -2071,7 +2214,7 @@
       },
       "outputs": [],
       "source": [
-        "TRAIN_JOB_RESOURCE_NAME = \"\"  # @param {type:\"string\"}"
+        "TRAIN_JOB_RESOURCE_NAME = \"[your-train-job-resource-name]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -2166,32 +2309,32 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "7c9330928aa1"
+        "id": "1TNzL_EGrVUm"
       },
       "source": [
         "# Serve ML features at scale with low latency\n",
-        "\n",
-        "At that time, you are ready **to deploy our simple model which would requires fetching preprocessed attributes as input features in real time**. \n",
-        "\n",
+        " \n",
+        "At that time, you are ready **to deploy our simple model which would requires fetching preprocessed attributes as input features in real time**.\n",
+        " \n",
         "Below you can see how it works\n",
-        "\n",
-        "<img src=\"./assets/online_serving_5.png\" width=\"600\">\n",
-        "\n",
-        "But think about those features for a second. \n",
-        "\n",
-        "Your behavioral features used to trained your model, they cannot be computed when you are going to serve the model online. \n",
-        "\n",
-        "How could you compute the number of time a user challenged a friend withing the last 24 hours on the fly?\n",
-        "\n",
-        "You simply can't do that. You need to be computed this feature on the server side and serve it with low latency. And becuase Bigquery is not optimized for those read operations, we need a different service that allows singleton lookup where the result is a single row with many columns.\n",
-        "\n",
-        "Also, even if it was not the case, when you deploy a model that requires preprocessing your data, you need to be sure to reproduce the same preprocessing steps you had when you trained it. If you are not able to do that a skew between training and serving data would happen and it will affect badly your model performance (and in the worst scenario break your serving system). \n",
-        "\n",
-        "You need a way to mitigate that in a way you don't need to implement those preprocessing steps online but just serve the same aggregated features you already have for training to generate online prediction. \n",
-        "\n",
-        "These are other valuable reasons to introduce Vertex AI Feature Store. With it, you have a service which helps you to serve feature at scale with low latency as they were available at training time mitigating in that way possible training-serving skew.\n",
-        "\n",
-        "Now that you know **why you need a feature store**, let's closing this journey by deploying your model and use feature store to retrieve features online, pass them to endpoint and generate predictions.\n"
+        " \n",
+        "<center><img src=\"./assets/online_serving_5.png\" width=\"800\"/></center>\n",
+        " \n",
+        "But think about those features for a second.\n",
+        " \n",
+        "Your behavioral features used to train your model, they cannot be computed when you are going to serve the model online.\n",
+        " \n",
+        "How could you compute the number of times a user challenged a friend within the last 24 hours on the fly?\n",
+        " \n",
+        "You need to be computed this feature on the server side and serve it with low latency. And because Bigquery is not optimized for those read operations, we need a different service that allows singleton lookup where the result is a single row with many columns.\n",
+        " \n",
+        "Also, even if it was not the case, when you deploy a model that requires preprocessing your data, you need to be sure to reproduce the same preprocessing steps you had when you trained it. If you are not able to do that a skew between training and serving data would happen and it will badly affect your model performance (and in the worst scenario break your serving system).\n",
+        " \n",
+        "You need a way to mitigate that in a way you don't need to implement those preprocessing steps online but just serve the same aggregated features you already have for training to generate online prediction.\n",
+        " \n",
+        "These are other valuable reasons to introduce Vertex AI Feature Store. With it, you have a service which helps you to serve features at scale with low latency as they were available at training time mitigating in that way possible training-serving skew.\n",
+        " \n",
+        "Now that you know **why you need a feature store**, let's conclude this journey by deploying your model using a feature store to retrieve features online, pass them to the endpoint and generate predictions.\n"
       ]
     },
     {
@@ -2221,13 +2364,13 @@
       },
       "outputs": [],
       "source": [
-        "simulate_prediction(endpoint=endpoint, n_requests=1000, latency=1)"
+        "simulate_prediction(endpoint=endpoint, n_requests=10, latency=1)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "TpV-iwP9qw9c"
+        "id": "8d3S1d1urZOy"
       },
       "source": [
         "## Cleaning up\n",
@@ -2267,11 +2410,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "sx_vKniMq9ZX"
+        "id": "FMXT2akXrZOy"
       },
       "outputs": [],
       "source": [
         "# Delete bucket\n",
+        "delete_bucket = False\n",
         "if (delete_bucket or os.getenv(\"IS_TESTING\")) and \"BUCKET_URI\" in globals():\n",
         "    ! gsutil -m rm -r $BUCKET_URI"
       ]

notebooks/community/ml_ops/stage1/README.md

@@ -76,7 +76,7 @@ The steps performed include:
     - image data
 ```
 
-[Get Started with Data Labeling](get_started_data_labeling.ipynb)
+[Get Started with Data Labeling](get_started_with_data_labeling.ipynb)
 
 ```
 The steps performed include:

notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb

@@ -174,7 +174,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -389,7 +389,7 @@
       },
       "outputs": [],
       "source": [
-        "i  # If you are running this notebook in Colab, run this cell and follow the\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",
@@ -1132,7 +1132,7 @@
       "source": [
         "dataframe[\"station_number\"] = pd.to_numeric(dataframe[\"station_number\"])\n",
         "labels = dataframe[\"mean_temp\"]\n",
-        "data = dataframe.drop(4)\n",
+        "data = dataframe.drop([\"mean_temp\"], axis=1)\n",
         "\n",
         "dtrain = xgb.DMatrix(data, label=labels)"
       ]

notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb

@@ -159,7 +159,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage1/get_started_vertex_datasets.ipynb

@@ -171,7 +171,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -188,7 +188,7 @@
         "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
         "! pip3 install --upgrade google-cloud-bigquery $USER_FLAG -q\n",
         "! pip3 install -U tensorflow-io==0.18 $USER_FLAG -q\n",
-        "! pip3 install --upgrade future $USER_FLAG -q"
+        "! pip3 install --upgrade db-dtypes $USER_FLAG -q! pip3 install --upgrade future $USER_FLAG -q"
       ]
     },
     {
@@ -408,12 +408,11 @@
         "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",
@@ -558,7 +557,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, location=REGION)"
+        "aip.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -612,26 +611,13 @@
         "Learn more about [All dataset documentation](https://cloud.google.com/vertex-ai/docs/datasets/datasets)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:flowers,csv,icn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = (\n",
-        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
-        ")"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:image,icn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create an Image Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `ImageDataset` class, which takes the following parameters:\n",
         "\n",
@@ -646,6 +632,19 @@
         "Learn more about [ImageDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-image)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:flowers,csv,icn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = (\n",
+        "    \"gs://cloud-samples-data/vision/automl_classification/flowers/all_data_v2.csv\"\n",
+        ")"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -663,24 +662,13 @@
         "print(dataset.resource_name)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:hmdb,csv,vcn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = \"gs://automl-video-demo-data/hmdb_split1_5classes_train_inf.csv\""
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:video,vcn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Video Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `VideoDataset` class, which takes the following parameters:\n",
         "\n",
@@ -694,6 +682,17 @@
         "Learn more about [VideoDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-video)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:hmdb,csv,vcn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://automl-video-demo-data/hmdb_split1_5classes_train_inf.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -711,24 +710,13 @@
         "print(dataset.resource_name)"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:happydb,csv,tcn"
-      },
-      "outputs": [],
-      "source": [
-        "IMPORT_FILE = \"gs://cloud-ml-data/NL-classification/happiness.csv\""
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "create_dataset:text,tcn"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Text Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `TextDataset` class, which takes the following parameters:\n",
         "\n",
@@ -743,6 +731,17 @@
         "Learn more about [TextDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-text)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:happydb,csv,tcn"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-ml-data/NL-classification/happiness.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -760,6 +759,24 @@
         "print(dataset.resource_name)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "source": [
+        "### Create a Tabular Dataset\n",
+        "\n",
+        "#### CSV input data\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class for CSV input data, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "\n",
+        "Learn more about [TabularDataset from CSV files](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_gcs_sample-python)"
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -768,27 +785,50 @@
       },
       "outputs": [],
       "source": [
-        "IMPORT_FILE = \"bq://bigquery-public-data.samples.gsod\"\n",
-        "BQ_TABLE = \"bigquery-public-data.samples.gsod\""
+        "IMPORT_FILE = \"gs://cloud-samples-data/tables/iris_1000.csv\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.TabularDataset.create(\n",
+        "    display_name=\"example\" + \"_\" + TIMESTAMP, gcs_source=[IMPORT_FILE]\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "create_dataset:tabular,bq,lrg,v2"
+        "id": "854dd1e0195c"
       },
       "source": [
-        "### Create the Dataset\n",
+        "#### BigQuery input data\n",
         "\n",
-        "#### CSV input data\n",
-        "\n",
-        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class, which takes the following parameters:\n",
+        "Next, create the `Dataset` resource using the `create` method for the `TabularDataset` class for BigQuery table input, which takes the following parameters:\n",
         "\n",
         "- `display_name`: The human readable name for the `Dataset` resource.\n",
-        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
-        "- `labels`: User defined metadata. In this example, you store the location of the Cloud Storage bucket containing the user defined data.\n",
+        "- `bq_source`: A list of one or more BigQuery tables to import the data items into the `Dataset` resource.\n",
         "\n",
-        "Learn more about [TabularDataset from CSV files](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_gcs_sample-python)"
+        "Learn more about [TabularDataset from BigQuery table](https://cloud.google.com/vertex-ai/docs/datasets/create-dataset-api#aiplatform_create_dataset_tabular_bigquery_sample-pythonn)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "86343c146300"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"bq://bigquery-public-data.samples.gsod\"\n",
+        "BQ_TABLE = \"bigquery-public-data.samples.gsod\""
       ]
     },
     {
@@ -806,15 +846,63 @@
         "print(dataset.resource_name)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "82e9fe20ce71"
+      },
+      "source": [
+        "#### Dataframe input data\n",
+        "\n",
+        "Next, create the `Dataset` resource using the `create_from_dataframe` method for the `TabularDataset` class for pandas dataframe input, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `df_source`: The pandas dataframe to import the data items into the `Dataset` resource.\n",
+        "- `staging_path`: The BigQuery table to store the imported data."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "import_file:covid,csv,forecast"
+        "id": "3805f945ffdd"
       },
       "outputs": [],
       "source": [
-        "IMPORT_FILE = \"gs://cloud-samples-data/ai-platform/covid/bigquery-public-covid-nyt-us-counties-train.csv\""
+        "# Download the table.\n",
+        "table = bigquery.TableReference.from_string(BQ_TABLE)\n",
+        "\n",
+        "rows = bqclient.list_rows(\n",
+        "    table,\n",
+        "    max_results=10000,\n",
+        "    selected_fields=[\n",
+        "        bigquery.SchemaField(\"station_number\", \"STRING\"),\n",
+        "        bigquery.SchemaField(\"year\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"month\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"day\", \"INTEGER\"),\n",
+        "        bigquery.SchemaField(\"mean_temp\", \"FLOAT\"),\n",
+        "    ],\n",
+        ")\n",
+        "\n",
+        "dataframe = rows.to_dataframe()\n",
+        "print(dataframe.head())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg,v2"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aip.TabularDataset.create_from_dataframe(\n",
+        "    display_name=\"example\" + \"_\" + TIMESTAMP,\n",
+        "    df_source=dataframe,\n",
+        "    staging_path=f\"bq://{PROJECT_ID}.samples.gsod\",\n",
+        ")\n",
+        "\n",
+        "print(dataset.resource_name)"
       ]
     },
     {
@@ -823,7 +911,7 @@
         "id": "create_dataset:tabular,forecast,v2"
       },
       "source": [
-        "### Create the Dataset\n",
+        "### Create a Time Series Dataset\n",
         "\n",
         "Next, create the `Dataset` resource using the `create` method for the `TimeSeriesDataset` class, which takes the following parameters:\n",
         "\n",
@@ -834,6 +922,17 @@
         "Learn more about [TimeSeriesDataset](https://cloud.google.com/vertex-ai/docs/datasets/prepare-tabular)."
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:covid,csv,forecast"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"gs://cloud-samples-data/ai-platform/covid/bigquery-public-covid-nyt-us-counties-train.csv\""
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -1279,7 +1378,7 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "# If on Workbench AI Notebook, then don't execute this code\n",
         "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        ! pip3 install fsspec\n",
@@ -1620,11 +1719,15 @@
       },
       "outputs": [],
       "source": [
+        "delete_bucket = False\n",
+        "\n",
         "# Delete the dataset using the Vertex dataset object\n",
-        "dataset.delete()\n",
+        "datasets = aip.TabularDataset.list(filter=f'display_name=\"example_{TIMESTAMP}\"')\n",
+        "for dataset in datasets:\n",
+        "    dataset.delete()\n",
         "\n",
         "# Delete the bucket\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"
       ]
     }

notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb

@@ -146,7 +146,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb

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

notebooks/community/ml_ops/stage1/mlops_data_management.ipynb

@@ -142,7 +142,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/README.md

@@ -119,6 +119,19 @@ The steps performed include:
 - Train a R model using `Vertex AI Trainingh` service with the R-to-Python training package.
 ```
 
+[Get Started with Custom Training Packages (R) and Deployment in R environment](get_started_vertex_training_r_using_r_kernel.ipynb)
+```
+The steps performed include:
+
+- Create a custom R training script
+- Create a custom R serving script
+- Create a custom R deployment (serving) container.
+- Train the model using `Vertex AI` custom training.
+- Create an `Endpoint` resource.
+- Deploy the `Model` resource (trained R model) to the `Endpoint` resource.
+- Make an online prediction.
+```
+
 [Get Started with Custom Training Packages (LightGBM)](get_started_vertex_training_lightgbm.ipynb)
 
 ```
@@ -222,19 +235,6 @@ The steps performed include:
 ```
 The steps performed include:
 
-- Get the training data.
-- Configure training parameters for the Vertex AI TabNet container.
-- Train the model using Vertex AI Training using CSV data.
-- Upload the model as a Vertex AI Model resource.
-- Deploy the Vertex AI Model resource to a Vertex AI Endpoint resource.
-- Make a prediction with the deployed model.
-- Hyperparameter tuning the Vertex AI TabNet model.
-- Train the model using Vertex AI Training using BigQuery table.
-```
-[Get Started with Vertex AI TabNet builtin algorithm](get_started_with_tabnet.ipynb)
-```
-The steps performed include:
-
 - Get the training data.
 - Configure training parameters for the Vertex AI TabNet container.
 - Train the model using Vertex AI Training using CSV data.

notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_automl_training.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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",
@@ -187,7 +187,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_bqml_training.ipynb

@@ -134,7 +134,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
         "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
         "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
@@ -442,6 +442,54 @@
         "! gsutil ls -al $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_service_account"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -730,32 +778,6 @@
         "print(\"{} created in {}\".format(tblname, job.ended - job.started))"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3b3aa4481cd7"
-      },
-      "outputs": [],
-      "source": [
-        "MODEL_QUERY = f\"\"\"\n",
-        "DROP MODEL `{BQ_DATASET_NAME}.{MODEL_NAME}`\n",
-        "\"\"\"\n",
-        "\n",
-        "job = bqclient.query(MODEL_QUERY)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "ef9e14b91475"
-      },
-      "outputs": [],
-      "source": [
-        "job"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1185,24 +1207,21 @@
         "\n",
         "### Setting permissions to automatically register the model\n",
         "\n",
-        "You need to set some additional IAM permissions for BigQuery ML to automatically upload and register the model after training. Depending on your service account, the setting of the permissions below may fail. In this case, we recommend executing the permissions in a Cloud Shell."
+        "You need to set some additional IAM permissions for BigQuery ML to automatically upload and register the model after training. Depending on your service account, the setting of the permissions below may fail. In this case, we recommend executing the permissions in a Cloud Shell.\n",
+        "\n",
+        "Learn more about [Setting permissions for Model Registry](https://cloud.devsite.corp.google.com/bigquery-ml/docs/managing-models-vertex\n"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "0472e888105e"
+        "id": "29229f72d13d"
       },
       "outputs": [],
       "source": [
         "! gcloud projects add-iam-policy-binding $PROJECT_ID \\\n",
-        "      --member='serviceAccount:cloud-dataengine@system.gserviceaccount.com' \\\n",
-        "      --role='roles/aiplatform.admin'\n",
-        "\n",
-        "! gcloud projects add-iam-policy-binding $PROJECT_ID \\\n",
-        "      --member='user:cloud-dataengine@prod.google.com' \\\n",
-        "      --role='roles/aiplatform.admin'"
+        "    --member=serviceAccount:$SERVICE_ACCOUNT --role=roles/aiplatform.admin --condition=None"
       ]
     },
     {
@@ -1283,6 +1302,20 @@
         "print(model.gca_resource)"
       ]
     },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "48e6ef5d5ffa"
+      },
+      "outputs": [],
+      "source": [
+        "models = aiplatform.Model.list()\n",
+        "for model in models:\n",
+        "    if model.gca_resource.display_name.startswith(\"bqml\"):\n",
+        "        print(model.gca_resource.display_name)"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {

notebooks/community/ml_ops/stage2/get_started_vertex_distributed_training.ipynb

@@ -160,7 +160,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "    <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_experiments.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        <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",
@@ -143,7 +143,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb

@@ -41,7 +41,7 @@
         "    \n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_feature_store.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "        </a>\n",
         "  </td>\n",
         "    \n",
@@ -145,7 +145,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",
@@ -362,12 +362,11 @@
         "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",
@@ -490,7 +489,7 @@
       "outputs": [],
       "source": [
         "# Represents featurestore resource path.\n",
-        "FEATURESTORE_NAME = \"movies\"\n",
+        "FEATURESTORE_NAME = \"movies_\" + TIMESTAMP\n",
         "\n",
         "featurestore = aiplatform.Featurestore.create(\n",
         "    featurestore_id=FEATURESTORE_NAME,\n",

notebooks/community/ml_ops/stage2/get_started_vertex_tensorboard.ipynb

@@ -194,7 +194,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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",
@@ -147,7 +147,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_lightgbm.ipynb

@@ -178,7 +178,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_pytorch.ipynb

@@ -191,7 +191,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_training_r.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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",
@@ -148,7 +148,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_sklearn.ipynb

@@ -50,9 +50,6 @@
         "    </a>\n",
         "  </td>\n",
         "</table>\n",
-        "    </a>\n",
-        "  </td>\n",
-        "</table>\n",
         "<br/><br/><br/>"
       ]
     },
@@ -186,7 +183,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb

@@ -136,7 +136,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_vertex_vizier.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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",
@@ -156,7 +156,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_with_cmek_training.ipynb

@@ -39,7 +39,7 @@
         "  </td>\n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_cmek_training.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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",
@@ -139,7 +139,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_with_tabnet.ipynb

@@ -133,7 +133,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_with_tfhub_models.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "  <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage2/get_started_with_tfhub_models.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\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",
@@ -145,7 +145,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb

@@ -84,11 +84,11 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Patent PDF Samples with Extracted Structured Data](https://pantheon.corp.google.com/marketplace/details/global-patents/labeled-patents?project=kudos-333820) from Google Public Data Sets. \n",
+        "The dataset used for this tutorial is the [Patent PDF Samples with Extracted Structured Data](https://console.cloud.google.com/marketplace/product/global-patents/labeled-patents) from Google Public Data Sets. \n",
         "\n",
         "This dataset includes data extracted from over 300 patent documents issued in the US and EU. The dataset includes links to Google Cloud Storage blobs for the first page of each patent, in addition to a number of extracted entities. \n",
         "\n",
-        "The data is published as a public dataset on `BigQuery`."
+        "The data is published as a [public dataset](https://cloud.google.com/bigquery/public-data) on `BigQuery`."
       ]
     },
     {
@@ -201,7 +201,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage2/mlops_experimentation.ipynb

@@ -40,7 +40,7 @@
         "  </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",
+        "        <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",
@@ -182,7 +182,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage3/README.md

@@ -166,6 +166,17 @@ The steps performed in this tutorial include:
 - Execute pipeline using customjob-level settings for machine resources
 ```
 
+[Get Started with Apache Airflow and Vertex AI Pipelines](get_started_with_airflow_and_vertex_pipelines.ipynb)
+
+```
+The steps performed in this tutorial include:
+
+- Create Cloud Composer environment.
+- Upload Airflow DAG to Composer environment that performs data processing -- i.e., creates a BigQuery table from a CSV file.
+- Create a Vertex Pipeline that triggers the Airflow DAG.
+- Execute the `Vertex AI Pipeline`.
+```
+
 ### E2E Stage Example
 
 [Stage 3: Formalization](mlops_formalization.ipynb)

notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb

@@ -40,7 +40,7 @@
         "  </td>\n",
         "    <td>\n",
         "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage3/get_started_with_automl_pipeline_components.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\\\" alt=\"Colab logo\"> Run in Colab\n",
+        "        <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",
@@ -133,7 +133,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage3/get_started_with_bq_tfdv_pipeline_components.ipynb

@@ -143,7 +143,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage3/get_started_with_bqml_pipeline_components.ipynb

@@ -149,7 +149,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage3/get_started_with_custom_training_pipeline_components.ipynb

@@ -153,7 +153,7 @@
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\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",

notebooks/community/ml_ops/stage4/README.md

@@ -75,6 +75,25 @@ The steps performed include:
     - Query your pipeline run metadata.
 ```
 
+[Get started with Vertex ML Metadata and AutoML](get_started_with_vertex_ml_metadata_and_automl.ipynb)
+
+```
+The steps performed include:
+
+- Create a `Dataset` resource.
+- Create a corresponding `google.VertexDataset` artifact.
+- Train a model using `AutoML`.
+- Create a corresponding `google.VertexModel` artifact.
+- Create an `Endpoint` resource.
+- Create a corresponding `google.Endpoint` artifact.
+- Deploy the train model to the `Endpoint`.
+- Create an execution and context for the `AutoML` training job and deployment.
+- Add the corresponding artifacts and context to the execution.
+- Add artifact links (event) to the execution.
+- Display the execution graph.
+```
+
+
 Get started with custom model evaluation
 
 Get started with A/B Testing

notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb

@@ -576,7 +576,7 @@
     "\n",
     "Setup up the following constants for Vertex AI:\n",
     "\n",
-    "- `API_ENDPOINT`: The Vertex AI API service endpoint for `FeatureStore` services."
+    "- `API_ENDPOINT`: The Vertex AI API service endpoint for `ML Metadata` services."
    ]
   },
   {

notebooks/community/ml_ops/stage5/README.md

@@ -57,3 +57,35 @@ The steps performed include:
 - Deploying a `Model` resource to a `Private Endpoint` resource.
 - Send a prediction request to a `Private Endpoint`
 ```
+
+[Get started with Vertex AI Endpoints and co-hosting models on shared VM](get_started_with_vertex_endpoint_and_shared_vm.ipynb)
+
+```
+The steps performed include:
+
+- Upload a pre-trained image classification model as a `Model` resource (model A).
+- Upload a pre-trained text sentence encoder model as a `Model` resource (model B).
+- Create a shared VM deployment resource pool.
+- List shared VM deployment resource pools.
+- Create two `Endpoint` resources.
+- Deploy first model (model A) to first `Endpoint` resource using shared VM deployment resource pool.
+- Deploy second model (model B) to second `Endpoint` resource using shared VM deployment resource pool.
+- Make a prediction request with first deployed model (model A).
+- Make a prediction request with second deployed model (model B).
+```
+
+[Get started with Auto-Scaling for Vertex AI Endpoints](get_started_with_autoscaling.ipynb)
+
+```
+The steps performed include:
+
+- Download a pretrained image classification model from TensorFlow Hub.
+- Upload the pretrained model as a `Model` resource.
+- Create an `Endpoint` resource.
+- Deploy `Model` resource for no-scaling (single node).
+- Deploy `Model` resource for manual scaling.
+- Deploy `Model` resource for auto-scaling.
+- Fine-tune scaling thresholds for CPU utilization.
+- Fine-tune scaling thresholds for GPU utilization.
+- Deploy mix of CPU and GPU model instances with auto-scaling to an `Endpoint` resource.
+```

notebooks/community/ml_ops/stage6/README.md

@@ -185,3 +185,20 @@ The steps performed include:
 7. Deploy the `Matching Engine Index` to a `Index Endpoint`.
 8. Make a matching engine prediction request.
 ```
+
+[Get started with Explainable AI and custom model server](get_started_with_xai_and_custom_server.ipynb)
+
+```
+The steps performed include:
+
+- Locally train a Pytorch tabular classifier.
+- Locally test the trained model.
+- Build a HTTP server using FastAPI.
+- Create a custom serving container with the trained model and FastAPI server.
+- Locally test the custom serving container.
+- Push the custom serving container to the Artifact Registry.
+- Upload the custom serving container as a `Model` resource.
+- Deploy the `Model` resource to an `Endpoint` resource.
+- Make a prediction request to the deployed custom serving container.
+- Make an explanation request to the deployed custom serving container.
+```

notebooks/community/ml_ops/stage7/README.md

@@ -0,0 +1,36 @@
+# Stage 7: Monitoring
+
+## Purpose
+
+Monitor predict requests to detect model degradation and alert or trigger degradation response procedures. 
+
+## Recommendations  
+
+Degradation includes, but not limited to:
+
+1. Health - deterioration in the operational performance of the serving binary.
+2. Latency - deterioration in the elapsed time to transmit a prediction response from the serving binary.
+3. Serving skew - detection of a distribution difference between the training data and the data seen at serving. This may be either or both the features of the input or the prediction of the output.
+4. Data drift - detection of a change of distribution in the input features of the serving data over time.
+5. Concept drift - degradation of the business objective.
+
+For cases of skew and drift, random samples of the serving requests/responses are collected in the serving binary. Another process continuously inspects the distribution of the random collected samples. This process may either alter or initiate retraining of the model once skew or drift exceeds pre-specified thresholds.
+
+In the case of concept drift, one may initiate a rollback of the blessed model and/or renewed A/B testing of the blessed model and previous blessed models.
+
+This stage may be done entirely by MLOps. We recommend:
+
+- When manually inspecting the operation of the serving binary, attach to the serving binary using the Vertex Serving Binary Debugger.
+- Use Google Cloud network monitoring to monitor the operational health of the serving binary.
+- Store network monitoring logs in Cloud Storage and view logs using StackDriver.
+- Use Vertex AI Model Monitoring to random sample prediction requests/responses and to measure distributions for skew and drift.
+- Store sampled prediction requests/responses in Big Query.
+- Use Vertex ML Metadata to periodically record serving distribution statistics.
+- Use Vertex Explainable AI to manually inspect for concept drift in business objectives.
+- Use Cloud Pub/Sub to automatically trigger re-training pipeline.
+
+<img src='stage7v2.png'>
+
+## Notebooks
+
+### Get Started

notebooks/community/neo4j/graph_paysim.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -42,6 +42,11 @@
         "      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/laeg/vertex-ai-samples/main/notebooks/community/neo4j/graph_paysim.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "</td>\n",
         "</table>"
       ]
     },
@@ -143,7 +148,7 @@
       },
       "outputs": [],
       "source": [
-        "!pip install --quiet --upgrade neo4j"
+        "!pip install --quiet --upgrade graphdatascience==1.0.0"
       ]
     },
     {
@@ -255,7 +260,7 @@
       "outputs": [],
       "source": [
         "import pandas as pd\n",
-        "from neo4j import GraphDatabase"
+        "from graphdatascience import GraphDataScience"
       ]
     },
     {
@@ -266,7 +271,19 @@
       },
       "outputs": [],
       "source": [
-        "driver = GraphDatabase.driver(DB_URL, auth=(DB_USER, DB_PASS))"
+        "# If you are connecting the client to an AuraDS instance, you can get the recommended non-default configuration settings of the Python Driver applied automatically. To achieve this, set the constructor argument aura_ds=True\n",
+        "gds = GraphDataScience(DB_URL, auth=(DB_USER, DB_PASS), aura_ds=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f14915ddd1fb"
+      },
+      "outputs": [],
+      "source": [
+        "gds.set_database(DB_NAME)"
       ]
     },
     {
@@ -287,19 +304,16 @@
       "outputs": [],
       "source": [
         "# node labels\n",
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "    CALL db.labels() YIELD label\n",
-        "    CALL apoc.cypher.run('MATCH (:`'+label+'`) RETURN count(*) as freq', {})\n",
-        "    YIELD value\n",
-        "    RETURN label, value.freq AS freq\n",
+        "result = gds.run_cypher(\n",
         "    \"\"\"\n",
-        "        ).data()\n",
-        "    )\n",
-        "df = pd.DataFrame(result)\n",
-        "display(df)"
+        "CALL db.labels() YIELD label\n",
+        "CALL apoc.cypher.run('MATCH (:`'+label+'`) RETURN count(*) as freq', {})\n",
+        "YIELD value\n",
+        "RETURN label, value.freq AS freq\n",
+        "\"\"\"\n",
+        ")\n",
+        "\n",
+        "display(result)"
       ]
     },
     {
@@ -311,20 +325,17 @@
       "outputs": [],
       "source": [
         "# relationship types\n",
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "      CALL db.relationshipTypes() YIELD relationshipType as type\n",
-        "      CALL apoc.cypher.run('MATCH ()-[:`'+type+'`]->() RETURN count(*) as freq', {})\n",
-        "      YIELD value\n",
-        "      RETURN type AS relationshipType, value.freq AS freq\n",
-        "      ORDER by freq DESC\n",
-        "      \"\"\"\n",
-        "        ).data()\n",
-        "    )\n",
-        "df = pd.DataFrame(result)\n",
-        "display(df)"
+        "result = gds.run_cypher(\n",
+        "    \"\"\"\n",
+        "CALL db.relationshipTypes() YIELD relationshipType as type\n",
+        "CALL apoc.cypher.run('MATCH ()-[:`'+type+'`]->() RETURN count(*) as freq', {})\n",
+        "YIELD value\n",
+        "RETURN type AS relationshipType, value.freq AS freq\n",
+        "ORDER by freq DESC\n",
+        "\"\"\"\n",
+        ")\n",
+        "\n",
+        "display(result)"
       ]
     },
     {
@@ -336,23 +347,20 @@
       "outputs": [],
       "source": [
         "# transaction types\n",
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "    MATCH (t:Transaction)\n",
-        "    WITH sum(t.amount) AS globalSum, count(t) AS globalCnt\n",
-        "    WITH *, 10^3 AS scaleFactor\n",
-        "    UNWIND ['CashIn', 'CashOut', 'Payment', 'Debit', 'Transfer'] AS txType\n",
-        "      CALL apoc.cypher.run('MATCH (t:' + txType + ')\n",
-        "        RETURN sum(t.amount) as txAmount, count(t) AS txCnt', {})\n",
-        "      YIELD value\n",
-        "    RETURN txType,value.txAmount AS TotalMarketValue\n",
+        "result = gds.run_cypher(\n",
         "    \"\"\"\n",
-        "        ).data()\n",
-        "    )\n",
-        "df = pd.DataFrame(result)\n",
-        "display(df)"
+        "      MATCH (t:Transaction)\n",
+        "      WITH sum(t.amount) AS globalSum, count(t) AS globalCnt\n",
+        "      WITH *, 10^3 AS scaleFactor\n",
+        "      UNWIND ['CashIn', 'CashOut', 'Payment', 'Debit', 'Transfer'] AS txType\n",
+        "        CALL apoc.cypher.run('MATCH (t:' + txType + ')\n",
+        "          RETURN sum(t.amount) as txAmount, count(t) AS txCnt', {})\n",
+        "        YIELD value\n",
+        "      RETURN txType,value.txAmount AS TotalMarketValue\n",
+        "    \"\"\"\n",
+        ")\n",
+        "\n",
+        "display(result)"
       ]
     },
     {
@@ -375,18 +383,14 @@
       },
       "outputs": [],
       "source": [
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "    CALL gds.graph.create.cypher('client_graph', \n",
-        "      'MATCH (c:Client) RETURN id(c) as id, c.num_transactions as num_transactions, c.total_transaction_amnt as total_transaction_amnt, c.is_fraudster as is_fraudster',\n",
-        "      'MATCH (c:Client)-[:PERFORMED]->(t:Transaction)-[:TO]->(c2:Client) return id(c) as source, id(c2) as target, sum(t.amount) as amount, \"TRANSACTED_WITH\" as type ')\n",
-        "    \"\"\"\n",
-        "        ).data()\n",
-        "    )\n",
-        "df = pd.DataFrame(result)\n",
-        "display(df)"
+        "# We get a tuple back with an object that represents the graph projection and the results of the GDS call\n",
+        "G, results = gds.graph.project.cypher(\n",
+        "    \"client_graph\",\n",
+        "    \"MATCH (c:Client) RETURN id(c) as id, c.num_transactions as num_transactions, c.total_transaction_amnt as total_transaction_amnt, c.is_fraudster as is_fraudster\",\n",
+        "    'MATCH (c:Client)-[:PERFORMED]->(t:Transaction)-[:TO]->(c2:Client) return id(c) as source, id(c2) as target, sum(t.amount) as amount, \"TRANSACTED_WITH\" as type ',\n",
+        ")\n",
+        "\n",
+        "display(results)"
       ]
     },
     {
@@ -406,25 +410,19 @@
       },
       "outputs": [],
       "source": [
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "    CALL gds.fastRP.mutate('client_graph',{\n",
-        "      relationshipWeightProperty:'amount',\n",
-        "      iterationWeights: [0.0, 1.00, 1.00, 0.80, 0.60],\n",
-        "      featureProperties: ['num_transactions', 'total_transaction_amnt'],\n",
-        "      propertyRatio: 0.25, \n",
-        "      nodeSelfInfluence: 0.15,\n",
-        "      embeddingDimension: 16,\n",
-        "      randomSeed: 1, \n",
-        "      mutateProperty:'embedding'\n",
-        "    })\n",
-        "    \"\"\"\n",
-        "        ).data()\n",
-        "    )\n",
-        "df = pd.DataFrame(result)\n",
-        "display(df)"
+        "results = gds.fastRP.mutate(\n",
+        "    G,\n",
+        "    relationshipWeightProperty=\"amount\",\n",
+        "    iterationWeights=[0.0, 1.00, 1.00, 0.80, 0.60],\n",
+        "    featureProperties=[\"num_transactions\", \"total_transaction_amnt\"],\n",
+        "    propertyRatio=0.25,\n",
+        "    nodeSelfInfluence=0.15,\n",
+        "    embeddingDimension=16,\n",
+        "    randomSeed=1,\n",
+        "    mutateProperty=\"embedding\",\n",
+        ")\n",
+        "\n",
+        "display(result)"
       ]
     },
     {
@@ -444,19 +442,11 @@
       },
       "outputs": [],
       "source": [
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "    CALL gds.graph.streamNodeProperties\n",
-        "    ('client_graph', ['embedding', 'num_transactions', 'total_transaction_amnt', 'is_fraudster'])\n",
-        "    YIELD nodeId, nodeProperty, propertyValue\n",
-        "    RETURN nodeId, nodeProperty, propertyValue\n",
-        "    \"\"\"\n",
-        "        ).data()\n",
-        "    )\n",
-        "df = pd.DataFrame(result)\n",
-        "df.head()"
+        "node_properties = gds.graph.streamNodeProperties(\n",
+        "    G, [\"embedding\", \"num_transactions\", \"total_transaction_amnt\", \"is_fraudster\"]\n",
+        ")\n",
+        "\n",
+        "node_properties.head()"
       ]
     },
     {
@@ -476,7 +466,9 @@
       },
       "outputs": [],
       "source": [
-        "x = df.pivot(index=\"nodeId\", columns=\"nodeProperty\", values=\"propertyValue\")\n",
+        "x = node_properties.pivot(\n",
+        "    index=\"nodeId\", columns=\"nodeProperty\", values=\"propertyValue\"\n",
+        ")\n",
         "x = x.reset_index()\n",
         "x.columns.name = None\n",
         "x.head()"
@@ -699,8 +691,8 @@
         "id": "ArK3cfKsdT1x"
       },
       "source": [
-        "## Train and deploy a model on GCP\n",
-        "We'll use the engineered features to train an AutoML Tables model, then deploy it to an endpoint"
+        "## Train and deploy a model with Vertex AI\n",
+        "We'll use the engineered features to train an AutoML Tabular Data, then deploy it to an endpoint"
       ]
     },
     {
@@ -782,8 +774,8 @@
         "id": "-NnDaATyWY7z"
       },
       "source": [
-        "## Loading Data into GCP Feature Store\n",
-        "In this section, we'll take our dataframe with newly engineered features and load that into GCP feature store."
+        "## Loading Data into Vertex AI Feature Store\n",
+        "In this section, we'll take our dataframe with newly engineered features and load that into Vertex AI Feature Store."
       ]
     },
     {
@@ -1083,14 +1075,7 @@
       },
       "outputs": [],
       "source": [
-        "with driver.session(database=DB_NAME) as session:\n",
-        "    result = session.read_transaction(\n",
-        "        lambda tx: tx.run(\n",
-        "            \"\"\"\n",
-        "        CALL gds.graph.drop('client_graph')\n",
-        "        \"\"\"\n",
-        "        ).data()\n",
-        "    )"
+        "gds.graph.drop(G)"
       ]
     },
     {

notebooks/community/sdk/SDK_BigQuery_Custom_Container_Training.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -26,25 +26,99 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "976753012196"
+        "id": "et4hRnB9mrau"
       },
       "source": [
-        "# Feedback or issues?\n",
-        "For any feedback or questions, please open an [issue](https://github.com/googleapis/python-aiplatform/issues)."
+        "<table align=\"left\">\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/sdk/SDK_BigQuery_Custom_Container_Training.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/sdk/SDK_BigQuery_Custom_Container_Training.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/master/notebooks/community/sdk/SDK_BigQuery_Custom_Container_Training.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>                                                                                               \n",
+        "</table>"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "8c3048cd1427"
+        "id": "wLMxmUTwn1td"
       },
       "source": [
-        "# Vertex SDK for Python: BigQuery Custom Container Training Example\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](https://cloud.google.com/vertex-ai/docs/general/notebooks).\n",
+        "###  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",
         "\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",
         "\n",
-        "Note: you may incur charges for training, prediction, storage or usage of other GCP products in connection with testing this SDK."
+        "Costs  \n",
+        "This tutorial uses billable components of Google Cloud: \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."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "g5dkyDy1obku"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Google Cloud Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "gyja44LCozU_"
+      },
+      "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."
       ]
     },
     {
@@ -65,7 +139,7 @@
         "id": "xOMNWzTbftDr"
       },
       "source": [
-        "# Install Vertex SDK for Python\n",
+        "# Install Vertex AI SDK for Python\n",
         "\n",
         "\n",
         "After the SDK installation the kernel will be automatically restarted."
@@ -106,10 +180,223 @@
       },
       "outputs": [],
       "source": [
-        "MY_PROJECT = \"YOUR PROJECT ID\"\n",
+        "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"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "_HRQg6eXiolk"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Sg6AbQRviolk"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6x6CSodKjMmg"
+      },
+      "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 Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "idpLDmlyjWyU"
+      },
+      "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",
+        "\n",
+        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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": "r2lr6-MVpXLP"
+      },
+      "source": [
+        "#### Timestamp\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "he2lcG3Jpdxu"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "VxkQeJLyjgyr"
+      },
+      "source": [
+        "### Create a Cloud Storage bucket\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "When you submit a training job using the Cloud 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",
+        "create Vertex AI model and endpoint resources in order to serve\n",
+        "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. We suggest that you [choose a region where Vertex AI services are\n",
+        "available](https://cloud.google.com/vertex-ai/docs/general/locations#available_regions)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "GF076Vmoioll"
+      },
+      "outputs": [],
+      "source": [
+        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "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\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ElTizrkXiolm"
+      },
+      "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": "3ar8qPT6iolm"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "T_Hq3rtPiolm"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "_KfwVmnIiolm"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -139,8 +426,8 @@
       "source": [
         "import os\n",
         "\n",
-        "os.environ[\"GOOGLE_CLOUD_PROJECT\"] = MY_PROJECT\n",
-        "!bq mk {MY_PROJECT}:ml_datasets"
+        "os.environ[\"GOOGLE_CLOUD_PROJECT\"] = PROJECT_ID\n",
+        "!bq mk {PROJECT_ID}:ml_datasets"
       ]
     },
     {
@@ -160,7 +447,7 @@
       },
       "outputs": [],
       "source": [
-        "!bq cp -n bigquery-public-data:ml_datasets.iris {MY_PROJECT}:ml_datasets.iris"
+        "!bq cp -n --project_id={PROJECT_ID} bigquery-public-data:ml_datasets.iris {PROJECT_ID}:ml_datasets.iris "
       ]
     },
     {
@@ -205,9 +492,9 @@
       "source": [
         "cloudbuild_yaml = \"\"\"steps:\n",
         "- name: 'gcr.io/cloud-builders/docker'\n",
-        "  args: [ 'build', '-t', 'gcr.io/{MY_PROJECT}/test-custom-container', '.' ]\n",
-        "images: ['gcr.io/{MY_PROJECT}/test-custom-container']\"\"\".format(\n",
-        "    MY_PROJECT=MY_PROJECT\n",
+        "  args: [ 'build', '-t', 'gcr.io/{PROJECT_ID}/test-custom-container', '.' ]\n",
+        "images: ['gcr.io/{PROJECT_ID}/test-custom-container']\"\"\".format(\n",
+        "    PROJECT_ID=PROJECT_ID\n",
         ")\n",
         "\n",
         "with open(f\"{CONTAINER_ARTIFACTS_DIR}/cloudbuild.yaml\", \"w\") as fp:\n",
@@ -220,7 +507,7 @@
         "id": "gQ_GUCtZftDz"
       },
       "source": [
-        "### Write Dockerfile"
+        "### Write The Dockerfile"
       ]
     },
     {
@@ -253,7 +540,7 @@
         "id": "9dfrLShaftDz"
       },
       "source": [
-        "### Write entrypoint script to invoke trainer"
+        "### Write the entrypoint script to invoke trainer"
       ]
     },
     {
@@ -357,7 +644,7 @@
         "id": "6LYlV4D2ftD0"
       },
       "source": [
-        "### Build Container"
+        "### Build The Container"
       ]
     },
     {
@@ -368,7 +655,7 @@
       },
       "outputs": [],
       "source": [
-        "!gcloud builds submit --config {CONTAINER_ARTIFACTS_DIR}/cloudbuild.yaml {CONTAINER_ARTIFACTS_DIR}"
+        "!gcloud builds submit --project={PROJECT_ID} --config {CONTAINER_ARTIFACTS_DIR}/cloudbuild.yaml {CONTAINER_ARTIFACTS_DIR}"
       ]
     },
     {
@@ -377,7 +664,7 @@
         "id": "Pf0pugbvftD1"
       },
       "source": [
-        "# Run Custom Container Training"
+        "# Run The Custom Container Training"
       ]
     },
     {
@@ -386,7 +673,7 @@
         "id": "7ee691569d8d"
       },
       "source": [
-        "## Initialize Vertex SDK for Python\n",
+        "## Initialize The Vertex AI SDK for Python\n",
         "\n",
         "Initialize the *client* for Vertex AI"
       ]
@@ -401,7 +688,7 @@
       "source": [
         "from google.cloud import aiplatform\n",
         "\n",
-        "aiplatform.init(project=MY_PROJECT, staging_bucket=MY_STAGING_BUCKET)"
+        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -424,7 +711,7 @@
       "outputs": [],
       "source": [
         "ds = aiplatform.TabularDataset.create(\n",
-        "    display_name=\"bq_iris_dataset\", bq_source=f\"bq://{MY_PROJECT}.ml_datasets.iris\"\n",
+        "    display_name=\"bq_iris_dataset\", bq_source=f\"bq://{PROJECT_ID}.ml_datasets.iris\"\n",
         ")"
       ]
     },
@@ -434,7 +721,7 @@
         "id": "ee242cc1f74c"
       },
       "source": [
-        "# Launch a Training Job to Create a Model\n",
+        "# Launch The Training Job to Create a Model\n",
         "\n",
         "We will train a model with the container we built above."
       ]
@@ -449,14 +736,14 @@
       "source": [
         "job = aiplatform.CustomContainerTrainingJob(\n",
         "    display_name=\"train-bq-iris\",\n",
-        "    container_uri=f\"gcr.io/{MY_PROJECT}/test-custom-container:latest\",\n",
+        "    container_uri=f\"gcr.io/{PROJECT_ID}/test-custom-container:latest\",\n",
         "    model_serving_container_image_uri=\"gcr.io/cloud-aiplatform/prediction/tf2-cpu.2-2:latest\",\n",
         ")\n",
         "model = job.run(\n",
         "    ds,\n",
         "    replica_count=1,\n",
         "    model_display_name=\"bq-iris-model\",\n",
-        "    bigquery_destination=f\"bq://{MY_PROJECT}\",\n",
+        "    bigquery_destination=f\"bq://{PROJECT_ID}\",\n",
         ")"
       ]
     },
@@ -466,7 +753,7 @@
         "id": "a7fa9b59f919"
       },
       "source": [
-        "# Deploy Your Model\n",
+        "# Deploy The Model\n",
         "\n",
         "Deploy your model, then wait until the model FINISHES deployment before proceeding to prediction."
       ]
@@ -488,7 +775,7 @@
         "id": "4dbd6c650a03"
       },
       "source": [
-        "# Predict on the Endpoint"
+        "# Make a prediction\n"
       ]
     },
     {
@@ -503,12 +790,46 @@
         "    [{\"sepal_length\": 5.1, \"sepal_width\": 2.5, \"petal_length\": 3.0, \"petal_width\": 1.1}]\n",
         ")"
       ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "MaoIczP8qu--"
+      },
+      "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:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "-UaP-qoKqzc1"
+      },
+      "outputs": [],
+      "source": [
+        "import os\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",
+        "\n",
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "! gsutil -m rm -r $BUCKET_URI  "
+      ]
     }
   ],
   "metadata": {
     "colab": {
       "collapsed_sections": [],
-      "name": "AI_Platform_(Unified)_SDK_BigQuery_Custom_Container_Training.ipynb",
+      "name": "SDK_BigQuery_Custom_Container_Training.ipynb",
       "toc_visible": true
     },
     "kernelspec": {

notebooks/community/vertex_endpoints/optimized_tensorflow_runtime/bert_optimized_online_prediction.ipynb

@@ -67,9 +67,9 @@
       "source": [
         "## Overview\n",
         "\n",
-        "In this sample we demonstrate how to fine-tune a BERT base classification model for sentiment analysis.\n",
+        "In this sample you learn how to fine-tune a BERT base classification model for sentiment analysis.\n",
         "\n",
-        "Then we export a trained model to Vertex AI Prediction service using an open source based TensorFlow 2.7 container and the optimized TensorFlow runtime container. We benchmark those models so we can compare their predictions.\n",
+        "Then you export a trained model to Vertex AI Prediction service using an open source based TensorFlow 2.7 container and the optimized TensorFlow runtime container, run performance evaluation for those models and compare their predictions.\n",
         "\n",
         "For additional information about Vertex AI Prediction optimized TensorFlow runtime containers, see https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
         "\n",
@@ -116,7 +116,7 @@
       "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."
       ]
     },
@@ -179,10 +179,10 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
         "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Workbench Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
         "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\""
@@ -196,12 +196,12 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install {USER_FLAG} --upgrade tensorflow==2.7.0\n",
-        "! pip3 install {USER_FLAG} --upgrade tensorflow-text==2.7.0\n",
-        "! pip3 install {USER_FLAG} --upgrade tensorflow-serving-api==2.7.0\n",
-        "! pip3 install {USER_FLAG} --upgrade tf-models-official==2.7.0\n",
-        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform\n",
-        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage"
+        "! pip3 install {USER_FLAG} --upgrade tensorflow==2.7.0 -q\n",
+        "! pip3 install {USER_FLAG} --upgrade tensorflow-text==2.7.0 -q\n",
+        "! pip3 install {USER_FLAG} --upgrade tensorflow-serving-api==2.7.0 -q\n",
+        "! pip3 install {USER_FLAG} --upgrade tf-models-official==2.7.0 -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q"
       ]
     },
     {
@@ -363,7 +363,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using  Vertex AI Workbench Notebooks**, your environment is already\n",
         "authenticated. Skip this step."
       ]
     },
@@ -412,10 +412,10 @@
         "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
         "# requests.\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
         "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "# If on  Vertex AI Workbench Notebooks, then don't execute this code\n",
         "if not IS_GOOGLE_CLOUD_NOTEBOOK:\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
@@ -571,7 +571,7 @@
         "id": "9cbb5302a3c4"
       },
       "source": [
-        "## Downloading dataset"
+        "## Download the dataset"
       ]
     },
     {
@@ -612,7 +612,7 @@
         "id": "8b7051896d19"
       },
       "source": [
-        "## Preprocess dataset"
+        "## Preprocess the dataset"
       ]
     },
     {
@@ -703,7 +703,7 @@
         "id": "d56746554dd6"
       },
       "source": [
-        "As a base for our model we take uncased BERT-Base model from TensorFlow Hub:\n",
+        "As a base for our model you take uncased BERT-Base model from TensorFlow Hub:\n",
         "https://tfhub.dev/tensorflow/bert_en_uncased_L-12_H-768_A-12/3"
       ]
     },
@@ -757,7 +757,7 @@
       },
       "source": [
         "Define a classification model by feeding the output BERT encoder model into dropout and dense layers.\n",
-        "For details, see the https://www.tensorflow.org/text/tutorials/classify_text_with_bert tutorial."
+        "Learn more about [Classify text with BERT]( https://www.tensorflow.org/text/tutorials/classify_text_with_bert)."
       ]
     },
     {
@@ -917,7 +917,7 @@
         "id": "11cc837b06f9"
       },
       "source": [
-        "Check the model signature.\n",
+        "Check the model signature to see which fields prediction request should have.\n",
         "\n",
         "Note that you might see a stacktrace message about a missing 'CaseFoldUTF8' op. This is a known issue with `saved_model_cli` that you can ignore."
       ]
@@ -948,7 +948,7 @@
         "id": "953eb5e1e86e"
       },
       "source": [
-        "Now we can generate requests to send to our model for inference. Requests are generated in the JSON Lines format, one request per line."
+        "Now you can generate requests to send to our model for inference. Requests are generated in the JSON Lines format, one request per line."
       ]
     },
     {
@@ -1047,7 +1047,7 @@
         "id": "5bbdded5d2ab"
       },
       "source": [
-        "The TensorFlow runtime has components that are lazily initialized. Lazy initialization might result in high latency for the first requests that are sent to a model after it's loaded. This latency can be several orders of magnitude higher than that of a single inference request. \n",
+        "The TensorFlow runtime has components that are lazily initialized. Lazy initialization might result in high latency for the first requests that are sent to a model after it's loaded. This latency can be several orders of magnitude higher than that of a single inference request.\n",
         "\n",
         "For more information about SavedModel warmup, see https://www.tensorflow.org/tfx/serving/saved_model_warmup.\n",
         "\n",
@@ -1209,9 +1209,9 @@
         "id": "83f62a939359"
       },
       "source": [
-        "The AI Platform Python client library works as a client/server model. \n",
+        "The AI Platform Python client library works as a client/server model.\n",
         "\n",
-        "We are going to use following clients in this sample:\n",
+        "You are going to use following clients in this sample:\n",
         "- Model Service for managing models.\n",
         "- Endpoint Service for deployment.\n",
         "- Prediction Service for serving."
@@ -1254,7 +1254,7 @@
         "\n",
         "`artifact_uri` argument should point to a GCS path where `saved_model.pb` file is located for your model.\n",
         "\n",
-        "`image_uri` specifies which docker image to use. Here we upload the same model using TF2.7 GPU and Vertex AI Prediction optimized TensorFlow runtime images."
+        "`image_uri` specifies which docker image to use. Here you upload the same model using TF2.7 GPU and Vertex AI Prediction optimized TensorFlow runtime images."
       ]
     },
     {
@@ -1386,7 +1386,7 @@
         "id": "5ff288387d03"
       },
       "source": [
-        "See [endpoint_service.create_endpoint](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_create_endpoint) API description for details."
+        "Learn more about [endpoint_service.create_endpoint](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_create_endpoint)."
       ]
     },
     {
@@ -1467,7 +1467,7 @@
         "id": "ebb2d55b45e0"
       },
       "source": [
-        "For details about the `enpoint_service.deploy_model` API, see [enpoint_service.deploy_model](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_deploy_model)."
+        "Learn more about [enpoint_service.deploy_model](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_deploy_model)."
       ]
     },
     {
@@ -1510,7 +1510,7 @@
       "source": [
         "tf_opt_gpu_deployed_model_dict = {\n",
         "    \"model\": tf_opt_gpu_model,\n",
-        "    \"display_name\": \"Criteo Kaggle optimized TensorFlow runtime GPU model\",\n",
+        "    \"display_name\": \"BERT Base optimized TensorFlow runtime GPU model\",\n",
         "    \"dedicated_resources\": {\n",
         "        \"min_replica_count\": 1,\n",
         "        \"max_replica_count\": 1,\n",
@@ -1540,7 +1540,7 @@
       "source": [
         "tf_opt_lossy_gpu_deployed_model_dict = {\n",
         "    \"model\": tf_opt_lossy_gpu_model,\n",
-        "    \"display_name\": \"Criteo Kaggle optimized TensorFlow runtime GPU model with lossy optimizations\",\n",
+        "    \"display_name\": \"BERT Base optimized TensorFlow runtime GPU model with lossy optimizations\",\n",
         "    \"dedicated_resources\": {\n",
         "        \"min_replica_count\": 1,\n",
         "        \"max_replica_count\": 1,\n",
@@ -1598,7 +1598,7 @@
         "id": "ca1dfbcdf81e"
       },
       "source": [
-        "Alternatively you can send POST REST requests without using the SDK. For more details, see https://cloud.google.com/vertex-ai/docs/predictions/online-predictions-custom-models#online_predict_custom_trained-drest.\n",
+        "Alternatively you can send POST REST requests without using the SDK. Learn more about https://cloud.google.com/vertex-ai/docs/predictions/online-predictions-custom-models#online_predict_custom_trained-drest.\n",
         "This method is slightly faster."
       ]
     },
@@ -1904,6 +1904,24 @@
         "You can see that the Vertex AI Prediction optimized TensorFlow runtime has signficantly higher throughput and lower latency compared to TensorFlow 2.7."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "06f2711e6221"
+      },
+      "source": [
+        "## (Optional) Compare performance of deployed models using MLPerf Inference loadgen"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "adcd7c46de26"
+      },
+      "source": [
+        "MLPerf Inference is a benchmark suite for measuring how fast systems can run models in a variety of deployment scenarios. MLPerf is now an industry standard way of measuring model performance. You can follow instructions at https://github.com/tensorflow/tpu/tree/master/models/experimental/inference/load_test to run MLPerf Inferenence benchmark for deployed models."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1921,7 +1939,7 @@
       "source": [
         "In this sample the Vertex Prediction optimized TensorFlow runtime is used with the `allow_precision_affecting_optimizations` flag set to `true` to gain additional speedup. Now let's check how those optimizations effect prediction results.\n",
         "\n",
-        "We compare the results of predictions for 32,000 requests for a model running on the optimized TensorFlow runtime with lossy optimizations and on TF2.7."
+        "Compare the results of predictions for 32,000 requests for a model running on the optimized TensorFlow runtime with lossy optimizations and on TF2.7."
       ]
     },
     {
@@ -2083,7 +2101,10 @@
       },
       "outputs": [],
       "source": [
-        "!gsutil rm -r $BUCKET_URI"
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    !gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/community/vertex_endpoints/optimized_tensorflow_runtime/tabular_optimized_online_prediction.ipynb

@@ -67,14 +67,14 @@
       "source": [
         "## Overview\n",
         "\n",
-        "In this sample we demonstrate how to train a tabular model using TensorFlow Keras or Estimator API using Criteo Kaggle dataset.\n",
-        "Next, we export a trained model to the Vertex AI Prediction service using open source based TensorFlow 2.7 container and the optimized TensorFlow runtime container. We benchmark those models side by side and compare predictions.\n",
+        "In this sample you learn how to train a tabular model using TensorFlow Keras or Estimator API using Criteo Kaggle dataset.\n",
+        "Next, you export a trained model to the Vertex AI Prediction service using open source based TensorFlow 2.7 container and the optimized TensorFlow runtime container, run performance evaluation for those models side by side and compare predictions.\n",
         "\n",
         "For additional information about Vertex AI Prediction optimized TensorFlow runtime containers, please refer to https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
         "\n",
         "### Dataset\n",
         "\n",
-        "We use Criteo Kaggle dataset, which takes about 4GB in this sample.\n",
+        "In this sample you use Criteo Kaggle dataset, which takes about 4GB.\n",
         "\n",
         "\n",
         "### Objective\n",
@@ -113,7 +113,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "**If you are using Colab or Google Cloud Notebooks**, your environment meets the requirements to run this notebook. You can skip this step."
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment meets the requirements to run this notebook. You can skip this step."
       ]
     },
     {
@@ -122,7 +122,7 @@
         "id": "gCuSR8GkAgzl"
       },
       "source": [
-        "**If you are not using Colab or Google Cloud Notebooks**, you must have the following in your environment to meet this notebook's requirements.\n",
+        "**If you are not using Colab or Vertex AI Workbench Notebooks**, you must have the following in your environment to meet this notebook's requirements.\n",
         "\n",
         "* The Google Cloud SDK\n",
         "* Git\n",
@@ -172,10 +172,10 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
         "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# Google Cloud Notebook requires dependencies to be installed with '--user'\n",
+        "# Vertex AI Workbench Notebook requires dependencies to be installed with '--user'\n",
         "USER_FLAG = \"\"\n",
         "if IS_GOOGLE_CLOUD_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\""
@@ -189,10 +189,10 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install {USER_FLAG} --upgrade tensorflow==2.7.0\n",
-        "! pip3 install {USER_FLAG} --upgrade tensorflow-serving-api==2.7.0\n",
-        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform\n",
-        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage"
+        "! pip3 install {USER_FLAG} --upgrade tensorflow==2.7.0 -q\n",
+        "! pip3 install {USER_FLAG} --upgrade tensorflow-serving-api==2.7.0 -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q"
       ]
     },
     {
@@ -345,7 +345,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
         "authenticated. Skip this step."
       ]
     },
@@ -395,10 +395,10 @@
         "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
         "# requests.\n",
         "\n",
-        "# The Google Cloud Notebook product has specific requirements\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
         "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
+        "# If on Vertex AI Workbench Notebooks, then don't execute this code\n",
         "if not IS_GOOGLE_CLOUD_NOTEBOOK:\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
@@ -556,7 +556,7 @@
         "id": "9ee07345bcc6"
       },
       "source": [
-        "## Downloading Dataset"
+        "## Download the dataset"
       ]
     },
     {
@@ -620,7 +620,7 @@
         "id": "ng-Nrc8UdbP2"
       },
       "source": [
-        "## Reading and transforming dataset\n",
+        "## Read and transform the dataset\n",
         "\n",
         "Before the model can be trained, the variables must be pre-processed.\n",
         "\n",
@@ -954,7 +954,7 @@
         "id": "AVibdmrufYRA"
       },
       "source": [
-        "Check the model signature."
+        "Check the model signature to see which fields prediction request should have."
       ]
     },
     {
@@ -986,7 +986,7 @@
         "Another option to train a model is to use the TensorFlow Estimator API. For more information, see\n",
         "https://github.com/tensorflow/docs/blob/r2.4/site/en/tutorials/estimator/premade.ipynb\n",
         "\n",
-        "The following code is provided only for illustration purposes. We use the Keras model for deployment."
+        "The following code is provided only for illustration purposes. You use the Keras model for deployment."
       ]
     },
     {
@@ -1232,7 +1232,7 @@
         "id": "9c75a550809d"
       },
       "source": [
-        "The TensorFlow runtime has components that are lazily initialized. Lazy initialization might result in high latency for the first requests that are sent to a model after it's loaded. This latency can be several orders of magnitude higher than that of a single inference request. \n",
+        "The TensorFlow runtime has components that are lazily initialized. Lazy initialization might result in high latency for the first requests that are sent to a model after it's loaded. This latency can be several orders of magnitude higher than that of a single inference request.\n",
         "\n",
         "For more information about SavedModel warmup, see https://www.tensorflow.org/tfx/serving/saved_model_warmup.\n",
         "\n",
@@ -1435,7 +1435,7 @@
         "id": "9d259d62f8a4"
       },
       "source": [
-        "The throughput and latency of the Criteo model we trained is sensitive to network performance."
+        "The throughput and latency of the Criteo model you trained is sensitive to network performance."
       ]
     },
     {
@@ -1488,7 +1488,7 @@
         "id": "743b3af8f747"
       },
       "source": [
-        "For simplicity, we setup VPC peering to the default network. You can create a different network for your project.\n",
+        "For simplicity, you setup VPC peering to the default network. You can create a different network for your project.\n",
         "\n",
         "If you setup VPC peering with any other network, make sure that the network already exists and that your VM is running on that network."
       ]
@@ -1598,12 +1598,16 @@
         "id": "lYFkS2H9dDfd"
       },
       "source": [
-        "See [model_service.upload_model](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.model_service.ModelServiceClient#google_cloud_aiplatform_v1_services_model_service_ModelServiceClient_upload_model) documentation for details.\n",
+        "Learn more about [model_service.upload_model](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.model_service.ModelServiceClient#google_cloud_aiplatform_v1_services_model_service_ModelServiceClient_upload_model).\n",
         "\n",
         "\n",
         "`artifact_uri` argument should point to a GCS path where `saved_model.pb` file is located for your model.\n",
         "\n",
-        "`image_uri` specifies which docker image to use. Here we upload the same model using TF2.7 GPU and Vertex AI Prediction optimized TensorFlow runtime images."
+        "`image_uri` specifies which docker image to use. Here we upload the same model using TF2.7 GPU and Vertex AI Prediction optimized TensorFlow runtime images.\n",
+        "\n",
+        "In order to be able to send requests to your models over gRPC, you need to set `model_name` argument and update `predict_route` and `health_route` accordingly.\n",
+        "\n",
+        "Please note that gRPC support in Vertex AI Prediction is still experimental."
       ]
     },
     {
@@ -1619,6 +1623,15 @@
         "    \"artifact_uri\": BUCKET_URI,\n",
         "    \"container_spec\": {\n",
         "        \"image_uri\": \"us-docker.pkg.dev/vertex-ai/prediction/tf2-cpu.2-7:latest\",\n",
+        "        \"args\": [\n",
+        "            \"--port=8500\",\n",
+        "            \"--rest_api_port=8080\",\n",
+        "            \"--model_name=default\",\n",
+        "            \"--model_base_path=$(AIP_STORAGE_URI)\",\n",
+        "        ],\n",
+        "        \"ports\": [{\"container_port\": 8080}],\n",
+        "        \"predict_route\": \"/v1/models/default:predict\",\n",
+        "        \"health_route\": \"/v1/models/default\",\n",
         "    },\n",
         "}\n",
         "tf27_cpu_model = (\n",
@@ -1642,6 +1655,15 @@
         "    \"artifact_uri\": BUCKET_URI,\n",
         "    \"container_spec\": {\n",
         "        \"image_uri\": \"us-docker.pkg.dev/vertex-ai/prediction/tf2-gpu.2-7:latest\",\n",
+        "        \"args\": [\n",
+        "            \"--port=8500\",\n",
+        "            \"--rest_api_port=8080\",\n",
+        "            \"--model_name=default\",\n",
+        "            \"--model_base_path=$(AIP_STORAGE_URI)\",\n",
+        "        ],\n",
+        "        \"ports\": [{\"container_port\": 8080}],\n",
+        "        \"predict_route\": \"/v1/models/default:predict\",\n",
+        "        \"health_route\": \"/v1/models/default\",\n",
         "    },\n",
         "}\n",
         "tf27_gpu_model = (\n",
@@ -1664,11 +1686,7 @@
         "- *allow_precompilation* - turns on model pre-compilation for better performance. Note that model precompilation happens when the first request with the new batch size arrives, and the response for that request is sent after precompilation is complete. To mitigate this, specify a warmup file (see the section earlier in this colab). Model precompilation works for different kinds of models, and in most cases has a positive effect on performance. However, we recommend that you try it out for your model before you enable it in production.\n",
         "- *allow_precision_affecting_optimizations* - enables precision affecting optimizations. In some cases this makes the model run significantly faster at the cost of very minimal loss to model prediction power. You should assess the precision impact to your model when using this optimization.\n",
         "\n",
-        "For the list of available optimized TensorFlow runtimer containers and options, see https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime.\n",
-        "\n",
-        "In order to be able to send requests to your models over gRPC, you need to set `model_name` argument and update `predict_route` and `health_route` accordingly.\n",
-        "\n",
-        "Please note that gRPC support in Vertex AI Prediction is still experimental and only available for models deployed using optimized TensorFlow runtime."
+        "For the list of available optimized TensorFlow runtimer containers and options, see https://cloud.google.com/vertex-ai/docs/predictions/optimized-tensorflow-runtime."
       ]
     },
     {
@@ -1768,7 +1786,7 @@
         "id": "e4279643c2cf"
       },
       "source": [
-        "See [endpoint_service.create_endpoint](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_create_endpoint) API description for details."
+        "Learn more about [endpoint_service.create_endpoint](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_create_endpoint)."
       ]
     },
     {
@@ -1887,7 +1905,7 @@
         "id": "f8586711566b"
       },
       "source": [
-        "For details about the `enpoint_service.deploy_model` API, see [enpoint_service.deploy_model](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_deploy_model)."
+        "Learn more about [enpoint_service.deploy_model](https://cloud.google.com/python/docs/reference/aiplatform/latest/google.cloud.aiplatform_v1.services.endpoint_service.EndpointServiceClient#google_cloud_aiplatform_v1_services_endpoint_service_EndpointServiceClient_deploy_model)."
       ]
     },
     {
@@ -2244,7 +2262,7 @@
       },
       "outputs": [],
       "source": [
-        "tf27_cpu_results = benchmark_rest_private_endpoint(\n",
+        "tf27_cpu_results = benchmark_grpc_private_endpoint(\n",
         "    tf27_cpu_endpoint, [10, 20, 30, 40, 50, 55]\n",
         ")\n",
         "tf27_cpu_results"
@@ -2258,7 +2276,7 @@
       },
       "outputs": [],
       "source": [
-        "tf27_gpu_results = benchmark_rest_private_endpoint(\n",
+        "tf27_gpu_results = benchmark_grpc_private_endpoint(\n",
         "    tf27_gpu_endpoint, [10, 20, 30, 40, 50, 60, 70, 75]\n",
         ")\n",
         "tf27_gpu_results"
@@ -2382,6 +2400,24 @@
         "You can see that the Vertex AI Prediction optimized TensorFlow runtime has signficantly higher throughput and lower latency compared to TensorFlow 2.7."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "3f369366c0af"
+      },
+      "source": [
+        "## (Optional) Compare performance of deployed models using MLPerf Inference loadgen"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bfd210c97934"
+      },
+      "source": [
+        "MLPerf Inference is a benchmark suite for measuring how fast systems can run models in a variety of deployment scenarios. MLPerf is now an industry standard way of measuring model performance. You can follow instructions at https://github.com/tensorflow/tpu/tree/master/models/experimental/inference/load_test to run MLPerf Inferenence benchmark for deployed models.\n"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -2559,7 +2595,10 @@
       },
       "outputs": [],
       "source": [
-        "!gsutil rm -r $BUCKET_URI"
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    !gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/notebook_template.ipynb

@@ -65,7 +65,7 @@
         "\n",
         "{TODO: Include a paragraph with Dataset information and where to obtain it.} \n",
         "\n",
-        "{TODO: Make sure the dataset is accessible to the public. **Googlers**: Add your dataset to the [public samples bucket](http://goto/cloudsamples#sample-storage-bucket) within gs://cloud-samples-data/ai-platform-unified, if it doesn't already exist there.}\n",
+        "{TODO: Make sure the dataset is accessible to the public. **Googlers**: Add your dataset to the [public samples bucket](http://goto/cloudsamples#sample-storage-bucket) within gs://cloud-samples-data/vertex-ai, if it doesn't already exist there.}\n",
         "\n",
         "### Objective\n",
         "\n",

notebooks/official/CODEOWNERS

@@ -21,4 +21,5 @@
 /feature_store/gapic-feature-store.ipynb @protorganizer @diemtvu
 /managed_notebooks @GoogleCloudPlatform/notebooks-team
 /pipelines/google_cloud_pipeline_components_bqml_text.ipynb @inardini
-/pipelines/google_cloud_pipelines_dataproc_tabular @inardini
+/pipelines/google_cloud_pipelines_dataproc_tabular @inardini
+/automl/automl_forecasting_bqml_arima_plus_comparison.ipynb @TheMichaelHu

notebooks/official/README.md

@@ -1,4 +1,513 @@
 # Google Cloud Vertex AI Official Notebooks
 
-The official notebooks are organized by Google Cloud Vertex AI products.
+The official notebooks are a collection of curated and non-curated notebooks authored by Google Cloud staff members. The curated notebooks are linked to in the [Vertex AI online web documentation](https://cloud.google.com/vertex-ai/docs/tutorials/jupyter-notebooks).
+
+The official notebooks are organized by Google Cloud Vertex AI services.
+
+## Manifest of Curated Notebooks
+
+### AutoML
+
+[AutoML text classification model](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl-text-classification.ipynb)
+
+<blockquote>
+In this tutorial, you learn how to use `AutoML` to train a text classification model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `AutoML Training`
+- `Vertex AI Model resource`
+
+The steps performed include:
+
+- Create a `Vertex AI Dataset`
+- Train an `AutoML` text classification `Model` resource.
+- Obtain the evaluation metrics for the `Model` resource.
+- Create an `Endpoint` resource.
+- Deploy the `Model` resource to the `Endpoint` resource.
+- Make an online prediction.
+- Make a batch prediction.
+</blockquote>
+
+[AutoML tabular forecasting model](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb)
+
+<blockquote>
+In this tutorial, you create an `AutoML` tabular forecasting model from a Python script, and then do a batch prediction using the Vertex AI SDK. 
+
+This tutorial uses the following Google Cloud ML services:
+
+- `AutoML Training`
+- `Vertex AI Batch Prediction`
+- `Vertex AI Model` resource
+
+The steps performed include:
+
+- Create a `Vertex AI Dataset` resource.
+- Train an `AutoML` tabular forecasting `Model` resource.
+- Obtain the evaluation metrics for the `Model` resource.
+- Make a batch prediction.
+</blockquote>
+
+### Vertex AI Training
+
+[Custom image classification model training and batch prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-batch.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Training` to create a custom trained model and use `Vertex AI Batch Prediction` to do a batch prediction on the trained model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Training`
+- `Vertex AI Batch Prediction`
+- `Vertex AI Model` resource
+
+The steps performed include:
+
+- Create a `Vertex AI` custom job for training a TensorFlow model.
+- Upload the trained model artifacts as a `Model` resource.
+- Make a batch prediction.
+</blockquote>
+
+[Custom image classification model training and online prediction](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-online.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Training` to create a custom-trained model from a Python script in a Docker container, and learn to use `Vertex AI Prediction` to do a prediction on the deployed model by sending data. 
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Training`
+- `Vertex AI Prediction`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a `Vertex AI` custom job for training a TensorFlow model.
+- Upload the trained model artifacts to a `Model` resource.
+- Create a serving `Endpoint` resource.
+- Deploy the Model resource to a serving `Endpoint` resource.
+- Make a prediction.
+- Undeploy the `Model` resource.
+</blockquote>
+
+### Vertex Explainable AI
+
+[AutoML tabular binary classification model with batch explanations](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `AutoML` to create a tabular binary classification model from a Python script, and then learn to use `Vertex AI Batch Prediction` to make predictions with explanations.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI AutoML`
+- `Vertex AI Batch Prediction`
+- `Vertex Explainable AI`
+- `Vertex AI Model` resource
+
+The steps performed include:
+
+- Create a `Vertex Dataset` resource.
+- Train an `AutoML` tabular binary classification model.
+- View the model evaluation metrics for the trained model.
+- Make a batch prediction request with explainability.
+</blockquote>
+
+[AutoML tabular binary classification model with online explanations](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_automl_tabular_classification_online_explain.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `AutoML` to create a tabular binary classification model from a Python script, and then learn to use `Vertex AI Online Prediction` to make online predictions with explanations. 
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI AutoML`
+- `Vertex AI Prediction`
+- `Vertex Explainable AI`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a `Vertex AI Dataset` resource.
+- Train an `AutoML` tabular binary classification model.
+- View the model evaluation metrics for the trained model.
+- Create a serving `Endpoint` resource.
+- Deploy the `Model` resource to a serving `Endpoint` resource.
+- Make an online prediction request with explainability.
+- Undeploy the `Model` resource.
+</blockquote>
+
+[Custom tabular regression model with batch explanations](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_tabular_regression_batch_explain.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Training` and `Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Batch Prediction` to make a batch prediction request with explanations. 
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Training`
+- `Vertex AI Batch Prediction`
+- `Vertex Explainable AI`
+- `Vertex AI Mode`l resource
+
+The steps performed include:
+
+- Create a `Vertex AI` custom job for training a TensorFlow model.
+- View the model evaluation for the trained model.
+- Set explanation parameters for when the model is deployed.
+- Upload the trained model artifacts and explanations as a `Model` resource.
+- Make a batch prediction with explanations.
+</blockquote>
+    
+[Custom tabular regression model with online explanations](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Training` and `Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Prediction` to make an online prediction request with explanations.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Training`
+- `Vertex AI Prediction`
+- `Vertex Explainable AI`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a `Vertex AI` custom job for training a TensorFlow model.
+- View the model evaluation for the trained model.
+- Set explanation parameters for when the model is deployed.
+- Upload the trained model artifacts and explanations as a `Model` resource.
+- Create a serving `Endpoint` resource.
+- Deploy the `Model` resource to a serving `Endpoint` resource.
+- Make a prediction with explanation.
+- Undeploy the `Model` resource.
+</blockquote>
+    
+[Custom image classification model with batch explanations](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Batch Prediction` to make a batch prediction request with explanations. 
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Training`
+- `Vertex AI Batch Prediction`
+- `Vertex Explainable AI`
+- `Vertex AI Model` resource
+
+The steps performed include:
+
+- Create a `Vertex AI` custom job for training a TensorFlow model.
+- View the model evaluation for the trained model.
+- Set explanation parameters for when the model is deployed.
+- Upload the trained model artifacts and explanation parameters as a `Model` resource.
+- Make a batch prediction with explanations.
+</blockquote>
+
+[Custom image classification model with online explanations](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_custom_image_classification_online_explain.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Prediction` to make an online prediction request with explanations. 
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Training`
+- `Vertex AI Online Prediction`
+- `Vertex Explainable AI`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a `Vertex AI` custom job for training a TensorFlow model.
+- View the model evaluation for the trained model.
+- Set explanation parameters for when the model is deployed.
+- Upload the trained model artifacts and explanations as a `Model` resource.
+- Create a serving `Endpoint` resource.
+- Deploy the `Model` resource to a serving `Endpoint` resource.
+- Make a prediction with explanation.
+- Undeploy the `Model` resource.
+</blockquote>
+
+### Vertex Feature Store
+
+[Managing features in a feature store](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/feature_store/gapic-feature-store.ipynb)
+
+<blockquote>
+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.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Feature Store`
+    
+The steps performed include:
+
+- Create featurestore, entity type, and feature resources.
+- Import feature data into `Vertex AI Feature Store` resource.
+- Serve online prediction requests using the imported features.
+- Access imported features in offline jobs, such as training jobs.
+
+</blockquote>
+
+### Vertex Model Monitoring
+
+[Monitoring drift detection in online serving](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring/model_monitoring.ipynb)
+
+<blockquote>
+In this notebook, you learn to use the `Vertex AI Model Monitoring` service to detect drift and anomalies in prediction requests from a deployed `Vertex AI Model` resource.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Model Monitoring`
+- `Vertex AI Prediction`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Upload a pre-trained model as a `Vertex AI Model` resource.
+- Create an `Vertex AI Endpoint` resource.
+- Deploy the `Model` resource to the `Endpoint` resource.
+- Configure the `Endpoint` resource for model monitoring.
+- Generate synthetic prediction requests.
+- Understand how to interpret the statistics, visualizations, other data reported by the model monitoring feature.
+</blockquote>
+    
+### Vertex ML Metadata
+
+[Tracking hyperparameters and metrics in custom training job](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb)
+
+<blockquote>
+In this notebook, you learn how to use `Vertex ML Metadata` to track training parameters and evaluation metrics.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex ML Metadata`
+- `Vertex AI Experiments`
+
+The steps performed include:
+
+- Track parameters and metrics for a `Vertex AI` custom trained model.
+- Extract and perform analysis for all parameters and metrics within an Experiment.
+</blockquote>
+
+[Tracking hyperparameters and metrics in locally trained job](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb)
+
+<blockquote>
+In this notebook, you learn how to use `Vertex ML Metadata` to track training parameters and evaluation metrics.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex ML Metadata`
+- `Vertex AI Experiments`
+
+The steps performed include:
+
+- Track parameters and metrics for a locally trained model.
+- Extract and perform analysis for all parameters and metrics within an Experiment.
+</blockquote>
+    
+### Vertex AI Pipelines
+
+[Creating Python function KFP components](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/lightweight_functions_component_io_kfp.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use the KFP SDK to build lightweight Python function-based components, and then you learn to use `Vertex AI Pipelines` to execute the pipeline.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+
+The steps performed include:
+
+- Build Python function-based KFP components.
+- Construct a KFP pipeline.
+    - Pass Artifacts and parameters between components, both by path reference and by value.
+    - Use the kfp.dsl.importer method.
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+    
+[AutoML image classification model pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` image classification model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+- `Google Cloud Pipeline Components`
+- `Vertex AutoML`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Create a `Vertex AI Dataset` resource.
+    - Train an `AutoML` image classification `Model` resource.
+    - Create an `Endpoint` resource.
+    - Deploys the `Model` resource to the `Endpoint` resource.
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+    
+[AutoML tabular classification model pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/automl_tabular_classification_beans.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an AutoML tabular classification model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+- `Google Cloud Pipeline Components`
+- `Vertex AutoML`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Create a `Dataset` resource.
+    - Train an `AutoML` tabular classification `Model` resource.
+    - Create an `Endpoint` resource.
+    - Deploys the `Model` resource to the `Endpoint` resource.
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+    
+[AutoML tabular regression model pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` tabular regression model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+- `Google Cloud Pipeline Components`
+- `Vertex AutoML`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Create a `Dataset` resource.
+    - Train an `AutoML` tabular regression `Model` resource.
+    - Create an `Endpoint` resource.
+    - Deploys the `Model` resource to the `Endpoint` resource.
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+
+[AutoML text classification model pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` text classification model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+- `Google Cloud Pipeline Components`
+- `Vertex AutoML`
+- `Vertex AI Model` resource
+"- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Create a `Dataset` resource.
+    - Train an AutoML text classification `Model` resource.
+    - Create an `Endpoint` resource.
+    - Deploys the `Model` resource to the `Endpoint` resource.
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+
+[Custom training and batch prediction using prebuilt components pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/custom_model_training_and_batch_prediction.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build a custom model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+- `Google Cloud Pipeline Components`
+- `Vertex AI Training`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Train a custom model.
+    - Upload the trained model as a `Model` resource.
+    - Create an `Endpoint` resource.
+- Deploy the `Model` resource to the `Endpoint` resource.
+- Make a batch prediction request.
+</blockquote>
+
+[Custom training using prebuilt and custom components pipeline](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_model_train_upload_deploy.ipynb)
+
+<blockquote>
+In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build and deploy a custom model.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+- `Google Cloud Pipeline Components`
+- `Vertex AI Training`
+- `Vertex AI Model` resource
+- `Vertex AI Endpoint` resource
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Train a custom model.
+    - Uploads the trained model as a `Model` resource.
+    - Creates an `Endpoint` resource.
+    - Deploys the `Model` resource to the `Endpoint` resource.
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+    
+[Introduction to control flow in pipelines](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/control_flow_kfp.ipynb)
+
+<blockquote>
+In this tutorial, you use the KFP SDK to build pipelines that use loops and conditionals, including nested examples.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+
+The steps performed include:
+
+- Create a KFP pipeline:
+    - Use control flow components
+- Compile the KFP pipeline.
+- Execute the KFP pipeline using `Vertex AI Pipelines`
+</blockquote>
+
+[Introduction to KFP components and pipelines](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/pipelines_intro_kfp.ipynb)
+
+<blockquote>
+In this tutorial, you use the KFP SDK to build pipelines.
+
+This tutorial uses the following Google Cloud ML services:
+
+- `Vertex AI Pipelines`
+
+The steps performed include:
+
+- Define and compile a `Vertex AI` pipeline.
+- Schedule a recurring pipeline run.
+- Specify which service account to use for a pipeline run.
+</blockquote>
+
+### Vertex AI Vizier
+
+[Using Vizier for multi-objective study](https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb)
+
+
+
+
  

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

@@ -32,21 +32,22 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/automl/automl-text-classification.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl-text-classification.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/automl/automl-text-classification.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/automl-text-classification.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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/raw/master/notebooks/official/automl/automl-text-classification.ipynb\">\n",
+        " <td>\n",
+        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/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",
+        "  </td>\n",
         "</table>"
       ]
     },
@@ -60,19 +61,30 @@
         "\n",
         "## Overview\n",
         "\n",
-        "This notebook walks you through the major phases of building and using a text classification model on [Vertex AI](https://cloud.google.com/vertex-ai/docs/). 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",
+        "This notebook walks you through the major phases of building and using a 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",
         "### Objective\n",
         "\n",
-        "In this notebook, you learn how to:\n",
+        "In this tutorial, you learn how to use `AutoML` to train a text classification model.\n",
         "\n",
-        "* Set up your development environment\n",
-        "* Create a dataset and import data\n",
-        "* Train an AutoML model\n",
-        "* Get and review evaluations for the model\n",
-        "* Deploy a model to an endpoint\n",
-        "* Get online predictions\n",
-        "* Get batch predictions\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `AutoML Training`\n",
+        "- `Vertex AI Model resource`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "* Create a `Vertex AI Dataset`.\n",
+        "* Train an `AutoML` text classification `Model` resource.\n",
+        "* Obtain the evaluation metrics for the `Model` resource.\n",
+        "* Create an `Endpoint` resource.\n",
+        "* Deploy the `Model` resource to the `Endpoint` resource.\n",
+        "* Make an online prediction\n",
+        "* Make a batch prediction\n",
         "\n",
         "### Costs\n",
         "\n",
@@ -107,7 +119,7 @@
       "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 Workbench AI Notebooks**, your environment already meets\n",
         "all the requirements to run this notebook. You can skip this step."
       ]
     },
@@ -148,32 +160,6 @@
         "1. Open this notebook in the Jupyter Notebook Dashboard."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "i1VRlEu-l0BW"
-      },
-      "source": [
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, Cloud Storage, and Compute Engine APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com). \n",
-        "\n",
-        "1. Follow the \"**Configuring your project**\" instructions from the Vertex Pipelines documentation.\n",
-        "\n",
-        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -182,7 +168,7 @@
       "source": [
         "### Install additional packages\n",
         "\n",
-        "This notebook uses the Python SDK for Vertex AI, which is contained in the `python-aiplatform` package. You must first install the package into your development environment."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
@@ -195,28 +181,73 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
-        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform google-cloud-storage jsonlines"
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform google-cloud-storage jsonlines"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "WReHDGG5g0XY"
+        "id": "e9255e3b156f"
       },
       "source": [
-        "### Set your project ID\n",
+        "### Restart the kernel\n",
         "\n",
-        "Finally, you must initialize the client library before you can send requests to the Vertex AI service. With the Python SDK, you initialize the client library as shown in the following cell. This tutorial also uses the Cloud Storage Python library for accessing batch prediction results.\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": "0c0b2427998a"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
         "\n",
-        "Be sure to provide the ID for your Google Cloud project in the `project` variable. This notebook uses the `us-central1` region, although you can change it to another region. \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": "435b8e413535"
+      },
+      "source": [
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "\n",
+        "1. [Enable the Vertex AI, BigQuery, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,bigquery,compute_component,storage_component).\n",
+        "\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n",
+        "\n",
+        "#### Set your project ID\n",
         "\n",
         "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
@@ -229,24 +260,7 @@
       },
       "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": "a82659ac2487"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -257,8 +271,107 @@
       },
       "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": "ea86e5a1da1d"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2e6b8b324ce1"
+      },
+      "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": "ae43d96c4b1b"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "5f4f5cccf897"
+      },
+      "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": "953fa6e5ddda"
+      },
+      "outputs": [],
+      "source": [
+        "from datetime import datetime\n",
+        "\n",
+        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "6c43a8673066"
+      },
+      "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."
       ]
     },
     {
@@ -269,22 +382,19 @@
       },
       "outputs": [],
       "source": [
-        "import sys\n",
-        "from datetime import datetime\n",
-        "\n",
-        "import jsonlines\n",
-        "from google.cloud import aiplatform, storage\n",
-        "from google.protobuf import json_format\n",
-        "\n",
-        "REGION = \"us-central1\"\n",
-        "\n",
         "# If you are running this notebook in Colab, run this cell and follow the\n",
         "# instructions to authenticate your GCP account. This provides access to your\n",
         "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
         "# requests.\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",
@@ -294,8 +404,129 @@
         "    # 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 ''\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e5755d1a554f"
+      },
+      "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": "d2de92accb67"
+      },
+      "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": "5ba09496accc"
+      },
+      "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": "b72bfdf29dae"
+      },
+      "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": "a4453435d115"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c4cf2cdebb50"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "96ad3d416327"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "93d685084cf2"
+      },
+      "source": [
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "152013538e59"
+      },
+      "outputs": [],
+      "source": [
+        "import jsonlines\n",
+        "from google.cloud import aiplatform, storage"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "03101a4492f3"
+      },
+      "source": [
+        "### Initialize Vertex AI \n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "740cd5c67c79"
+      },
+      "outputs": [],
+      "source": [
         "aiplatform.init(project=PROJECT_ID, location=REGION)"
       ]
     },
@@ -309,9 +540,9 @@
         "\n",
         "The notebook uses the 'Happy Moments' dataset for demonstration purposes. You can change it to another text classification dataset that [conforms to the data preparation requirements](https://cloud.google.com/vertex-ai/docs/datasets/prepare-text#classification).\n",
         "\n",
-        "Using the Python SDK, you can create a dataset and import the dataset in one call to `TextDataset.create()`, as shown in the following cell.\n",
+        "Using the Python SDK, you create a dataset and import the dataset in one call to `TextDataset.create()`, as shown in the following cell.\n",
         "\n",
-        "Creating and importing data is a long-running operation. This next step can take a while. The sample waits for the operation to complete, outputting statements as the operation progresses. The statements contain the full name of the dataset that you will use in the following section.\n",
+        "Creating and importing data is a long-running operation. This next step can take a while. The `create()` method waits for the operation to complete, outputting statements as the operation progresses. The statements contain the full name of the dataset that you will use in the following section.\n",
         "\n",
         "**Note**: You can close the noteboook while you wait for this operation to complete. "
       ]
@@ -325,8 +556,6 @@
       "outputs": [],
       "source": [
         "# Use a timestamp to ensure unique resources\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
-        "\n",
         "src_uris = \"gs://cloud-ml-data/NL-classification/happiness.csv\"\n",
         "display_name = f\"e2e-text-dataset-{TIMESTAMP}\""
       ]
@@ -466,11 +695,9 @@
         "id": "caaa3f32b12e"
       },
       "source": [
-        "## Get and review model evaluation scores\n",
+        "## Review model evaluation scores\n",
         "\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 deployed the model or you can list all of the models in your project. When listing your models, you can provide filter criteria to narrow down your search."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -481,94 +708,10 @@
       },
       "outputs": [],
       "source": [
-        "models = aiplatform.Model.list(filter=f'display_name=\"{model_display_name}\"')\n",
-        "print(models)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8481b6878ed2"
-      },
-      "source": [
-        "Using the model name (in the format `projects/[PROJECT_NAME]/locations/us-central1/models/[MODEL_ID]`), you can get its model evaluations. To get model evaluations, you must use the underlying service client.\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "Building a service client requires that you provide the name of the regionalized hostname used for your model. In this tutorial, the hostname is `us-central1-aiplatform.googleapis.com` because the model was created in the `us-central1` location."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a8443fc8861f"
-      },
-      "outputs": [],
-      "source": [
-        "# Get the ID of the model\n",
-        "model_name = \"[your-model-resource-name]\"\n",
-        "if model_name == \"[your-model-resource-name]\":\n",
-        "    # Use the `resource_name` of the Model instance you created previously\n",
-        "    model_name = model.resource_name\n",
-        "    print(f\"Model name: {model_name}\")\n",
-        "\n",
-        "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": \"us-central1-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aiplatform.gapic.ModelServiceClient(\n",
-        "    client_options=client_options\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "b8a788593609"
-      },
-      "source": [
-        "Before you can view the model evaluation you must first list all of the evaluations for that model. Each model can have multiple evaluations, although a new model is likely to only have one. "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fdcb045e29f2"
-      },
-      "outputs": [],
-      "source": [
-        "model_evaluations = model_service_client.list_model_evaluations(parent=model_name)\n",
-        "model_evaluation = list(model_evaluations)[0]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cd7d3afae05c"
-      },
-      "source": [
-        "Now that you have the model evaluation, you can look at your model's scores. If you have questions about what the scores mean, review the [public documentation](https://cloud.google.com/vertex-ai/docs/training/evaluating-automl-models#text).\n",
-        "\n",
-        "The results returned from the service are formatted as [`google.protobuf.Value`](https://googleapis.dev/python/protobuf/latest/google/protobuf/struct_pb2.html) objects. You can transform the return object as a `dict` for easier reading and parsing."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "6eb9ccb0a0a0"
-      },
-      "outputs": [],
-      "source": [
-        "model_eval_dict = json_format.MessageToDict(model_evaluation._pb)\n",
-        "metrics = model_eval_dict[\"metrics\"]\n",
-        "confidence_metrics = metrics[\"confidenceMetrics\"]\n",
-        "\n",
-        "print(f'Area under precision-recall curve (AuPRC): {metrics[\"auPrc\"]}')\n",
-        "for confidence_scores in confidence_metrics:\n",
-        "    metrics = confidence_scores.keys()\n",
-        "    print(\"\\n\")\n",
-        "    for metric in metrics:\n",
-        "        print(f\"\\t{metric}: {confidence_scores[metric]}\")"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -720,25 +863,6 @@
         "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."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "1e0759fbb219"
-      },
-      "outputs": [],
-      "source": [
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")\n",
-        "BUCKET_NAME = \"[your-bucket-name]\"\n",
-        "\n",
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
-        "    BUCKET_NAME = f\"automl-text-notebook-{TIMESTAMP}\"\n",
-        "\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\"\n",
-        "\n",
-        "! gsutil mb -l $REGION $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -749,7 +873,7 @@
       "source": [
         "# Instantiate the Storage client and create the new bucket\n",
         "storage = storage.Client()\n",
-        "bucket = storage.bucket(BUCKET_NAME)\n",
+        "bucket = storage.bucket(BUCKET_URI)\n",
         "\n",
         "# Iterate over the prediction instances, creating a new TXT file\n",
         "# for each.\n",
@@ -964,7 +1088,9 @@
       },
       "outputs": [],
       "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
+        "delete_bucket = False\n",
+        "\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI\n",
         "\n",
         "batch_job.delete()\n",

notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb

@@ -32,23 +32,24 @@
         "# Vertex AI SDK : AutoML training image object detection model for batch prediction\n",
         "\n",
         "<table align=\"left\">\n",
+        " \n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_image_object_detection_batch.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/automl/sdk_automl_image_object_detection_batch.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_image_object_detection_batch.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/automl/sdk_automl_image_object_detection_batch.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://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_image_object_detection_batch.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",
+        "  </td>                    \n",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -168,7 +169,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_aip:mbsdk"
+        "id": "hw7H6ADSv5mI"
       },
       "outputs": [],
       "source": [
@@ -189,20 +190,29 @@
         "id": "install_storage"
       },
       "source": [
-        "Install the latest GA version of *google-cloud-storage* library as well."
+        "Install the latest GA version of *google-cloud-storage* library."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "install_storage"
+        "id": "d6Pa6Sybv5mK"
       },
       "outputs": [],
       "source": [
         "! pip3 install -U google-cloud-storage $USER_FLAG"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9_zWlX10v5mL"
+      },
+      "source": [
+        "Install the latest version of *tensorflow* library."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -211,8 +221,7 @@
       },
       "outputs": [],
       "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
+        "! pip3 install --upgrade tensorflow $USER_FLAG"
       ]
     },
     {
@@ -230,7 +239,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "restart"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
@@ -282,7 +291,9 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "import os\n",
+        "\n",
+        "PROJECT_ID = \"\""
       ]
     },
     {
@@ -293,11 +304,32 @@
       },
       "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",
+        "# 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)"
+        "    print(\"Project ID: \", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "W2F5WRyhv5mO"
+      },
+      "source": [
+        "Otherwise, set your project ID here."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "d7-MjQafv5mO"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -335,11 +367,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "kAfG6tDAv5mQ"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -357,7 +392,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "timestamp"
+        "id": "PzKW-zT_v5mR"
       },
       "outputs": [],
       "source": [
@@ -397,7 +432,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "FvQeFm3Gv5mR"
       },
       "outputs": [],
       "source": [
@@ -475,7 +510,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_bucket"
+        "id": "09kHSsKmv5mT"
       },
       "outputs": [],
       "source": [
@@ -495,7 +530,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "validate_bucket"
+        "id": "N9JY-esPv5mU"
       },
       "outputs": [],
       "source": [
@@ -540,7 +575,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk"
+        "id": "w2Oa_jZSv5mV"
       },
       "outputs": [],
       "source": [
@@ -597,7 +632,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "quick_peek:csv"
+        "id": "ITshYFagv5mZ"
       },
       "outputs": [],
       "source": [
@@ -629,7 +664,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_dataset:image,iod"
+        "id": "FYyaPzfRv5mc"
       },
       "outputs": [],
       "source": [
@@ -677,7 +712,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "create_automl_pipeline:image,iod"
+        "id": "vtAgY1Nmv5md"
       },
       "outputs": [],
       "source": [
@@ -719,7 +754,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "run_automl_pipeline:image"
+        "id": "SvV1nFDTv5md"
       },
       "outputs": [],
       "source": [
@@ -750,7 +785,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "evaluate_the_model:mbsdk"
+        "id": "RcpDJMgev5me"
       },
       "outputs": [],
       "source": [
@@ -833,7 +868,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "copy_test_items:batch_prediction"
+        "id": "JXpg67zjv5mf"
       },
       "outputs": [],
       "source": [
@@ -869,7 +904,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "make_batch_file:automl,image"
+        "id": "hFjX62hvv5mg"
       },
       "outputs": [],
       "source": [
@@ -901,14 +936,27 @@
         "- `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",
+        "-  `machine_type`: The type of machine for running batch prediction on dedicated resources. Not specifying machine type will                      result in batch prediction job being run with automatic resources.\n",
+        "-  `starting_replica_count`: The number of machine replicas used at the start of the batch operation. If not set, Vertex AI decides starting number, not greater than `max_replica_count`. Only used if `machine_type` is set.\n",
+        "-  `max_replica_count`: The maximum number of machine replicas the batch operation may be scaled to. Only used if `machine_type` is set. Default is 10.\n",
         "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "axn-CW7xv5mg"
+      },
+      "source": [
+        "For AutoML models, only manual scaling is supported. In manual scaling both starting_replica_count and max_replica_count have the same value.\n",
+        "For this batch job we are using manual scaling. Here we are setting both starting_replica_count and max_replica_count to the same value that is 1. "
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "batch_request:mbsdk"
+        "id": "5VMMaJhbv5mh"
       },
       "outputs": [],
       "source": [
@@ -916,6 +964,9 @@
         "    job_display_name=\"salads_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_input_uri,\n",
         "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    machine_type=\"n1-standard-4\",\n",
+        "    starting_replica_count=1,\n",
+        "    max_replica_count=1,\n",
         "    sync=False,\n",
         ")\n",
         "\n",
@@ -937,7 +988,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "batch_request_wait:mbsdk"
+        "id": "Yc3YaEqGv5mh"
       },
       "outputs": [],
       "source": [
@@ -967,7 +1018,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "get_batch_prediction:mbsdk,iod"
+        "id": "UGGJxFjEv5mh"
       },
       "outputs": [],
       "source": [
@@ -986,8 +1037,7 @@
         "    with tf.io.gfile.GFile(name=gfile_name, mode=\"r\") as gfile:\n",
         "        for line in gfile.readlines():\n",
         "            line = json.loads(line)\n",
-        "            print(line)\n",
-        "            break"
+        "            print(line)"
       ]
     },
     {
@@ -1014,27 +1064,26 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "cleanup:mbsdk"
+        "id": "_Olkhs6xv5mi"
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    dataset.delete()\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    model.delete()\n",
+        "# Delete the model using the Vertex model object\n",
+        "model.delete()\n",
         "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    job.delete()\n",
+        "# Delete the AutoML or Pipeline trainig job\n",
+        "job.delete()\n",
         "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    batch_predict_job.delete()\n",
+        "# Delete the batch prediction job using the Vertex batch prediction object\n",
+        "batch_predict_job.delete()\n",
         "\n",
-        "    if os.getenv(\"IS_TESTING\"):\n",
-        "        ! gsutil rm -r $BUCKET_URI"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb

@@ -29,22 +29,22 @@
         "id": "title"
       },
       "source": [
-        "# Vertex SDK: AutoML tabular forecasting model for batch prediction\n",
+        "# Vertex AI SDK: AutoML tabular forecasting model for batch prediction\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.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/tree/master/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_forecasting_batch.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",
@@ -62,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to create tabular forecasting models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
+        "This tutorial demonstrates how to use the Vertex AI SDK to create tabular forecasting models and do batch prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
     {
@@ -84,13 +84,19 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML tabular forecasting 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` tabular forecasting 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:\n",
+        "\n",
+        "- `AutoML Training`\n",
+        "- `Vertex AI Batch Prediction`\n",
+        "- `Vertex AI Model` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex `Dataset` resource.\n",
-        "- Train the model.\n",
-        "- View the model evaluation.\n",
+        "- 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"
       ]
     },
@@ -122,7 +128,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\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",
         "\n",
         "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
         "\n",
@@ -155,7 +161,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the latest version of Vertex AI SDK for Python."
       ]
     },
     {
@@ -168,14 +174,19 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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\n",
-        "! pip3 install --upgrade tensorflow $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 --upgrade tensorflow $USER_FLAG -q"
       ]
     },
     {
@@ -302,7 +313,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -337,7 +351,7 @@
       "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 Workbench AI 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",
@@ -372,8 +386,11 @@
         "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",
@@ -409,7 +426,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -421,7 +439,8 @@
       "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_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -493,9 +512,9 @@
         "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."
       ]
     },
     {
@@ -655,8 +674,8 @@
         "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
         "- `target_column`: The name of the column to train as the label.\n",
         "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
-        "- `time_column`:\n",
-        "- `time_series_identifier_column`:\n",
+        "- `time_column`: Time-series column for the forecast model.\n",
+        "- `time_series_identifier_column`: ID column for the time-series column.\n",
         "\n",
         "The `run` method when completed returns the `Model` resource.\n",
         "\n",
@@ -697,9 +716,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when you deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for "
       ]
     },
     {
@@ -710,21 +728,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aiplatform.Model.list(filter=f\"display_name={MODEL_DISPLAY_NAME}\")\n",
-        "model = models[0]\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = aiplatform.initializer.global_config.get_client_options()\n",
-        "model_service_client = aiplatform.gapic.ModelServiceClient(\n",
-        "    client_options=client_options\n",
-        ")\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=model.resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -746,13 +753,14 @@
       "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 Model resource is trained, you can make a batch prediction by invoking the batch_predict() method using a BigQuery source and destination, 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",
-        "- `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",
+        "- `bigquery_source`: BigQuery URI to a table, up to 2000 characters long. For example: `bq://projectId.bqDatasetId.bqTableId`\n",
+        "- `bigquery_destination_prefix`: The BigQuery dataset or table for storing the batch prediction resuls.\n",
+        "- `instances_format`: The format for the input instances. Since a BigQuery source is used here, this should be set to `bigquery`.\n",
+        "- `predictions_format`: The format for the output predictions, `bigquery` is used here to output to a BigQuery table.\n",
+        "- `generate_explanations`: Set to `True` to generate explanations.\n",
         "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
       ]
     },
@@ -794,7 +802,9 @@
         "id": "99b7a9287ba6"
       },
       "source": [
-        "`batch_predict` can export predictions either to BigQuery or GCS. The BQ option is commented out below and the predictions will be exported to the BUCKET_URI."
+        "For AutoML models, manual scaling can be adjusted by setting both min and max nodes i.e., `starting_replica_count` and `max_replica_count` as the same value(in this example, set to 1). The node count can be increased or decreased as required by load.\n",
+        " \n",
+        "`batch_predict` can export predictions either to BigQuery or GCS. The BigQuery options are commented out below and the predictions will be exported to the BUCKET_URI."
       ]
     },
     {
@@ -813,9 +823,9 @@
         "    job_display_name=f\"iowa_liquor_sales_forecasting_predictions_{TIMESTAMP}\",\n",
         "    bigquery_source=PREDICTION_DATASET_BQ_PATH,\n",
         "    instances_format=\"bigquery\",\n",
-        "    # bigquery_destination_prefix=batch_predict_bq_output_uri_prefix,\n",
-        "    gcs_destination_prefix=BUCKET_URI,\n",
+        "    bigquery_destination_prefix=batch_predict_bq_output_uri_prefix,\n",
         "    predictions_format=\"bigquery\",\n",
+        "    generate_explanation=True,\n",
         "    sync=False,\n",
         ")\n",
         "\n",
@@ -850,14 +860,9 @@
         "id": "get_batch_prediction:mbsdk,forecast"
       },
       "source": [
-        "### Get the predictions\n",
+        "### Get the predictions and explanations\n",
         "\n",
-        "Next, get the results from the completed batch prediction job.\n",
-        "\n",
-        "The results are written to the Cloud Storage output bucket you specified in the batch prediction request. You call the method iter_outputs() to get a list of each Cloud Storage file generated with the results. Each file contains one or more prediction requests in a CSV format:\n",
-        "\n",
-        "- CSV header + predicted_label\n",
-        "- CSV row + prediction, per prediction request"
+        "Next, get the results from the completed batch prediction job and print them out. Each result row will include the prediction and explanation."
       ]
     },
     {
@@ -868,21 +873,8 @@
       },
       "outputs": [],
       "source": [
-        "import tensorflow as tf\n",
-        "\n",
-        "bp_iter_outputs = batch_prediction_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)\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",
-        "            print(line)"
+        "for row in batch_prediction_job.iter_outputs():\n",
+        "    print(row)"
       ]
     },
     {
@@ -894,9 +886,11 @@
         "### Visualize the forecasts\n",
         "\n",
         "Lastly, follow the given link to visualize the generated forecasts in [Data Studio](https://support.google.com/datastudio/answer/6283323?hl=en).\n",
-        "The code block included in this section dynamically generates a Data Studio link that specifies the template, the location of the forecasts, and the query to generate the chart. The data is populated from the forecasts generated earlier.\n",
+        "The code block included in this section dynamically generates a Data Studio link that specifies the template, the location of the forecasts, and the query to generate the chart. The data is populated from the forecasts generated using BigQuery options where the destination dataset is `batch_predict_bq_output_dataset_path`.\n",
         "\n",
-        "You can inspect the used template at https://datastudio.google.com/c/u/0/reporting/067f70d2-8cd6-4a4c-a099-292acd1053e8. This was created by Google specifically to view forecasting predictions."
+        "You can inspect the used template at https://datastudio.google.com/c/u/0/reporting/067f70d2-8cd6-4a4c-a099-292acd1053e8. This was created by Google specifically to view forecasting predictions.\n",
+        "\n",
+        "**Note:** The Data Studio dashboard can only show the charts properly when the `batch_predict` job is run successfully using the BigQuery options."
       ]
     },
     {

notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb

@@ -0,0 +1,956 @@
+{
+  "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"
+      },
+      "source": [
+        "# Vertex AI SDK for Python: AutoML training tabular regression model for batch prediction using BigQuery\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_automl_tabular_regression_batch_bq.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_automl_tabular_regression_batch_bq.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/automl/sdk_automl_tabular_regression_batch_bq.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>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "overview:automl"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK for Python to create tabular regression 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:gsod,lrg"
+      },
+      "source": [
+        "### Dataset\n",
+        "\n",
+        "The dataset used for this tutorial is the [GSOD dataset](https://console.cloud.google.com/marketplace/product/noaa-public/gsod) from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). In this version of the dataset, you use the year, month, and day fields to predict the mean daily temperature (mean_temp)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "objective:automl,training,online_prediction"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML tabular regression model and deploy it for batch prediction using the Vertex AI SDK for Python. You can alternatively create and deploy models using the `gcloud` command-line tool or batch using the Cloud Console.\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex AI `Dataset` resource.\n",
+        "- Train the model.\n",
+        "- View the model evaluation.\n",
+        "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
+        "- Make a prediction.\n",
+        "- Undeploy the `Model`."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "costs"
+      },
+      "source": [
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "* Cloud Storage\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
+        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "setup_local"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "If you are using Colab or Vertex AI Workbench, 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"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the latest version of the Vertex AI SDK for Python."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_aip:mbsdk"
+      },
+      "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",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "install_storage"
+      },
+      "source": [
+        "Install the latest version of *google-cloud-storage*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "install_storage"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U google-cloud-storage $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b2f8bf1a1c31"
+      },
+      "source": [
+        "Install the latest version of *google-cloud-bigquery*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fb18bb35a386"
+      },
+      "outputs": [],
+      "source": [
+        "! pip3 install -U \"google-cloud-bigquery[pandas]\" $USER_FLAG"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Restart the kernel\n",
+        "\n",
+        "After installing the packages, restart the notebook kernel."
+      ]
+    },
+    {
+      "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": "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 $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. If you are running this notebook locally, install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "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 throughout the rest of this notebook. The following 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\"}"
+      ]
+    },
+    {
+      "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, 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": "gcp_authenticate"
+      },
+      "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",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "\n",
+        "**Click Create service account**.\n",
+        "\n",
+        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "\n",
+        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "\n",
+        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "gcp_authenticate"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
+        "\n",
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "# If on Google Cloud Notebook, then don't execute this code\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "    if \"google.colab\" in sys.modules:\n",
+        "        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",
+        "        ! gcloud auth login"
+      ]
+    },
+    {
+      "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 the corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tutorial_start:automl"
+      },
+      "source": [
+        "# Tutorial\n",
+        "\n",
+        "Now you are ready to start creating your own AutoML tabular regression model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "import_file:u_dataset,bq"
+      },
+      "source": [
+        "#### Location of BigQuery training data.\n",
+        "\n",
+        "Set the `IMPORT_File` variable to the location of the data table in BigQuery."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "import_file:gsod,bq,lrg"
+      },
+      "outputs": [],
+      "source": [
+        "IMPORT_FILE = \"bigquery-public-data.samples.gsod\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "07d8e5973590"
+      },
+      "source": [
+        "#### Prepare the batch prediction data\n",
+        "\n",
+        "Create two datasets from the original data."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "63a447565c9c"
+      },
+      "outputs": [],
+      "source": [
+        "from google.cloud import bigquery\n",
+        "\n",
+        "# Create client in default region\n",
+        "bq_client = bigquery.Client(\n",
+        "    project=PROJECT_ID,\n",
+        "    credentials=aiplatform.initializer.global_config.credentials,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "56ade963c098"
+      },
+      "outputs": [],
+      "source": [
+        "# Create training dataset in default region\n",
+        "TRAINING_INPUT_DATASET_ID = f\"gsod_training_{TIMESTAMP}\"\n",
+        "bq_dataset = bigquery.Dataset(f\"{PROJECT_ID}.{TRAINING_INPUT_DATASET_ID}\")\n",
+        "bq_dataset = bq_client.create_dataset(bq_dataset)\n",
+        "print(f\"Created dataset {bq_client.project}.{bq_dataset.dataset_id}\")\n",
+        "\n",
+        "# Create test dataset in default region\n",
+        "PREDICTION_INPUT_DATASET_ID = f\"gsod_prediction_{TIMESTAMP}\"\n",
+        "bq_dataset = bigquery.Dataset(f\"{PROJECT_ID}.{PREDICTION_INPUT_DATASET_ID}\")\n",
+        "bq_dataset = bq_client.create_dataset(bq_dataset)\n",
+        "print(f\"Created dataset {bq_client.project}.{bq_dataset.dataset_id}\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5b790c91182f"
+      },
+      "outputs": [],
+      "source": [
+        "# Select top 3000 rows of dataset\n",
+        "TRAINING_SIZE = 3000\n",
+        "query = f\"\"\"\n",
+        "        SELECT *\n",
+        "        FROM {IMPORT_FILE}\n",
+        "        LIMIT {TRAINING_SIZE}\n",
+        "        \"\"\"\n",
+        "\n",
+        "TRAINING_INPUT_TABLE_ID = f\"{PROJECT_ID}.{TRAINING_INPUT_DATASET_ID}.test\"\n",
+        "job_config = bigquery.QueryJobConfig(destination=TRAINING_INPUT_TABLE_ID)\n",
+        "\n",
+        "query_job = bq_client.query(query, job_config=job_config)  # API request\n",
+        "query_job.result()  # Waits for query to finish"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8f841da4574b"
+      },
+      "outputs": [],
+      "source": [
+        "# Select a subset of the original dataset for testing\n",
+        "PREDICTION_SIZE = 100\n",
+        "query = f\"\"\"\n",
+        "        SELECT *\n",
+        "        FROM {IMPORT_FILE}\n",
+        "        LIMIT {PREDICTION_SIZE}\n",
+        "        OFFSET {TRAINING_SIZE}        \n",
+        "        \"\"\"\n",
+        "\n",
+        "PREDICTION_INPUT_TABLE_ID = f\"{PROJECT_ID}.{PREDICTION_INPUT_DATASET_ID}.prediction\"\n",
+        "job_config = bigquery.QueryJobConfig(destination=PREDICTION_INPUT_TABLE_ID)\n",
+        "\n",
+        "query_job = bq_client.query(query, job_config=job_config)  # API request\n",
+        "query_job.result()  # Waits for query to finish"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg"
+      },
+      "source": [
+        "### Create the Dataset\n",
+        "\n",
+        "Use `TabularDataset.create()` to create a `TabularDataset` resource, which takes the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Dataset` resource.\n",
+        "- `gcs_source`: A list of one or more dataset index files to import the data items into the `Dataset` resource.\n",
+        "- `bq_source`: Alternatively, import data items from a BigQuery table into the `Dataset` resource.\n",
+        "\n",
+        "This operation may take several minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_dataset:tabular,bq,lrg"
+      },
+      "outputs": [],
+      "source": [
+        "dataset = aiplatform.TabularDataset.create(\n",
+        "    display_name=\"NOAA historical weather data\" + \"_\" + TIMESTAMP,\n",
+        "    bq_source=[f\"bq://{TRAINING_INPUT_TABLE_ID}\"],\n",
+        ")\n",
+        "\n",
+        "label_column = \"mean_temp\"\n",
+        "\n",
+        "print(dataset.resource_name)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_transformations:gsod"
+      },
+      "outputs": [],
+      "source": [
+        "COLUMN_SPECS = {\n",
+        "    \"year\": \"auto\",\n",
+        "    \"month\": \"auto\",\n",
+        "    \"day\": \"auto\",\n",
+        "}\n",
+        "\n",
+        "label_column = \"mean_temp\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_automl_pipeline:tabular,lrg,transformations"
+      },
+      "source": [
+        "### Create and run training pipeline\n",
+        "\n",
+        "To train an AutoML model, create and run a training pipeline.\n",
+        "\n",
+        "#### Create training pipeline\n",
+        "\n",
+        "Create an AutoML training pipeline using the `AutoMLTabularTrainingJob` class, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `TrainingJob` resource.\n",
+        "- `optimization_prediction_type`: The type task to train the model for.\n",
+        "  - `classification`: A tabular classification model.\n",
+        "  - `regression`: A tabular regression model.\n",
+        "- `column_transformations`: (Optional): Transformations to apply to the input columns\n",
+        "- `optimization_objective`: The optimization objective (minimize or maximize).\n",
+        "  - binary classification:\n",
+        "    - `minimize-log-loss`\n",
+        "    - `maximize-au-roc`\n",
+        "    - `maximize-au-prc`\n",
+        "    - `maximize-precision-at-recall`\n",
+        "    - `maximize-recall-at-precision`\n",
+        "  - multi-class classification:\n",
+        "    - `minimize-log-loss`\n",
+        "  - regression:\n",
+        "    - `minimize-rmse`\n",
+        "    - `minimize-mae`\n",
+        "    - `minimize-rmsle`\n",
+        "\n",
+        "The instantiated object is the DAG (directed acyclic graph) for the training pipeline."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_automl_pipeline:tabular,lrg,transformations"
+      },
+      "outputs": [],
+      "source": [
+        "training_job = aiplatform.AutoMLTabularTrainingJob(\n",
+        "    display_name=\"gsod_\" + TIMESTAMP,\n",
+        "    optimization_prediction_type=\"regression\",\n",
+        "    optimization_objective=\"minimize-rmse\",\n",
+        "    column_specs=COLUMN_SPECS,\n",
+        ")\n",
+        "\n",
+        "print(training_job)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "run_automl_pipeline:tabular"
+      },
+      "source": [
+        "#### Run the training pipeline\n",
+        "\n",
+        "Run the training job by invoking the `run` method with the following parameters:\n",
+        "\n",
+        "- `dataset`: The `Dataset` resource to train the model.\n",
+        "- `model_display_name`: The human readable name for the trained model.\n",
+        "- `training_fraction_split`: The percentage of the dataset to use for training.\n",
+        "- `test_fraction_split`: The percentage of the dataset to use for test (holdout data).\n",
+        "- `validation_fraction_split`: The percentage of the dataset to use for validation.\n",
+        "- `target_column`: The name of the column to train as the label.\n",
+        "- `budget_milli_node_hours`: (optional) Maximum training time specified in unit of millihours (1000 = hour).\n",
+        "- `disable_early_stopping`: If `True`, training maybe completed before using the entire budget if the service believes it cannot further improve on the model objective measurements.\n",
+        "\n",
+        "The `run` method when completed returns the `Model` resource.\n",
+        "\n",
+        "The execution of the training pipeline will take upto 20 minutes."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "run_automl_pipeline:tabular"
+      },
+      "outputs": [],
+      "source": [
+        "model = training_job.run(\n",
+        "    dataset=dataset,\n",
+        "    model_display_name=\"gsod_\" + TIMESTAMP,\n",
+        "    training_fraction_split=0.6,\n",
+        "    validation_fraction_split=0.2,\n",
+        "    test_fraction_split=0.2,\n",
+        "    budget_milli_node_hours=1000,\n",
+        "    disable_early_stopping=False,\n",
+        "    target_column=label_column,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "source": [
+        "## Review model evaluation scores\n",
+        "After your model has finished training, you can review its evaluation scores."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "evaluate_the_model:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "# Get evaluations\n",
+        "model_evaluations = model.list_model_evaluations()\n",
+        "\n",
+        "model_evaluation = list(model_evaluations)[0]\n",
+        "print(model_evaluation)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "337625a4c33c"
+      },
+      "source": [
+        "## Send a batch prediction request\n",
+        "\n",
+        "Now you can make a batch prediction."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "93bc53cc960d"
+      },
+      "source": [
+        "### Create a results dataset\n",
+        "\n",
+        "Create a dataset to store the prediction results."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "f49e90431fcd"
+      },
+      "outputs": [],
+      "source": [
+        "# Create results dataset in default region\n",
+        "RESULTS_DATASET_ID = f\"gsod_results_{TIMESTAMP}\"\n",
+        "bq_dataset = bigquery.Dataset(f\"{PROJECT_ID}.{RESULTS_DATASET_ID}\")\n",
+        "bq_dataset = bq_client.create_dataset(bq_dataset)\n",
+        "print(f\"Created dataset {bq_client.project}.{bq_dataset.dataset_id}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "36c070503d2f"
+      },
+      "source": [
+        "### Make the batch prediction request\n",
+        "\n",
+        "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",
+        "- `instances_format`: The format for the input instances, either 'bigquery', '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",
+        "- `accelerator_type`: The hardware accelerator type.\n",
+        "- `accelerator_count`: The number of accelerators to attach to a worker replica.\n",
+        "- `sync`: If set to True, the call will block while waiting for the asynchronous batch job to complete."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bbd40d78ea46"
+      },
+      "outputs": [],
+      "source": [
+        "# Note: The bigquery_source and bigquery_destination_prefix must be in the same region\n",
+        "PREDICTION_RESULTS_DATASET_ID = f\"{PROJECT_ID}.{RESULTS_DATASET_ID}\"\n",
+        "\n",
+        "batch_predict_job = model.batch_predict(\n",
+        "    job_display_name=\"tabular_regression_batch_predict_job\",\n",
+        "    bigquery_source=f\"bq://{PREDICTION_INPUT_TABLE_ID}\",\n",
+        "    instances_format=\"bigquery\",\n",
+        "    predictions_format=\"bigquery\",\n",
+        "    bigquery_destination_prefix=f\"bq://{PREDICTION_RESULTS_DATASET_ID}\",\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4fc95aae00b0"
+      },
+      "source": [
+        "###  View the batch prediction results\n",
+        "\n",
+        "Use the BigQuery Python client to query the destination table and return results as a Pandas dataframe."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "fafe1b0f654b"
+      },
+      "outputs": [],
+      "source": [
+        "dataframe = (\n",
+        "    bq_client.query(f\"SELECT * FROM `{PREDICTION_RESULTS_DATASET_ID}.*`\")\n",
+        "    .result()\n",
+        "    .to_dataframe()\n",
+        ")\n",
+        "\n",
+        "print(dataframe.head())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "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",
+        "\n",
+        "- Model\n",
+        "- AutoML Training Job\n",
+        "- Batch Job\n",
+        "- Cloud Storage Bucket"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "3be2c2bf9146"
+      },
+      "outputs": [],
+      "source": [
+        "# Delete BigQuery datasets\n",
+        "bq_client.delete_dataset(\n",
+        "    f\"{PROJECT_ID}.{TRAINING_INPUT_DATASET_ID}\",\n",
+        "    delete_contents=True,\n",
+        "    not_found_ok=True,\n",
+        ")\n",
+        "\n",
+        "bq_client.delete_dataset(\n",
+        "    f\"{PROJECT_ID}.{PREDICTION_INPUT_DATASET_ID}\",\n",
+        "    delete_contents=True,\n",
+        "    not_found_ok=True,\n",
+        ")\n",
+        "\n",
+        "bq_client.delete_dataset(\n",
+        "    f\"{PROJECT_ID}.{RESULTS_DATASET_ID}\", delete_contents=True, not_found_ok=True\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cleanup:mbsdk"
+      },
+      "outputs": [],
+      "source": [
+        "# Delete Vertex AI resources\n",
+        "dataset.delete()\n",
+        "model.delete()\n",
+        "training_job.delete()\n",
+        "batch_predict_job.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "name": "sdk_automl_tabular_regression_batch_bq.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/custom/sdk-custom-image-classification-batch.ipynb

@@ -33,16 +33,22 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/custom/sdk-custom-image-classification-batch.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-batch.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/sdk-custom-image-classification-batch.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-batch.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
+        " <td>\n",
+        "    <a href=\"https://console.cloud.google.com/ai/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/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",
         "</table>\n",
         "<br/><br/><br/>"
       ]
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK for Python to train and deploy a custom image classification model for batch prediction."
+        "This tutorial demonstrates how to use the Vertex AI SDK for Python to train and deploy a custom image classification model for batch prediction."
       ]
     },
     {
@@ -78,14 +84,23 @@
       "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 do a prediction on 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 tutorial, you learn to use `Vertex AI Training` to create a custom trained model and use `Vertex AI Batch Prediction` to do a batch prediction on the trained model.\n",
+        "\n",
+        "\n",
+        "create a custom-trained model from a Python script in a Docker container using the Vertex AI SDK for Python, and then do a prediction on 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:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Batch Prediction`\n",
+        "- `Vertex AI Model` resource\n",
+        "\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex AI custom job for training a model.\n",
-        "- Train a TensorFlow model.\n",
-        "- Make a batch prediction.\n",
-        "- Cleanup resources."
+        "- Create a `Vertex AI` custom job for training a TensorFlow model.\n",
+        "- Upload the trained model artifacts as a `Model` resource.\n",
+        "- Make a batch prediction."
       ]
     },
     {
@@ -108,15 +123,57 @@
         "to generate a cost estimate based on your projected usage."
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a5cb73702a9b"
+      },
+      "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Workbench AI Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
+        "\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "install_aip"
       },
       "source": [
-        "## Installation\n",
+        "### Install additional packages\n",
         "\n",
-        "Install the latest (preview) version of Vertex SDK for Python."
+        "Install the following packages for executing this notebook."
       ]
     },
     {
@@ -129,84 +186,21 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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 GA version of *google-cloud-storage* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "qssss-KSlugo"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade google-cloud-storage"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_pillow"
-      },
-      "source": [
-        "Install the *pillow* library for loading images."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "vhP4dtWUlugp"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade pillow"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_numpy"
-      },
-      "source": [
-        "Install the *numpy* library for manipulation of image data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "80-_pO4olugp"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade numpy"
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-aiplatform -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install {USER_FLAG} --upgrade pillow -q\n",
+        "! pip3 install {USER_FLAG} --upgrade numpy -q"
       ]
     },
     {
@@ -287,24 +281,7 @@
       },
       "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\"}"
       ]
     },
     {
@@ -315,8 +292,56 @@
       },
       "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": "09021c90b34c"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "88dd74c4c84e"
+      },
+      "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": "5c615e53149f"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -351,7 +376,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using Workbench AI 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",
@@ -386,18 +411,19 @@
       },
       "outputs": [],
       "source": [
-        "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",
@@ -426,12 +452,7 @@
         "trained model that results from your job in the same bucket. Using this model artifact, you can then create Vertex AI model resources.\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."
       ]
     },
     {
@@ -442,8 +463,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -454,8 +475,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -475,7 +497,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -495,7 +517,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -504,9 +526,21 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9dcd3eedadfb"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import sys\n",
         "\n",
-        "Next, set up some variables used throughout the tutorial."
+        "from google.cloud import aiplatform"
       ]
     },
     {
@@ -515,9 +549,9 @@
         "id": "import_aip"
       },
       "source": [
-        "#### Import Vertex SDK for Python\n",
+        "### Initialize Vertex AI \n",
         "\n",
-        "Import the Vertex SDK for Python into your Python environment and initialize it."
+        "Initialize the Vertex AI SDK for Python for your project."
       ]
     },
     {
@@ -528,13 +562,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "from google.cloud import aiplatform\n",
-        "from google.cloud.aiplatform import gapic as aip\n",
-        "\n",
-        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -545,17 +573,18 @@
       "source": [
         "#### Set hardware accelerators\n",
         "\n",
-        "You can set hardware accelerators for both training and prediction.\n",
+        "You can set hardware accelerators for training and prediction.\n",
         "\n",
-        "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `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",
+        "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
         "\n",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "    (aiplatform.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.\n",
         "\n",
-        "*Note*: TensorFlow releases earlier than 2.3 for GPU support fail to load the custom model in this tutorial. This issue is caused by static graph operations that are generated in the serving function. This is a known issue, which is fixed in TensorFlow 2.3. If you encounter this issue with your own custom models, use a container image for TensorFlow 2.3 or later with GPU support."
+        "Learn more about [hardware accelerator support for your region](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators).\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. This 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."
       ]
     },
     {
@@ -566,9 +595,9 @@
       },
       "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)"
       ]
     },
     {
@@ -579,9 +608,11 @@
       "source": [
         "#### Set pre-built containers\n",
         "\n",
-        "Vertex AI provides pre-built containers to run training and prediction.\n",
+        "Set the pre-built Docker container image for training and prediction.\n",
         "\n",
-        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers) and [Pre-built containers for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers)"
+        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/ai-platform-unified/docs/training/pre-built-containers).\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
       ]
     },
     {
@@ -595,8 +626,12 @@
         "TRAIN_VERSION = \"tf-gpu.2-1\"\n",
         "DEPLOY_VERSION = \"tf2-gpu.2-1\"\n",
         "\n",
-        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
         "\n",
         "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
         "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
@@ -701,7 +736,7 @@
       "outputs": [],
       "source": [
         "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, JOB_NAME)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
         "    TRAIN_STRATEGY = \"single\"\n",
@@ -1022,7 +1057,7 @@
         "BATCH_PREDICTION_INSTANCES_FILE = \"batch_prediction_instances.jsonl\"\n",
         "\n",
         "BATCH_PREDICTION_GCS_SOURCE = (\n",
-        "    BUCKET_NAME + \"/batch_prediction_instances/\" + BATCH_PREDICTION_INSTANCES_FILE\n",
+        "    BUCKET_URI + \"/batch_prediction_instances/\" + BATCH_PREDICTION_INSTANCES_FILE\n",
         ")\n",
         "\n",
         "# Write instances at JSONL\n",
@@ -1082,7 +1117,7 @@
         "DESTINATION_FOLDER = \"batch_prediction_results\"\n",
         "\n",
         "# The Cloud Storage bucket to upload results to\n",
-        "BATCH_PREDICTION_GCS_DEST_PREFIX = BUCKET_NAME + \"/\" + DESTINATION_FOLDER\n",
+        "BATCH_PREDICTION_GCS_DEST_PREFIX = BUCKET_URI + \"/\" + DESTINATION_FOLDER\n",
         "\n",
         "# Make SDK batch_predict method call\n",
         "batch_prediction_job = model.batch_predict(\n",
@@ -1132,10 +1167,10 @@
         "\n",
         "# Get most recently modified directory\n",
         "latest_directory = max(\n",
-        "    [\n",
+        "    (\n",
         "        os.path.join(RESULTS_DIRECTORY_FULL, d)\n",
         "        for d in os.listdir(RESULTS_DIRECTORY_FULL)\n",
-        "    ],\n",
+        "    ),\n",
         "    key=os.path.getmtime,\n",
         ")\n",
         "\n",
@@ -1225,8 +1260,8 @@
         "# Delete the model\n",
         "model.delete()\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil -m rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/custom/sdk-custom-image-classification-online.ipynb

@@ -33,16 +33,22 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/custom/sdk-custom-image-classification-online.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-online.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/sdk-custom-image-classification-online.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/custom/sdk-custom-image-classification-online.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/main/notebooks/official/custom/sdk-custom-image-classification-online.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/>"
       ]
@@ -56,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK for Python to train and deploy a custom image classification model for online prediction."
+        "This tutorial demonstrates how to use the Vertex AI SDK for Python to train and deploy a custom image classification model for online prediction."
       ]
     },
     {
@@ -78,12 +84,20 @@
       "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 do a prediction on 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 tutorial, you learn to use `Vertex AI Training` to create a custom-trained model from a Python script in a Docker container, and learn to use `Vertex AI Prediction` to do a prediction on 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:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Prediction`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex AI custom job for training a model.\n",
-        "- Train a TensorFlow model.\n",
+        "- Create a `Vertex AI` custom job for training a TensorFlow model.\n",
+        "- Upload the trained model artifacts to a `Model` resource.\n",
+        "- Create a serving `Endpoint` resource.\n",
         "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
         "- Make a prediction.\n",
         "- Undeploy the `Model` resource."
@@ -117,7 +131,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest (preview) version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -130,84 +144,21 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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 GA version of *google-cloud-storage* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "qssss-KSlugo"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade google-cloud-storage"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_pillow"
-      },
-      "source": [
-        "Install the *pillow* library for loading images."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "vhP4dtWUlugp"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade pillow"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_numpy"
-      },
-      "source": [
-        "Install the *numpy* library for manipulation of image data."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "80-_pO4olugp"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade numpy"
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "! pip3 install {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install {USER_FLAG} --upgrade pillow -q\n",
+        "! pip3 install {USER_FLAG} --upgrade numpy -q"
       ]
     },
     {
@@ -288,24 +239,7 @@
       },
       "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\"}"
       ]
     },
     {
@@ -316,8 +250,56 @@
       },
       "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": "250cb8c648d5"
+      },
+      "outputs": [],
+      "source": [
+        "! gcloud config set project $PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2aa333eca058"
+      },
+      "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": "d8b34ef9a3d0"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -352,7 +334,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already\n",
+        "**If you are using Workbench AI 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",
@@ -387,19 +369,19 @@
       },
       "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",
@@ -430,12 +412,7 @@
         "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."
       ]
     },
     {
@@ -446,8 +423,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -458,8 +435,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -479,7 +457,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -499,7 +477,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -510,7 +488,23 @@
       "source": [
         "### Set up variables\n",
         "\n",
-        "Next, set up some variables used throughout the tutorial."
+        "Next, set up some variables used throughout the tutorial.\n",
+        "\n",
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8a9846bc4a2e"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import sys\n",
+        "\n",
+        "from google.cloud import aiplatform"
       ]
     },
     {
@@ -519,9 +513,9 @@
         "id": "import_aip"
       },
       "source": [
-        "#### Import Vertex SDK for Python\n",
+        "### Initialize Vertex AI SDK for Python\n",
         "\n",
-        "Import the Vertex SDK for Python into your Python environment and initialize it."
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
       ]
     },
     {
@@ -532,13 +526,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "from google.cloud import aiplatform\n",
-        "from google.cloud.aiplatform import gapic as aip\n",
-        "\n",
-        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_NAME)"
+        "aiplatform.init(project=PROJECT_ID, location=REGION, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -553,7 +541,7 @@
         "\n",
         "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `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",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\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",
@@ -570,9 +558,9 @@
       },
       "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)"
       ]
     },
     {
@@ -583,9 +571,14 @@
       "source": [
         "#### Set pre-built containers\n",
         "\n",
-        "Vertex AI provides pre-built containers to run training and prediction.\n",
         "\n",
-        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/vertex-ai/docs/training/pre-built-containers) and [Pre-built containers for prediction](https://cloud.google.com/vertex-ai/docs/predictions/pre-built-containers)"
+        "Set the pre-built Docker container image for training and prediction.\n",
+        "\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for training](https://cloud.google.com/ai-platform-unified/docs/training/pre-built-containers).\n",
+        "\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
       ]
     },
     {
@@ -599,8 +592,12 @@
         "TRAIN_VERSION = \"tf-gpu.2-1\"\n",
         "DEPLOY_VERSION = \"tf2-gpu.2-1\"\n",
         "\n",
-        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
         "\n",
         "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
         "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
@@ -705,7 +702,7 @@
       "outputs": [],
       "source": [
         "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, JOB_NAME)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
         "    TRAIN_STRATEGY = \"single\"\n",
@@ -1185,8 +1182,8 @@
         "# Delete the endpoint\n",
         "endpoint.delete()\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil -m rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_batch_explain.ipynb

@@ -33,18 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_binary_classification_batch_explain.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_automl_tabular_binary_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/tree/master/notebooks/official/automl/sdk_automl_tabular_binary_classification_batch_explain.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/explainable_ai/sdk_automl_tabular_binary_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/platform/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_binary_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/tree/main/notebooks/official/explainable_ai/sdk_automl_tabular_binary_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",
         "  </td>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex 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."
+        "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."
       ]
     },
     {
@@ -83,13 +84,21 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML tabular binary classification model from a Python script, and send a batch prediction request with explainability 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 learn to use `AutoML` to create a tabular binary classification model from a Python script, and then learn to use `Vertex AI Batch Prediction` to make predictions with explanations. 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:\n",
+        "\n",
+        "- `Vertex AI AutoML`\n",
+        "- `Vertex AI Batch Prediction`\n",
+        "- `Vertex Explainable AI`\n",
+        "- `Vertex AI Model` resource\n",
+        "\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex `Dataset` resource.\n",
-        "- Train the model.\n",
-        "- View the model evaluation.\n",
+        "- Create a `Vertex Dataset` resource.\n",
+        "- Train an `AutoML` tabular binary classification model.\n",
+        "- View the model evaluation metrics for the trained model.\n",
         "- Make a batch prediction request with explainability.\n",
         "\n",
         "There is one key difference between using batch prediction and using online prediction:\n",
@@ -127,7 +136,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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 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",
@@ -160,7 +169,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -173,45 +182,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $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 {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install --upgrade tensorflow $USER_FLAG"
       ]
     },
     {
@@ -373,23 +357,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Workbench AI 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."
       ]
     },
     {
@@ -408,8 +400,11 @@
         "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",
@@ -432,7 +427,7 @@
         "\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."
       ]
@@ -445,7 +440,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -456,8 +452,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -477,7 +474,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -497,7 +494,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -529,9 +526,9 @@
         "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."
       ]
     },
     {
@@ -542,7 +539,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -750,9 +747,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -763,18 +759,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=bank_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -831,7 +819,7 @@
         "\n",
         "! cut -d, -f1-16 tmp.csv > batch.csv\n",
         "\n",
-        "gcs_input_uri = BUCKET_NAME + \"/test.csv\"\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.csv\"\n",
         "\n",
         "! gsutil cp batch.csv $gcs_input_uri"
       ]
@@ -866,7 +854,7 @@
         "batch_predict_job = model.batch_predict(\n",
         "    job_display_name=\"bank_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_NAME,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
         "    instances_format=\"csv\",\n",
         "    predictions_format=\"csv\",\n",
         "    generate_explanation=True,\n",
@@ -950,17 +938,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -971,60 +949,14 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Set this to true only if you'd like to delete your bucket\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "model.delete()\n",
+        "batch_predict_job.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_automl_tabular_classification_online_explain.ipynb

@@ -33,18 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_classification_online_explain.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_classification_online_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/tree/master/notebooks/official/automl/sdk_automl_tabular_classification_online_explain.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_automl_tabular_classification_online_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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_automl_tabular_classification_online_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/tree/main/notebooks/official/explainable_ai/sdk_automl_tabular_binary_classification_online_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",
         "  </td>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to create tabular classification models and do online prediction with explanation using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
+        "This tutorial demonstrates how to use the Vertex AI SDK to create tabular classification models and do online prediction with explanation using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
       ]
     },
     {
@@ -83,16 +84,25 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML tabular classification model and deploy for online prediction with explainability from a Python script 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 learn to use `AutoML` to create a tabular binary classification model from a Python script, and then learn to use `Vertex AI Online Prediction` to make online predictions with explanations. 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:\n",
+        "\n",
+        "- `Vertex AI AutoML`\n",
+        "- `Vertex AI Prediction`\n",
+        "- `Vertex Explainable AI`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex `Dataset` resource.\n",
-        "- Train the model.\n",
-        "- View the model evaluation.\n",
+        "- Create a `Vertex Dataset` resource.\n",
+        "- Train an `AutoML` tabular binary classification model.\n",
+        "- View the model evaluation metrics for the trained model.\n",
+        "- Create a serving `Endpoint` resource.\n",
         "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
-        "- Make a prediction request with explainability.\n",
-        "- Undeploy the Model."
+        "- Make an online prediction request with explainability.\n",
+        "- Undeploy the `Model` resource."
       ]
     },
     {
@@ -123,7 +133,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -156,7 +166,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -169,67 +179,23 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_tabulate"
-      },
-      "source": [
-        "Install the latest GA version of *Tabulate* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tabulate"
-      },
-      "outputs": [],
-      "source": [
+        "# 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 {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install --upgrade tensorflow $USER_FLAG\n",
         "! pip3 install -U tabulate $USER_FLAG"
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -389,23 +355,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Workbench AI 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."
       ]
     },
     {
@@ -424,8 +398,11 @@
         "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",
@@ -448,7 +425,7 @@
         "\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."
       ]
@@ -461,7 +438,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -472,8 +450,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -493,7 +472,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -513,7 +492,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -545,9 +524,9 @@
         "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."
       ]
     },
     {
@@ -558,7 +537,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -766,9 +745,8 @@
       },
       "source": [
         "## Review model evaluation scores\n",
-        "After your model has finished training, you can review the evaluation scores for it.\n",
         "\n",
-        "First, you need to get a reference to the new model. As with datasets, you can either use the reference to the model variable you created when deployed the model or you can list all of the models in your project."
+        "After your model training has finished, you can review the evaluation scores for it using the `list_model_evaluations()` method. This method will return an iterator for each evaluation slice."
       ]
     },
     {
@@ -779,18 +757,10 @@
       },
       "outputs": [],
       "source": [
-        "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=iris_\" + TIMESTAMP)\n",
+        "model_evaluations = model.list_model_evaluations()\n",
         "\n",
-        "# Get a reference to the Model Service client\n",
-        "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
-        "model_service_client = aip.gapic.ModelServiceClient(client_options=client_options)\n",
-        "\n",
-        "model_evaluations = model_service_client.list_model_evaluations(\n",
-        "    parent=models[0].resource_name\n",
-        ")\n",
-        "model_evaluation = list(model_evaluations)[0]\n",
-        "print(model_evaluation)"
+        "for model_evaluation in model_evaluations:\n",
+        "    print(model_evaluation.to_dict())"
       ]
     },
     {
@@ -1087,17 +1057,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1108,60 +1068,14 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "model.delete()\n",
+        "endpoint.delete()\n",
+        "dataset.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_custom_image_classification_batch_explain.ipynb

@@ -33,18 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/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/automl/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/tree/master/notebooks/official/automl/sdk_custom_image_classification_batch_explain.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/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/tree/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",
         "  </td>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to train and deploy a custom image classification model for batch prediction with explanation."
+        "This tutorial demonstrates how to use the Vertex AI SDK to train and deploy a custom image classification model for batch prediction with explanation."
       ]
     },
     {
@@ -83,16 +84,21 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create a custom model, with a training pipeline, from a Python script in a Google prebuilt Docker container using the Vertex SDK, and then do a batch prediction with explanations on the uploaded model.  You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "In this tutorial, you learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Batch Prediction` to make a batch prediction request with explanations. You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Batch Prediction`\n",
+        "- `Vertex Explainable AI`\n",
+        "- `Vertex AI Model` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex custom job for training a model.\n",
-        "- Train the TensorFlow model.\n",
-        "- Retrieve and load the model artifacts.\n",
-        "- View the model evaluation.\n",
-        "- Set explanation parameters.\n",
-        "- Upload the model as a Vertex `Model` resource.\n",
+        "- Create a `Vertex AI` custom job for training a TensorFlow model.\n",
+        "- View the model evaluation for the trained model.\n",
+        "- Set explanation parameters for when the model is deployed.\n",
+        "- Upload the trained model artifacts and explanation parameters as a `Model` resource.\n",
         "- Make a batch prediction with explanations."
       ]
     },
@@ -124,7 +130,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -157,7 +163,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -170,55 +176,21 @@
       "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\") 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",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
+        "\n",
+        "! 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",
         "\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"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_cv2"
-      },
-      "outputs": [],
-      "source": [
         "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",
@@ -384,23 +356,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Workbench AI 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."
       ]
     },
     {
@@ -419,8 +399,11 @@
         "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",
@@ -456,7 +439,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -467,8 +451,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -488,7 +473,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -508,7 +493,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -540,9 +525,9 @@
         "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."
       ]
     },
     {
@@ -553,7 +538,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -568,7 +553,7 @@
         "\n",
         "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
         "\n",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "    (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
         "\n",
         "\n",
         "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
@@ -631,7 +616,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2-1\"\n",
+        "    TF = \"2-5\"\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -652,8 +637,13 @@
         "    else:\n",
         "        DEPLOY_VERSION = \"tf-cpu.{}\".format(TF)\n",
         "\n",
-        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
+        "\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
         "\n",
         "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
         "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
@@ -1727,17 +1717,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1748,60 +1728,14 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "model.delete()\n",
+        "batch_predict_job.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
         "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_NAME"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_custom_image_classification_online_explain.ipynb

@@ -33,18 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_custom_image_classification_online_explain.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_custom_image_classification_online_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/tree/master/notebooks/official/automl/sdk_custom_image_classification_online_explain.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_custom_image_classification_online_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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_custom_image_classification_online_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/tree/main/notebooks/official/explainable_ai/sdk_custom_image_classification_online_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",
         "  </td>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to train and deploy a custom image classification model for online prediction with explanation."
+        "This tutorial demonstrates how to use the Vertex AI SDK to train and deploy a custom image classification model for online prediction with explanation."
       ]
     },
     {
@@ -83,16 +84,23 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create a custom model from a Python script in a Google prebuilt Docker container using the Vertex SDK, and then do a prediction with explanations on the deployed model by sending data. You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "In this tutorial, you learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Prediction` to make an online prediction request with explanations. You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Online Prediction`\n",
+        "- `Vertex Explainable AI`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex custom job for training a model.\n",
-        "- Train a TensorFlow model.\n",
-        "- Retrieve and load the model artifacts.\n",
-        "- View the model evaluation.\n",
-        "- Set explanation parameters.\n",
-        "- Upload the model as a Vertex `Model` resource.\n",
+        "- Create a `Vertex AI` custom job for training a TensorFlow model.\n",
+        "- View the model evaluation for the trained model.\n",
+        "- Set explanation parameters for when the model is deployed.\n",
+        "- Upload the trained model artifacts and explanations as a `Model` resource.\n",
+        "- Create a serving `Endpoint` resource.\n",
         "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
         "- Make a prediction with explanation.\n",
         "- Undeploy the `Model` resource."
@@ -126,7 +134,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -159,7 +167,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -172,59 +180,25 @@
       "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\") 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",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
+        "\n",
+        "! 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",
         "\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"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_cv2"
-      },
-      "outputs": [],
-      "source": [
         "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"
+        "    ! pip3 install --upgrade opencv-python-headless $USER_FLAG -q"
       ]
     },
     {
@@ -386,23 +360,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Workbench AI 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."
       ]
     },
     {
@@ -421,8 +403,11 @@
         "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",
@@ -458,7 +443,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -469,8 +455,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -490,7 +477,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -510,7 +497,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -542,9 +529,9 @@
         "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."
       ]
     },
     {
@@ -555,7 +542,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -570,7 +557,7 @@
         "\n",
         "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
         "\n",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "    (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
         "\n",
         "\n",
         "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
@@ -633,7 +620,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2-1\"\n",
+        "    TF = \"2-5\"\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -654,8 +641,12 @@
         "    else:\n",
         "        DEPLOY_VERSION = \"tf-cpu.{}\".format(TF)\n",
         "\n",
-        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
         "\n",
         "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
         "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
@@ -932,7 +923,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_cifar10.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_cifar10.tar.gz"
       ]
     },
     {
@@ -1000,7 +991,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -1767,17 +1758,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1788,60 +1769,13 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "endpoint.delete()\n",
+        "model.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_custom_tabular_regression_batch_explain.ipynb

@@ -33,18 +33,19 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_custom_tabular_regression_batch_explain.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_custom_tabular_regression_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/tree/master/notebooks/official/automl/sdk_custom_tabular_regression_batch_explain.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/automl/sdk_custom_tabular_regression_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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_custom_tabular_regression_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/tree/main/notebooks/official/explainable_ai/sdk_custom_tabular_regression_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",
         "  </td>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to train and deploy a custom tabular regression model for batch prediction with explanation."
+        "This tutorial demonstrates how to use the Vertex AI SDK to train and deploy a custom tabular regression model for batch prediction with explanation."
       ]
     },
     {
@@ -83,16 +84,22 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create a custom model, with a training pipeline, from a Python script in a Google prebuilt Docker container using the Vertex SDK, and then do a batch prediction with explanations on the uploaded model.  You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "In this tutorial, you learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Batch Prediction` to make a batch prediction request with explanations.  You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Batch Prediction`\n",
+        "- `Vertex Explainable AI`\n",
+        "- `Vertex AI Model` resource\n",
+        "\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex custom job for training a model.\n",
-        "- Train the TensorFlow model.\n",
-        "- Retrieve and load the model artifacts.\n",
-        "- View the model evaluation.\n",
-        "- Set explanation parameters.\n",
-        "- Upload the model as a Vertex `Model` resource.\n",
+        "- Create a `Vertex AI` custom job for training a TensorFlow model.\n",
+        "- View the model evaluation for the trained model.\n",
+        "- Set explanation parameters for when the model is deployed.\n",
+        "- Upload the trained model artifacts and explanations as a `Model` resource.\n",
         "- Make a batch prediction with explanations."
       ]
     },
@@ -124,7 +131,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -146,7 +153,7 @@
         "\n",
         "5. Run `jupyter notebook` on the command line in a terminal shell to launch Jupyter.\n",
         "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+        "6. Open this notebook in the Jupyter Notebook Dashboard."
       ]
     },
     {
@@ -157,7 +164,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -170,45 +177,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $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 {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install --upgrade tensorflow $USER_FLAG -q"
       ]
     },
     {
@@ -370,23 +352,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Workbench AI 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."
       ]
     },
     {
@@ -405,8 +395,11 @@
         "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",
@@ -442,7 +435,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -453,8 +447,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -474,7 +469,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -494,7 +489,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -526,9 +521,9 @@
         "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."
       ]
     },
     {
@@ -539,7 +534,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -554,7 +549,7 @@
         "\n",
         "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
         "\n",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "    (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
         "\n",
         "\n",
         "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
@@ -617,7 +612,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2-1\"\n",
+        "    TF = \"2-5\"\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -629,17 +624,17 @@
         "    else:\n",
         "        DEPLOY_VERSION = \"tf2-cpu.{}\".format(TF)\n",
         "else:\n",
-        "    if TRAIN_GPU:\n",
-        "        TRAIN_VERSION = \"tf-gpu.{}\".format(TF)\n",
-        "    else:\n",
-        "        TRAIN_VERSION = \"tf-cpu.{}\".format(TF)\n",
         "    if DEPLOY_GPU:\n",
         "        DEPLOY_VERSION = \"tf-gpu.{}\".format(TF)\n",
         "    else:\n",
         "        DEPLOY_VERSION = \"tf-cpu.{}\".format(TF)\n",
         "\n",
-        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
         "\n",
         "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
         "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
@@ -920,7 +915,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -988,7 +983,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -1474,7 +1469,7 @@
         "\n",
         "! cut -d, -f1-16 tmp.csv > batch.csv\n",
         "\n",
-        "gcs_input_uri = BUCKET_NAME + \"/test.csv\"\n",
+        "gcs_input_uri = BUCKET_URI + \"/test.csv\"\n",
         "\n",
         "! gsutil cp batch.csv $gcs_input_uri"
       ]
@@ -1512,7 +1507,7 @@
         "batch_predict_job = model.batch_predict(\n",
         "    job_display_name=\"boston_\" + TIMESTAMP,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_NAME,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
         "    instances_format=\"csv\",\n",
         "    predictions_format=\"jsonl\",\n",
         "    machine_type=DEPLOY_COMPUTE,\n",
@@ -1601,17 +1596,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1622,60 +1607,16 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "model.delete()\n",
+        "try:\n",
+        "    batch_predict_job.delete()\n",
+        "except Exception as e:\n",
+        "    print(e)\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/explainable_ai/sdk_custom_tabular_regression_online_explain.ipynb

@@ -44,7 +44,8 @@
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/tree/master/notebooks/official/automl/sdk_custom_tabular_regression_online_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/tree/main/notebooks/official/explainable_ai/sdk_custom_tabular_regression_online_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",
         "  </td>\n",
@@ -61,7 +62,7 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use the Vertex SDK to train and deploy a custom tabular regression model for online prediction with explanation."
+        "This tutorial demonstrates how to use the Vertex AI SDK to train and deploy a custom tabular regression model for online prediction with explanation."
       ]
     },
     {
@@ -83,16 +84,23 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create a custom model from a Python script in a Google prebuilt Docker container using the Vertex SDK, and then do a prediction with explanations on the deployed model by sending data. You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "In this tutorial, you learn to use `Vertex AI Training and Explainable AI` to create a custom image classification model with explanations, and then you learn to use `Vertex AI Prediction` to make an online prediction request with explanations.  You can alternatively create custom models using `gcloud` command-line tool or online using Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Training`\n",
+        "- `Vertex AI Prediction`\n",
+        "- `Vertex Explainable AI`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a Vertex custom job for training a model.\n",
-        "- Train a TensorFlow model.\n",
-        "- Retrieve and load the model artifacts.\n",
-        "- View the model evaluation.\n",
-        "- Set explanation parameters.\n",
-        "- Upload the model as a Vertex `Model` resource.\n",
+        "- Create a `Vertex AI` custom job for training a TensorFlow model.\n",
+        "- View the model evaluation for the trained model.\n",
+        "- Set explanation parameters for when the model is deployed.\n",
+        "- Upload the trained model artifacts and explanations as a `Model` resource.\n",
+        "- Create a serving `Endpoint` resource.\n",
         "- Deploy the `Model` resource to a serving `Endpoint` resource.\n",
         "- Make a prediction with explanation.\n",
         "- Undeploy the `Model` resource."
@@ -126,7 +134,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -159,7 +167,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -172,45 +180,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_tensorflow"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade tensorflow $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 {USER_FLAG} --upgrade google-cloud-storage -q\n",
+        "! pip3 install --upgrade tensorflow $USER_FLAG -q"
       ]
     },
     {
@@ -372,23 +355,31 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Workbench AI 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."
       ]
     },
     {
@@ -407,8 +398,11 @@
         "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",
@@ -444,7 +438,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -455,8 +450,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -476,7 +472,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -496,7 +492,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -528,9 +524,9 @@
         "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."
       ]
     },
     {
@@ -541,7 +537,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -556,7 +552,7 @@
         "\n",
         "Set the variables `TRAIN_GPU/TRAIN_NGPU` and `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Telsa K80 GPUs allocated to each VM, you would specify:\n",
         "\n",
-        "    (aip.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "    (aip.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
         "\n",
         "\n",
         "Otherwise specify `(None, None)` to use a container image to run on a CPU.\n",
@@ -619,7 +615,7 @@
         "if os.getenv(\"IS_TESTING_TF\"):\n",
         "    TF = os.getenv(\"IS_TESTING_TF\")\n",
         "else:\n",
-        "    TF = \"2-1\"\n",
+        "    TF = \"2-5\"\n",
         "\n",
         "if TF[0] == \"2\":\n",
         "    if TRAIN_GPU:\n",
@@ -640,8 +636,12 @@
         "    else:\n",
         "        DEPLOY_VERSION = \"tf-cpu.{}\".format(TF)\n",
         "\n",
-        "TRAIN_IMAGE = \"gcr.io/cloud-aiplatform/training/{}:latest\".format(TRAIN_VERSION)\n",
-        "DEPLOY_IMAGE = \"gcr.io/cloud-aiplatform/prediction/{}:latest\".format(DEPLOY_VERSION)\n",
+        "TRAIN_IMAGE = \"{}-docker.pkg.dev/vertex-ai/training/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], TRAIN_VERSION\n",
+        ")\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
         "\n",
         "print(\"Training:\", TRAIN_IMAGE, TRAIN_GPU, TRAIN_NGPU)\n",
         "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
@@ -922,7 +922,7 @@
         "! rm -f custom.tar custom.tar.gz\n",
         "! tar cvf custom.tar custom\n",
         "! gzip custom.tar\n",
-        "! gsutil cp custom.tar.gz $BUCKET_NAME/trainer_boston.tar.gz"
+        "! gsutil cp custom.tar.gz $BUCKET_URI/trainer_boston.tar.gz"
       ]
     },
     {
@@ -990,7 +990,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
         "\n",
         "EPOCHS = 20\n",
         "STEPS = 100\n",
@@ -1733,17 +1733,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- AutoML Training Job\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -1754,60 +1744,13 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "endpoint.delete()\n",
+        "model.delete()\n",
         "\n",
-        "    # Delete the model using the Vertex model object\n",
-        "    try:\n",
-        "        if \"model\" in globals():\n",
-        "            model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the endpoint using the Vertex endpoint object\n",
-        "    try:\n",
-        "        if \"endpoint\" in globals():\n",
-        "            endpoint.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the AutoML or Pipeline trainig job\n",
-        "    try:\n",
-        "        if \"dag\" in globals():\n",
-        "            dag.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the custom trainig job\n",
-        "    try:\n",
-        "        if \"job\" in globals():\n",
-        "            job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the batch prediction job using the Vertex batch prediction object\n",
-        "    try:\n",
-        "        if \"batch_predict_job\" in globals():\n",
-        "            batch_predict_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    # Delete the hyperparameter tuning job using the Vertex hyperparameter tuning object\n",
-        "    try:\n",
-        "        if \"hpt_job\" in globals():\n",
-        "            hpt_job.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "\n",
-        "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

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

@@ -675,14 +675,68 @@
         "    print(e)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "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."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "9kiqrBN6E28r"
+      },
+      "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",
+        "\n",
+        "v1beta1_admin_client = v1beta1_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",
+        "            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",
+        "                ),\n",
+        "                numerical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
+        "                ),\n",
+        "                categorical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
+        "                ),\n",
+        "            ),\n",
+        "        ),\n",
+        "    )\n",
+        ")"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "85b1f59fbf6d"
       },
       "source": [
-        "Feature [monitoring](https://cloud.google.com/vertex-ai/docs/featurestore/monitoring) is in preview, so you need to use v1beta1 Python. The easiest way to set this 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",
-        "\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 v1beta1 SDK.\n",
         "\n",
         "You can view monitoring statistics on [console UI](https://console.cloud.google.com/vertex-ai/features)."
       ]
@@ -708,7 +762,7 @@
         "    client_options={\"api_endpoint\": API_ENDPOINT}\n",
         ")\n",
         "\n",
-        "# Enable monitoring for users entity type.\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",
@@ -719,6 +773,13 @@
         "            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",
+        "                    staleness_days=30,\n",
+        "                ),\n",
+        "                numerical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
+        "                ),\n",
+        "                categorical_threshold_config=v1beta1_featurestore_monitoring_pb2.FeaturestoreMonitoringConfig.ThresholdConfig(\n",
+        "                    value=0.001,\n",
         "                ),\n",
         "            ),\n",
         "        ),\n",
@@ -754,6 +815,7 @@
         "                feature=feature_pb2.Feature(\n",
         "                    value_type=feature_pb2.Feature.ValueType.INT64,\n",
         "                    description=\"User age\",\n",
+        "                    disable_monitoring=False,\n",
         "                ),\n",
         "                feature_id=\"age\",\n",
         "            ),\n",
@@ -761,6 +823,8 @@
         "                feature=feature_pb2.Feature(\n",
         "                    value_type=feature_pb2.Feature.ValueType.STRING,\n",
         "                    description=\"User gender\",\n",
+        "                    # Default is False. If True, Feature 'gender' monitoring analysis is disabled.\n",
+        "                    disable_monitoring=True,\n",
         "                ),\n",
         "                feature_id=\"gender\",\n",
         "            ),\n",
@@ -1030,6 +1094,8 @@
         "    ],\n",
         "    feature_time_field=\"update_time\",\n",
         "    worker_count=1,\n",
+        "    # Default is False. If True, the import feature analysis won't happen for this specific operation.\n",
+        "    disable_ingestion_analysis=False,\n",
         ")"
       ]
     },
@@ -1438,9 +1504,7 @@
   ],
   "metadata": {
     "colab": {
-      "collapsed_sections": [
-        "ze4-nDLfK4pw"
-      ],
+      "collapsed_sections": [],
       "name": "gapic-feature-store.ipynb",
       "toc_visible": true
     },

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

@@ -31,7 +31,7 @@
       "source": [
         "<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/community/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",
@@ -66,12 +66,20 @@
         "\n",
         "### Objective\n",
         "\n",
-        "In this notebook, you will learn how to:\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",
         "\n",
-        "    * Create featurestore, entity type, and feature resources. \n",
-        "    * Import your features into Vertex AI Feature Store.\n",
-        "    * Serve online prediction requests using the imported features.\n",
-        "    * Access imported features in offline jobs, such as training jobs.\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\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",
         "\n",
         "### Costs \n",
         "\n",
@@ -152,9 +160,9 @@
         "id": "i7EUnXsZhAGF"
       },
       "source": [
-        "### Install additional packages\n",
+        "## Installation\n",
         "\n",
-        "For this notebook, you need the Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -167,24 +175,18 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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": "wyy5Lbnzg5fi"
-      },
-      "outputs": [],
-      "source": [
-        "! pip install {USER_FLAG} --upgrade google-cloud-aiplatform"
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -260,24 +262,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -290,7 +275,76 @@
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
         "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "print(\"Project ID: \", PROJECT_ID)"
+        "    # 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": "250cb8c648d5"
+      },
+      "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 = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "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\")"
       ]
     },
     {
@@ -343,19 +397,19 @@
       },
       "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",
@@ -385,18 +439,11 @@
       },
       "outputs": [],
       "source": [
-        "from google.cloud import aiplatform\n",
         "from google.cloud.aiplatform import Feature, Featurestore\n",
         "\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\"\n",
-        "\n",
         "FEATURESTORE_ID = \"movie_prediction\"\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\n",
-        "\n",
-        "aiplatform.init(project=PROJECT_ID, location=REGION)"
+        "ONLINE_STORE_FIXED_NODE_COUNT = 1"
       ]
     },
     {

notebooks/official/matching_engine/two-tower-model-introduction.ipynb

@@ -796,7 +796,7 @@
         "\n",
         "    ```\n",
         "    export TENSORBOARD_DIR=gs://xxxxx/tensorboard\n",
-        "    tensorboard --logdir=${TENSORBOARD_DIR} --port=8080\n",
+        "    tensorboard --logdir=${TENSORBOARD_DIR} --port=8080 --load_fast=false\n",
         "    ```\n",
         "\n",
         "2. Click the \"Web Preview\" button at the top-right of the Cloud Shell window (looks like an eye in a rectangle). \n",
@@ -1049,6 +1049,7 @@
       },
       "outputs": [],
       "source": [
+        "import json\n",
         "request = json.dumps({\"instances\": input_items})\n",
         "with open(\"request.json\", \"w\") as writer:\n",
         "    writer.write(f\"{request}\\n\")\n",

notebooks/official/migration/UJ15 Vertex SDK AutoML Object Tracking.ipynb

@@ -33,12 +33,12 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ15%20Vertex%20SDK%20AutoML%20Object%20Tracking.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/ai-platform-samples/blob/main/vertex-ai-samples/tree/master/notebooks/official/migration/UJ15%20Vertex%20SDK%20AutoML%20Object%20Tracking.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/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ15%20Vertex%20SDK%20AutoML%20Object%20Tracking.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/ai-platform-samples/blob/master/vertex-ai-samples/blob/main/notebooks/official/migration/UJ15%20Vertex%20SDK%20AutoML%20Object%20Tracking.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",
@@ -55,7 +55,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Traffic](https://todo) from [??](todo). The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+        "The dataset used for this tutorial is the Traffic. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
       ]
     },
     {

notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.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/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.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/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.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/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.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",
@@ -68,17 +68,24 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook demonstrates how to track metrics and parameters for Vertex AI custom training jobs, and how to perform detailed analysis using this data.\n",
+        "This notebook demonstrates how to track metrics and parameters for `Vertex AI` custom training jobs, and how to perform detailed analysis using this data.\n",
         "\n",
         "### Dataset\n",
         "\n",
         "This example uses the Abalone Dataset. For more information about this dataset please visit: https://archive.ics.uci.edu/ml/datasets/abalone\n",
         "### Objective\n",
         "\n",
-        "In this notebook, you will learn how to use Vertex AI SDK for Python to:\n",
+        "In this notebook, you learn how to use `Vertex ML Metadata` to track training parameters and evaluation metrics.\n",
         "\n",
-        "    * Track training parameters and prediction metrics for a custom training job.\n",
-        "    * Extract and perform analysis for all parameters and metrics within an Experiment.\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex ML Metadata`\n",
+        "- `Vertex AI Experiments`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Track parameters and metrics for a `Vertex AI` custom trained model.\n",
+        "- Extract and perform analysis for all parameters and metrics within an Experiment.\n",
         "\n",
         "### Costs \n",
         "\n",
@@ -165,26 +172,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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": "qblyW_dcyOQA"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U tensorflow $USER_FLAG\n",
-        "! python3 -m pip install {USER_FLAG} google-cloud-aiplatform --upgrade\n",
-        "! pip3 install scikit-learn {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 tensorflow $USER_FLAG -q\n",
+        "! pip3 install scikit-learn {USER_FLAG} -q"
       ]
     },
     {
@@ -273,24 +274,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -302,16 +286,11 @@
       "outputs": [],
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "XsnuGoJM9mUw"
-      },
-      "source": [
-        "Set gcloud config to your project ID."
+        "    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)"
       ]
     },
     {
@@ -325,6 +304,37 @@
         "!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 = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -408,6 +418,7 @@
         "# requests.\n",
         "\n",
         "# If on Google Cloud Notebooks, 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\"):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
@@ -440,12 +451,7 @@
         "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."
       ]
     },
     {
@@ -456,8 +462,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -468,11 +474,9 @@
       },
       "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-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {

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

@@ -32,12 +32,12 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
@@ -76,10 +76,17 @@
         "\n",
         "### Objective\n",
         "\n",
-        "In this notebook, you will learn how to use Vertex SDK for Python to:\n",
+        "In this notebook, you learn how to use `Vertex ML Metadata` to track training parameters and evaluation metrics.\n",
         "\n",
-        "    * Track parameters and metrics for a locally trained model.\n",
-        "    * Extract and perform analysis for all parameters and metrics within an Experiment.\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex ML Metadata`\n",
+        "- `Vertex AI Experiments`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Track parameters and metrics for a locally trained model.\n",
+        "- Extract and perform analysis for all parameters and metrics within an Experiment.\n",
         "\n",
         "### Costs \n",
         "\n",
@@ -152,9 +159,9 @@
         "id": "i7EUnXsZhAGF"
       },
       "source": [
-        "### Install additional packages\n",
+        "## Installation\n",
         "\n",
-        "Run the following commands to install the Vertex SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -165,24 +172,21 @@
       },
       "outputs": [],
       "source": [
-        "import sys\n",
+        "import os\n",
         "\n",
-        "if \"google.colab\" in sys.modules:\n",
-        "    USER_FLAG = \"\"\n",
-        "else:\n",
-        "    USER_FLAG = \"--user\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "wyy5Lbnzg5fi"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U tensorflow==2.8 $USER_FLAG\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+        "! pip3 install -U tensorflow==2.8 {USER_FLAG} -q"
       ]
     },
     {
@@ -271,24 +275,7 @@
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = !gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "qJYoRfYng0XZ"
-      },
-      "source": [
-        "Otherwise, set your project ID here."
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -300,7 +287,53 @@
       "outputs": [],
       "source": [
         "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+        "    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,
+      "metadata": {
+        "id": "09021c90b34c"
+      },
+      "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 = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -449,10 +482,7 @@
       },
       "outputs": [],
       "source": [
-        "EXPERIMENT_NAME = \"\"  # @param {type:\"string\"}\n",
-        "REGION = \"[your-region]\"  # @param {type:\"string\"}\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
+        "EXPERIMENT_NAME = \"\"  # @param {type:\"string\"}"
       ]
     },
     {

notebooks/official/model_monitoring/model_monitoring.ipynb

@@ -35,17 +35,17 @@
         "\n",
         "<table align=\"left\">\n",
         "  <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%2Fmaster%2Fnotebooks%2Fcommunity%2Fmodel_monitoring%2Fmodel_monitoring_feature_attribs.ipynb\">\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%2Fofficial%2Fmodel_monitoring%2Fmodel_monitoring.ipynb\">\n",
         "       <img src=\"https://www.gstatic.com/cloud/images/navigation/vertex-ai.svg\" alt=\"Google Cloud Notebooks\">Open in Cloud Notebook\n",
         "    </a>\n",
         "  </td> \n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/model_monitoring/model_monitoring_feature_attribs.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring/model_monitoring.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Open in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/model_monitoring/model_monitoring_feature_attribs.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model_monitoring/model_monitoring.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",
@@ -99,20 +99,24 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this notebook, you will learn how to... \n",
+        "In this notebook, you learn to use the `Vertex AI Model Monitoring` service to detect drift and anomalies in prediction requests from a deployed `Vertex AI Model` resource. \n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Model Monitoring`\n",
+        "- `Vertex AI Prediction`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Upload a pre-trained model as a `Vertex AI Model` resource.\n",
+        "- Create an `Vertex AI Endpoint` resource.\n",
+        "- Deploy the `Model` resource to the `Endpoint` resource.\n",
+        "- Configure the `Endpoint` resource for model monitoring.\n",
+        "- Generate synthetic prediction requests.\n",
+        "- Understand how to interpret the statistics, visualizations, other data reported by the model monitoring feature.\n",
         "\n",
-        "* deploy a pre-trained model\n",
-        "* configure model monitoring\n",
-        "* generate some artificial traffic\n",
-        "* understand how to interpret the statistics, visualizations, other data reported by the model monitoring feature"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "8yVpQt-JHKPF"
-      },
-      "source": [
         "### Costs \n",
         "\n",
         "This tutorial uses billable components of Google Cloud:\n",
@@ -130,19 +134,43 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "8yVpQt-JHKPF"
       },
       "source": [
-        "### The example model\n",
+        "### Set up your local development environment\n",
         "\n",
-        "The model you'll use in this notebook is based on [this blog post](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml). The idea behind this model is that your company has extensive log data describing how your game users have interacted with the site. The raw data contains the following categories of information:\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",
-        "- identity - unique player identitity numbers\n",
-        "- demographic features - information about the player, such as the geographic region in which a player is located\n",
-        "- behavioral features - counts of the number of times a  player has triggered certain game events, such as reaching a new level\n",
-        "- churn propensity - this is the label or target feature, it provides an estimated probability that this player will churn, i.e. stop being an active player.\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
         "\n",
-        "The blog article referenced above explains how to use BigQuery to store the raw data, pre-process it for use in machine learning, and train a model. Because this notebook focuses on model monitoring, rather than training models, you're going to reuse a pre-trained version of this model, which has been exported to Google Cloud Storage. In the next section, you will setup your environment and import this model into your own project."
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
+        "\n",
+        "The Google Cloud guide to [setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
+        "\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
+        "\n",
+        "1. To install Jupyter, run `pip install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
+        "\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "\n",
+        "1. Open this notebook in the Jupyter Notebook dashboard."
       ]
     },
     {
@@ -157,36 +185,19 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "i7EUnXsZhAGF"
+        "id": "f3848df1e5b0"
       },
       "source": [
-        "### Setup your dependencies"
+        "## Installation\n",
+        "\n",
+        "Install the packages required for executing this notebook."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "020040f91150"
-      },
-      "outputs": [],
-      "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",
-        "\n",
-        "# Google Cloud 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": "UcwUlnMnfo3i"
+        "id": "b24b232ee039"
       },
       "outputs": [],
       "source": [
@@ -194,43 +205,58 @@
         "import pprint as pp\n",
         "import sys\n",
         "\n",
-        "import IPython\n",
-        "\n",
         "assert sys.version_info.major == 3, \"This notebook requires Python 3.\"\n",
         "\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q\n",
+        "\n",
         "# Install Python package dependencies.\n",
         "print(\"Installing TensorFlow and TensorFlow Data Validation (TFDV)\")\n",
         "! pip3 install {USER_FLAG} --quiet --upgrade tensorflow tensorflow_data_validation[visualization]\n",
         "! rm -f /opt/conda/lib/python3.7/site-packages/tensorflow/core/kernels/libtfkernel_sobol_op.so\n",
         "! pip3 install {USER_FLAG} --quiet --upgrade google-api-python-client google-auth-oauthlib google-auth-httplib2 oauth2client requests\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-aiplatform\n",
         "! pip3 install {USER_FLAG} --quiet --upgrade explainable_ai_sdk\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-storage==1.32.0\n",
+        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-storage==1.32.0"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "hhq5zEbGg0XX"
+      },
+      "source": [
+        "### Restart the kernel\n",
         "\n",
-        "# Automatically restart kernel after installing new packages.\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    print(\"Restarting kernel...\")\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)\n",
-        "    print(\"Done.\")"
+        "After you install the SDK, you need to restart the notebook kernel so it can find the packages. You can restart kernel from *Kernel -> Restart Kernel*, or running the following:"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "8rv5wnmA6BTd"
+        "id": "EzrelQZ22IZj"
       },
       "outputs": [],
       "source": [
-        "# Import required packages.\n",
+        "# Automatically restart kernel after installs\n",
         "import os\n",
-        "import random\n",
-        "import sys\n",
-        "import time\n",
         "\n",
-        "import matplotlib.pyplot as plt\n",
-        "import numpy as np"
+        "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)"
       ]
     },
     {
@@ -247,33 +273,153 @@
         "\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. You'll use the *gcloud* command throughout this notebook. In the following cell, enter your project name and run the cell to authenticate yourself with the Google Cloud and initialize your *gcloud* configuration settings.\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",
-        "**For this lab, we're going to use region us-central1 for all our resources (BigQuery training data, Cloud Storage bucket, model and endpoint locations, etc.). Those resources can be deployed in other regions, as long as they're consistently co-located, but we're going to use one fixed region to keep things as simple and error free as possible.**"
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "WReHDGG5g0XY"
+      },
+      "source": [
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "cellView": "form",
-        "id": "wxiE6dEWOFm3"
+        "id": "oM1iC_MfAts1"
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
-        "REGION = \"us-central1\"\n",
-        "SUFFIX = \"aiplatform.googleapis.com\"\n",
-        "API_ENDPOINT = f\"{REGION}-{SUFFIX}\"\n",
-        "PREDICT_API_ENDPOINT = f\"{REGION}-prediction-{SUFFIX}\"\n",
-        "if os.getenv(\"IS_TESTING\"):\n",
-        "    !gcloud --quiet components install beta\n",
-        "    !gcloud --quiet components update\n",
-        "!gcloud config set project $PROJECT_ID\n",
-        "!gcloud config set ai/region $REGION\n",
-        "os.environ[\"GOOGLE_CLOUD_PROJECT\"] = PROJECT_ID"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "riG_qUokg0XZ"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\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": "09021c90b34c"
+      },
+      "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 = \"us-central1\"  # @param {type: \"string\"}"
+      ]
+    },
+    {
+      "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": "dr--iN2kAylZ"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench notebooks**, your environment is already\n",
+        "authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click **Create**. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
@@ -293,11 +439,19 @@
       },
       "outputs": [],
       "source": [
-        "# The Google Cloud Notebook product has specific requirements\n",
-        "IS_GOOGLE_CLOUD_NOTEBOOK = os.path.exists(\"/opt/deeplearning/metadata/env_version\")\n",
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your GCP account. This provides access to your\n",
+        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+        "# requests.\n",
         "\n",
-        "# If on Google Cloud Notebooks, then don't execute this code\n",
-        "if not IS_GOOGLE_CLOUD_NOTEBOOK:\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",
@@ -307,9 +461,70 @@
         "    # 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 ''\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "XoEqT2Y4DJmf"
+      },
+      "source": [
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8353fb6d69a0"
+      },
+      "outputs": [],
+      "source": [
+        "# Import required packages.\n",
+        "import os\n",
+        "import random\n",
+        "import sys\n",
+        "import time\n",
         "\n",
-        "!gcloud services enable aiplatform.googleapis.com"
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "51010fc06d8c"
+      },
+      "outputs": [],
+      "source": [
+        "SUFFIX = \"aiplatform.googleapis.com\"\n",
+        "API_ENDPOINT = f\"{REGION}-{SUFFIX}\"\n",
+        "PREDICT_API_ENDPOINT = f\"{REGION}-prediction-{SUFFIX}\"\n",
+        "if os.getenv(\"IS_TESTING\"):\n",
+        "    !gcloud --quiet components install beta\n",
+        "    !gcloud --quiet components update\n",
+        "!gcloud config set ai/region $REGION\n",
+        "os.environ[\"GOOGLE_CLOUD_PROJECT\"] = PROJECT_ID"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "tvgnzT1CKxrO"
+      },
+      "source": [
+        "### The example model\n",
+        "\n",
+        "The model you'll use in this notebook is based on [this blog post](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml). The idea behind this model is that your company has extensive log data describing how your game users have interacted with the site. The raw data contains the following categories of information:\n",
+        "\n",
+        "- identity - unique player identitity numbers\n",
+        "- demographic features - information about the player, such as the geographic region in which a player is located\n",
+        "- behavioral features - counts of the number of times a  player has triggered certain game events, such as reaching a new level\n",
+        "- churn propensity - this is the label or target feature, it provides an estimated probability that this player will churn, i.e. stop being an active player.\n",
+        "\n",
+        "The blog article referenced above explains how to use BigQuery to store the raw data, pre-process it for use in machine learning, and train a model. Because this notebook focuses on model monitoring, rather than training models, you're going to reuse a pre-trained version of this model, which has been exported to Google Cloud Storage. In the next section, you will setup your environment and import this model into your own project."
       ]
     },
     {

notebooks/official/pipelines/automl_tabular_classification_beans.ipynb

@@ -33,22 +33,24 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/automl_tabular_classification_beans.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/automl_tabular_classification_beans.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/pipelines/automl_tabular_classification_beans.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/automl_tabular_classification_beans.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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/automl_tabular_classification_beans.ipynb\">\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/pipelines/automl_tabular_classification_beans.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",
+        "     </a>\n",
         "  </td>\n",
         "</table>\n",
+        "</table>\n",
         "<br/><br/><br/>"
       ]
     },
@@ -86,14 +88,26 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML tabular classification using a pipeline with components from  `google_cloud_pipeline_components`.\n",
+        "In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` tabular classification model.\n",
+        "\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "- `Vertex AutoML`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a `Dataset` resource.\n",
-        "- Train an AutoML `Model` resource.\n",
-        "- Creates an `Endpoint` resource.\n",
-        "- Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Create a KFP pipeline:\n",
+        "    - Create a `Dataset` resource.\n",
+        "    - Train an AutoML tabular classification `Model` resource.\n",
+        "    - Create an `Endpoint` resource.\n",
+        "    - Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Compile the KFP pipeline.\n",
+        "- Execute the KFP pipeline using `Vertex AI Pipelines`\n",
         "\n",
         "The components are [documented here](https://google-cloud-pipeline-components.readthedocs.io/en/latest/google_cloud_pipeline_components.aiplatform.html#module-google_cloud_pipeline_components.aiplatform)."
       ]
@@ -126,7 +140,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -172,53 +186,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[full] $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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-pipeline-components* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade"
+        "# 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\n",
+        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade -q"
       ]
     },
     {
@@ -401,23 +382,30 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebook**, 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 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."
       ]
     },
     {
@@ -436,8 +424,11 @@
         "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",
@@ -473,7 +464,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -484,8 +476,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -505,7 +498,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -525,7 +518,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -563,9 +556,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -588,9 +588,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -660,7 +660,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/beans\".format(BUCKET_NAME)"
+        "PIPELINE_ROOT = \"{}/pipeline_root/beans\".format(BUCKET_URI)"
       ]
     },
     {
@@ -708,7 +708,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -1168,8 +1168,8 @@
         "except Exception as e:\n",
         "    print(e)\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/pipelines/control_flow_kfp.ipynb

@@ -33,20 +33,21 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/control_flow_kfp.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/control_flow_kfp.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/pipelines/control_flow_kfp.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/control_flow_kfp.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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/control_flow_kfp.ipynb\">\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/pipelines/control_flow_kfp.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",
+        "     </a>\n",
         "  </td>\n",
         "</table>\n",
         "<br/><br/><br/>"
@@ -71,7 +72,18 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you use the KFP SDK to build pipelines that use loops and conditionals, including nested examples."
+        "In this tutorial, you use the KFP SDK to build pipelines that use loops and conditionals, including nested examples.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a KFP pipeline:\n",
+        "    - Use control flow components\n",
+        "- Compile the KFP pipeline.\n",
+        "- Execute the KFP pipeline using `Vertex AI Pipelines`"
       ]
     },
     {
@@ -102,7 +114,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -135,7 +147,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -148,53 +160,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_kfp"
-      },
-      "source": [
-        "Install the latest GA version of *KFP SDK* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_kfp"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install $USER kfp --upgrade"
+        "# 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\n",
+        "! pip3 install {USER_FLAG} kfp google-cloud-pipeline-components --upgrade -q"
       ]
     },
     {
@@ -376,23 +355,30 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebook**, 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 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."
       ]
     },
     {
@@ -411,8 +397,11 @@
         "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",
@@ -448,7 +437,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -459,8 +449,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -480,7 +471,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -500,7 +491,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -538,9 +529,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -563,9 +561,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -588,7 +586,12 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import json\n",
+        "\n",
+        "import google.cloud.aiplatform as aip\n",
+        "from kfp import dsl\n",
+        "from kfp.v2 import compiler\n",
+        "from kfp.v2.dsl import component"
       ]
     },
     {
@@ -610,31 +613,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/control\".format(BUCKET_NAME)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "additional_imports"
-      },
-      "source": [
-        "Additional imports."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_kfp"
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "from kfp import dsl\n",
-        "from kfp.v2 import compiler\n",
-        "from kfp.v2.dsl import component"
+        "PIPELINE_ROOT = \"{}/pipeline_root/control\".format(BUCKET_URI)"
       ]
     },
     {
@@ -656,7 +635,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -983,8 +962,8 @@
         "except Exception as e:\n",
         "    print(e)\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.ipynb

@@ -33,20 +33,21 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.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/pipelines/google_cloud_pipeline_components_automl_images.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_images.ipynb\">\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/pipelines/google_cloud_pipeline_components_automl_images.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",
+        "     </a>\n",
         "  </td>\n",
         "</table>\n",
         "<br/><br/><br/>"
@@ -60,7 +61,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This notebook shows how to use the components defined in [`google_cloud_pipeline_components`](https://github.com/kubeflow/pipelines/tree/master/components/google-cloud) to build an AutoML image classification workflow on [Vertex AI Pipelines](https://cloud.google.com/vertex-ai/docs/pipelines)."
+        "This notebook shows how to use the components defined in [`google_cloud_pipeline_components`](https://github.com/kubeflow/pipelines/tree/master/components/google-cloud) to build an `AutoML` image classification workflow on [Vertex AI Pipelines](https://cloud.google.com/vertex-ai/docs/pipelines)."
       ]
     },
     {
@@ -82,14 +83,26 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML image classification using a pipeline with components from  `google_cloud_pipeline_components`.\n",
+        "In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` image classification model.\n",
+        "\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "- `Vertex AutoML`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a `Dataset` resource.\n",
-        "- Train an AutoML `Model` resource.\n",
-        "- Creates an `Endpoint` resource.\n",
-        "- Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Create a KFP pipeline:\n",
+        "    - Create a `Dataset` resource.\n",
+        "    - Train an AutoML image classification `Model` resource.\n",
+        "    - Create an `Endpoint` resource.\n",
+        "    - Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Compile the KFP pipeline.\n",
+        "- Execute the KFP pipeline using `Vertex AI Pipelines`\n",
         "\n",
         "The components are [documented here](https://google-cloud-pipeline-components.readthedocs.io/en/latest/google_cloud_pipeline_components.aiplatform.html#module-google_cloud_pipeline_components.aiplatform)."
       ]
@@ -122,7 +135,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -155,7 +168,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -168,53 +181,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-pipeline-components* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade"
+        "# 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\n",
+        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade -q"
       ]
     },
     {
@@ -397,23 +377,30 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebook**, 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 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."
       ]
     },
     {
@@ -432,8 +419,11 @@
         "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",
@@ -469,7 +459,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -480,8 +471,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -501,7 +493,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -521,7 +513,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -559,9 +551,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].replace('*', '').strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -584,9 +583,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -609,7 +608,8 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aip\n",
+        "import kfp"
       ]
     },
     {
@@ -631,27 +631,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/flowers\".format(BUCKET_NAME)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "additional_imports"
-      },
-      "source": [
-        "Additional imports."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_pipelines:min"
-      },
-      "outputs": [],
-      "source": [
-        "import kfp"
+        "PIPELINE_ROOT = \"{}/pipeline_root/flowers\".format(BUCKET_URI)"
       ]
     },
     {
@@ -673,7 +653,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -825,16 +805,7 @@
         "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
         "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
         "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial -- *Note:* this is auto-generated and not all resources may be applicable for this tutorial:\n",
-        "\n",
-        "- Dataset\n",
-        "- Pipeline\n",
-        "- Model\n",
-        "- Endpoint\n",
-        "- Batch Job\n",
-        "- Custom Job\n",
-        "- Hyperparameter Tuning Job\n",
-        "- Cloud Storage Bucket"
+        "Otherwise, you can delete the individual resources you created in this tutorial."
       ]
     },
     {
@@ -845,96 +816,10 @@
       },
       "outputs": [],
       "source": [
-        "delete_dataset = True\n",
-        "delete_pipeline = True\n",
-        "delete_model = True\n",
-        "delete_endpoint = True\n",
-        "delete_batchjob = True\n",
-        "delete_customjob = True\n",
-        "delete_hptjob = True\n",
-        "delete_bucket = True\n",
+        "delete_bucket = False\n",
         "\n",
-        "try:\n",
-        "    if delete_model and \"DISPLAY_NAME\" in globals():\n",
-        "        models = aip.Model.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        model = models[0]\n",
-        "        aip.Model.delete(model)\n",
-        "        print(\"Deleted model:\", model)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "try:\n",
-        "    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",
-        "        endpoint = endpoints[0]\n",
-        "        endpoint.undeploy_all()\n",
-        "        aip.Endpoint.delete(endpoint.resource_name)\n",
-        "        print(\"Deleted endpoint:\", endpoint)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_dataset and \"DISPLAY_NAME\" in globals():\n",
-        "    if \"image\" == \"tabular\":\n",
-        "        try:\n",
-        "            datasets = aip.TabularDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.TabularDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "    if \"image\" == \"image\":\n",
-        "        try:\n",
-        "            datasets = aip.ImageDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.ImageDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "    if \"image\" == \"text\":\n",
-        "        try:\n",
-        "            datasets = aip.TextDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.TextDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "    if \"image\" == \"video\":\n",
-        "        try:\n",
-        "            datasets = aip.VideoDataset.list(\n",
-        "                filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "            )\n",
-        "            dataset = datasets[0]\n",
-        "            aip.VideoDataset.delete(dataset.resource_name)\n",
-        "            print(\"Deleted dataset:\", dataset)\n",
-        "        except Exception as e:\n",
-        "            print(e)\n",
-        "\n",
-        "try:\n",
-        "    if delete_pipeline and \"DISPLAY_NAME\" in globals():\n",
-        "        pipelines = aip.PipelineJob.list(\n",
-        "            filter=f\"display_name={DISPLAY_NAME}\", order_by=\"create_time\"\n",
-        "        )\n",
-        "        pipeline = pipelines[0]\n",
-        "        aip.PipelineJob.delete(pipeline.resource_name)\n",
-        "        print(\"Deleted pipeline:\", pipeline)\n",
-        "except Exception as e:\n",
-        "    print(e)\n",
-        "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb

@@ -33,20 +33,21 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.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/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.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/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_tabular.ipynb\">\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/pipelines/google_cloud_pipeline_components_automl_tabular.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",
+        "     </a>\n",
         "  </td>\n",
         "</table>\n",
         "<br/><br/><br/>"
@@ -84,14 +85,26 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML tabular regression using a pipeline with components from  `google_cloud_pipeline_components`.\n",
+        "In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` tabular regression model.\n",
+        "\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "- `Vertex AutoML`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a `Dataset` resource.\n",
-        "- Train an AutoML `Model` resource.\n",
-        "- Creates an `Endpoint` resource.\n",
-        "- Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Create a KFP pipeline:\n",
+        "    - Create a `Dataset` resource.\n",
+        "    - Train an AutoML tabular regression `Model` resource.\n",
+        "    - Create an `Endpoint` resource.\n",
+        "    - Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Compile the KFP pipeline.\n",
+        "- Execute the KFP pipeline using `Vertex AI Pipelines`\n",
         "\n",
         "The components are [documented here](https://google-cloud-pipeline-components.readthedocs.io/en/latest/google_cloud_pipeline_components.aiplatform.html#module-google_cloud_pipeline_components.aiplatform)."
       ]
@@ -124,7 +137,7 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud 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",
@@ -157,7 +170,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -170,53 +183,20 @@
       "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\") and not os.getenv(\"VIRTUAL_ENV\")\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"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-pipeline-components* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade"
+        "# 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\n",
+        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade -q"
       ]
     },
     {
@@ -399,23 +379,30 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebook**, 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 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."
       ]
     },
     {
@@ -434,8 +421,11 @@
         "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",
@@ -471,7 +461,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -482,8 +473,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -503,7 +495,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -523,7 +515,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -561,9 +553,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -586,9 +585,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -611,7 +610,8 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aip\n",
+        "import kfp"
       ]
     },
     {
@@ -633,27 +633,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/cal_housing\".format(BUCKET_NAME)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "additional_imports"
-      },
-      "source": [
-        "Additional imports."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_pipelines:gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "import kfp"
+        "PIPELINE_ROOT = \"{}/pipeline_root/cal_housing\".format(BUCKET_URI)"
       ]
     },
     {
@@ -675,7 +655,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -946,8 +926,8 @@
         "except Exception as e:\n",
         "    print(e)\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket and os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],