Merge branch 'main' into model_monitor_batch

* Update the vizier codelab to replace the gapic library with new Vertex Vizier SDK.

* Added the [project_id] and [region] in the parameter field.

* Fixed the lint errors for vizier sample.

Co-authored-by: Ivan Cheung <ivans.mailbox@gmail.com>
Co-authored-by: Andrew Ferlitsch <aferlitsch@google.com>

.github/workflows/linter/Dockerfile

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

.github/workflows/linter/run_linter.sh

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

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

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

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

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

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

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

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

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

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

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

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

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

notebooks/community/CODEOWNERS

@@ -17,6 +17,7 @@
 /explainable_ai/SDK_Custom_Container_XAI.ipynb @brianchunkang
 /matching_engine/sdk_matching_engine_for_indexing.ipynb @ivanmkc
 /matching_engine/matching_engine_for_indexing.ipynb @yinghsienwu
+/matching_engine/stream_update_for_matching_engine.ipynb @peterping666
 /sdk/pytorch_lightning_custom_container_training.ipynb @brianchunkang
 /tensorboard @yfang1
 /feature_store @nayaknishant @morgandu
@@ -27,4 +28,6 @@
 /notebooks/community/ml_ops/stage2/get_started_with_visionapi_and_automl.ipynb @mansari
 /notebooks/community/neo4j/graph_paysim.ipynb @benofben @laeg
 /notebooks/community/ml_ops/stage1/get_started_with_visionapi_and_vertex_datasets.ipynb @mansari
-/notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb @inardini
+/notebooks/community/pipelines/google_cloud_pipeline_components_bqml_pipeline_demand_forecasting.ipynb @inardini
+/notebooks/community/ml_ops/stage2/get_started_vertex_hpt_r_kernel.ipynb @fhirschmann
+/notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb @fhirschmann

notebooks/community/ml_ops/stage1/get_started_with_data_labeling.ipynb

@@ -212,7 +212,7 @@
         "\n",
         "3. [Enable the Vertex AI APIs and Compute Engine APIs.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component)\n",
         "\n",
-        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Google Cloud Notebooks.\n",
+        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Vertex AI Workbench Notebooks.\n",
         "\n",
         "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
@@ -374,15 +374,8 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "32e1cd21a5d5"
-      },
-      "source": [
+        "authenticated. \n",
+        "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
         "when prompted to authenticate your account via oAuth.\n",
         "\n",

notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb

@@ -1,879 +0,0 @@
-{
-  "cells": [
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "copyright"
-      },
-      "outputs": [],
-      "source": [
-        "# Copyright 2022 Google LLC\n",
-        "#\n",
-        "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
-        "# you may not use this file except in compliance with the License.\n",
-        "# You may obtain a copy of the License at\n",
-        "#\n",
-        "#     https://www.apache.org/licenses/LICENSE-2.0\n",
-        "#\n",
-        "# Unless required by applicable law or agreed to in writing, software\n",
-        "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
-        "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
-        "# See the License for the specific language governing permissions and\n",
-        "# limitations under the License."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "title:generic,gcp"
-      },
-      "source": [
-        "# E2E ML on GCP: MLOps stage 6 : serving: get started with re-importing AutoML tabular models\n",
-        "\n",
-        "<table align=\"left\">\n",
-        "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb\">\n",
-        "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
-        "      View on GitHub\n",
-        "    </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb\">\n",
-        "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
-        "        </a>\n",
-        "  </td>\n",
-        "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage6/get_started_automl_tabular_exported_deploy.ipynb\">\n",
-        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
-        "      Open in Vertex AI Workbench\n",
-        "    </a>\n",
-        "  </td>\n",
-        "</table>\n",
-        "<br/><br/><br/>"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "overview:mlops"
-      },
-      "source": [
-        "## Overview\n",
-        "\n",
-        "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with AutoML Training."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "objective:mlops,stage2,get_started_automl_training"
-      },
-      "source": [
-        "### Objective\n",
-        "\n",
-        "In this tutorial, you learn how to use `AutoML Tabular` for re-importing exported model artifacts as a `Model` resource. This is useful for example, if one wants to move the exported model across projects.\n",
-        "\n",
-        "This tutorial uses the following Google Cloud ML services:\n",
-        "\n",
-        "- `AutoML Tabular`\n",
-        "- `Vertex AI Model` resource\n",
-        "- `Vertex AI Prediction`\n",
-        "\n",
-        "The steps performed include:\n",
-        "\n",
-        "- Importing a pretrained AutoML tabular exported model artifacts, as a `Model` resource.\n",
-        "- Create an `Endpoint` resource.\n",
-        "- Deploy the `Model` resource to the `Endpoint` resource.\n",
-        "- Make a prediction."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "dataset:flowers,icn"
-      },
-      "source": [
-        "### Dataset\n",
-        "\n",
-        "This tutorial uses a pretrained AutoML tabular model with exported model artifacts.\n",
-        "\n",
-        "\n",
-        "The tabular dataset used for the pretrained model is the GSOD dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). The version of the dataset you use only the fields year, month and day to predict the value of mean daily temperature (mean_temp).\n",
-        "\n",
-        "*Note:* This version of the exported model contains the custom op and requires the model server: us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "fb3451ce8e47"
-      },
-      "source": [
-        "### Costs\n",
-        "This tutorial uses billable components of Google Cloud:\n",
-        "\n",
-        "- Vertex AI\n",
-        "- Cloud Storage\n",
-        "\n",
-        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_mlops"
-      },
-      "source": [
-        "## Installations\n",
-        "\n",
-        "Install the packages required for executing this notebook."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_mlops"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
-        "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "# Install the packages\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
-        "! pip3 install --upgrade google-cloud-storage {USER_FLAG} -q"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "restart"
-      },
-      "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "restart"
-      },
-      "outputs": [],
-      "source": [
-        "import os\n",
-        "\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    # Automatically restart kernel after installs\n",
-        "    import IPython\n",
-        "\n",
-        "    app = IPython.Application.instance()\n",
-        "    app.kernel.do_shutdown(True)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "project_id"
-      },
-      "source": [
-        "## Before you begin\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
-        "\n",
-        "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
-        "\n",
-        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
-        "\n",
-        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "56d591439df1"
-      },
-      "source": [
-        "#### Set your project ID\n",
-        "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID:\", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "set_gcloud_project_id"
-      },
-      "outputs": [],
-      "source": [
-        "! gcloud config set project $PROJECT_ID"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "region"
-      },
-      "source": [
-        "#### Region\n",
-        "\n",
-        "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
-        "\n",
-        "- Americas: `us-central1`\n",
-        "- Europe: `europe-west4`\n",
-        "- Asia Pacific: `asia-east1`\n",
-        "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
-        "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "region"
-      },
-      "outputs": [],
-      "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
-        "\n",
-        "if REGION == \"[your-region]\":\n",
-        "    REGION = \"us-central1\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "timestamp"
-      },
-      "source": [
-        "#### Timestamp\n",
-        "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "timestamp"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "3ffa6b6c7cdb"
-      },
-      "source": [
-        "### Authenticate your Google Cloud account\n",
-        "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
-        "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
-        "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "1. **Click Create service account**.\n",
-        "\n",
-        "2. In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "2b72272258fc"
-      },
-      "outputs": [],
-      "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = \"google.colab\" in sys.modules\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "bucket:mbsdk"
-      },
-      "source": [
-        "### Create a Cloud Storage bucket\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "bucket"
-      },
-      "outputs": [],
-      "source": [
-        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
-        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "autoset_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
-        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "create_bucket"
-      },
-      "source": [
-        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "create_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil mb -l $REGION $BUCKET_URI"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "source": [
-        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "validate_bucket"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "setup_vars"
-      },
-      "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aiplatform"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "init_aip:mbsdk"
-      },
-      "source": [
-        "### Initialize Vertex AI SDK for Python\n",
-        "\n",
-        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "init_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "machine:training"
-      },
-      "source": [
-        "#### Set machine type\n",
-        "\n",
-        "Next, set the machine type to use for training.\n",
-        "\n",
-        "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training.\n",
-        " - `machine type`\n",
-        "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
-        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
-        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
-        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
-        "\n",
-        "*Note: The following is not supported for training:*\n",
-        "\n",
-        " - `standard`: 2 vCPUs\n",
-        " - `highcpu`: 2, 4 and 8 vCPUs\n",
-        "\n",
-        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "machine:training"
-      },
-      "outputs": [],
-      "source": [
-        "if os.getenv(\"IS_TESTING_DEPLOY_MACHINE\"):\n",
-        "    MACHINE_TYPE = os.getenv(\"IS_TESTING_DEPLOY_MACHINE\")\n",
-        "else:\n",
-        "    MACHINE_TYPE = \"n1-standard\"\n",
-        "\n",
-        "VCPU = \"4\"\n",
-        "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
-        "print(\"Train machine type\", DEPLOY_COMPUTE)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "import_file:u_dataset,csv"
-      },
-      "source": [
-        "### Location of pretrained `AutoML Tabular` exported model\n",
-        "\n",
-        "Now set the variable `MODEL_PACKAGE` to the location of the exported model artifacts in Cloud Storage."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_file:flowers,csv,icn"
-      },
-      "outputs": [],
-      "source": [
-        "MODEL_PACKAGE = \"gs://cloud-samples-data/vertex-ai/tabular-workflows/models/custom_op\""
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "quick_peek:csv"
-      },
-      "source": [
-        "#### Quick peek at your model package.\n",
-        "\n",
-        "Next, take a look at the contents of the model package for the exported AutoML tabular model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "quick_peek:csv"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls {MODEL_PACKAGE}"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "automl_tabular_intro"
-      },
-      "source": [
-        "## AutoML tabular models\n",
-        "\n",
-        "AutoML can train the following types of tabular models:\n",
-        "\n",
-        "- classification\n",
-        "- regression\n",
-        "- forecasting\n",
-        "\n",
-        "A model can be trained for either automatic deployment to the cloud or exported for manual deployment to the cloud. In this tutorial, you use a pretrained exported AutoML tabular model.\n",
-        "\n",
-        "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)\n",
-        "\n",
-        "Learn more about [Exporting AutoML Tabular models](https://cloud.google.com/vertex-ai/docs/export/export-model-tabular)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "c10efb34321b"
-      },
-      "source": [
-        "### Set the model server\n",
-        "\n",
-        "Next, you set the pre-built container for the model server. The container will be a version of `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server`. If the model package contains an `environment.json` file, use the container version specified by the key `container_uri`; otherwise, use `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server:latest` "
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "a5f271de9040"
-      },
-      "outputs": [],
-      "source": [
-        "import json\n",
-        "\n",
-        "output = !gsutil cat {MODEL_PACKAGE}/environment.json\n",
-        "\n",
-        "MODEL_SERVER = json.loads(output[0])[\"container_uri\"]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "e8ce91147c93"
-      },
-      "source": [
-        "### Upload the pretrained exported `AutoML Tabular` model package to a `Vertex AI Model` resource\n",
-        "\n",
-        "Next, you upload the model artifacts for the pretrained exported `AutoML Tabular` model into a `Vertex AI Model` resource, using the `Model.upload()` method with the following parameters:\n",
-        "\n",
-        "- `display_name`: A human readable name for the `Model` resource.\n",
-        "- `artifact_uri`: The Cloud Storage location of the model package.\n",
-        "- `serving_container_image_uri`: The serving container image.\n",
-        "- `serving_container_ports`: The serving port.\n",
-        "\n",
-        "*Note:* When you upload the model artifacts to a `Vertex Model` resource, you specify the corresponding deployment container image."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "7988eae27f80"
-      },
-      "outputs": [],
-      "source": [
-        "model = aiplatform.Model.upload(\n",
-        "    display_name=\"gsod_\" + TIMESTAMP,\n",
-        "    artifact_uri=MODEL_PACKAGE,\n",
-        "    serving_container_image_uri=MODEL_SERVER,\n",
-        "    serving_container_ports=[8080],\n",
-        ")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "628de0914ba1"
-      },
-      "source": [
-        "## Creating an `Endpoint` resource\n",
-        "\n",
-        "You create an `Endpoint` resource using the `Endpoint.create()` method. At a minimum, you specify the display name for the endpoint. Optionally, you can specify the project and location (region); otherwise the settings are inherited by the values you set when you initialized the Vertex AI SDK with the `init()` method.\n",
-        "\n",
-        "In this example, the following parameters are specified:\n",
-        "\n",
-        "- `display_name`: A human readable name for the `Endpoint` resource.\n",
-        "- `project`: Your project ID.\n",
-        "- `location`: Your region.\n",
-        "- `labels`: (optional) User defined metadata for the `Endpoint` in the form of key/value pairs.\n",
-        "\n",
-        "This method returns an `Endpoint` object.\n",
-        "\n",
-        "Learn more about [Vertex AI Endpoints](https://cloud.google.com/vertex-ai/docs/predictions/deploy-model-api)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0ea443f9593b"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint = aiplatform.Endpoint.create(\n",
-        "    display_name=\"gsod_\" + TIMESTAMP,\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    labels={\"your_key\": \"your_value\"},\n",
-        ")\n",
-        "\n",
-        "print(endpoint)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ca3fa3f6a894"
-      },
-      "source": [
-        "## Deploying `Model` resources to an `Endpoint` resource.\n",
-        "\n",
-        "You can deploy one of more `Vertex AI Model` resource instances to the same endpoint. Each `Vertex AI Model` resource that is deployed will have its own deployment container for the serving binary. \n",
-        "\n",
-        "*Note:* For this example, you specified the deployment container for the exported AutoML Tabular model in the previous step of uploading the model artifacts to a `Vertex AI Model` resource.\n",
-        "\n",
-        "To deploy, you specify the following additional configuration settings:\n",
-        "\n",
-        "- The machine type.\n",
-        "- The (if any) type and number of GPUs.\n",
-        "- Static, manual or auto-scaling of VM instances.\n",
-        "\n",
-        "In this example, you deploy the model with the minimal amount of specified parameters, as follows:\n",
-        "\n",
-        "- `model`: The `Model` resource.\n",
-        "- `deployed_model_displayed_name`: The human readable name for the deployed model instance.\n",
-        "- `machine_type`: The machine type for each VM instance.\n",
-        "\n",
-        "Do to the requirements to provision the resource, this may take upto a few minutes."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "4e93b034a72f"
-      },
-      "outputs": [],
-      "source": [
-        "response = endpoint.deploy(\n",
-        "    model=model,\n",
-        "    deployed_model_display_name=\"gsod_\" + TIMESTAMP,\n",
-        "    machine_type=DEPLOY_COMPUTE,\n",
-        ")\n",
-        "\n",
-        "print(response)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "f75331c946d5"
-      },
-      "source": [
-        "## Make a prediction\n",
-        "\n",
-        "Finally, you make an online prediction using the `endpoint()` method, with the following parameters:\n",
-        "\n",
-        "- `instances`: The instances to predict.\n",
-        "\n",
-        "The following is the for a prediction request:\n",
-        "\n",
-        "    [ INSTANCE_1, INSTANCE_2, ... ]\n",
-        "    \n",
-        "    INSTANCE : { \"column_1\": value, \"column_2\": value, ... }\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "72683bd9d777"
-      },
-      "outputs": [],
-      "source": [
-        "INSTANCES = [{\"year\": \"2020\", \"month\": \"1\", \"day\": \"23\"}]\n",
-        "\n",
-        "prediction = endpoint.predict(instances=INSTANCES)\n",
-        "print(prediction)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "endpoint_delete:mbsdk"
-      },
-      "source": [
-        "#### Delete the endpoint\n",
-        "\n",
-        "The method 'delete()' will delete the endpoint."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "endpoint_delete:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint.undeploy_all()\n",
-        "endpoint.delete()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "model_delete:mbsdk"
-      },
-      "source": [
-        "#### Delete the model\n",
-        "\n",
-        "The method 'delete()' will delete the model."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "model_delete:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "model.delete()"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "cleanup"
-      },
-      "source": [
-        "# Cleaning up\n",
-        "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
-        "\n",
-        "Otherwise, you can delete the individual resources you created in this tutorial.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "cleanup"
-      },
-      "outputs": [],
-      "source": [
-        "# Set this to true only if you'd like to delete your bucket\n",
-        "delete_bucket = False\n",
-        "\n",
-        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
-        "    ! gsutil rm -r $BUCKET_URI"
-      ]
-    }
-  ],
-  "metadata": {
-    "colab": {
-      "name": "get_started_automl_tabular_exported_deploy.ipynb",
-      "toc_visible": true
-    },
-    "kernelspec": {
-      "display_name": "Python 3",
-      "name": "python3"
-    }
-  },
-  "nbformat": 4,
-  "nbformat_minor": 0
-}

notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.ipynb

@@ -0,0 +1,898 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "copyright"
+   },
+   "outputs": [],
+   "source": [
+    "# Copyright 2022 Google LLC\n",
+    "#\n",
+    "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
+    "# you may not use this file except in compliance with the License.\n",
+    "# You may obtain a copy of the License at\n",
+    "#\n",
+    "#     https://www.apache.org/licenses/LICENSE-2.0\n",
+    "#\n",
+    "# Unless required by applicable law or agreed to in writing, software\n",
+    "# distributed under the License is distributed on an \"AS IS\" BASIS,\n",
+    "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
+    "# See the License for the specific language governing permissions and\n",
+    "# limitations under the License."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "title:generic,gcp"
+   },
+   "source": [
+    "# E2E ML on GCP: MLOps stage 6 : serving: get started with re-importing AutoML tabular models\n",
+    "\n",
+    "<table align=\"left\">\n",
+    "  <td>\n",
+    "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_with_automl_tabular_exported_deploy.ipynb\">\n",
+    "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
+    "      View on GitHub\n",
+    "    </a>\n",
+    "  </td>\n",
+    "  <td>\n",
+    "        <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage6/get_started_automl_with_tabular_exported_deploy.ipynb\">\n",
+    "        <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+    "        </a>\n",
+    "  </td>\n",
+    "  <td>\n",
+    "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage6/get_started_automl_with_tabular_exported_deploy.ipynb\">\n",
+    "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+    "      Open in Vertex AI Workbench\n",
+    "    </a>\n",
+    "  </td>\n",
+    "</table>\n",
+    "<br/><br/><br/>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "overview:mlops"
+   },
+   "source": [
+    "## Overview\n",
+    "\n",
+    "\n",
+    "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 2 : experimentation: get started with AutoML Training."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "objective:mlops,stage2,get_started_automl_training"
+   },
+   "source": [
+    "### Objective\n",
+    "\n",
+    "In this tutorial, you learn how to use `AutoML Tabular` for re-importing exported model artifacts as a `Model` resource. This is useful for example, if one wants to move the exported model across projects.\n",
+    "\n",
+    "This tutorial uses the following Google Cloud ML services:\n",
+    "\n",
+    "- `AutoML Tabular`\n",
+    "- `Vertex AI Model` resource\n",
+    "- `Vertex AI Prediction`\n",
+    "\n",
+    "The steps performed include:\n",
+    "\n",
+    "- Importing a pretrained AutoML tabular exported model artifacts, as a `Model` resource.\n",
+    "- Create an `Endpoint` resource.\n",
+    "- Deploy the `Model` resource to the `Endpoint` resource.\n",
+    "- Make a prediction."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dataset:flowers,icn"
+   },
+   "source": [
+    "### Dataset\n",
+    "\n",
+    "This tutorial uses a pretrained AutoML tabular model with exported model artifacts.\n",
+    "\n",
+    "\n",
+    "The tabular dataset used for the pretrained model is the GSOD dataset from [BigQuery public datasets](https://cloud.google.com/bigquery/public-data). The version of the dataset you use only the fields year, month and day to predict the value of mean daily temperature (mean_temp).\n",
+    "\n",
+    "*Note:* This version of the exported model contains the custom op and requires the model server: us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "fb3451ce8e47"
+   },
+   "source": [
+    "### Costs\n",
+    "This tutorial uses billable components of Google Cloud:\n",
+    "\n",
+    "- Vertex AI\n",
+    "- Cloud Storage\n",
+    "\n",
+    "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage pricing](https://cloud.google.com/storage/pricing) and use the [Pricing Calculator](https://cloud.google.com/products/calculator/) to generate a cost estimate based on your projected usage."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "install_mlops"
+   },
+   "source": [
+    "## Installations\n",
+    "\n",
+    "Install the packages required for executing this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "install_mlops"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# The Vertex AI Workbench Notebook product has specific requirements\n",
+    "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+    "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+    "    \"/opt/deeplearning/metadata/env_version\"\n",
+    ")\n",
+    "\n",
+    "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+    "USER_FLAG = \"\"\n",
+    "if IS_WORKBENCH_NOTEBOOK:\n",
+    "    USER_FLAG = \"--user\"\n",
+    "\n",
+    "# Install the packages\n",
+    "\n",
+    "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+    "! pip3 install --upgrade google-cloud-storage {USER_FLAG} -q"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "restart"
+   },
+   "source": [
+    "### Restart the kernel\n",
+    "\n",
+    "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "restart"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"IS_TESTING\"):\n",
+    "    # Automatically restart kernel after installs\n",
+    "    import IPython\n",
+    "\n",
+    "    app = IPython.Application.instance()\n",
+    "    app.kernel.do_shutdown(True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "project_id"
+   },
+   "source": [
+    "## Before you begin\n",
+    "\n",
+    "### Set up your Google Cloud project\n",
+    "\n",
+    "**The following steps are required, regardless of your notebook environment.**\n",
+    "\n",
+    "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+    "\n",
+    "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+    "\n",
+    "1. [Enable the Vertex AI, Compute Engine and Cloud Storage APIs](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage_component).\n",
+    "\n",
+    "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+    "\n",
+    "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
+    "Cloud SDK uses the right project for all the commands in this notebook.\n",
+    "\n",
+    "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "56d591439df1"
+   },
+   "source": [
+    "#### Set your project ID\n",
+    "\n",
+    "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "set_project_id"
+   },
+   "outputs": [],
+   "source": [
+    "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "autoset_project_id"
+   },
+   "outputs": [],
+   "source": [
+    "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+    "    # Get your GCP project id from gcloud\n",
+    "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+    "    PROJECT_ID = shell_output[0]\n",
+    "    print(\"Project ID:\", PROJECT_ID)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "set_gcloud_project_id"
+   },
+   "outputs": [],
+   "source": [
+    "! gcloud config set project $PROJECT_ID"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "region"
+   },
+   "source": [
+    "#### Region\n",
+    "\n",
+    "You can also change the `REGION` variable, which is used for operations\n",
+    "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+    "\n",
+    "- Americas: `us-central1`\n",
+    "- Europe: `europe-west4`\n",
+    "- Asia Pacific: `asia-east1`\n",
+    "\n",
+    "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+    "\n",
+    "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "region"
+   },
+   "outputs": [],
+   "source": [
+    "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+    "\n",
+    "if REGION == \"[your-region]\":\n",
+    "    REGION = \"us-central1\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "timestamp"
+   },
+   "source": [
+    "#### Timestamp\n",
+    "\n",
+    "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "timestamp"
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "3ffa6b6c7cdb"
+   },
+   "source": [
+    "### Authenticate your Google Cloud account\n",
+    "\n",
+    "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
+    "\n",
+    "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+    "\n",
+    "**Otherwise**, follow these steps:\n",
+    "\n",
+    "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+    "\n",
+    "1. **Click Create service account**.\n",
+    "\n",
+    "2. In the **Service account name** field, enter a name, and click **Create**.\n",
+    "\n",
+    "3. In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex AI\" into the filter box, and select **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+    "\n",
+    "4. Click Create. A JSON file that contains your key downloads to your local environment.\n",
+    "\n",
+    "5. Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "2b72272258fc"
+   },
+   "outputs": [],
+   "source": [
+    "# If you are running this notebook in Colab, run this cell and follow the\n",
+    "# instructions to authenticate your GCP account. This provides access to your\n",
+    "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
+    "# requests.\n",
+    "\n",
+    "import os\n",
+    "import sys\n",
+    "\n",
+    "# If on Vertex AI Workbench, then don't execute this code\n",
+    "IS_COLAB = \"google.colab\" in sys.modules\n",
+    "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+    "    \"DL_ANACONDA_HOME\"\n",
+    "):\n",
+    "    if \"google.colab\" in sys.modules:\n",
+    "        from google.colab import auth as google_auth\n",
+    "\n",
+    "        google_auth.authenticate_user()\n",
+    "\n",
+    "    # If you are running this notebook locally, replace the string below with the\n",
+    "    # path to your service account key and run this cell to authenticate your GCP\n",
+    "    # account.\n",
+    "    elif not os.getenv(\"IS_TESTING\"):\n",
+    "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "bucket:mbsdk"
+   },
+   "source": [
+    "### Create a Cloud Storage bucket\n",
+    "\n",
+    "**The following steps are required, regardless of your notebook environment.**\n",
+    "\n",
+    "When you initialize the Vertex SDK for Python, you specify a Cloud Storage staging bucket. The staging bucket is where all the data associated with your dataset and model resources are retained across sessions.\n",
+    "\n",
+    "Set the name of your Cloud Storage bucket below. Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "bucket"
+   },
+   "outputs": [],
+   "source": [
+    "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+    "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "autoset_bucket"
+   },
+   "outputs": [],
+   "source": [
+    "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
+    "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+    "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "create_bucket"
+   },
+   "source": [
+    "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "create_bucket"
+   },
+   "outputs": [],
+   "source": [
+    "! gsutil mb -l $REGION $BUCKET_URI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "validate_bucket"
+   },
+   "source": [
+    "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "validate_bucket"
+   },
+   "outputs": [],
+   "source": [
+    "! gsutil ls -al $BUCKET_URI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "setup_vars"
+   },
+   "source": [
+    "### Set up variables\n",
+    "\n",
+    "Next, set up some variables used throughout the tutorial.\n",
+    "### Import libraries and define constants"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "import_aip:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "import google.cloud.aiplatform as aiplatform"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "init_aip:mbsdk"
+   },
+   "source": [
+    "### Initialize Vertex AI SDK for Python\n",
+    "\n",
+    "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "init_aip:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "aiplatform.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "machine:training"
+   },
+   "source": [
+    "#### Set machine type\n",
+    "\n",
+    "Next, set the machine type to use for training.\n",
+    "\n",
+    "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training.\n",
+    " - `machine type`\n",
+    "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
+    "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+    "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+    " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+    "\n",
+    "*Note: The following is not supported for training:*\n",
+    "\n",
+    " - `standard`: 2 vCPUs\n",
+    " - `highcpu`: 2, 4 and 8 vCPUs\n",
+    "\n",
+    "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "machine:training"
+   },
+   "outputs": [],
+   "source": [
+    "if os.getenv(\"IS_TESTING_DEPLOY_MACHINE\"):\n",
+    "    MACHINE_TYPE = os.getenv(\"IS_TESTING_DEPLOY_MACHINE\")\n",
+    "else:\n",
+    "    MACHINE_TYPE = \"n1-standard\"\n",
+    "\n",
+    "VCPU = \"4\"\n",
+    "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+    "print(\"Train machine type\", DEPLOY_COMPUTE)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "import_file:u_dataset,csv"
+   },
+   "source": [
+    "### Location of pretrained `AutoML Tabular` exported model\n",
+    "\n",
+    "Now set the variable `MODEL_PACKAGE` to the location of the exported model artifacts in Cloud Storage."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "import_file:flowers,csv,icn"
+   },
+   "outputs": [],
+   "source": [
+    "MODEL_PACKAGE = \"gs://cloud-samples-data/vertex-ai/tabular-workflows/models/custom_op\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "quick_peek:csv"
+   },
+   "source": [
+    "#### Quick peek at your model package.\n",
+    "\n",
+    "Next, take a look at the contents of the model package for the exported AutoML tabular model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "quick_peek:csv"
+   },
+   "outputs": [],
+   "source": [
+    "! gsutil ls {MODEL_PACKAGE}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "automl_tabular_intro"
+   },
+   "source": [
+    "## AutoML tabular models\n",
+    "\n",
+    "AutoML can train the following types of tabular models:\n",
+    "\n",
+    "- classification\n",
+    "- regression\n",
+    "- forecasting\n",
+    "\n",
+    "A model can be trained for either automatic deployment to the cloud or exported for manual deployment to the cloud. In this tutorial, you use a pretrained exported AutoML tabular model.\n",
+    "\n",
+    "Learn more about [AutoML Model Types](https://cloud.google.com/vertex-ai/docs/start/automl-model-types)\n",
+    "\n",
+    "Learn more about [Exporting AutoML Tabular models](https://cloud.google.com/vertex-ai/docs/export/export-model-tabular)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "c10efb34321b"
+   },
+   "source": [
+    "### Set the model server\n",
+    "\n",
+    "Next, you set the pre-built container for the model server. The container will be a version of `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server`. If the model package contains an `environment.json` file, use the container version specified by the key `container_uri`; otherwise, use `us-docker.pkg.dev/vertex-ai/automl-tabular/prediction-server:latest` "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "a5f271de9040"
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "output = !gsutil cat {MODEL_PACKAGE}/environment.json\n",
+    "\n",
+    "MODEL_SERVER = json.loads(output[0])[\"container_uri\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "e8ce91147c93"
+   },
+   "source": [
+    "### Upload the pretrained exported `AutoML Tabular` model package to a `Vertex AI Model` resource\n",
+    "\n",
+    "Next, you upload the model artifacts for the pretrained exported `AutoML Tabular` model into a `Vertex AI Model` resource, using the `Model.upload()` method with the following parameters:\n",
+    "\n",
+    "- `display_name`: A human readable name for the `Model` resource.\n",
+    "- `artifact_uri`: The Cloud Storage location of the model package.\n",
+    "- `serving_container_image_uri`: The serving container image.\n",
+    "- `serving_container_ports`: The serving port.\n",
+    "\n",
+    "*Note:* When you upload the model artifacts to a `Vertex Model` resource, you specify the corresponding deployment container image."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7988eae27f80"
+   },
+   "outputs": [],
+   "source": [
+    "model = aiplatform.Model.upload(\n",
+    "    display_name=\"gsod_\" + TIMESTAMP,\n",
+    "    artifact_uri=MODEL_PACKAGE,\n",
+    "    serving_container_image_uri=MODEL_SERVER,\n",
+    "    serving_container_ports=[8080],\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "628de0914ba1"
+   },
+   "source": [
+    "## Creating an `Endpoint` resource\n",
+    "\n",
+    "You create an `Endpoint` resource using the `Endpoint.create()` method. At a minimum, you specify the display name for the endpoint. Optionally, you can specify the project and location (region); otherwise the settings are inherited by the values you set when you initialized the Vertex AI SDK with the `init()` method.\n",
+    "\n",
+    "In this example, the following parameters are specified:\n",
+    "\n",
+    "- `display_name`: A human readable name for the `Endpoint` resource.\n",
+    "- `project`: Your project ID.\n",
+    "- `location`: Your region.\n",
+    "- `labels`: (optional) User defined metadata for the `Endpoint` in the form of key/value pairs.\n",
+    "\n",
+    "This method returns an `Endpoint` object.\n",
+    "\n",
+    "Learn more about [Vertex AI Endpoints](https://cloud.google.com/vertex-ai/docs/predictions/deploy-model-api)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "0ea443f9593b"
+   },
+   "outputs": [],
+   "source": [
+    "endpoint = aiplatform.Endpoint.create(\n",
+    "    display_name=\"gsod_\" + TIMESTAMP,\n",
+    "    project=PROJECT_ID,\n",
+    "    location=REGION,\n",
+    "    labels={\"your_key\": \"your_value\"},\n",
+    ")\n",
+    "\n",
+    "print(endpoint)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ca3fa3f6a894"
+   },
+   "source": [
+    "## Deploying `Model` resources to an `Endpoint` resource.\n",
+    "\n",
+    "You can deploy one of more `Vertex AI Model` resource instances to the same endpoint. Each `Vertex AI Model` resource that is deployed will have its own deployment container for the serving binary. \n",
+    "\n",
+    "*Note:* For this example, you specified the deployment container for the exported AutoML Tabular model in the previous step of uploading the model artifacts to a `Vertex AI Model` resource.\n",
+    "\n",
+    "To deploy, you specify the following additional configuration settings:\n",
+    "\n",
+    "- The machine type.\n",
+    "- The (if any) type and number of GPUs.\n",
+    "- Static, manual or auto-scaling of VM instances.\n",
+    "\n",
+    "In this example, you deploy the model with the minimal amount of specified parameters, as follows:\n",
+    "\n",
+    "- `model`: The `Model` resource.\n",
+    "- `deployed_model_displayed_name`: The human readable name for the deployed model instance.\n",
+    "- `machine_type`: The machine type for each VM instance.\n",
+    "\n",
+    "Do to the requirements to provision the resource, this may take upto a few minutes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "4e93b034a72f"
+   },
+   "outputs": [],
+   "source": [
+    "response = endpoint.deploy(\n",
+    "    model=model,\n",
+    "    deployed_model_display_name=\"gsod_\" + TIMESTAMP,\n",
+    "    machine_type=DEPLOY_COMPUTE,\n",
+    ")\n",
+    "\n",
+    "print(response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "f75331c946d5"
+   },
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "Finally, you make an online prediction using the `endpoint()` method, with the following parameters:\n",
+    "\n",
+    "- `instances`: The instances to predict.\n",
+    "\n",
+    "The following is the for a prediction request:\n",
+    "\n",
+    "    [ INSTANCE_1, INSTANCE_2, ... ]\n",
+    "    \n",
+    "    INSTANCE : { \"column_1\": value, \"column_2\": value, ... }\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "72683bd9d777"
+   },
+   "outputs": [],
+   "source": [
+    "INSTANCES = [{\"year\": \"2020\", \"month\": \"1\", \"day\": \"23\"}]\n",
+    "\n",
+    "prediction = endpoint.predict(instances=INSTANCES)\n",
+    "print(prediction)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "endpoint_delete:mbsdk"
+   },
+   "source": [
+    "#### Delete the endpoint\n",
+    "\n",
+    "The method 'delete()' will delete the endpoint."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "endpoint_delete:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "endpoint.undeploy_all()\n",
+    "endpoint.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "model_delete:mbsdk"
+   },
+   "source": [
+    "#### Delete the model\n",
+    "\n",
+    "The method 'delete()' will delete the model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "model_delete:mbsdk"
+   },
+   "outputs": [],
+   "source": [
+    "model.delete()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "cleanup"
+   },
+   "source": [
+    "# Cleaning up\n",
+    "\n",
+    "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
+    "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+    "\n",
+    "Otherwise, you can delete the individual resources you created in this tutorial.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "cleanup"
+   },
+   "outputs": [],
+   "source": [
+    "# Set this to true only if you'd like to delete your bucket\n",
+    "delete_bucket = False\n",
+    "\n",
+    "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+    "    ! gsutil rm -r $BUCKET_URI"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "name": "get_started_automl_tabular_exported_deploy.ipynb",
+   "toc_visible": true
+  },
+  "environment": {
+   "kernel": "python3",
+   "name": "common-cpu.m95",
+   "type": "gcloud",
+   "uri": "gcr.io/deeplearning-platform-release/base-cpu:m95"
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/community/ml_ops/stage6/get_started_with_custom_image_model_batch.ipynb

@@ -741,13 +741,16 @@
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
-        "The batch server accepts the following input formats:\n",
+        "The batch server accepts the following input formats for custom image models:\n",
         "\n",
         "- JSONL\n",
-        "- CSV\n",
-        "- TFRecords\n",
         "- File-List\n",
-        "- BigQuery table\n",
+        "\n",
+        "### Output format for batch prediction jobs\n",
+        "\n",
+        "The batch server accepts the following output formats for custom image models:\n",
+        "\n",
+        "- JSONL\n",
         "\n",
         "### Pivot format\n",
         "\n",
@@ -1306,7 +1309,6 @@
       "source": [
         "### Send the prediction request\n",
         "\n",
-        "BLAH\n",
         "\n",
         "To make a batch prediction request, call the model object's `batch_predict` method with the following parameters: \n",
         "- `instances_format`: The format of the batch prediction request file: \"jsonl\", \"csv\", \"bigquery\", \"tf-record\", \"tf-record-gzip\" or \"file-list\"\n",

notebooks/community/ml_ops/stage6/get_started_with_custom_tabular_model_batch.ipynb

@@ -110,7 +110,7 @@
         "- 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",
+        "- churn propensity - this is the label or target feature, it provides an estimated probability that this player may churn, i.e. stop being an active player.\n",
         "\n",
         "**CSV batch input example**\n",
         "\n",
@@ -574,7 +574,7 @@
         "\n",
         "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."
+        "*Note*: TF releases before 2.3 for GPU support fails 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."
       ]
     },
     {
@@ -638,7 +638,7 @@
         "\n",
         "Next, set the machine type to use for prediction.\n",
         "\n",
-        "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for prediction.\n",
+        "- Set the variable `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you use for for prediction.\n",
         " - `machine type`\n",
         "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
         "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
@@ -712,18 +712,23 @@
         "\n",
         "Batch prediction provides the ability to do offline batch processing of large amounts of prediction requests. Resources are only provisioned during the batch process and then deprovisioned when the batch request is completed. The results are stored in Cloud Storage, in contrast to online prediction where the results are returned as a HTTP response packet.\n",
         "\n",
-        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server will convert to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
+        "The input format for your batch job is dependent on the format supported by your model server. Foremost, the web server in your model server must support a JSONL format, which the web server converts to a format support either directly by the model input intertace or a serving function interface. For batch prediction, this JSONL format is referred to as the `pivot` format.\n",
         "\n",
         "### Input format for batch prediction jobs\n",
         "\n",
-        "The batch server accepts the following input formats:\n",
+        "The batch server accepts the following input formats for custom tabular models:\n",
         "\n",
         "- JSONL\n",
         "- CSV\n",
-        "- TFRecords\n",
-        "- File-List\n",
         "- BigQuery table\n",
         "\n",
+        "### Output format for batch prediction jobs\n",
+        "\n",
+        "The batch server accepts the following output formats for custom tabular models:\n",
+        "\n",
+        "- JSONL\n",
+        "- BigQuery table (when input is BigQuery table)\n",
+        "\n",
         "### Pivot format\n",
         "\n",
         "The batch server converts the input format to the `pivot` (JSONL) format as follows:\n",
@@ -744,7 +749,7 @@
         "\n",
         "**CSV**\n",
         "\n",
-        "The csv header in the first line will always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
+        "The csv header in the first line is always be ignored. String fields are required to be double quoted explicitly, otherwise the row is discarded and parsing error messages are outputted to error files. Non-quoted values are always transferred as floats.\n",
         "\n",
         "    col1,col2,col3\n",
         "    1,3,\"cat1\"\n",
@@ -905,7 +910,7 @@
         "- `prediction_format`: The format of the batch prediction response file: \"jsonl\", \"csv\", \"bigquery\", \"tf-record\", \"tf-record-gzip\" or \"file-list\"\n",
         "- `job_display_name`: The human readable name for the prediction job.\n",
         " - `gcs_source`: A list of one or more Cloud Storage paths to your batch prediction requests.\n",
-        "- `gcs_destination_prefix`: The Cloud Storage path that the service will write the predictions to.\n",
+        "- `gcs_destination_prefix`: The Cloud Storage path that the service writes the predictions to.\n",
         "- `model_parameters`: Additional filtering parameters for serving prediction results.\n",
         "- `machine_type`: The type of machine to use for training.\n",
         "- `accelerator_type`: The hardware accelerator type.\n",
@@ -1098,12 +1103,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "0d078e5e8953"
+        "id": "776346c90074"
       },
       "outputs": [],
       "source": [
-        "DATA_DIR = \"gs://cloud-samples-data/ai-platform/iris/iris_data.csv\"\n",
-        "! gsutil cat $data_dir | head -n 10 > test.csv\n",
+        "data_file = \"gs://cloud-samples-data/ai-platform/iris/iris_data.csv\"\n",
+        "! gsutil cat $data_file | head -n 10 > test.csv\n",
         "\n",
         "! cat test.csv\n",
         "\n",
@@ -1209,6 +1214,264 @@
         "            break"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9ce65fff362b"
+      },
+      "source": [
+        "#### Delete the batch prediction job\n",
+        "\n",
+        "You can delete your batch prediction job using the `delete()` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "5943dfde5123"
+      },
+      "outputs": [],
+      "source": [
+        "batch_prediction_job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d61289b87070"
+      },
+      "source": [
+        "## Batch prediction with BigQuery input format\n",
+        "\n",
+        "Next, you do the same batch job, except the input format is a BigQuery table. When the input format is a BigQuery table, the output format has to be a BigQuery table as well. To use BigQuery as the input format, your model must take its input as a list (array) of values. "
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "csv_to_bq"
+      },
+      "source": [
+        "### Create a BigQuery dataset from CSV files\n",
+        "\n",
+        "You can create a BigQuery dataset from CSV files using the BigQuery `create_dataset()` and `load_table_from_uri()` methods, as follows:\n",
+        "\n",
+        "- `create_dataset()`: Creates an empty BigQuery dataset, with the following parameters:\n",
+        " - `dataset_ref`: The `DatasetReference` created from the dataset_id -- e.g., samples.\n",
+        "- `load_table_from_uri()`: Loads one or more CSV files into a table within the corresponding dataset, with the following parameters:\n",
+        " - `url`: A set of one or more CVS files in Cloud Storage storage.\n",
+        " - `table`: The `TableReference` for the table.\n",
+        " - `job_config`: Specifications on how to load the CSV data.\n",
+        "\n",
+        "Learn more about [Importing CSV data into BigQuery](https://www.tensorflow.org/io/tutorials/bigquery#import_census_data_into_bigquery)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "csv_to_bq"
+      },
+      "outputs": [],
+      "source": [
+        "LOCATION = \"us\"\n",
+        "\n",
+        "CSV_SCHEMA = [\n",
+        "    bigquery.SchemaField(\"sepal_length\", \"FLOAT\"),\n",
+        "    bigquery.SchemaField(\"sepal_width\", \"FLOAT\"),\n",
+        "    bigquery.SchemaField(\"petal_length\", \"FLOAT\"),\n",
+        "    bigquery.SchemaField(\"petal_width\", \"FLOAT\"),\n",
+        "]\n",
+        "\n",
+        "DATASET_ID = \"batch\"\n",
+        "TABLE_ID = \"slice1\"\n",
+        "\n",
+        "\n",
+        "def create_bigquery_dataset(dataset_id):\n",
+        "    dataset = bigquery.Dataset(\n",
+        "        bigquery.dataset.DatasetReference(PROJECT_ID, dataset_id)\n",
+        "    )\n",
+        "    dataset.location = \"us\"\n",
+        "\n",
+        "    try:\n",
+        "        dataset = bqclient.create_dataset(dataset)  # API request\n",
+        "        return True\n",
+        "    except Exception as err:\n",
+        "        print(err)\n",
+        "        if err.code != 409:  # http_client.CONFLICT\n",
+        "            raise\n",
+        "    return False\n",
+        "\n",
+        "\n",
+        "def load_data_into_bigquery(url, dataset_id, table_id):\n",
+        "    create_bigquery_dataset(dataset_id)\n",
+        "    dataset = bqclient.dataset(dataset_id)\n",
+        "    table = dataset.table(table_id)\n",
+        "\n",
+        "    job_config = bigquery.LoadJobConfig()\n",
+        "    job_config.write_disposition = bigquery.WriteDisposition.WRITE_TRUNCATE\n",
+        "    job_config.source_format = bigquery.SourceFormat.CSV\n",
+        "    job_config.schema = CSV_SCHEMA\n",
+        "    job_config.skip_leading_rows = 1  # heading\n",
+        "\n",
+        "    load_job = bqclient.load_table_from_uri(url, table, job_config=job_config)\n",
+        "    print(\"Starting job {}\".format(load_job.job_id))\n",
+        "\n",
+        "    load_job.result()  # Waits for table load to complete.\n",
+        "    print(\"Job finished.\")\n",
+        "\n",
+        "    destination_table = bqclient.get_table(table)\n",
+        "    print(\"Loaded {} rows.\".format(destination_table.num_rows))\n",
+        "\n",
+        "    return destination_table\n",
+        "\n",
+        "\n",
+        "bq_table = load_data_into_bigquery(data_file, DATASET_ID, TABLE_ID)\n",
+        "print(bq_table)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "send_prediction_request:image"
+      },
+      "source": [
+        "### Send the batch prediction request\n",
+        "\n",
+        "Again, you make a batch prediction request with the `batch_predict()` method, but with the following changes in parameters:\n",
+        "\n",
+        "- `instances_format`: Set to 'bigquery'\n",
+        "- `predictions_format`: Set to 'bigquery'\n",
+        "- `bigquery_source`: Used instead of `gcs_source`.\n",
+        "- `bigquery_destination_prefix`: Used instead of `gcs_destination_prefix`"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1cf1076178fc"
+      },
+      "outputs": [],
+      "source": [
+        "MIN_NODES = 1\n",
+        "MAX_NODES = 1\n",
+        "\n",
+        "# The name of the job\n",
+        "BATCH_PREDICTION_JOB_NAME = \"churn_batch-\" + UUID\n",
+        "\n",
+        "# Folder in the bucket to write results to\n",
+        "DESTINATION_FOLDER = \"batch_prediction_results_bq\"\n",
+        "\n",
+        "# The Cloud Storage bucket to upload results to\n",
+        "BATCH_PREDICTION_GCS_DEST_PREFIX = BUCKET_URI + \"/\" + DESTINATION_FOLDER\n",
+        "\n",
+        "BQ_TABLE_SOURCE = f\"bq://{PROJECT_ID}.{bq_table.dataset_id}.{bq_table.table_id}\"\n",
+        "\n",
+        "# Make SDK batch_predict method call\n",
+        "batch_prediction_job = model.batch_predict(\n",
+        "    instances_format=\"bigquery\",\n",
+        "    predictions_format=\"bigquery\",\n",
+        "    job_display_name=BATCH_PREDICTION_JOB_NAME,\n",
+        "    bigquery_source=BQ_TABLE_SOURCE,\n",
+        "    bigquery_destination_prefix=f\"bq://{PROJECT_ID}.batch\",\n",
+        "    model_parameters=None,\n",
+        "    machine_type=DEPLOY_COMPUTE,\n",
+        "    accelerator_type=DEPLOY_GPU,\n",
+        "    accelerator_count=DEPLOY_NGPU,\n",
+        "    starting_replica_count=MIN_NODES,\n",
+        "    max_replica_count=MAX_NODES,\n",
+        "    sync=True,\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "get_batch_prediction:mbsdk,custom,icn"
+      },
+      "source": [
+        "### Get the predictions\n",
+        "\n",
+        "Next, get the results from the completed batch prediction job.\n",
+        "\n",
+        "The results are written to a BigQuery table at the BigQuery dataset path you specified as the destination. The batch server creates the table, where the table location is specified by:\n",
+        "\n",
+        "`batch_prediction_job.output_info.bigquery_output_dataset`: The project and dataset components.\n",
+        "`batch_prediction_job.output_info.bigquery_output_table`: The table component.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "cd515ed616c8"
+      },
+      "outputs": [],
+      "source": [
+        "BQ_RESULTS_TABLE = (\n",
+        "    batch_prediction_job.output_info.bigquery_output_dataset\n",
+        "    + \".\"\n",
+        "    + batch_prediction_job.output_info.bigquery_output_table\n",
+        ")\n",
+        "\n",
+        "print(BQ_RESULTS_TABLE)\n",
+        "\n",
+        "table = bigquery.TableReference.from_string(BQ_RESULTS_TABLE[5:])\n",
+        "\n",
+        "rows = bqclient.list_rows(table, max_results=10)\n",
+        "\n",
+        "for row in rows:\n",
+        "    print(row)\n",
+        "    for key, value in row.items():\n",
+        "        pass"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c7cda79d0e42"
+      },
+      "source": [
+        "#### Delete the batch prediction job\n",
+        "\n",
+        "You can delete your batch prediction job using the `delete()` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "de4b5c638c2a"
+      },
+      "outputs": [],
+      "source": [
+        "batch_prediction_job.delete()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "e5d4b9c51e86"
+      },
+      "source": [
+        "#### Delete the model\n",
+        "\n",
+        "You can delete your model using the `delete()` method."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "00fa6a7b4f24"
+      },
+      "outputs": [],
+      "source": [
+        "model.delete()"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1232,16 +1495,6 @@
       "outputs": [],
       "source": [
         "delete_bucket = False\n",
-        "delete_model = True\n",
-        "delete_batch_job = True\n",
-        "\n",
-        "if delete_model:\n",
-        "    try:\n",
-        "        model.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
-        "if delete_batch_job:\n",
-        "    batch_prediction_job.delete()\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -rf {BUCKET_URI}"

notebooks/community/model_monitoring/batch_prediction_model_monitoring.ipynb

@@ -3,7 +3,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "d3069d95",
       "metadata": {
         "cellView": "form",
         "id": "d3069d95"
@@ -11,7 +10,7 @@
       "outputs": [],
       "source": [
         "# @title Copyright & License (click to expand)\n",
-        "# Copyright 2021 Google LLC\n",
+        "# Copyright 2022 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -28,7 +27,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "546c53de",
       "metadata": {
         "id": "546c53de"
       },
@@ -46,13 +44,16 @@
         "        <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
-        "  </td>\n",
+        "  </td><td>\n",
+        "    <a href=\"https://console.cloud.google.com/ai-platform/notebooks/deploy-notebook?name=Model%20Monitoring&download_url=https%3A%2F%2Fraw.githubusercontent.com%2FGoogleCloudPlatform%2Fvertex-ai-samples%2Fmain%2Fnotebooks%2Fcommunity%2Fmodel_monitoring%2Fbatch_prediction_model_monitoring.ipynb\">\n",
+        "       <img src=\"https://www.gstatic.com/cloud/images/navigation/vertex-ai.svg\" alt=\"Google Cloud Notebooks\">Open in Workbench AI Notebook\n",
+        "    </a>\n",
+        "  </td> \n",
         "</table>"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "53fd1070",
       "metadata": {
         "id": "53fd1070"
       },
@@ -64,7 +65,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "8b26c855",
       "metadata": {
         "id": "8b26c855"
       },
@@ -98,7 +98,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d52ba95b",
       "metadata": {
         "id": "d52ba95b"
       },
@@ -110,7 +109,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "e64fb18a",
       "metadata": {
         "id": "e64fb18a"
       },
@@ -123,7 +121,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "9d839347",
       "metadata": {
         "id": "9d839347"
       },
@@ -142,7 +139,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "738fce1f",
       "metadata": {
         "id": "738fce1f"
       },
@@ -155,7 +151,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "4536fe4e",
       "metadata": {
         "id": "4536fe4e"
       },
@@ -178,14 +173,13 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "# Install Python package dependencies.\n",
-        "! pip3 install -q tensorflow-data-validation $USER_FLAG\n",
-        "! pip3 install -q google-api-core $USER_FLAG\n",
-        "! pip3 install -q google-cloud-aiplatform $USER_FLAG"
+        "! pip3 install -q {USER_FLAG} tensorflow-data-validation \\\n",
+        "                              google-api-core \\\n",
+        "                              google-cloud-aiplatform"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "6e98402b",
       "metadata": {
         "id": "6e98402b"
       },
@@ -198,7 +192,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "9775c9ff",
       "metadata": {
         "id": "9775c9ff"
       },
@@ -217,7 +210,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "d5737134",
       "metadata": {
         "id": "d5737134"
       },
@@ -242,7 +234,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "cfb1a1d5",
       "metadata": {
         "id": "cfb1a1d5"
       },
@@ -255,50 +246,33 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "cf8535e4",
       "metadata": {
         "id": "cf8535e4"
       },
       "outputs": [],
       "source": [
-        "import os\n",
-        "\n",
-        "PROJECT_ID = \"\"\n",
-        "\n",
-        "# Get your Google Cloud project ID from gcloud\n",
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
-        "    PROJECT_ID = shell_output[0]\n",
-        "    print(\"Project ID: \", PROJECT_ID)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "05a2d397",
-      "metadata": {
-        "id": "05a2d397"
-      },
-      "source": [
-        "Otherwise, set your project ID here.\n"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "1c2be4bd",
       "metadata": {
         "id": "1c2be4bd"
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"\" or PROJECT_ID is None:\n",
-        "    PROJECT_ID = \"python-docs-samples-tests\"  # @param {type:\"string\"}"
+        "if PROJECT_ID == \"\" or not PROJECT_ID or PROJECT_ID == \"[your-project-id]\":\n",
+        "    PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "    # Get your GCP project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c129705c",
       "metadata": {
         "id": "c129705c"
       },
@@ -309,32 +283,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "71404c9f",
-      "metadata": {
-        "id": "71404c9f"
-      },
-      "source": [
-        "#### Set your email address\n",
-        "This is used for delivering model monitoring notifications.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "id": "4b1d2b69",
-      "metadata": {
-        "id": "4b1d2b69"
-      },
-      "outputs": [],
-      "source": [
-        "EMAIL_ADDRESS = \"[your-email-address]\"  # @param {type:\"string\"}\n",
-        "if not EMAIL_ADDRESS or EMAIL_ADDRESS == \"[your-email-address]\":\n",
-        "    print(\"EMAIL_ADDRESS not specified, please correct before proceeding.\")"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "83340af4",
       "metadata": {
         "id": "83340af4"
       },
@@ -356,18 +304,73 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "4814ea21",
       "metadata": {
         "id": "4814ea21"
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "06571eb4063b"
+      },
+      "source": [
+        "#### UUID\n",
+        "\n",
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4e166d927e36"
+      },
+      "outputs": [],
+      "source": [
+        "import random\n",
+        "import string\n",
+        "\n",
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "71404c9f"
+      },
+      "source": [
+        "#### Set your email address\n",
+        "This is used for delivering model monitoring notifications.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "4b1d2b69"
+      },
+      "outputs": [],
+      "source": [
+        "EMAIL_ADDRESS = \"[your-email-address]\"  # @param {type:\"string\"}\n",
+        "if not EMAIL_ADDRESS or EMAIL_ADDRESS == \"[your-email-address]\":\n",
+        "    print(\"EMAIL_ADDRESS not specified, please correct before proceeding.\")"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "20a546c3",
       "metadata": {
         "id": "20a546c3"
       },
@@ -375,16 +378,35 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench notebooks**, your environment is already\n",
-        "authenticated. Skip this step.\n",
+        "authenticated.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
-        "when prompted to authenticate your account via oAuth.\n"
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click **Create**. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "06c51076",
       "metadata": {
         "id": "06c51076"
       },
@@ -421,73 +443,284 @@
     },
     {
       "cell_type": "markdown",
-      "id": "6b01af18",
       "metadata": {
-        "id": "6b01af18"
+        "id": "bucket:custom"
       },
       "source": [
-        "### Upload the model\n",
+        "### Create a Cloud Storage bucket\n",
         "\n",
-        "The churn propensity model you'll be using in this notebook has been trained in BigQuery ML and exported to a Google Cloud Storage bucket. This illustrates how you can easily export a trained model and move a model from one cloud service to another. \n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "Next, import the model. **If you've already imported your model, you can skip this step.**"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "id": "9638ad2c",
-      "metadata": {
-        "id": "9638ad2c"
-      },
-      "source": [
-        "<span id=\"papermill-error-cell\" style=\"color:red; font-family:Helvetica Neue, Helvetica, Arial, sans-serif; font-size:2em;\">Execution using papermill encountered an exception here and stopped:</span>"
+        "Set the name of your Cloud Storage bucket below, which you use in this tutorial to upload the `input schema` for the monitoring service.\n",
+        "\n",
+        "Bucket names must be globally unique across all Google Cloud projects, including those outside of your organization."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "926e3ba8",
       "metadata": {
-        "id": "926e3ba8"
+        "id": "bucket"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
-        "import json\n",
-        "import time\n",
-        "import re\n",
-        "import tensorflow as tf\n",
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "source": [
+        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "create_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil mb -l $REGION $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "source": [
+        "Finally, validate access to your Cloud Storage bucket by examining its contents:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "validate_bucket"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil ls -al $BUCKET_URI"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "a0d294ff6d10"
+      },
+      "source": [
+        "### Import libraries"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "bd7a633296eb"
+      },
+      "outputs": [],
+      "source": [
+        "import google.cloud.aiplatform as aiplatform\n",
         "import tensorflow_data_validation as tfdv\n",
-        "from tensorflow_data_validation.utils import io_util \n",
-        "from tensorflow_metadata.proto.v0 import statistics_pb2\n",
-        "\n",
-        "MODEL_DISPLAY_NAME=f\"batch_prediction_monitoring_test_model_{datetime.now().strftime('%Y%m%d%H%M%S')}\"\n",
-        "CONTAINER_IMAGE_URI=\"us-docker.pkg.dev/cloud-aiplatform/prediction/tf2-cpu.2-4:latest\"\n",
-        "ARTIFACT_URI=\"gs://mco-mm/churn\"\n",
-        "\n",
-        "output = ! gcloud ai models upload \\\n",
-        "  --region=$REGION \\\n",
-        "  --display-name=$MODEL_DISPLAY_NAME \\\n",
-        "  --artifact-uri=$ARTIFACT_URI \\\n",
-        "  --container-image-uri=$CONTAINER_IMAGE_URI \\\n",
-        "  --format=\"value(model)\"\n",
-        "MODEL_ID = output[1].split(\"/\")[5]\n",
-        "print(f\"Model {MODEL_ID} created.\")"
+        "from tensorflow_data_validation.utils import io_util\n",
+        "from tensorflow_metadata.proto.v0 import statistics_pb2"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "source": [
+        "### Initialize Vertex AI SDK for Python\n",
+        "\n",
+        "Initialize the Vertex AI SDK for Python for your project and corresponding bucket."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "init_aip:mbsdk,all"
+      },
+      "outputs": [],
+      "source": [
+        "aiplatform.init(project=PROJECT_ID, location=REGION)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "accelerators:training,prediction"
+      },
+      "source": [
+        "#### Set hardware accelerators\n",
+        "\n",
+        "You can set hardware accelerators for prediction (e.g., GPUs) or choose not to use any (CPU). Hardware accelertors lower the latency response for a prediction request. When choosing a hardware accelerators, consider the additional cost trade-off over latency.\n",
+        "\n",
+        "Set the variables `DEPLOY_GPU/DEPLOY_NGPU` to use a container image supporting a GPU and the number of GPUs allocated to the virtual machine (VM) instance. For example, to use a GPU container image with 4 Nvidia Tesla K80 GPUs allocated to each VM, you would specify:\n",
+        "\n",
+        "    (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 4)\n",
+        "\n",
+        "See the [locations where accelerators are available](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators).\n",
+        "\n",
+        "Otherwise specify `(None, None)` to use a container image to run on a CPU."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xd5PLXDTlugv"
+      },
+      "outputs": [],
+      "source": [
+        "GPU = False\n",
+        "if GPU:\n",
+        "    DEPLOY_GPU, DEPLOY_NGPU = (aiplatform.gapic.AcceleratorType.NVIDIA_TESLA_K80, 1)\n",
+        "else:\n",
+        "    DEPLOY_GPU, DEPLOY_NGPU = (None, None)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "container:training,prediction"
+      },
+      "source": [
+        "#### Set pre-built containers\n",
+        "\n",
+        "Set the pre-built Docker container image for prediction.\n",
+        "\n",
+        "For the latest list, see [Pre-built containers for prediction](https://cloud.google.com/ai-platform-unified/docs/predictions/pre-built-containers)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1u1mr18jlugv"
+      },
+      "outputs": [],
+      "source": [
+        "if GPU:\n",
+        "    DEPLOY_VERSION = \"tf2-gpu.2-5\"\n",
+        "else:\n",
+        "    DEPLOY_VERSION = \"tf2-cpu.2-5\"\n",
+        "\n",
+        "DEPLOY_IMAGE = \"{}-docker.pkg.dev/vertex-ai/prediction/{}:latest\".format(\n",
+        "    REGION.split(\"-\")[0], DEPLOY_VERSION\n",
+        ")\n",
+        "\n",
+        "print(\"Deployment:\", DEPLOY_IMAGE, DEPLOY_GPU, DEPLOY_NGPU)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "machine:training,prediction"
+      },
+      "source": [
+        "#### Set machine types\n",
+        "\n",
+        "Next, set the machine types to use for training and prediction.\n",
+        "\n",
+        "- Set the variable `DEPLOY_COMPUTE` to configure your compute resources for prediction.\n",
+        " - `machine type`\n",
+        "     - `n1-standard`: 3.75GB of memory per vCPU\n",
+        "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
+        "     - `n1-highcpu`: 0.9 GB of memory per vCPU\n",
+        " - `vCPUs`: number of \\[2, 4, 8, 16, 32, 64, 96 \\]\n",
+        "\n",
+        "*Note: You may also use n2 and e2 machine types for training and deployment, but they do not support GPUs*."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "YAXwbqKKlugv"
+      },
+      "outputs": [],
+      "source": [
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "TRAIN_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Train machine type\", TRAIN_COMPUTE)\n",
+        "\n",
+        "MACHINE_TYPE = \"n1-standard\"\n",
+        "\n",
+        "VCPU = \"4\"\n",
+        "DEPLOY_COMPUTE = MACHINE_TYPE + \"-\" + VCPU\n",
+        "print(\"Deploy machine type\", DEPLOY_COMPUTE)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9bf06cd476e9"
+      },
+      "source": [
+        "### Upload the model artifacts as a `Vertex AI Model` resource\n",
+        "\n",
+        "First, you upload the pre-trained custom tabular model artifacts as a `Vertex AI Model` resource using the `upload()` method, with the following parameters:\n",
+        "\n",
+        "- `display_name`: The human readable name for the `Model` resource.\n",
+        "- `artifact_uri`: The Cloud Storage location of the model artifacts.\n",
+        "- `serving_container_image`: The serving container image to use when the model is deployed to a `Vertex AI Endpoint` resource.\n",
+        "- `sync`: Whether to wait for the process to complete, or return immediately (async)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0193f247e216"
+      },
+      "outputs": [],
+      "source": [
+        "MODEL_ARTIFACT_URI = \"gs://mco-mm/churn\"\n",
+        "\n",
+        "model = aiplatform.Model.upload(\n",
+        "    display_name=\"churn_\" + UUID,\n",
+        "    artifact_uri=MODEL_ARTIFACT_URI,\n",
+        "    serving_container_image_uri=DEPLOY_IMAGE,\n",
+        "    sync=True,\n",
+        ")\n",
+        "\n",
+        "print(model)"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "a4305ddf",
       "metadata": {
         "id": "a4305ddf"
       },
       "source": [
-        "## Submit a batch prediction request with model monitoring enabled"
+        "## Submit a batch prediction request with model monitoring enabled\n"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "053fde99",
       "metadata": {
         "id": "053fde99"
       },
@@ -503,7 +736,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "b832ad31",
       "metadata": {
         "id": "b832ad31"
       },
@@ -511,20 +743,17 @@
       "source": [
         "# Copy files to your projects gs bucket to avoid permission issues.\n",
         "# Ignore any error(s) for bucket already exists.\n",
-        "OUTPUT_GS_PATH = f\"gs://{PROJECT_ID.replace('-', '_')}_bp_mm_output\"\n",
-        "INPUT_GS_PATH = f\"gs://{PROJECT_ID.replace('-', '_')}_bp_mm_input\"\n",
+        "OUTPUT_GS_PATH = f\"{BUCKET_URI}/bp_mm_output\"\n",
+        "INPUT_GS_PATH = f\"{BUCKET_URI}/bp_mm_input\"\n",
         "PUBLIC_TRAINING_DATASET = \"gs://bp_mm_public_data/churn/churn_bp_insample.csv\"\n",
         "TRAINING_DATASET = f\"{INPUT_GS_PATH}/churn_bp_insample.csv\"\n",
         "TRAINING_DATASET_FORMAT = \"csv\"\n",
         "\n",
-        "! gsutil mb -p {PROJECT_ID} -l {REGION} -b on {INPUT_GS_PATH}\n",
-        "! gsutil mb -p {PROJECT_ID} -l {REGION} -b on {OUTPUT_GS_PATH}\n",
         "! gsutil copy $PUBLIC_TRAINING_DATASET $INPUT_GS_PATH"
       ]
     },
     {
       "cell_type": "markdown",
-      "id": "34c95126",
       "metadata": {
         "id": "34c95126"
       },
@@ -541,21 +770,18 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "3a54368a",
       "metadata": {
         "id": "3a54368a"
       },
       "outputs": [],
       "source": [
-        "now = datetime.now()\n",
         "INPUT_URI = \"gs://bp_mm_public_data/churn/churn_bp_outsample.jsonl\"\n",
         "OUTPUT_URI = OUTPUT_GS_PATH\n",
         "INSTANCES_FORMAT = \"jsonl\"\n",
         "PREDICTIONS_FORMAT = \"jsonl\"\n",
         "JOB_NAME_PREFIX = \"bp_mm_demo\"\n",
-        "MODEL_NAME = f\"projects/{PROJECT_ID}/locations/{REGION}/models/{MODEL_ID}\"\n",
-        "MACHINE_TYPE = \"n1-standard-8\"\n",
-        "BATCH_PREDICTION_JOB_NAME = JOB_NAME_PREFIX + \"_\" + now.strftime(\"%Y%m%d%H%M%S\")\n",
+        "MODEL_NAME = model.resource_name\n",
+        "BATCH_PREDICTION_JOB_NAME = JOB_NAME_PREFIX + \"_\" + UUID\n",
         "\n",
         "from google.cloud.aiplatform_v1beta1.types import (\n",
         "    BatchDedicatedResources, BatchPredictionJob, GcsDestination, GcsSource,\n",
@@ -573,7 +799,7 @@
         "        gcs_destination=GcsDestination(output_uri_prefix=OUTPUT_URI),\n",
         "    ),\n",
         "    dedicated_resources=BatchDedicatedResources(\n",
-        "        machine_spec=MachineSpec(machine_type=MACHINE_TYPE),\n",
+        "        machine_spec=MachineSpec(machine_type=DEPLOY_COMPUTE),\n",
         "        starting_replica_count=1,\n",
         "        max_replica_count=1,\n",
         "    ),\n",
@@ -604,7 +830,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "cae39778",
       "metadata": {
         "id": "cae39778"
       },
@@ -617,7 +842,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "bcdd4a47",
       "metadata": {
         "id": "bcdd4a47"
       },
@@ -638,7 +862,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "49ec90a0",
       "metadata": {
         "id": "49ec90a0"
       },
@@ -651,7 +874,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "c30496b5",
       "metadata": {
         "id": "c30496b5"
       },
@@ -664,7 +886,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "831651c2",
       "metadata": {
         "id": "831651c2"
       },
@@ -684,7 +905,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "a705c10b",
       "metadata": {
         "id": "a705c10b"
       },
@@ -695,7 +915,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "2bbdddac",
       "metadata": {
         "id": "2bbdddac"
       },
@@ -708,7 +927,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "f6c674e9",
       "metadata": {
         "id": "f6c674e9"
       },
@@ -746,7 +964,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "233b1266",
       "metadata": {
         "id": "233b1266"
       },
@@ -759,7 +976,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "4e8c00a7",
       "metadata": {
         "id": "4e8c00a7"
       },
@@ -774,7 +990,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "497a0016",
       "metadata": {
         "id": "497a0016"
       },
@@ -790,7 +1005,6 @@
     {
       "cell_type": "code",
       "execution_count": null,
-      "id": "eabc3f81",
       "metadata": {
         "id": "eabc3f81"
       },
@@ -806,7 +1020,6 @@
     },
     {
       "cell_type": "markdown",
-      "id": "0aa0219d",
       "metadata": {
         "id": "0aa0219d"
       },

notebooks/notebook_template.ipynb

@@ -29,6 +29,8 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
+        "# [TODO] Add your H1 title heading here\n",
+        "\n",
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
@@ -80,7 +82,7 @@
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- * {TODO: Add high level bullets for the steps of performed in the notebook}"
+        "- *{TODO: Add high level bullets for the steps of performed in the notebook}*"
       ]
     },
     {
@@ -109,35 +111,31 @@
         "This tutorial uses billable components of Google Cloud:\n",
         "\n",
         "* Vertex AI\n",
+        "* {TODO: BigQyuery}\n",
         "* Cloud Storage\n",
         "\n",
-        "{TODO: Include links to pricing documentation for each product you listed above.}\n",
+        "{TODO: Include links to pricing documentation for each product you listed above.\n",
+        " NOTE: If you use BigQuery or Dataflow, you need to add this to the pricing.\n",
+        "}\n",
         "\n",
-        "Learn about [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing) and [Cloud Storage\n",
-        "pricing](https://cloud.google.com/storage/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing),\n",
+        "{ TODO: [BigQuery pricing](https://cloud.google.com/bigquery/pricing), }\n",
+        "and [Cloud Storage pricing](https://cloud.google.com/storage/pricing), \n",
+        "and use the [Pricing Calculator](https://cloud.google.com/products/calculator/)\n",
         "to generate a cost estimate based on your projected usage."
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "ze4-nDLfK4pw"
-      },
-      "source": [
-        "### Set up your local development environment\n",
-        "\n",
-        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
-        "all the requirements to run this notebook. You can skip this step."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "gCuSR8GkAgzl"
       },
       "source": [
+        "### Set up your local development environment\n",
+        "\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
+        "\n",
         "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
         "You need the following:\n",
         "\n",
@@ -204,7 +202,7 @@
         "    USER_FLAG = \"--user\"\n",
         "\n",
         "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
-        "# TODO: Add remaining package installs here"
+        "# TODO: Add remaining package installs here. All packages should be on a single pip install to resolve dependencies"
       ]
     },
     {
@@ -237,21 +235,14 @@
         "    app.kernel.do_shutdown(True)"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "lWEdiXsJg0XY"
-      },
-      "source": [
-        "## Before you begin"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
         "id": "BF1j6f9HApxa"
       },
       "source": [
+        "## Before you begin\n",
+        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
@@ -412,21 +403,14 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "dr--iN2kAylZ"
+        "id": "sBCra4QMA2wR"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. Skip this step."
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "sBCra4QMA2wR"
-      },
-      "source": [
+        "authenticated. \n",
+        "\n",
         "**If you are using Colab**, run the cell below and follow the instructions\n",
         "when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -481,7 +465,7 @@
         "    # path to your service account key and run this cell to authenticate your GCP\n",
         "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
       ]
     },
     {
@@ -497,7 +481,7 @@
         "\n",
         "{TODO: Adjust wording in the first paragraph to fit your use case - explain how your tutorial uses the Cloud Storage bucket. The example below shows how Vertex AI uses the bucket for training.}\n",
         "\n",
-        "When you submit a training job using the Cloud SDK, you upload a Python package\n",
+        "When you submit a training job using the Vertex AI SDK, you upload a Python package\n",
         "containing your training code to a Cloud Storage bucket. Vertex AI runs\n",
         "the code from this package. In this tutorial, Vertex AI also saves the\n",
         "trained model that results from your job in the same bucket. Using this model artifact, you can then\n",

notebooks/notebook_template_review.py

@@ -56,7 +56,7 @@ def parse_notebook(path):
         # cell 1 is copyright
         nth = 0
         cell, nth = get_cell(path, cells, nth)
-        if not cell['source'][0].startswith('# Copyright'):
+        if not 'Copyright' in cell['source'][0]:
             report_error(path, 0, "missing copyright cell")
             
         # check for notices

notebooks/official/CODEOWNERS

@@ -16,6 +16,7 @@
 /model_monitoring @andrewferlitsch
 /tensorboard @zbl94
 
+/bigquery_ml/bqml-online-prediction.ipynb @polong-lin
 /model_monitoring/model_monitoring.ipynb @mco-gh
 /ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb @jialuzh
 /ml_metadata/sdk-metric-parameter-tracking-for-locally-trained-models.ipynb @jialuzh
@@ -28,6 +29,9 @@
 /automl/automl_forecasting_bqml_arima_plus_comparison.ipynb @TheMichaelHu
 /automl/automl_tabular_on_vertex_pipelines.ipynb @helinwang
 /custom/custom_training_tensorboard_profiler.ipynb @itseric
-/workbench/spark/spark_sample_notebook.ipynb @bmiro
+/workbench/spark/spark_sample_notebook.ipynb @bradmiro
+/workbench/spark/spark_ml.ipynb @bradmiro
 /model-registry/bqml-vertexai-model-registry.ipynb @soheilazangeneh
 /workbench/exploratory_data_analysis/explore_data_in_bigquery_with_workbench.ipynb @alokpattani
+/model_evaluation/automl_tabular_classification_model_evaluation.ipynb @soheilazangeneh
+/model_evaluation/automl_tabular_regression_model_evaluation.ipynb @soheilazangeneh

notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb

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

notebooks/official/automl/sdk_automl_tabular_regression_batch_bq.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# Copyright 2022 Google LLC.\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",

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

@@ -32,18 +32,18 @@
         "<table align=\"left\">\n",
         "\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/community/bigquery_ml/bqml-online-prediction.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/bigquery_ml/bqml-online-prediction.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -63,7 +63,7 @@
         "\n",
         "### Dataset\n",
         "\n",
-        "The dataset, [available publicly on BigQuery](https://console.cloud.google.com/bigquery?project=bigquery-public-data&d=ga4_obfuscated_sample_ecommerce&p=bigquery-public-data&page=dataset), comes from obfuscated [Google Analytics 4 data](https://support.google.com/analytics/answer/10937659) from the [Google Merchandise Store](https://shop.googlemerchandisestore.com/).\n",
+        "The dataset, <a href=\"https://console.cloud.google.com/bigquery?project=bigquery-public-data&d=ga4_obfuscated_sample_ecommerce&p=bigquery-public-data&page=dataset\" target=\"_blank\">available publicly on BigQuery</a>, comes from obfuscated <a href=\"https://support.google.com/analytics/answer/10937659\" target=\"_blank\">Google Analytics 4 data</a> from the <a href=\"https://shop.googlemerchandisestore.com/\" target=\"_blank\">Google Merchandise Store</a>).\n",
         "\n",
         "### Objective\n",
         "\n",
@@ -95,9 +95,9 @@
         "* Vertex AI\n",
         "\n",
         "\n",
-        "Learn about [BigQuery Pricing](https://cloud.google.com/bigquery/pricing), [BigQuery ML pricing](https://cloud.google.com/bigquery-ml/pricing), [Vertex AI\n",
-        "pricing](https://cloud.google.com/vertex-ai/pricing), and use the [Pricing\n",
-        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "Learn about <a href=\"https://cloud.google.com/bigquery/pricing\" target=\"_blank\">BigQuery Pricing</a>, <a href=\"https://cloud.google.com/bigquery-ml/pricing\" target=\"_blank\">BigQuery ML pricing</a>, <a href=\"https://cloud.google.com/vertex-ai/pricing\" target=\"_blank\">Vertex AI\n",
+        "pricing</a>, and use the <a href=\"https://cloud.google.com/products/calculator/\" target=\"_blank\">Pricing\n",
+        "Calculator</a>\n",
         "to generate a cost estimate based on your projected usage."
       ]
     },
@@ -128,18 +128,18 @@
         "* virtualenv\n",
         "* Jupyter notebook running in a virtual environment with Python 3\n",
         "\n",
-        "The Google Cloud guide to [Setting up a Python development\n",
-        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
-        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "The Google Cloud guide to <a href=\"https://cloud.google.com/python/setup\" target=\"_blank\">Setting up a Python development\n",
+        "environment</a> and the <a href=\"https://jupyter.org/install\" target=\"_blank\">Jupyter\n",
+        "installation guide</a> provide detailed instructions\n",
         "for meeting these requirements. The following steps provide a condensed set of\n",
         "instructions:\n",
         "\n",
-        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
+        "1. <a href=\"https://cloud.google.com/sdk/docs/\" target=\"_blank\">Install and initialize the Cloud SDK.</a>\n",
         "\n",
-        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
+        "1. <a href=\"https://cloud.google.com/python/setup#installing_python\" target=\"_blank\">Install Python 3.</a>\n",
         "\n",
-        "1. [Install\n",
-        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "1. <a href=\"https://cloud.google.com/python/setup#installing_and_using_virtualenv\" target=\"_blank\">Install\n",
+        "   virtualenv</a>\n",
         "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
         "\n",
         "1. To install Jupyter, run `pip3 install jupyter` on the\n",
@@ -234,13 +234,13 @@
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "1. <a href=\"https://console.cloud.google.com/cloud-resource-manager\" target=\"_blank\">Select or create a Google Cloud project</a>. When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
+        "1. <a href=\"https://cloud.google.com/billing/docs/how-to/modify-project\" target=\"_blank\">Make sure that billing is enabled for your project</a>.\n",
         "\n",
-        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "1. <a href=\"https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com\" target=\"_blank\">Enable the Vertex AI API</a>.\n",
         "\n",
-        "1. If you are running this notebook locally, you will need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
+        "1. If you are running this notebook locally, you will need to install the <a href=\"https://cloud.google.com/sdk\" target=\"_blank\">Cloud SDK</a>.\n",
         "\n",
         "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
@@ -267,7 +267,7 @@
       },
       "outputs": [],
       "source": [
-        "PROJECT_ID = \"YOUR-PROJECT-ID\"\n",
+        "PROJECT_ID = \"[YOUR-PROJECT-ID]\"\n",
         "\n",
         "# Get your Google Cloud project ID from gcloud\n",
         "import os\n",
@@ -314,9 +314,9 @@
         "- Europe: `europe-west4`\n",
         "- Asia Pacific: `asia-east1`\n",
         "\n",
-        "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
+        "You might not be able to use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
         "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
+        "Learn more about <a href=\"https://cloud.google.com/vertex-ai/docs/general/locations\" target=\"_blank\">Vertex AI regions</a>."
       ]
     },
     {
@@ -339,9 +339,9 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -352,9 +352,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -380,8 +387,7 @@
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "1. In the Cloud Console, go to the [**Create service account key**\n",
-        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "1. In the Cloud Console, go to the <a href=\"https://console.cloud.google.com/apis/credentials/serviceaccountkey\" target=\"_blank\">**Create service account key** page</a>.\n",
         "\n",
         "2. Click **Create service account**.\n",
         "\n",
@@ -486,7 +492,10 @@
       },
       "outputs": [],
       "source": [
+        "from typing import Union\n",
+        "\n",
         "import google.cloud.aiplatform as vertex_ai\n",
+        "import pandas as pd\n",
         "from google.cloud import bigquery"
       ]
     },
@@ -550,24 +559,17 @@
       "outputs": [],
       "source": [
         "# Wrapper to use BigQuery client to run query/job, return job ID or result as DF\n",
-        "def bq_query(sql):\n",
+        "def run_bq_query(sql: str) -> Union[str, pd.DataFrame]:\n",
         "    \"\"\"\n",
         "    Input: SQL query, as a string, to execute in BigQuery\n",
         "    Returns the query results as a pandas DataFrame, or error, if any\n",
         "    \"\"\"\n",
-        "    # Import Exceptions library to help with dataset error catching\n",
-        "    from google.cloud.exceptions import BadRequest\n",
         "\n",
         "    # Try dry run before executing query to catch any errors\n",
-        "    try:\n",
-        "        job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)\n",
-        "\n",
-        "        bq_client.query(sql, job_config=job_config)\n",
-        "\n",
-        "    except BadRequest as err:\n",
-        "        print(err)\n",
-        "        return\n",
+        "    job_config = bigquery.QueryJobConfig(dry_run=True, use_query_cache=False)\n",
+        "    bq_client.query(sql, job_config=job_config)\n",
         "\n",
+        "    # If dry run succeeds without errors, proceed to run query\n",
         "    job_config = bigquery.QueryJobConfig()\n",
         "    client_result = bq_client.query(sql, job_config=job_config)\n",
         "\n",
@@ -589,7 +591,7 @@
         "\n",
         "BigQuery ML (BQML) provides the capability to train ML tabular models, such as classification, regression, forecasting, and matrix factorization, in BigQuery using SQL syntax directly. BigQuery ML uses the scalable infrastructure of BigQuery ML so you don't need to set up additional infrastructure for training or batch serving.\n",
         "\n",
-        "Learn more about [BigQuery ML documentation](https://cloud.google.com/bigquery-ml/docs)."
+        "Learn more about <a href=\"https://cloud.google.com/bigquery-ml/docs\" target=\"_blank\">BigQuery ML documentation</a>."
       ]
     },
     {
@@ -600,9 +602,13 @@
       },
       "outputs": [],
       "source": [
-        "BQ_DATASET_NAME = \"ga4_churnprediction\"\n",
+        "BQ_DATASET_NAME = f\"ga4_churnprediction_{UUID}\"\n",
         "\n",
-        "bq_query(f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\")"
+        "sql_create_dataset = f\"\"\"CREATE SCHEMA IF NOT EXISTS {BQ_DATASET_NAME}\"\"\"\n",
+        "\n",
+        "print(sql_create_dataset)\n",
+        "\n",
+        "run_bq_query(sql_create_dataset)"
       ]
     },
     {
@@ -620,7 +626,7 @@
         "id": "49dd00d5fbe5"
       },
       "source": [
-        "Inpect data that has been pre-processed from [Google Analytics 4 data from the Google Merchandise Store](https://support.google.com/analytics/answer/10937659) so that it can be used for classification. For more information on how this data was prepared, read [this blog post](https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml).\n",
+        "Inpect data that has been pre-processed from <a href=\"https://support.google.com/analytics/answer/10937659\" target=\"_blank\">Google Analytics 4 data from the Google Merchandise Store</a> so that it can be used for classification. For more information on how this data was prepared, read <a href=\"https://cloud.google.com/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml\" target=\"_blank\">this blog post</a>.\n",
         "\n",
         "As seen below, each row represents a single user, and the columns represent their demographic features, their aggregated behavioral features in the first 24 hours of visiting the Google Merchandise Store, and the label (whether the user churned or returned any time after the first 24 hours)."
       ]
@@ -641,7 +647,7 @@
         "LIMIT\n",
         "    100\n",
         "\"\"\"\n",
-        "bq_query(sql_inspect)"
+        "run_bq_query(sql_inspect)"
       ]
     },
     {
@@ -662,9 +668,9 @@
         "The query below trains a logistic regression model using BigQuery ML. BigQuery resources are used to train the model.\n",
         "\n",
         "In the `OPTIONS` parameter:\n",
-        "* with `model_registry=\"vertex_ai\"`, the BigQuery ML model will automatically be [registered to Vertex AI Model Registry](https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml), which enables you to view all of your registered models and its versions on Google Cloud in one place.\n",
+        "* with `model_registry=\"vertex_ai\"`, the BigQuery ML model will automatically be <a href=\"https://cloud.google.com/vertex-ai/docs/model-registry/model-registry-bqml\" target=\"_blank\">registered to Vertex AI Model Registry</a>, which enables you to view all of your registered models and its versions on Google Cloud in one place.\n",
         "\n",
-        "* `vertex_ai_model_version_aliases allows you to set aliases to help you keep track of your model version ([documentation](https://cloud.google.com/vertex-ai/docs/model-registry/model-alias))."
+        "* `vertex_ai_model_version_aliases allows you to set aliases to help you keep track of your model version (<a href=\"https://cloud.google.com/vertex-ai/docs/model-registry/model-alias\" target=\"_blank\">documentation</a>)."
       ]
     },
     {
@@ -677,7 +683,7 @@
       "source": [
         "# this cell may take ~1 min to run\n",
         "\n",
-        "BQML_MODEL_NAME = \"bqmlmodelchurn\"\n",
+        "BQML_MODEL_NAME = f\"bqml_model_churn_{UUID}\"\n",
         "\n",
         "sql_train_model_bqml = f\"\"\"\n",
         "CREATE OR REPLACE MODEL {BQ_DATASET_NAME}.{BQML_MODEL_NAME}    \n",
@@ -696,7 +702,7 @@
         "\n",
         "print(sql_train_model_bqml)\n",
         "\n",
-        "bq_query(sql_train_model_bqml)"
+        "run_bq_query(sql_train_model_bqml)"
       ]
     },
     {
@@ -714,7 +720,7 @@
         "id": "2aaaae772f67"
       },
       "source": [
-        "With the model created, you can now evaluate the logistic regression model. Behind the scenes, BigQuery ML automatically [split the data](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method), which makes it easier to quickly train and evaluate models."
+        "With the model created, you can now evaluate the logistic regression model. Behind the scenes, BigQuery ML automatically <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-create#data_split_method\" target=\"_blank\">split the data</a>, which makes it easier to quickly train and evaluate models."
       ]
     },
     {
@@ -734,7 +740,7 @@
         "\n",
         "print(sql_evaluate_model)\n",
         "\n",
-        "bq_query(sql_evaluate_model)"
+        "run_bq_query(sql_evaluate_model)"
       ]
     },
     {
@@ -745,7 +751,7 @@
       "source": [
         "These metrics help you understand the performance of the model. \n",
         "\n",
-        "There are various metrics for logistic regression and other model types (full list of metrics can be found in the [documentation](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate#mlevaluate_output))."
+        "There are various metrics for logistic regression and other model types (full list of metrics can be found in the <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-evaluate#mlevaluate_output\" target=\"_blank\">documentation</a>)."
       ]
     },
     {
@@ -765,7 +771,7 @@
       "source": [
         "Make a batch prediction in BigQuery ML on the original training data to check the probability of churn for each of the users, as seen in the `probability` column, with the predicted label under the `predicted_churn` column.\n",
         "\n",
-        "[ML.EXPLAIN_PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict) has built-in [Explainable AI](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-xai-overview). This allows you to see the top contributing features to each prediction and interpret how it was computed."
+        "<a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict\" target=\"_blank\">ML.EXPLAIN_PREDICT</a> has built-in <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-xai-overview\" target=\"_blank\">Explainable AI</a>. This allows you to see the top contributing features to each prediction and interpret how it was computed."
       ]
     },
     {
@@ -787,7 +793,7 @@
         "\n",
         "print(sql_explain_predict)\n",
         "\n",
-        "bq_query(sql_explain_predict)"
+        "run_bq_query(sql_explain_predict)"
       ]
     },
     {
@@ -796,7 +802,7 @@
         "id": "fa1f96c0f452"
       },
       "source": [
-        "Since the `top_feature_attributions` is a nested column, you can unnest the array ([documentation](https://cloud.google.com/bigquery/docs/reference/standard-sql/arrays)) into separate rows for each of the features. In other words, since ML.EXPLAIN_PREDICT provides the top 5 most important features, using `UNNEST` results in 5 rows per prediction:"
+        "Since the `top_feature_attributions` is a nested column, you can unnest the array (<a href=\"https://cloud.google.com/bigquery/docs/reference/standard-sql/arrays\" target=\"_blank\">documentation</a>) into separate rows for each of the features. In other words, since ML.EXPLAIN_PREDICT provides the top 5 most important features, using `UNNEST` results in 5 rows per prediction:"
       ]
     },
     {
@@ -827,7 +833,7 @@
         "\n",
         "print(sql_explain_predict)\n",
         "\n",
-        "bq_query(sql_explain_predict)"
+        "run_bq_query(sql_explain_predict)"
       ]
     },
     {
@@ -847,7 +853,7 @@
       "source": [
         "When the model was trained in BigQuery ML, the line `model_registry=\"vertex_ai\"` registered the model to Vertex AI Model Registry automatically upon completion.\n",
         "\n",
-        "You can view the model on the [Vertex AI Model Registry page](https://console.cloud.google.com/vertex-ai/models), or use the code below to check that it was successfully registered:"
+        "You can view the model on the <a href=\"https://console.cloud.google.com/vertex-ai/models\" target=\"_blank\">Vertex AI Model Registry page</a>, or use the code below to check that it was successfully registered:"
       ]
     },
     {
@@ -858,12 +864,7 @@
       },
       "outputs": [],
       "source": [
-        "print(f\"BQML_MODEL_NAME = {BQML_MODEL_NAME}\")\n",
-        "\n",
-        "models = vertex_ai.Model.list(\n",
-        "    filter=f\"display_name={BQML_MODEL_NAME}\", order_by=\"update_time\"\n",
-        ")\n",
-        "model = models[0]\n",
+        "model = vertex_ai.Model(model_name=BQML_MODEL_NAME)\n",
         "\n",
         "print(model.gca_resource)"
       ]
@@ -883,7 +884,7 @@
         "id": "b6120dcc1ff6"
       },
       "source": [
-        "While BigQuery ML supports batch prediction with [ML.PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-predict) and [ML.EXPLAIN_PREDICT](https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict), BigQuery ML is not suitable for real-time predictions where you need low latency predictions with potentially high frequency of requests.\n",
+        "While BigQuery ML supports batch prediction with <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-predict\" target=\"_blank\">ML.PREDICT</a> and <a href=\"https://cloud.google.com/bigquery-ml/docs/reference/standard-sql/bigqueryml-syntax-explain-predict\" target=\"_blank\">ML.EXPLAIN_PREDICT</a>, BigQuery ML is not suitable for real-time predictions where you need low latency predictions with potentially high frequency of requests.\n",
         "\n",
         "In other words, deploying the BigQuery ML model to an endpoint enables you to do online predictions."
       ]
@@ -906,30 +907,6 @@
         "To deploy your model to an endpoint, you will first need to create an endpoint before you deploy the model to it."
       ]
     },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "3ce73125dff6"
-      },
-      "outputs": [],
-      "source": [
-        "def create_endpoint(\n",
-        "    project: str,\n",
-        "    display_name: str,\n",
-        "    location: str,\n",
-        "):\n",
-        "    endpoint = vertex_ai.Endpoint.create(\n",
-        "        display_name=display_name,\n",
-        "        project=project,\n",
-        "        location=location,\n",
-        "    )\n",
-        "\n",
-        "    print(endpoint.display_name)\n",
-        "    print(endpoint.resource_name)\n",
-        "    return endpoint"
-      ]
-    },
     {
       "cell_type": "code",
       "execution_count": null,
@@ -938,17 +915,16 @@
       },
       "outputs": [],
       "source": [
-        "endpoint_name = f\"{BQML_MODEL_NAME}-{TIMESTAMP}\"\n",
+        "ENDPOINT_NAME = f\"{BQML_MODEL_NAME}-endpoint\"\n",
         "\n",
-        "print(\n",
-        "    f\"\"\"\n",
-        "PROJECT_ID: {PROJECT_ID},\n",
-        "endpoint_name: {endpoint_name}\n",
-        "REGION: {REGION}\n",
-        "\"\"\"\n",
+        "endpoint = vertex_ai.Endpoint.create(\n",
+        "    display_name=ENDPOINT_NAME,\n",
+        "    project=PROJECT_ID,\n",
+        "    location=REGION,\n",
         ")\n",
         "\n",
-        "create_endpoint(PROJECT_ID, endpoint_name, REGION)"
+        "print(endpoint.display_name)\n",
+        "print(endpoint.resource_name)"
       ]
     },
     {
@@ -966,31 +942,7 @@
         "id": "951ed1693f6b"
       },
       "source": [
-        "List the endpoints to make sure it has successfully been created. You can also view your endpoints on the [Vertex AI Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints?project=polong-contentdev)."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0a9bad8d9ad4"
-      },
-      "outputs": [],
-      "source": [
-        "endpoint = vertex_ai.Endpoint.list(\n",
-        "    # filter=f'display_name={endpoint_name}', # optional: filter by specific endpoint name\n",
-        "    order_by=\"update_time\"\n",
-        ")\n",
-        "endpoint[-1]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "2431a4d28d97"
-      },
-      "source": [
-        "Retrieve the endpoint id so you can use it in the next step."
+        "List the endpoints to make sure it has successfully been created. (You can also view your endpoints on the <a href=\"https://console.cloud.google.com/vertex-ai/endpoints\" target=\"_blank\">Vertex AI Endpoints page</a>)."
       ]
     },
     {
@@ -1001,7 +953,7 @@
       },
       "outputs": [],
       "source": [
-        "endpoint[-1].to_dict()"
+        "endpoint.list()"
       ]
     },
     {
@@ -1019,74 +971,19 @@
         "id": "6a90be5b77a2"
       },
       "source": [
-        "With the model, you can now deploy it to an endpoint. "
+        "With the new endpoint, you can now deploy your model."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "af323ea42c5b"
-      },
-      "outputs": [],
-      "source": [
-        "from typing import Dict, Optional, Sequence, Tuple\n",
-        "\n",
-        "\n",
-        "def deploy_model_with_automatic_resources_sample(\n",
-        "    project,\n",
-        "    location,\n",
-        "    model_name: str,\n",
-        "    endpoint: Optional[vertex_ai.Endpoint] = None,\n",
-        "    deployed_model_display_name: Optional[str] = None,\n",
-        "    traffic_percentage: Optional[int] = 0,\n",
-        "    traffic_split: Optional[Dict[str, int]] = None,\n",
-        "    min_replica_count: int = 1,\n",
-        "    max_replica_count: int = 1,\n",
-        "    metadata: Optional[Sequence[Tuple[str, str]]] = (),\n",
-        "    sync: bool = True,\n",
-        "):\n",
-        "    \"\"\"\n",
-        "    model_name: A fully-qualified model resource name or model ID.\n",
-        "          Example: \"projects/123/locations/us-central1/models/456\" or\n",
-        "          \"456\" when project and location are initialized or passed.\n",
-        "    \"\"\"\n",
-        "\n",
-        "    model = vertex_ai.Model(model_name=model_name)\n",
-        "\n",
-        "    model.deploy(\n",
-        "        endpoint=endpoint,\n",
-        "        deployed_model_display_name=deployed_model_display_name,\n",
-        "        traffic_percentage=traffic_percentage,\n",
-        "        traffic_split=traffic_split,\n",
-        "        min_replica_count=min_replica_count,\n",
-        "        max_replica_count=max_replica_count,\n",
-        "        metadata=metadata,\n",
-        "        sync=sync,\n",
-        "    )\n",
-        "\n",
-        "    model.wait()\n",
-        "\n",
-        "    print(model.display_name)\n",
-        "    print(model.resource_name)\n",
-        "    return"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "9e6763369af4"
+        "id": "c70ecc568ee5"
       },
       "outputs": [],
       "source": [
         "# deploying the model to the endpoint may take 10-15 minutes\n",
-        "deploy_model_with_automatic_resources_sample(\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    model_name=BQML_MODEL_NAME,\n",
-        "    endpoint=endpoint[-1],\n",
-        ")"
+        "model.deploy(endpoint=endpoint)"
       ]
     },
     {
@@ -1095,7 +992,7 @@
         "id": "c303d779477b"
       },
       "source": [
-        "You can also check on the status of your model by visiting the [Vertex AI Endpoints page](https://console.cloud.google.com/vertex-ai/endpoints)."
+        "You can also check on the status of your model by visiting the <a href=\"https://console.cloud.google.com/vertex-ai/endpoints\" target=\"_blank\">Vertex AI Endpoints page</a>."
       ]
     },
     {
@@ -1168,35 +1065,12 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "2c6093ce9f8a"
+        "id": "b4839f31d2f8"
       },
       "outputs": [],
       "source": [
-        "def endpoint_predict_sample(\n",
-        "    project: str, location: str, instances: list, endpoint: str\n",
-        "):\n",
-        "    endpoint = vertex_ai.Endpoint(endpoint)\n",
-        "\n",
-        "    prediction = endpoint.predict(instances=instances)\n",
-        "    return prediction"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "0c41fd6eeb6f"
-      },
-      "outputs": [],
-      "source": [
-        "prediction_response = endpoint_predict_sample(\n",
-        "    project=PROJECT_ID,\n",
-        "    location=REGION,\n",
-        "    instances=df_sample_requests_list,\n",
-        "    endpoint=endpoint[-1].name,\n",
-        ")\n",
-        "\n",
-        "prediction_response"
+        "prediction = endpoint.predict(df_sample_requests_list)\n",
+        "print(prediction)"
       ]
     },
     {
@@ -1216,7 +1090,7 @@
       },
       "outputs": [],
       "source": [
-        "prediction_response.predictions"
+        "prediction.predictions"
       ]
     },
     {
@@ -1227,8 +1101,8 @@
       "source": [
         "## Cleaning up\n",
         "\n",
-        "To clean up all Google Cloud resources used in this project, you can [delete the Google Cloud\n",
-        "project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects) you used for the tutorial.\n",
+        "To clean up all Google Cloud resources used in this project, you can <a href=\"https://cloud.google.com/resource-manager/docs/creating-managing-projects#shutting_down_projects\" target=\"_blank\">delete the Google Cloud\n",
+        "project</a> you used for the tutorial.\n",
         "\n",
         "Otherwise, you can delete the individual resources you created in this tutorial:"
       ]
@@ -1241,18 +1115,12 @@
       },
       "outputs": [],
       "source": [
-        "# MODEL_ID = model.name\n",
+        "# Undeploy model from endpoint and delete endpoint\n",
+        "endpoint.undeploy_all()\n",
+        "endpoint.delete()\n",
         "\n",
-        "ENDPOINT_ID = int(endpoint[-1].name)\n",
-        "\n",
-        "# Undeploy model from endpoint\n",
-        "endpoint[-1].undeploy_all()\n",
-        "\n",
-        "# Delete endpoint resource\n",
-        "! gcloud ai endpoints delete $ENDPOINT_ID --quiet --region $REGION\n",
-        "\n",
-        "# Delete BigQuery ML model\n",
-        "! bq rm -f --model $PROJECT_ID\\:$BQ_DATASET_NAME\\.$BQML_MODEL_NAME"
+        "# Delete BigQuery dataset, including the BigQuery ML model\n",
+        "! bq rm -r -f $PROJECT_ID:$BQ_DATASET_NAME"
       ]
     }
   ],

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

@@ -263,7 +263,7 @@
         "\n",
         "2. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "3. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com).\n",
+        "3. [Enable the following APIs: Vertex AI API, Cloud Resource Manager API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,cloudresourcemanager.googleapis.com).\n",
         "\n",
         "4. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",

notebooks/official/migration/UJ11 Vertex SDK Hyperparameter Tuning.ipynb

@@ -32,17 +32,24 @@
         "# Vertex AI: Vertex AI Migration: Hyperparameter Tuning\n",
         "\n",
         "<table align=\"left\">\n",
+        "\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/UJ11%20Vertex%20SDK%20Hyperparameter%20Tuning.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ11 Vertex SDK Hyperparameter Tuning.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/UJ11%20Vertex%20SDK%20Hyperparameter%20Tuning.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ11 Vertex SDK Hyperparameter Tuning.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/migration/UJ11 Vertex SDK Hyperparameter Tuning.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/>"
       ]
@@ -55,7 +62,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the [Boston Housing Prices dataset](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html). The version of the dataset you will use in this tutorial is built into TensorFlow. The trained model predicts the median price of a house in units of 1K USD."
+        "The dataset used for this tutorial is the [Boston Housing Prices dataset](https://www.cs.toronto.edu/~delve/data/boston/bostonDetail.html). The version of the dataset you use in this tutorial is built into TensorFlow. The trained model predicts the median price of a house in units of 1K USD."
       ]
     },
     {
@@ -138,7 +145,7 @@
         "else:\n",
         "    USER_FLAG = \"\"\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
+        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG -q"
       ]
     },
     {
@@ -158,7 +165,7 @@
       },
       "outputs": [],
       "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
+        "! pip3 install -U google-cloud-storage $USER_FLAG -q"
       ]
     },
     {
@@ -212,7 +219,7 @@
         "\n",
         "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
         "\n",
-        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
         "\n",
         "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
@@ -285,7 +292,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -294,9 +304,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -307,9 +317,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -320,7 +337,7 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Google Cloud Notebooks**, your environment is already authenticated.\n",
         "\n",
         "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
         "\n",
@@ -355,8 +372,11 @@
         "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",
@@ -392,7 +412,8 @@
       },
       "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}\""
       ]
     },
     {
@@ -403,8 +424,9 @@
       },
       "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-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -424,7 +446,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
@@ -444,7 +466,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -489,7 +511,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -511,7 +533,7 @@
         "\n",
         "Learn more [here](https://cloud.google.com/vertex-ai/docs/general/locations#accelerators) hardware accelerator support for your region\n",
         "\n",
-        "*Note*: TF releases before 2.3 for GPU support will fail to load the custom model in this tutorial. It is a known issue and fixed in TF 2.3 -- which is caused by static graph ops that are generated in the serving function. If you encounter this issue on your own custom models, use a container image for TF 2.3 with GPU support."
+        "*Note*: TF releases before 2.3 for GPU support  fail to load the custom model in this tutorial. It is a known issue and fixed in TF 2.3 -- which is caused by static graph ops that are generated in the serving function. If you encounter this issue on your own custom models, use a container image for TF 2.3 with GPU support."
       ]
     },
     {
@@ -522,6 +544,8 @@
       },
       "outputs": [],
       "source": [
+        "import os\n",
+        "\n",
         "if os.getenv(\"IS_TESTING_TRAIN_GPU\"):\n",
         "    TRAIN_GPU, TRAIN_NGPU = (\n",
         "        aip.gapic.AcceleratorType.NVIDIA_TESLA_K80,\n",
@@ -605,7 +629,7 @@
         "\n",
         "Next, set the machine type to use for training and prediction.\n",
         "\n",
-        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you will use for for training and prediction.\n",
+        "- Set the variables `TRAIN_COMPUTE` and `DEPLOY_COMPUTE` to configure  the compute resources for the VMs you use for for training and prediction.\n",
         " - `machine type`\n",
         "     - `n1-standard`: 3.75GB of memory per vCPU.\n",
         "     - `n1-highmem`: 6.5GB of memory per vCPU\n",
@@ -657,7 +681,7 @@
         "\n",
         "#### Package layout\n",
         "\n",
-        "Before you start the training, you will look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
+        "Before you start the training, you look at how a Python package is assembled for a custom training job. When unarchived, the package contains the following directory/file layout.\n",
         "\n",
         "- PKG-INFO\n",
         "- README.md\n",
@@ -673,7 +697,7 @@
         "\n",
         "#### Package Assembly\n",
         "\n",
-        "In the following cells, you will assemble the training package."
+        "In the following cells, you assemble the training package."
       ]
     },
     {
@@ -721,7 +745,7 @@
         "- Build a DNN model.\n",
         "- The number of units per dense layer and learning rate hyperparameter values are used during the build and compile of the model.\n",
         "- A definition of a callback `HPTCallback` which obtains the validation loss at the end of each epoch (`on_epoch_end()`) and reports it to the hyperparameter tuning service using `hpt.report_hyperparameter_tuning_metric()`.\n",
-        "- Train the model with the `fit()` method and specify a callback which will report the validation loss back to the hyperparameter tuning service."
+        "- Train the model with the `fit()` method and specify a callback which report the validation loss back to the hyperparameter tuning service."
       ]
     },
     {
@@ -854,7 +878,7 @@
         "! 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"
       ]
     },
     {
@@ -885,7 +909,7 @@
         "\n",
         "Now define the machine specification for your custom training job. This tells Vertex what type of machine instance to provision for the training.\n",
         "  - `machine_type`: The type of GCP instance to provision -- e.g., n1-standard-8.\n",
-        "  - `accelerator_type`: The type, if any, of hardware accelerator. In this tutorial if you previously set the variable `TRAIN_GPU != None`, you are using a GPU; otherwise you will use a CPU.\n",
+        "  - `accelerator_type`: The type, if any, of hardware accelerator. In this tutorial if you previously set the variable `TRAIN_GPU != None`, you are using a GPU; otherwise you use a CPU.\n",
         "  - `accelerator_count`: The number of accelerators."
       ]
     },
@@ -943,7 +967,7 @@
       "source": [
         "### Define the worker pool specification\n",
         "\n",
-        "Next, you define the worker pool specification for your custom training job. The worker pool specification will consist of the following:\n",
+        "Next, you define the worker pool specification for your custom training job. The worker pool specification  consist of the following:\n",
         "\n",
         "- `replica_count`: The number of instances to provision of this machine type.\n",
         "- `machine_spec`: The hardware specification.\n",
@@ -955,11 +979,11 @@
         "\n",
         "-`executor_image_spec`: This is the docker image which is configured for your custom training job.\n",
         "\n",
-        "-`package_uris`: This is a list of the locations (URIs) of your python training packages to install on the provisioned instance. The locations need to be in a Cloud Storage bucket. These can be either individual python files or a zip (archive) of an entire package. In the later case, the job service will unzip (unarchive) the contents into the docker image.\n",
+        "-`package_uris`: This is a list of the locations (URIs) of your python training packages to install on the provisioned instance. The locations need to be in a Cloud Storage bucket. These can be either individual python files or a zip (archive) of an entire package. In the later case, the job service  unzip (unarchive) the contents into the docker image.\n",
         "\n",
-        "-`python_module`: The Python module (script) to invoke for running the custom training job. In this example, you will be invoking `trainer.task.py` -- note that it was not neccessary to append the `.py` suffix.\n",
+        "-`python_module`: The Python module (script) to invoke for running the custom training job. In this example, you  be invoking `trainer.task.py` -- note that it was not neccessary to append the `.py` suffix.\n",
         "\n",
-        "-`args`: The command line arguments to pass to the corresponding Pythom module. In this example, you will be setting:\n",
+        "-`args`: The command line arguments to pass to the corresponding Pythom module. In this example, you  be setting:\n",
         "  - `\"--model-dir=\" + MODEL_DIR` : The Cloud Storage location where to store the model artifacts. There are two ways to tell the training script where to save the model artifacts:\n",
         "      - direct: You pass the Cloud Storage location as a command line argument to your training script (set variable `DIRECT = True`), or\n",
         "      - indirect: The service passes the Cloud Storage location as the environment variable `AIP_MODEL_DIR` to your training script (set variable `DIRECT = False`). In this case, you tell the service the model artifact location in the job specification.\n",
@@ -979,8 +1003,8 @@
       },
       "outputs": [],
       "source": [
-        "JOB_NAME = \"custom_job_\" + TIMESTAMP\n",
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_NAME, JOB_NAME)\n",
+        "JOB_NAME = \"custom_job_\" + UUID\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, JOB_NAME)\n",
         "\n",
         "if not TRAIN_NGPU or TRAIN_NGPU < 2:\n",
         "    TRAIN_STRATEGY = \"single\"\n",
@@ -1012,7 +1036,7 @@
         "        \"disk_spec\": disk_spec,\n",
         "        \"python_package_spec\": {\n",
         "            \"executor_image_uri\": TRAIN_IMAGE,\n",
-        "            \"package_uris\": [BUCKET_NAME + \"/trainer_boston.tar.gz\"],\n",
+        "            \"package_uris\": [BUCKET_URI + \"/trainer_boston.tar.gz\"],\n",
         "            \"python_module\": \"trainer.task\",\n",
         "            \"args\": CMDARGS,\n",
         "        },\n",
@@ -1051,9 +1075,7 @@
       },
       "outputs": [],
       "source": [
-        "job = aip.CustomJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP, worker_pool_specs=worker_pool_spec\n",
-        ")\n",
+        "job = aip.CustomJob(display_name=\"boston_\" + UUID, worker_pool_specs=worker_pool_spec)\n",
         "\n",
         "# print(job)"
       ]
@@ -1085,7 +1107,7 @@
         "from google.cloud.aiplatform import hyperparameter_tuning as hpt\n",
         "\n",
         "hpt_job = aip.HyperparameterTuningJob(\n",
-        "    display_name=\"boston_\" + TIMESTAMP,\n",
+        "    display_name=\"boston_\" + UUID,\n",
         "    custom_job=job,\n",
         "    metric_spec={\n",
         "        \"val_loss\": \"minimize\",\n",
@@ -1155,7 +1177,7 @@
       "source": [
         "### Display the hyperparameter tuning job trial results\n",
         "\n",
-        "After the hyperparameter tuning job has completed, the property `trials` will return the results for each trial."
+        "After the hyperparameter tuning job has completed, the property `trials`  return the results for each trial."
       ]
     },
     {
@@ -1350,7 +1372,7 @@
         "        print(e)\n",
         "\n",
         "    if \"BUCKET_NAME\" in globals():\n",
-        "        ! gsutil rm -r $BUCKET_NAME"
+        "        ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/migration/UJ4 Vertex SDK AutoML Tabular Binary Classification.ipynb

@@ -32,19 +32,64 @@
         "# Vertex AI: Vertex AI Migration: AutoML Tabular Binary Classification\n",
         "\n",
         "<table align=\"left\">\n",
+        "\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/UJ4%20Vertex%20SDK%20AutoML%20Tabular%20Binary%20Classification.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ4 Vertex SDK AutoML Tabular Binary 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/ai-platform-samples/blob/master/vertex-ai-samples/tree/master/notebooks/official/migration/UJ4%20Vertex%20SDK%20AutoML%20Tabular%20Binary%20Classification.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/migration/UJ4 Vertex SDK AutoML Tabular Binary 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",
-        "</table>\n",
-        "<br/><br/><br/>"
+        "  <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/migration/UJ4 Vertex SDK AutoML Tabular Binary 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>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fb82f94bbbc7"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "\n",
+        "This tutorial demonstrates how to use the Vertex AI SDK to create tabular binary classification models and do online prediction using a Google Cloud [AutoML](https://cloud.google.com/vertex-ai/docs/start/automl-users) model."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "9f80bba45dd5"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you create an AutoML tabular binary classification model and deploy for online prediction from a Python script using the Vertex AI SDK. You can alternatively create and deploy models using the `gcloud` command-line tool or online using the Cloud Console.\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services and resources:\n",
+        "\n",
+        "- Vertex AI managed Datasets\n",
+        "- Vertex AI Training\n",
+        "- Vertex AI Endpoints\n",
+        "- Vertex AI prediction\n",
+        "\n",
+        "The steps performed include:\n",
+        "\n",
+        "- Create a Vertex `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`"
       ]
     },
     {
@@ -55,7 +100,7 @@
       "source": [
         "### Dataset\n",
         "\n",
-        "The dataset used for this tutorial is the Bank Marketing. This dataset does not require any feature engineering. The version of the dataset you will use in this tutorial is stored in a public Cloud Storage bucket."
+        "The dataset used for this tutorial is the [Bank Marketing](https://pantheon.corp.google.com/storage/browser/_details/cloud-ml-tables-data/bank-marketing.csv) . This dataset does not require any feature engineering. The version of the dataset you use in this tutorial is stored in a public Cloud Storage bucket."
       ]
     },
     {
@@ -86,29 +131,38 @@
       "source": [
         "### Set up your local development environment\n",
         "\n",
-        "If you are using Colab or Google Cloud Notebooks, your environment already meets all the requirements to run this notebook. You can skip this step.\n",
+        "**If you are using Colab or Vertex AI Workbench Notebooks**, your environment already meets\n",
+        "all the requirements to run this notebook. You can skip this step.\n",
         "\n",
-        "Otherwise, make sure your environment meets this notebook's requirements. You need the following:\n",
+        "**Otherwise**, make sure your environment meets this notebook's requirements.\n",
+        "You need the following:\n",
         "\n",
-        "- The Cloud Storage SDK\n",
-        "- Git\n",
-        "- Python 3\n",
-        "- virtualenv\n",
-        "- Jupyter notebook running in a virtual environment with Python 3\n",
+        "* The Google Cloud SDK\n",
+        "* Git\n",
+        "* Python 3\n",
+        "* virtualenv\n",
+        "* Jupyter notebook running in a virtual environment with Python 3\n",
         "\n",
-        "The Cloud Storage guide to [Setting up a Python development environment](https://cloud.google.com/python/setup) and the [Jupyter installation guide](https://jupyter.org/install) provide detailed instructions for meeting these requirements. The following steps provide a condensed set of instructions:\n",
+        "The Google Cloud guide to [Setting up a Python development\n",
+        "environment](https://cloud.google.com/python/setup) and the [Jupyter\n",
+        "installation guide](https://jupyter.org/install) provide detailed instructions\n",
+        "for meeting these requirements. The following steps provide a condensed set of\n",
+        "instructions:\n",
         "\n",
-        "1. [Install and initialize the SDK](https://cloud.google.com/sdk/docs/).\n",
+        "1. [Install and initialize the Cloud SDK.](https://cloud.google.com/sdk/docs/)\n",
         "\n",
-        "2. [Install Python 3](https://cloud.google.com/python/setup#installing_python).\n",
+        "1. [Install Python 3.](https://cloud.google.com/python/setup#installing_python)\n",
         "\n",
-        "3. [Install virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv) and create a virtual environment that uses Python 3.  Activate the virtual environment.\n",
+        "1. [Install\n",
+        "   virtualenv](https://cloud.google.com/python/setup#installing_and_using_virtualenv)\n",
+        "   and create a virtual environment that uses Python 3. Activate the virtual environment.\n",
         "\n",
-        "4. To install Jupyter, run `pip3 install jupyter` on the command-line in a terminal shell.\n",
+        "1. To install Jupyter, run `pip3 install jupyter` on the\n",
+        "command-line in a terminal shell.\n",
         "\n",
-        "5. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
+        "1. To launch Jupyter, run `jupyter notebook` on the command-line in a terminal shell.\n",
         "\n",
-        "6. Open this notebook in the Jupyter Notebook Dashboard.\n"
+        "1. Open this notebook in the Jupyter Notebook Dashboard."
       ]
     },
     {
@@ -119,7 +173,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex SDK for Python."
+        "Install the following packages required to execute this notebook. "
       ]
     },
     {
@@ -132,33 +186,18 @@
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_storage"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-storage* and *tensorflow* libraries as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_storage"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U google-cloud-storage 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 fsspec gcsfs $USER_FLAG"
       ]
     },
     {
@@ -169,7 +208,7 @@
       "source": [
         "### Restart the kernel\n",
         "\n",
-        "Once you've installed the additional packages, you need to restart the notebook kernel so it can find the packages."
+        "After you install the additional packages, you need to restart the notebook kernel so it can find the packages."
       ]
     },
     {
@@ -180,6 +219,7 @@
       },
       "outputs": [],
       "source": [
+        "# Automatically restart kernel after installs\n",
         "import os\n",
         "\n",
         "if not os.getenv(\"IS_TESTING\"):\n",
@@ -193,31 +233,38 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin:nogpu"
+        "id": "c27795e4f4a1"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU runtime\n",
-        "\n",
-        "This tutorial does not require a GPU runtime.\n",
-        "\n",
         "### Set up your Google Cloud project\n",
         "\n",
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
         "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "1. [Make sure that billing is enabled for your project](https://cloud.google.com/billing/docs/how-to/modify-project).\n",
         "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "1. [Enable the Vertex AI API](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com). \n",
         "\n",
-        "4. If you are running this notebook locally, you will need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
+        "1. If you are running this notebook locally, you need to install the [Cloud SDK](https://cloud.google.com/sdk).\n",
         "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "1. Enter your project ID in the cell below. Then run the cell to make sure the\n",
         "Cloud SDK uses the right project for all the commands in this notebook.\n",
         "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "1460fd744366"
+      },
+      "source": [
+        "#### Set your project ID\n",
+        "\n",
+        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
       ]
     },
     {
@@ -266,7 +313,7 @@
         "#### Region\n",
         "\n",
         "You can also change the `REGION` variable, which is used for operations\n",
-        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. We recommend that you choose the region closest to you.\n",
+        "throughout the rest of this notebook.  Below are regions supported for Vertex AI. It is recommended that you choose the region closest to you.\n",
         "\n",
         "- Americas: `us-central1`\n",
         "- Europe: `europe-west4`\n",
@@ -274,7 +321,7 @@
         "\n",
         "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
         "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -285,7 +332,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"us-central1\"  # @param {type: \"string\"}"
+        "REGION = \"[your-region]\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -294,9 +344,9 @@
         "id": "timestamp"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -307,36 +357,52 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "32e1cd21a5d5"
       },
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebooks**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
+        "authenticated. \n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**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."
       ]
     },
     {
@@ -355,8 +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",
@@ -379,7 +448,7 @@
         "\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."
       ]
@@ -392,7 +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}\""
       ]
     },
     {
@@ -403,8 +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-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -424,7 +495,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION -p $PROJECT_ID $BUCKET_URI"
       ]
     },
     {
@@ -444,7 +515,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -453,9 +524,6 @@
         "id": "setup_vars"
       },
       "source": [
-        "### Set up variables\n",
-        "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
         "### Import libraries and define constants"
       ]
     },
@@ -467,7 +535,8 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aip\n",
+        "import pandas as pd"
       ]
     },
     {
@@ -476,9 +545,9 @@
         "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."
       ]
     },
     {
@@ -594,7 +663,7 @@
       "outputs": [],
       "source": [
         "dataset = aip.TabularDataset.create(\n",
-        "    display_name=\"Bank Marketing\" + \"_\" + TIMESTAMP, gcs_source=[IMPORT_FILE]\n",
+        "    display_name=\"Bank Marketing\" + \"_\" + UUID, gcs_source=[IMPORT_FILE]\n",
         ")\n",
         "\n",
         "print(dataset.resource_name)"
@@ -678,13 +747,13 @@
       },
       "outputs": [],
       "source": [
-        "dag = aip.AutoMLTabularTrainingJob(\n",
-        "    display_name=\"bank_\" + TIMESTAMP,\n",
+        "job = aip.AutoMLTabularTrainingJob(\n",
+        "    display_name=\"bank_\" + UUID,\n",
         "    optimization_prediction_type=\"classification\",\n",
         "    optimization_objective=\"minimize-log-loss\",\n",
         ")\n",
         "\n",
-        "print(dag)"
+        "print(job)"
       ]
     },
     {
@@ -730,9 +799,9 @@
       },
       "outputs": [],
       "source": [
-        "model = dag.run(\n",
+        "model = job.run(\n",
         "    dataset=dataset,\n",
-        "    model_display_name=\"bank_\" + TIMESTAMP,\n",
+        "    model_display_name=\"bank_\" + UUID,\n",
         "    training_fraction_split=0.6,\n",
         "    validation_fraction_split=0.2,\n",
         "    test_fraction_split=0.2,\n",
@@ -808,7 +877,7 @@
       "outputs": [],
       "source": [
         "# Get model resource ID\n",
-        "models = aip.Model.list(filter=\"display_name=bank_\" + TIMESTAMP)\n",
+        "models = aip.Model.list(filter=\"display_name=bank_\" + UUID)\n",
         "\n",
         "# Get a reference to the Model Service client\n",
         "client_options = {\"api_endpoint\": f\"{REGION}-aiplatform.googleapis.com\"}\n",
@@ -887,7 +956,7 @@
       "source": [
         "### Make test items\n",
         "\n",
-        "You will use synthetic data as a test data items. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
+        "You use synthetic data as a test data items. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
       ]
     },
     {
@@ -898,7 +967,7 @@
       "source": [
         "### Make the batch input file\n",
         "\n",
-        "Now make a batch input file, which you will store in your local Cloud Storage bucket. Unlike image, video and text, the batch input file for tabular is only supported for CSV. For CSV file, you make:\n",
+        "Now make a batch input file, which you store in your local Cloud Storage bucket. Unlike image, video and text, the batch input file for tabular is only supported for CSV. For CSV file, you make:\n",
         "\n",
         "- The first line is the heading with the feature (fields) heading names.\n",
         "- Each remaining line is a separate prediction request with the corresponding feature values.\n",
@@ -922,7 +991,7 @@
         "\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"
       ]
@@ -954,9 +1023,9 @@
       "outputs": [],
       "source": [
         "batch_predict_job = model.batch_predict(\n",
-        "    job_display_name=\"bank_\" + TIMESTAMP,\n",
+        "    job_display_name=\"bank_\" + UUID,\n",
         "    gcs_source=gcs_input_uri,\n",
-        "    gcs_destination_prefix=BUCKET_NAME,\n",
+        "    gcs_destination_prefix=BUCKET_URI,\n",
         "    instances_format=\"csv\",\n",
         "    predictions_format=\"csv\",\n",
         "    sync=False,\n",
@@ -1064,21 +1133,20 @@
       },
       "outputs": [],
       "source": [
-        "import tensorflow as tf\n",
-        "\n",
         "bp_iter_outputs = batch_predict_job.iter_outputs()\n",
         "\n",
         "prediction_results = list()\n",
         "for blob in bp_iter_outputs:\n",
-        "    if blob.name.split(\"/\")[-1].startswith(\"prediction\"):\n",
+        "    if blob.name.split(\"/\")[-1].startswith(\"prediction.results\"):\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)"
+        "    df = pd.read_csv(gfile_name)\n",
+        "    print(f\"File name: {gfile_name}\")\n",
+        "    print(\"Prediction: \\n\\n\\n\\n\")\n",
+        "    print(df)\n",
+        "    print(\"\\n\\n\\n\")"
       ]
     },
     {
@@ -1089,11 +1157,20 @@
       "source": [
         "*Example Output:*\n",
         "\n",
-        "    Age,Job,MaritalStatus,Education,Default,Balance,Housing,Loan,Contact,Day,Month,Duration,Campaign,PDays,Previous,POutcome,Deposit_1_scores,Deposit_2_scores\n",
+        "    File name: gs://vertex-ai-devaip-5j22pmou/prediction-bank_5j22pmou-2022_08_24T01_05_46_028Z/prediction.results-00005-of-00008.csv\n",
+        "Prediction: \n",
         "\n",
-        "    72,retired,married,secondary,no,5715,no,no,cellular,17,nov,1127,5,184,3,success,0.4721628427505493,0.5278371572494507\n",
         "\n",
-        "    57,blue-collar,married,secondary,no,668,no,no,telephone,17,nov,508,4,-1,0,unknown,0.9005520343780518,0.09944798052310944"
+        "\n",
+        "\n",
+        "    Age          Job MaritalStatus  Education Default  Balance Housing Loan  \\\n",
+        "0    57  blue-collar       married  secondary      no      668      no   no   \n",
+        "\n",
+        "     Contact  Day Month  Duration  Campaign  PDays  Previous POutcome  \\\n",
+        "0  telephone   17   nov       508         4     -1         0  unknown   \n",
+        "\n",
+        "    Deposit_1_scores  Deposit_2_scores  \n",
+        "0          0.847498          0.152502  "
       ]
     },
     {
@@ -1173,7 +1250,7 @@
       "source": [
         "### Make test item\n",
         "\n",
-        "You will use synthetic data as a test data item. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
+        "You use synthetic data as a test data item. Don't be concerned that we are using synthetic data -- we just want to demonstrate how to make a prediction."
       ]
     },
     {
@@ -1293,13 +1370,10 @@
         "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"
       ]
     },
@@ -1311,60 +1385,24 @@
       },
       "outputs": [],
       "source": [
-        "delete_all = True\n",
+        "# Delete the dataset using the Vertex dataset object\n",
+        "dataset.delete()\n",
         "\n",
-        "if delete_all:\n",
-        "    # Delete the dataset using the Vertex dataset object\n",
-        "    try:\n",
-        "        if \"dataset\" in globals():\n",
-        "            dataset.delete()\n",
-        "    except Exception as e:\n",
-        "        print(e)\n",
+        "# Delete the model using the Vertex model object\n",
+        "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",
+        "# Delete the endpoint using the Vertex endpoint object\n",
+        "endpoint.delete()\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",
+        "# Delete the AutoML or Pipeline trainig job\n",
+        "job.delete()\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",
+        "# Delete the batch prediction job using the Vertex batch prediction object\n",
+        "batch_predict_job.delete()\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"
+        "delete_bucket = False\n",
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil -m rm -r $BUCKET_URI"
       ]
     }
   ],

notebooks/official/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb

@@ -8,7 +8,7 @@
       },
       "outputs": [],
       "source": [
-        "# Copyright 2022 Google LLC\n",
+        "# Copyright 2021 Google LLC\n",
         "#\n",
         "# Licensed under the Apache License, Version 2.0 (the \"License\");\n",
         "# you may not use this file except in compliance with the License.\n",
@@ -29,23 +29,21 @@
         "id": "JAPoU8Sm5E6e"
       },
       "source": [
-        "# Vertex AI: Track parameters and metrics for custom training jobs\n",
-        "\n",
         "<table align=\"left\">\n",
         "\n",
         "  <td>\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",
+        "    <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",
         "      <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/ml_metadata/sdk-metric-parameter-tracking-for-custom-jobs.ipynb\">\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",
         "      <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/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/blob/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",
@@ -56,39 +54,48 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "tvgnzT1CKxrO"
+        "id": "j9gUDU_3vV9d"
       },
       "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."
+        "# Vertex AI: Track parameters and metrics for custom training jobs"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "37147bd9c3c4"
+        "id": "2e0464050974"
+      },
+      "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."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b95ab729fccd"
       },
       "source": [
         "### Objective\n",
         "\n",
-        "In this notebook, you learn how to use `Vertex ML Metadata` to track training parameters and evaluation metrics.\n",
+        "In this notebook, you will learn how to use Vertex AI SDK for Python to:\n",
         "\n",
-        "This tutorial uses the following Google Cloud ML services:\n",
-        "\n",
-        "- `Vertex ML Metadata`\n",
-        "- `Vertex AI Experiments`\n",
+        "This tutorial uses the following Google Cloud ML services and resources:\n",
+        "- Vertex AI Dataset\n",
+        "- Vertex AI Model\n",
+        "- Vertex AI Endpoint\n",
+        "- Vertex AI Custom Training Job\n",
         "\n",
         "The steps performed include:\n",
-        "\n",
-        "- Track parameters and metrics for a `Vertex AI` custom trained model.\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."
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "96cb18467417"
+        "id": "9fd87cf689bf"
       },
       "source": [
         "### Dataset\n",
@@ -99,7 +106,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "c831245dc1d5"
+        "id": "tvgnzT1CKxrO"
       },
       "source": [
         "### Costs \n",
@@ -181,14 +188,14 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "IaYsrh0Tc17L"
+        "id": "qblyW_dcyOQA"
       },
       "outputs": [],
       "source": [
         "import os\n",
         "\n",
         "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
         "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
         "    \"/opt/deeplearning/metadata/env_version\"\n",
         ")\n",
@@ -198,9 +205,10 @@
         "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"
+        "\n",
+        "! pip3 install -U tensorflow $USER_FLAG\n",
+        "! python3 -m pip3 install {USER_FLAG} google-cloud-aiplatform --upgrade\n",
+        "! pip3 install scikit-learn {USER_FLAG}"
       ]
     },
     {
@@ -285,7 +293,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "oM1iC_MfAts1"
+        "id": "cde8e0876d62"
       },
       "outputs": [],
       "source": [
@@ -296,11 +304,11 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "riG_qUokg0XZ"
+        "id": "oM1iC_MfAts1"
       },
       "outputs": [],
       "source": [
-        "if PROJECT_ID == \"[your-project-id]\" or PROJECT_ID == \"\" or PROJECT_ID is None:\n",
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
         "    # Get your GCP project id from gcloud\n",
         "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
         "    PROJECT_ID = shell_output[0]\n",
@@ -321,7 +329,7 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "region"
+        "id": "47bc07d4231b"
       },
       "source": [
         "#### Region\n",
@@ -335,14 +343,14 @@
         "\n",
         "You may not use a multi-regional bucket for training with Vertex AI. Not all regions provide support for all Vertex AI services.\n",
         "\n",
-        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)"
+        "Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "region"
+        "id": "959545da671a"
       },
       "outputs": [],
       "source": [
@@ -358,9 +366,9 @@
         "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append it onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
@@ -371,9 +379,16 @@
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of length 8\n",
+        "def generate_uuid():\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=8))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -385,7 +400,7 @@
         "### Authenticate your Google Cloud account\n",
         "\n",
         "**If you are using Vertex AI Workbench**, your environment is already\n",
-        "authenticated. "
+        "authenticated. Skip this step."
       ]
     },
     {
@@ -435,7 +450,6 @@
         "# 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",
@@ -460,7 +474,7 @@
         "**The following steps are required, regardless of your notebook environment.**\n",
         "\n",
         "\n",
-        "When you submit a training job using the Cloud SDK, you upload a Python package\n",
+        "When you submit a training job using the Vertex AI SDK, you upload a Python package\n",
         "containing your training code to a Cloud Storage bucket. Vertex AI runs\n",
         "the code from this package. In this tutorial, Vertex AI also saves the\n",
         "trained model that results from your job in the same bucket. Using this model artifact, you can then\n",
@@ -492,8 +506,8 @@
       "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"
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -615,7 +629,7 @@
       "outputs": [],
       "source": [
         "if EXPERIMENT_NAME == \"\" or EXPERIMENT_NAME is None:\n",
-        "    EXPERIMENT_NAME = \"my-experiment-\" + TIMESTAMP"
+        "    EXPERIMENT_NAME = \"my-experiment-\" + UUID"
       ]
     },
     {
@@ -655,10 +669,10 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "9nokDKBAxwV8"
+        "id": "f8fd397cc4f6"
       },
       "source": [
-        "This example uses the Abalone Dataset. For more information about this dataset please visit: https://archive.ics.uci.edu/ml/datasets/abalone"
+        "### Download the Dataset to Cloud Storage"
       ]
     },
     {
@@ -681,9 +695,9 @@
         "id": "35QVNhACqcTJ"
       },
       "source": [
-        "### Create a Vertex AI Dataset from a CSV\n",
+        "### Create a Vertex AI Tabular dataset from CSV data\n",
         "\n",
-        "A Vertex AI Dataset can be used to create an AutoML model or a custom model. "
+        "A Vertex AI dataset can be used to create an AutoML model or a custom model. "
       ]
     },
     {
@@ -696,7 +710,7 @@
       "source": [
         "ds = aiplatform.TabularDataset.create(display_name=\"abalone\", gcs_source=[gcs_csv_path])\n",
         "\n",
-        "print(ds.resource_name)"
+        "ds.resource_name"
       ]
     },
     {
@@ -707,7 +721,7 @@
       "source": [
         "### Write the training script\n",
         "\n",
-        "Run the following cell to create the training script that is used in the sample custom training job."
+        "Next, you create the training script that is used in the sample custom training job."
       ]
     },
     {
@@ -735,9 +749,6 @@
         "                    default=64, type=int,\n",
         "                    help='Number of unit for first layer.')\n",
         "args = parser.parse_args()\n",
-        "# uncomment and bump up replica_count for distributed training\n",
-        "# strategy = tf.distribute.experimental.MultiWorkerMirroredStrategy()\n",
-        "# tf.distribute.experimental_set_strategy(strategy)\n",
         "\n",
         "col_names = [\"Length\", \"Diameter\", \"Height\", \"Whole weight\", \"Shucked weight\", \"Viscera weight\", \"Shell weight\", \"Age\"]\n",
         "target = \"Age\"\n",
@@ -771,7 +782,7 @@
         "id": "Yp2clkOJSDhR"
       },
       "source": [
-        "### Launch a custom training job and track its trainig parameters on Vertex AI ML Metadata"
+        "### Launch a custom training job and track its trainig parameters on Vertex ML Metadata"
       ]
     },
     {
@@ -797,11 +808,7 @@
         "id": "k_QorXXztzPH"
       },
       "source": [
-        "Start a new experiment run to track training parameters and start the training job. \n",
-        "\n",
-        "Prior to executing the training job, you call the `start_run()` method to initialize the start of the experiment, and then use the `log_params()` to log the parameters used in the experiment.\n",
-        "\n",
-        "*Note:* This operation will take around 10 mins."
+        "Start a new experiment run to track training parameters and start the training job. Note that this operation will take around 10 mins."
       ]
     },
     {
@@ -830,7 +837,7 @@
         "id": "5vhDsMJNqcTW"
       },
       "source": [
-        "### Deploy Model and calculate prediction metrics"
+        "### Deploy model and calculate prediction metrics"
       ]
     },
     {
@@ -839,7 +846,7 @@
         "id": "O-uCOL3Naap4"
       },
       "source": [
-        "Deploy model to Google Cloud. This operation may take a few minutes."
+        "Next, deploy your Vertex AI Model resource to a Vertex AI Endpoint resource. This operation will take 10-20 mins."
       ]
     },
     {
@@ -859,7 +866,7 @@
         "id": "JY-5skFhasWs"
       },
       "source": [
-        "Once model is deployed, perform online prediction using the `abalone_test` dataset and calculate prediction metrics."
+        "### Prediction dataset preparation and online prediction"
       ]
     },
     {
@@ -868,6 +875,8 @@
         "id": "saw50bqwa-dR"
       },
       "source": [
+        "Once model is deployed, perform online prediction using the `abalone_test` dataset and calculate prediction metrics.\n",
+        "\n",
         "Prepare the prediction dataset."
       ]
     },
@@ -920,7 +929,7 @@
         "id": "_HphZ38obJeB"
       },
       "source": [
-        "### Perform online prediction"
+        "Perform online prediction."
       ]
     },
     {
@@ -932,7 +941,7 @@
       "outputs": [],
       "source": [
         "prediction = endpoint.predict(test_dataset.tolist())\n",
-        "print(prediction)"
+        "prediction"
       ]
     },
     {
@@ -941,11 +950,7 @@
         "id": "TDKiv_O7bNwE"
       },
       "source": [
-        "### Calculate and track prediction evaluation metrics.\n",
-        "\n",
-        "Next, log the evaluation metrics for your experiment.\n",
-        "\n",
-        "Once the experiment is completed, you call the `end_run()` method to indicate the end of tracking for the experiment."
+        "Calculate and track prediction evaluation metrics."
       ]
     },
     {
@@ -959,9 +964,7 @@
         "mse = mean_squared_error(test_labels, prediction.predictions)\n",
         "mae = mean_absolute_error(test_labels, prediction.predictions)\n",
         "\n",
-        "aiplatform.log_metrics({\"mse\": mse, \"mae\": mae})\n",
-        "\n",
-        "aiplatform.end_run()"
+        "aiplatform.log_metrics({\"mse\": mse, \"mae\": mae})"
       ]
     },
     {

notebooks/official/model-registry/bqml-vertexai-model-registry.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/official/bigquery-ml/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model-registry/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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/bigquery-ml/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model-registry/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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/official/bigquery-ml/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/model-registry/bqml-vertexai-model-registry.ipynb\" target=\"_blank\">\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",
@@ -677,7 +677,7 @@
       "source": [
         "### Find the model in the Vertex Model Registry\n",
         "\n",
-        "You can use the `Vertex AI Model list()` method with a filter query to find the automatically registered model."
+        "You can use the `Vertex AI Model()` method with `model_name` parameter to find the automatically registered model."
       ]
     },
     {

notebooks/official/model_monitoring/model_monitoring.ipynb

@@ -223,12 +223,23 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
+        "# Don't bother installing tensorflow or explainable_ai_sdk on Colab\n",
+        "extra_pkgs = \"tensorflow explainable_ai_sdk\"\n",
+        "if \"google.colab\" in sys.modules:\n",
+        "  extra_pkgs = \"\"\n",
+        "\n",
         "# Install required packages.\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade google-cloud-aiplatform\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade tensorflow\n",
-        "! pip3 install {USER_FLAG} --quiet --upgrade explainable_ai_sdk\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-storage==1.32.0"
+        "! pip3 install {USER_FLAG} \\\n",
+        "    google-cloud-aiplatform \\\n",
+        "    explainable_ai_sdk \\\n",
+        "    $extra_pkgs \\\n",
+        "    google-api-python-client \\\n",
+        "    google-auth-oauthlib \\\n",
+        "    google-auth-httplib2 \\\n",
+        "    oauth2client \\\n",
+        "    requests \\\n",
+        "    protobuf==3.20.* \\\n",
+        "    google-cloud-storage==1.32.0 "
       ]
     },
     {
@@ -562,7 +573,7 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "init_aip:mbsdk,region"
+        "id": "wGa5T9eRR8Mz"
       },
       "outputs": [],
       "source": [

notebooks/official/pipelines/pipelines_intro_kfp.ipynb

@@ -81,7 +81,6 @@
         "The steps performed include:\n",
         "\n",
         "- Define and compile a `Vertex AI` pipeline.\n",
-        "- Schedule a recurring pipeline run.\n",
         "- Specify which service account to use for a pipeline run."
       ]
     },
@@ -97,13 +96,9 @@
         "\n",
         "* Vertex AI\n",
         "* Cloud Storage\n",
-        "* Cloud Functions\n",
-        "* Cloud Scheduler\n",
         "\n",
         "Learn about [Vertex AI pricing](https://cloud.google.com/vertex-ai/pricing),\n",
         "[Cloud Storage pricing](https://cloud.google.com/storage/pricing),\n",
-        "[Cloud Functions pricing](ttps://cloud.google.com/functions/pricing), and\n",
-        "[Clould Scheduler pricing]((https://cloud.google.com/scheduler/pricing)),\n",
         "and use the [Pricing\n",
         "Calculator](https://cloud.google.com/products/calculator/)\n",
         "to generate a cost estimate based on your projected usage."
@@ -926,69 +921,6 @@
         "job.delete()"
       ]
     },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "schedule_pipeline_run"
-      },
-      "source": [
-        "## Recurring pipeline runs: create a scheduled pipeline job\n",
-        "\n",
-        "This section shows how to create a **scheduled pipeline job**.  You do this using the pipeline you already defined.\n",
-        "\n",
-        "Under the hood, the scheduled jobs are supported by the Cloud Scheduler and a Cloud Functions function.  Check first that the APIs for both of these services are enabled.\n",
-        "You will need to first enable the [enable the Cloud Scheduler API](http://console.cloud.google.com/apis/library/cloudscheduler.googleapis.com) and the [Cloud Functions and Cloud Build APIs](https://console.cloud.google.com/flows/enableapi?apiid=cloudfunctions,cloudbuild.googleapis.com) if you have not already done so.\n",
-        "Note:you need to [create an App Engine app for your project](https://cloud.google.com/scheduler/docs/quickstart) if one does not already exist.\n",
-        "\n",
-        "\n",
-        "See the [Cloud Scheduler](https://cloud.google.com/scheduler/docs/configuring/cron-job-schedules) documentation for more on the cron syntax.\n",
-        "\n",
-        "Create a scheduled pipeline job, passing as an argument the job specification file that you compiled above.\n",
-        "\n",
-        "*Note:* You can pass a `parameter_values` dict that specifies the pipeline input parameters you want to use."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "Ty5hDoNX2Ou8"
-      },
-      "outputs": [],
-      "source": [
-        "if not os.getenv(\"IS_TESTING\"):\n",
-        "    from kfp.v2.google.client import AIPlatformClient  # noqa: F811\n",
-        "\n",
-        "    api_client = AIPlatformClient(project_id=PROJECT_ID, region=REGION)\n",
-        "\n",
-        "    # adjust time zone and cron schedule as necessary\n",
-        "    response = api_client.create_schedule_from_job_spec(\n",
-        "        job_spec_path=\"intro_pipeline.json\",\n",
-        "        schedule=\"2 * * * *\",\n",
-        "        time_zone=\"America/Los_Angeles\",  # change this as necessary\n",
-        "        parameter_values={\"text\": \"Hello world!\"},\n",
-        "        # pipeline_root=PIPELINE_ROOT  # this argument is necessary if you did not specify PIPELINE_ROOT as part of the pipeline definition.\n",
-        "    )"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "J8AP1viy2Ou8"
-      },
-      "source": [
-        "Once the scheduled job is created, you can see it listed in the [Cloud Scheduler](https://console.cloud.google.com/cloudscheduler/) panel in the Console.\n",
-        "\n",
-        "<a href=\"https://storage.googleapis.com/amy-jo/images/kf-pls/pipelines_scheduler.png\" target=\"_blank\"><img src=\"https://storage.googleapis.com/amy-jo/images/kf-pls/pipelines_scheduler.png\" width=\"95%\"/></a>\n",
-        "\n",
-        "You can test the setup from the Cloud Scheduler panel by clicking 'RUN NOW'.\n",
-        "\n",
-        "> **Note**: The implementation is using a Cloud Functions function, which you can see listed in the [Cloud Functions](https://console.cloud.google.com/functions/list) panel in the console as `templated_http_request-v1`.\n",
-        "Don't delete this function, as it will prevent the Cloud Scheduler jobs from actually kicking off the pipeline run.  If you do delete it, create a new scheduled job in order to recreate the function.\n",
-        "\n",
-        "When you're done experimenting, you probably want to **PAUSE** your scheduled job from the Cloud Scheduler panel, so that the recurrent jobs do not keep running."
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -1222,7 +1154,7 @@
       "outputs": [],
       "source": [
         "delete_pipeline = True\n",
-        "delete_bucket = True\n",
+        "delete_bucket = False\n",
         "\n",
         "try:\n",
         "    if delete_pipeline and \"DISPLAY_NAME\" in globals():\n",

notebooks/official/vizier/gapic-vizier-multi-objective-optimization.ipynb

@@ -123,6 +123,7 @@
         "if IS_WORKBENCH_NOTEBOOK:\n",
         "    USER_FLAG = \"--user\"\n",
         "\n",
+        "! pip3 install google-vizier==0.0.4\n",
         "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q"
       ]
     },
@@ -350,9 +351,9 @@
       "outputs": [],
       "source": [
         "import datetime\n",
-        "import json\n",
         "\n",
-        "from google.cloud import aiplatform"
+        "from google.cloud import aiplatform\n",
+        "from google.cloud.aiplatform.vizier import Study, pyvizier"
       ]
     },
     {
@@ -384,11 +385,9 @@
         "# These will be automatically filled in.\n",
         "STUDY_DISPLAY_NAME = \"{}_study_{}\".format(\n",
         "    PROJECT_ID.replace(\"-\", \"\"), datetime.datetime.now().strftime(\"%Y%m%d_%H%M%S\")\n",
-        ")  # @param {type: 'string'}\n",
-        "ENDPOINT = REGION + \"-aiplatform.googleapis.com\"\n",
+        ")\n",
         "PARENT = \"projects/{}/locations/{}\".format(PROJECT_ID, REGION)\n",
         "\n",
-        "print(\"ENDPOINT: {}\".format(ENDPOINT))\n",
         "print(\"REGION: {}\".format(REGION))\n",
         "print(\"PARENT: {}\".format(PARENT))"
       ]
@@ -413,34 +412,21 @@
       "outputs": [],
       "source": [
         "# Parameter Configuration\n",
-        "\n",
-        "param_r = {\"parameter_id\": \"r\", \"double_value_spec\": {\"min_value\": 0, \"max_value\": 1}}\n",
-        "\n",
-        "param_theta = {\n",
-        "    \"parameter_id\": \"theta\",\n",
-        "    \"double_value_spec\": {\"min_value\": 0, \"max_value\": 1.57},\n",
-        "}\n",
+        "problem = pyvizier.StudyConfig()\n",
+        "problem.algorithm = pyvizier.Algorithm.RANDOM_SEARCH\n",
         "\n",
         "# Objective Metrics\n",
-        "metric_y1 = {\"metric_id\": \"y1\", \"goal\": \"MINIMIZE\"}\n",
+        "problem.metric_information.append(\n",
+        "    pyvizier.MetricInformation(name=\"y1\", goal=pyvizier.ObjectiveMetricGoal.MINIMIZE)\n",
+        ")\n",
+        "problem.metric_information.append(\n",
+        "    pyvizier.MetricInformation(name=\"y2\", goal=pyvizier.ObjectiveMetricGoal.MAXIMIZE)\n",
+        ")\n",
         "\n",
-        "# Objective Metrics\n",
-        "metric_y2 = {\"metric_id\": \"y2\", \"goal\": \"MAXIMIZE\"}\n",
-        "\n",
-        "# Put it all together in a study configuration\n",
-        "study = {\n",
-        "    \"display_name\": STUDY_DISPLAY_NAME,\n",
-        "    \"study_spec\": {\n",
-        "        \"algorithm\": \"RANDOM_SEARCH\",\n",
-        "        \"parameters\": [\n",
-        "            param_r,\n",
-        "            param_theta,\n",
-        "        ],\n",
-        "        \"metrics\": [metric_y1, metric_y2],\n",
-        "    },\n",
-        "}\n",
-        "\n",
-        "print(json.dumps(study, indent=2, sort_keys=True))"
+        "# Defines the parameters configuration.\n",
+        "root = problem.search_space.select_root()\n",
+        "root.add_float_param(\"r\", 0, 1.0, scale_type=pyvizier.ScaleType.LINEAR)\n",
+        "root.add_float_param(\"theta\", 0, 1.57, scale_type=pyvizier.ScaleType.LINEAR)"
       ]
     },
     {
@@ -462,10 +448,9 @@
       },
       "outputs": [],
       "source": [
-        "vizier_client = aiplatform.gapic.VizierServiceClient(\n",
-        "    client_options=dict(api_endpoint=ENDPOINT)\n",
-        ")\n",
-        "study = vizier_client.create_study(parent=PARENT, study=study)\n",
+        "aiplatform.init(project=PROJECT_ID, location=REGION)\n",
+        "study = Study.create_or_load(display_name=STUDY_DISPLAY_NAME, problem=problem)\n",
+        "\n",
         "STUDY_ID = study.name\n",
         "print(\"STUDY_ID: {}\".format(STUDY_ID))"
       ]
@@ -515,11 +500,12 @@
         "            r, theta, y1, y2\n",
         "        )\n",
         "    )\n",
-        "    metric1 = {\"metric_id\": \"y1\", \"value\": y1}\n",
-        "    metric2 = {\"metric_id\": \"y2\", \"value\": y2}\n",
+        "    measurement = pyvizier.Measurement()\n",
+        "    measurement.metrics[\"y1\"] = y1\n",
+        "    measurement.metrics[\"y2\"] = y2\n",
         "\n",
         "    # Return the results for this trial\n",
-        "    return [metric1, metric2]"
+        "    return measurement"
       ]
     },
     {
@@ -545,11 +531,11 @@
       },
       "outputs": [],
       "source": [
-        "client_id = \"client1\"  # @param {type: 'string'}\n",
-        "suggestion_count_per_request = 5  # @param {type: 'integer'}\n",
-        "max_trial_id_to_stop = 4  # @param {type: 'integer'}\n",
+        "worker_id = \"worker1\"  # @param {type: 'string'}\n",
+        "suggestion_count_per_request = 3  # @param {type: 'integer'}\n",
+        "max_trial_id_to_stop = 6  # @param {type: 'integer'}\n",
         "\n",
-        "print(\"client_id: {}\".format(client_id))\n",
+        "print(\"worker_id: {}\".format(worker_id))\n",
         "print(\"suggestion_count_per_request: {}\".format(suggestion_count_per_request))\n",
         "print(\"max_trial_id_to_stop: {}\".format(max_trial_id_to_stop))"
       ]
@@ -573,42 +559,17 @@
       },
       "outputs": [],
       "source": [
-        "trial_id = 0\n",
-        "while int(trial_id) < max_trial_id_to_stop:\n",
-        "    suggest_response = vizier_client.suggest_trials(\n",
-        "        {\n",
-        "            \"parent\": STUDY_ID,\n",
-        "            \"suggestion_count\": suggestion_count_per_request,\n",
-        "            \"client_id\": client_id,\n",
-        "        }\n",
-        "    )\n",
+        "while len(study.trials()) < max_trial_id_to_stop:\n",
+        "    trials = study.suggest(count=suggestion_count_per_request, worker=worker_id)\n",
         "\n",
-        "    for suggested_trial in suggest_response.result().trials:\n",
-        "        trial_id = suggested_trial.name.split(\"/\")[-1]\n",
-        "        trial = vizier_client.get_trial({\"name\": suggested_trial.name})\n",
-        "\n",
-        "        if trial.state in [\"COMPLETED\", \"INFEASIBLE\"]:\n",
-        "            continue\n",
-        "\n",
-        "        for param in trial.parameters:\n",
-        "            if param.parameter_id == \"r\":\n",
-        "                r = param.value\n",
-        "            elif param.parameter_id == \"theta\":\n",
-        "                theta = param.value\n",
-        "        print(\"Trial : r is {}, theta is {}.\".format(r, theta))\n",
-        "\n",
-        "        vizier_client.add_trial_measurement(\n",
-        "            {\n",
-        "                \"trial_name\": suggested_trial.name,\n",
-        "                \"measurement\": {\n",
-        "                    \"metrics\": CreateMetrics(suggested_trial.name, r, theta)\n",
-        "                },\n",
-        "            }\n",
+        "    for suggested_trial in trials:\n",
+        "        measurement = CreateMetrics(\n",
+        "            suggested_trial.name,\n",
+        "            suggested_trial.parameters[\"r\"].value,\n",
+        "            suggested_trial.parameters[\"theta\"].value,\n",
         "        )\n",
-        "\n",
-        "        response = vizier_client.complete_trial(\n",
-        "            {\"name\": suggested_trial.name, \"trial_infeasible\": False}\n",
-        "        )"
+        "        suggested_trial.add_measurement(measurement=measurement)\n",
+        "        suggested_trial.complete(measurement=measurement)"
       ]
     },
     {
@@ -630,8 +591,7 @@
       },
       "outputs": [],
       "source": [
-        "optimal_trials = vizier_client.list_optimal_trials({\"parent\": STUDY_ID})\n",
-        "\n",
+        "optimal_trials = study.optimal_trials()\n",
         "print(\"optimal_trials: {}\".format(optimal_trials))"
       ]
     },
@@ -655,7 +615,7 @@
       },
       "outputs": [],
       "source": [
-        "vizier_client.delete_study({\"name\": STUDY_ID})"
+        "study.delete()"
       ]
     }
   ],