update

notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb

@@ -29,22 +29,22 @@
         "id": "title:generic,gcp"
       },
       "source": [
-        "# E2E ML on GCP: MLOps stage 4 : formalization: get started with Vertex ML Metadata\n",
+        "# Get started with Vertex ML Metadata\n",
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/get_started_with_vertex_ml_metadata.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/ml_metadata/get_started_with_vertex_ml_metadata.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/stage4/get_started_with_vertex_ml_metadata.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/official/ml_metadata/get_started_with_vertex_ml_metadata.ipynb\">\n",
         "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
         "    </a>\n",
@@ -62,7 +62,9 @@
         "## Overview\n",
         "\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI for E2E MLOps on Google Cloud in production. This tutorial covers stage 4 : formalization: get started with Vertex ML Metadata."
+        "This tutorial demonstrates how to use Vertex ML Metadata.\n",
+        "\n",
+        "Learn more about [Vertex ML Metadata](https://cloud.google.com/vertex-ai/docs/ml-metadata)."
       ]
     },
     {
@@ -144,19 +146,32 @@
       "source": [
         "import os\n",
         "\n",
-        "# The Vertex AI Workbench Notebook product has specific requirements\n",
-        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\")\n",
-        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
-        "    \"/opt/deeplearning/metadata/env_version\"\n",
-        ")\n",
+        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] \\\n",
+        "                         google-cloud-pipeline-components  --quiet"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "restart"
+      },
+      "source": [
+        "### Colab only: Uncomment the following cell to restart the kernel"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "D-ZBOjErv5mM"
+      },
+      "outputs": [],
+      "source": [
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\n",
         "\n",
-        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
-        "USER_FLAG = \"\"\n",
-        "if IS_WORKBENCH_NOTEBOOK:\n",
-        "    USER_FLAG = \"--user\"\n",
-        "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform[tensorboard] $USER_FLAG -q\n",
-        "! pip3 install --upgrade google-cloud-pipeline-components $USER_FLAG -q"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
@@ -170,63 +185,27 @@
         "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": "before_you_begin"
       },
       "source": [
-        "## Before you begin\n",
-        "\n",
-        "### GPU runtime\n",
-        "\n",
-        "*Make sure you're running this notebook in a GPU runtime if you have that option. In Colab, select* **Runtime > Change Runtime Type > GPU**\n",
-        "\n",
-        "### Set up your Google Cloud project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the following APIs: Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component,storage-component.googleapis.com)\n",
-        "\n",
-        "4. If you are running this notebook locally, you need to install the [Cloud SDK]((https://cloud.google.com/sdk)).\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+        "## Before you begin"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "project_id"
+        "id": "before_you_begin:nogpu"
       },
       "source": [
-        "#### Set your project ID\n",
+        "### Set your project ID\n",
         "\n",
-        "**If you don't know your project ID**, you may be able to get your project ID using `gcloud`."
+        "**If you don't know your project ID**, try the following:\n",
+        "* Run `gcloud config list`.\n",
+        "* Run `gcloud projects list`.\n",
+        "* See the support page: [Locate the project ID](https://support.google.com/googleapi/answer/7014113)"
       ]
     },
     {
@@ -237,33 +216,10 @@
       },
       "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"
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}\n",
+        "\n",
+        "# Set the project id\n",
+        "! gcloud config set project {PROJECT_ID}"
       ]
     },
     {
@@ -274,16 +230,7 @@
       "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)."
+        "You can also change the `REGION` variable used by Vertex AI. Learn more about [Vertex AI regions](https://cloud.google.com/vertex-ai/docs/general/locations)."
       ]
     },
     {
@@ -294,34 +241,7 @@
       },
       "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\")"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -332,57 +252,70 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already authenticated. Skip this step.\n",
-        "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
-        "\n",
-        "**Otherwise**, follow these steps:\n",
-        "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
-        "\n",
-        "**Click Create service account**.\n",
-        "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
-        "\n",
-        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
-        "\n",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
-        "\n",
-        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "FvQeFm3Gv5mR"
+      },
+      "source": [
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "ad1138a125ea"
+      },
+      "source": [
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "gcp_authenticate"
+        "id": "ce6043da7b33"
+      },
+      "outputs": [],
+      "source": [
+        "# ! gcloud auth login"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
       },
       "outputs": [],
       "source": [
-        "# If you are running this notebook in Colab, run this cell and follow the\n",
-        "# instructions to authenticate your GCP account. This provides access to your\n",
-        "# Cloud Storage bucket and lets you submit training jobs and prediction\n",
-        "# requests.\n",
-        "\n",
-        "import os\n",
-        "import sys\n",
-        "\n",
-        "# If on Vertex AI Workbench, then don't execute this code\n",
         "IS_COLAB = False\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
-        "    \"DL_ANACONDA_HOME\"\n",
-        "):\n",
-        "    if \"google.colab\" in sys.modules:\n",
-        "        IS_COLAB = True\n",
-        "        from google.colab import auth as google_auth\n",
-        "\n",
-        "        google_auth.authenticate_user()\n",
-        "\n",
-        "    # If you are running this notebook locally, replace the string below with the\n",
-        "    # path to your service account key and run this cell to authenticate your GCP\n",
-        "    # account.\n",
-        "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()\n",
+        "# IS_COLAB = True"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "c13224697bfb"
+      },
+      "source": [
+        "**4. Service account or other**\n",
+        "* See how to grant Cloud Storage permissions to your service account at https://cloud.google.com/storage/docs/gsutil/commands/iam#ch-examples."
       ]
     },
     {
@@ -393,11 +326,7 @@
       "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."
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -408,21 +337,7 @@
       },
       "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_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_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -445,26 +360,6 @@
         "! 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": {
@@ -545,19 +440,7 @@
       "source": [
         "### Set up variables\n",
         "\n",
-        "Next, set up some variables used throughout the tutorial.\n",
-        "### Import libraries and define constants"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_aip:mbsdk"
-      },
-      "outputs": [],
-      "source": [
-        "import google.cloud.aiplatform as aip"
+        "Next, set up some variables used throughout the tutorial."
       ]
     },
     {
@@ -579,7 +462,10 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform_v1beta1 as aip_beta"
+        "from datetime import datetime\n",
+        "\n",
+        "import google.cloud.aiplatform_v1beta1 as aip_beta\n",
+        "from google.cloud import aiplatform"
       ]
     },
     {
@@ -707,7 +593,7 @@
       "outputs": [],
       "source": [
         "metadata_store = clients[\"metadata\"].create_metadata_store(\n",
-        "    parent=PARENT, metadata_store_id=\"my-metadata-store\"\n",
+        "    parent=PARENT, metadata_store_id=\"my-metadata-store-unique\"\n",
         ")\n",
         "\n",
         "metadata_store_id = str(metadata_store.result())[7:-2]\n",
@@ -1144,7 +1030,7 @@
       "source": [
         "from kfp.v2 import compiler, dsl\n",
         "from kfp.v2.dsl import (Artifact, Dataset, Input, Metrics, Model, Output,\n",
-        "                        OutputPath, component, pipeline)"
+        "                        OutputPath, component)"
       ]
     },
     {
@@ -1196,7 +1082,7 @@
       "outputs": [],
       "source": [
         "@component(\n",
-        "    packages_to_install=[\"google-cloud-bigquery\", \"pandas\", \"pyarrow\"],\n",
+        "    packages_to_install=[\"google-cloud-bigquery\", \"pandas\", \"pyarrow\", \"db-dtypes\"],\n",
         "    base_image=\"python:3.9\",\n",
         "    output_component_file=\"create_dataset.yaml\",\n",
         ")\n",
@@ -1214,7 +1100,7 @@
         "\n",
         "\n",
         "@component(\n",
-        "    packages_to_install=[\"sklearn\", \"pandas\", \"joblib\"],\n",
+        "    packages_to_install=[\"scikit-learn\", \"pandas\", \"joblib\"],\n",
         "    base_image=\"python:3.9\",\n",
         "    output_component_file=\"beans_model_component.yaml\",\n",
         ")\n",
@@ -1298,7 +1184,7 @@
         "    # A name for the pipeline.\n",
         "    name=\"mlmd-pipeline\",\n",
         ")\n",
-        "def pipeline(\n",
+        "def my_pipeline(\n",
         "    bq_table: str = \"\",\n",
         "    output_data_path: str = \"data.csv\",\n",
         "    project: str = PROJECT_ID,\n",
@@ -1332,20 +1218,22 @@
       "source": [
         "NOW = datetime.now().isoformat().replace(\".\", \":\")[:-7]\n",
         "\n",
-        "compiler.Compiler().compile(pipeline_func=pipeline, package_path=\"mlmd_pipeline.json\")\n",
+        "compiler.Compiler().compile(\n",
+        "    pipeline_func=my_pipeline, package_path=\"mlmd_pipeline.json\"\n",
+        ")\n",
         "\n",
-        "run1 = aip.PipelineJob(\n",
+        "run1 = aiplatform.PipelineJob(\n",
         "    display_name=\"mlmd-pipeline\",\n",
         "    template_path=\"mlmd_pipeline.json\",\n",
-        "    job_id=\"mlmd-pipeline-small-{}\".format(TIMESTAMP),\n",
+        "    job_id=\"mlmd-pipeline-small-unique\",\n",
         "    parameter_values={\"bq_table\": \"sara-vertex-demos.beans_demo.small_dataset\"},\n",
         "    enable_caching=True,\n",
         ")\n",
         "\n",
-        "run2 = aip.PipelineJob(\n",
+        "run2 = aiplatform.PipelineJob(\n",
         "    display_name=\"mlmd-pipeline\",\n",
         "    template_path=\"mlmd_pipeline.json\",\n",
-        "    job_id=\"mlmd-pipeline-large-{}\".format(TIMESTAMP),\n",
+        "    job_id=\"mlmd-pipeline-large-unique\",\n",
         "    parameter_values={\"bq_table\": \"sara-vertex-demos.beans_demo.large_dataset\"},\n",
         "    enable_caching=True,\n",
         ")\n",
@@ -1382,7 +1270,7 @@
       },
       "outputs": [],
       "source": [
-        "df = aip.get_pipeline_df(pipeline=\"mlmd-pipeline\")\n",
+        "df = aiplatform.get_pipeline_df(pipeline=\"mlmd-pipeline\")\n",
         "print(df)"
       ]
     },
@@ -1466,6 +1354,10 @@
       },
       "outputs": [],
       "source": [
+        "metadata_store_id = (\n",
+        "    f\"projects/{PROJECT_ID}/locations/{REGION}/metadataStores/my-metadata-store-unique\"\n",
+        ")\n",
+        "\n",
         "clients[\"metadata\"].delete_metadata_store(name=metadata_store_id)"
       ]
     },