Merge branch 'main' into instance_schema

* Update build_model_experimentation_lineage_with_prebuild_code.ipynb

* Update build_model_experimentation_lineage_with_prebuild_code.ipynb

* Update build_model_experimentation_lineage_with_prebuild_code.ipynb

* Update build_model_experimentation_lineage_with_prebuild_code.ipynb

* Update build_model_experimentation_lineage_with_prebuild_code.ipynb

Co-authored-by: Andrew Ferlitsch <aferlitsch@google.com>

notebooks/community/CODEOWNERS

@@ -33,3 +33,4 @@
 /notebooks/community/ml_ops/stage2/get_started_vertex_training_r_using_r_kernel.ipynb @fhirschmann
 /notebooks/community/vertex-ai-samples/notebooks/community/model_registry/vertex_ai_model_registry_bqml_custom_model_versioning.ipynb @inardini
 /notebooks/community/vertex-ai-samples/notebooks/community/model_registry/vertex_ai_model_registry_automl_model_versioning.ipynb @inardini
+/notebooks/community/vizier/conversions_vertex_vizier_and_open_source_vizier.ipynb @halio-g

notebooks/community/ml_ops/stage1/get_started_bq_datasets.ipynb

@@ -245,7 +245,7 @@
       "source": [
         "# Common code setup for notebook tutorials\n",
         "\n",
-        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/setup.py -O setup.py\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.py -O setup.py\n",
         "\n",
         "%run setup.py --bucket"
       ]
@@ -260,7 +260,7 @@
       "source": [
         "# Other Common setup instructions for notebook tutorials\n",
         "\n",
-        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/setup.md -O setup.md\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.md -O setup.md\n",
         "\n",
         "%load setup.md"
       ]

notebooks/community/ml_ops/stage1/get_started_dataflow.ipynb

@@ -241,7 +241,7 @@
       "source": [
         "# Common code setup for notebook tutorials\n",
         "\n",
-        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/setup.py -O setup.py\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.py -O setup.py\n",
         "\n",
         "%run setup.py --bucket"
       ]
@@ -256,7 +256,7 @@
       "source": [
         "# Other Common setup instructions for notebook tutorials\n",
         "\n",
-        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/setup.md -O setup.md\n",
+        "! wget https://raw.githubusercontent.com/GoogleCloudPlatform/vertex-ai-samples/main/notebooks/community/ml_ops/setup.md -O setup.md\n",
         "\n",
         "%load setup.md "
       ]

notebooks/community/ml_ops/stage2/get_started_vertex_training_xgboost.ipynb

@@ -297,25 +297,32 @@
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "timestamp"
+        "id": "06571eb4063b"
       },
       "source": [
-        "#### Timestamp\n",
+        "#### UUID\n",
         "\n",
-        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a timestamp for each instance session, and append the timestamp onto the name of resources you create in this tutorial."
+        "If you are in a live tutorial session, you might be using a shared test account or project. To avoid name collisions between users on resources created, you create a uuid for each instance session, and append it onto the name of resources you create in this tutorial."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "JYtXOocrox9Q"
+        "id": "4e166d927e36"
       },
       "outputs": [],
       "source": [
-        "from datetime import datetime\n",
+        "import random\n",
+        "import string\n",
         "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "\n",
+        "# Generate a uuid of a specifed length(default=8)\n",
+        "def generate_uuid(length: int = 8) -> str:\n",
+        "    return \"\".join(random.choices(string.ascii_lowercase + string.digits, k=length))\n",
+        "\n",
+        "\n",
+        "UUID = generate_uuid()"
       ]
     },
     {
@@ -362,12 +369,11 @@
         "import sys\n",
         "\n",
         "# If on Vertex AI Workbench, then don't execute this code\n",
-        "IS_COLAB = False\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
         "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
         "    \"DL_ANACONDA_HOME\"\n",
         "):\n",
         "    if \"google.colab\" in sys.modules:\n",
-        "        IS_COLAB = True\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
         "        google_auth.authenticate_user()\n",
@@ -402,7 +408,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_URI = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -413,8 +420,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_URI == \"\" or BUCKET_URI is None or BUCKET_URI == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_URI = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + UUID\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -749,6 +757,7 @@
         "import hypertune\n",
         "import argparse\n",
         "import logging\n",
+        "import numpy as np\n",
         "\n",
         "from sklearn.model_selection import train_test_split\n",
         "from sklearn.metrics import accuracy_score\n",
@@ -790,16 +799,23 @@
         "def train_model(dtrain):\n",
         "    logging.info(\"Start training ...\")\n",
         "    # Train XGBoost model\n",
-        "    model = xgb.train({}, dtrain, num_boost_round=args.boost_rounds)\n",
+        "    params = {\n",
+        "        'objective': 'multi:softprob',\n",
+        "        'num_class': 3\n",
+        "    }\n",
+        "    model = xgb.train(params, dtrain, num_boost_round=args.boost_rounds)\n",
         "    logging.info(\"Training completed\")\n",
         "    return model\n",
         "\n",
         "def evaluate_model(model, test_data, test_labels):\n",
         "    dtest = xgb.DMatrix(test_data)\n",
         "    pred = model.predict(dtest)\n",
-        "    predictions = [round(value) for value in pred]\n",
+        "    predictions = [np.around(value) for value in pred]\n",
         "    # evaluate predictions\n",
-        "    accuracy = accuracy_score(test_labels, predictions)\n",
+        "    try:\n",
+        "        accuracy = accuracy_score(test_labels, predictions)\n",
+        "    except:\n",
+        "        accuracy = 0.0\n",
         "    logging.info(f\"Evaluation completed with model accuracy: {accuracy}\")\n",
         "\n",
         "    # report metric for hyperparameter tuning\n",
@@ -893,7 +909,7 @@
       },
       "outputs": [],
       "source": [
-        "DISPLAY_NAME = \"iris_\" + TIMESTAMP\n",
+        "DISPLAY_NAME = \"iris_\" + UUID\n",
         "\n",
         "job = aip.CustomPythonPackageTrainingJob(\n",
         "    display_name=DISPLAY_NAME,\n",
@@ -932,7 +948,7 @@
       },
       "outputs": [],
       "source": [
-        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, TIMESTAMP)\n",
+        "MODEL_DIR = \"{}/{}\".format(BUCKET_URI, UUID)\n",
         "DATASET_DIR = \"gs://cloud-samples-data/ai-platform/iris\"\n",
         "\n",
         "ROUNDS = 20\n",
@@ -983,7 +999,7 @@
       "source": [
         "if TRAIN_GPU:\n",
         "    model = job.run(\n",
-        "        model_display_name=\"iris_\" + TIMESTAMP,\n",
+        "        model_display_name=\"iris_\" + UUID,\n",
         "        args=CMDARGS,\n",
         "        replica_count=1,\n",
         "        machine_type=TRAIN_COMPUTE,\n",
@@ -994,7 +1010,7 @@
         "    )\n",
         "else:\n",
         "    model = job.run(\n",
-        "        model_display_name=\"iris_\" + TIMESTAMP,\n",
+        "        model_display_name=\"iris_\" + UUID,\n",
         "        args=CMDARGS,\n",
         "        replica_count=1,\n",
         "        machine_type=TRAIN_COMPUTE,\n",
@@ -1095,7 +1111,7 @@
       },
       "outputs": [],
       "source": [
-        "delete_bucket = False\n",
+        "delete_bucket = True\n",
         "\n",
         "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
         "    ! gsutil rm -r $BUCKET_URI"

notebooks/community/ml_ops/stage6/get_started_with_xgboost_model_online.ipynb

@@ -670,6 +670,56 @@
         "print(\"Train machine type\", DEPLOY_COMPUTE)"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8ac30ffa72b5"
+      },
+      "source": [
+        "### Create the instance schema\n",
+        "\n",
+        "The instance.yaml file is used to validate the format of the input request before it goes to the model server. If you are sending correctly you don't need instance.yaml. If you get bad requests, the instance.yaml will give a more meaningful error msg than what you probably get from the model server.\n",
+        "\n",
+        "*The instance.yaml can also be reused as the input schema for Model Monitoring custom models.*\n",
+        "\n",
+        "\n",
+        "\n",
+        "Learn more about [Predict schemas](https://cloud.google.com/vertex-ai/docs/reference/rest/v1/PredictSchemata)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "59becb56ad34"
+      },
+      "outputs": [],
+      "source": [
+        "yaml = \"\"\"type: array\n",
+        "properties:\n",
+        "  sepal_length:\n",
+        "    type: numeric\n",
+        "  sepal_width:\n",
+        "    type: numeric\n",
+        "  petal_length:\n",
+        "    type: numeric\n",
+        "  petal_width:\n",
+        "    type: numeric\n",
+        "required:\n",
+        "  - sepal_length\n",
+        "  - sepal_width\n",
+        "  - petal_length\n",
+        "  - petal_width\n",
+        "\"\"\"\n",
+        "\n",
+        "print(yaml)\n",
+        "\n",
+        "with open(\"instance.yaml\", \"w\") as f:\n",
+        "    f.write(yaml)\n",
+        "\n",
+        "! gsutil cp instance.yaml {BUCKET_URI}/instance.yaml"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -709,6 +759,7 @@
         "    display_name=f\"xgboost_iris_{UUID}\",\n",
         "    serving_container_image_uri=DEPLOY_IMAGE,\n",
         "    artifact_uri=MODEL_ARTIFACTS,\n",
+        "    instance_schema_uri=f\"{BUCKET_URI}/instance.yaml\",\n",
         "    is_default_version=True,\n",
         "    version_aliases=[\"v1\", \"version1\"],\n",
         "    version_description=\"This is the first version of the model\",\n",
@@ -749,7 +800,7 @@
       "outputs": [],
       "source": [
         "endpoint = aiplatform.Endpoint.create(\n",
-        "    display_name=\"flowers_\" + UUID,\n",
+        "    display_name=\"xgboost_iris_\" + UUID,\n",
         "    project=PROJECT_ID,\n",
         "    location=REGION,\n",
         "    labels={\"your_key\": \"your_value\"},\n",

notebooks/community/prediction/custom_prediction_routines/SDK_Custom_Predict_SDK_Integration.ipynb

@@ -53,7 +53,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a scikit-learn model on Vertex AI Predictions. This is currently a **preview** feature. Pre-GA products and features might have limited support, and changes to pre-GA products and features might not be compatible with other pre-GA versions. For more information, see the [launch stage descriptions](https://cloud.google.com/products#product-launch-stages).\n",
+        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a scikit-learn model on Vertex AI Predictions.\n",
         "\n",
         "\n",
         "\n",

notebooks/community/prediction/custom_prediction_routines/SDK_Custom_Predict_and_Handler_SDK_Integration.ipynb

@@ -53,7 +53,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a scikit-learn model on Vertex AI Predictions. This is currently a **preview** feature. Pre-GA products and features might have limited support, and changes to pre-GA products and features might not be compatible with other pre-GA versions. For more information, see the [launch stage descriptions](https://cloud.google.com/products#product-launch-stages).\n",
+        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a scikit-learn model on Vertex AI Predictions.\n",
         "\n",
         "\n",
         "\n",

notebooks/community/prediction/custom_prediction_routines/SDK_Custom_Preprocess.ipynb

@@ -53,7 +53,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a scikit-learn model on Vertex AI Predictions. This is currently a **preview** feature. Pre-GA products and features might have limited support, and changes to pre-GA products and features might not be compatible with other pre-GA versions. For more information, see the [launch stage descriptions](https://cloud.google.com/products#product-launch-stages).\n",
+        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a scikit-learn model on Vertex AI Predictions.\n",
         "\n",
         "\n",
         "\n",

notebooks/community/prediction/custom_prediction_routines/SDK_Pytorch_Custom_Predict.ipynb

@@ -53,7 +53,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a PyTorch model on Vertex AI Predictions. This is currently a **preview** feature. Pre-GA products and features might have limited support, and changes to pre-GA products and features might not be compatible with other pre-GA versions. For more information, see the [launch stage descriptions](https://cloud.google.com/products#product-launch-stages).\n",
+        "This tutorial demonstrates how to use Vertex AI SDK to build a custom container that uses the Custom Prediction Routine model server to serve a PyTorch model on Vertex AI Predictions.\n",
         "\n",
         "\n",
         "\n",

notebooks/community/prediction/custom_prediction_routines/SDK_Triton_PyTorch_Local_Prediction.ipynb

@@ -53,7 +53,7 @@
       "source": [
         "## Overview\n",
         "\n",
-        "This tutorial demonstrates how to use Vertex AI SDK to locally test [NVIDIA Triton inference server](https://developer.nvidia.com/nvidia-triton-inference-server) to serve a PyTorch model and deploy it to Vertex AI Predictions. This is currently a **preview** feature. Pre-GA products and features might have limited support, and changes to pre-GA products and features might not be compatible with other pre-GA versions. For more information, see the [launch stage descriptions](https://cloud.google.com/products#product-launch-stages).\n",
+        "This tutorial demonstrates how to use Vertex AI SDK to locally test [NVIDIA Triton inference server](https://developer.nvidia.com/nvidia-triton-inference-server) to serve a PyTorch model and deploy it to Vertex AI Predictions.\n",
         "\n",
         "\n",
         "### Dataset\n",

notebooks/community/vizier/conversions_vertex_vizier_and_open_source_vizier.ipynb

@@ -0,0 +1,619 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "7fPc-KWUi2Xd"
+      },
+      "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": "eoXf8TfQoVth"
+      },
+      "source": [
+        "# Convert between Vertex AI Vizier and Open Source Vizier\n",
+        "\n",
+        "<table align=\"left\">\n",
+        "\n",
+        "  <td>\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/vizier/conversions_vertex_vizier_and_open_source_vizier.ipynb\">\n",
+        "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
+        "    </a>\n",
+        "  </td>\n",
+        "  <td>\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/vizier/conversions_vertex_vizier_and_open_source_vizier.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/vizier/conversions_vertex_vizier_and_open_source_vizier.ipynb\">\n",
+        "        <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
+        "      Open in Vertex AI Workbench\n",
+        "    </a>\n",
+        "  </td>\n",
+        "</table>"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "b397c59391b1"
+      },
+      "source": [
+        "## Overview\n",
+        "\n",
+        "This tutorial demonstrates how to migrate code between [Vertex AI Vizier](https://cloud.google.com/vertex-ai/docs/vizier/overview) and [Open Source(OSS) Vizier](https://oss-vizier.readthedocs.io/). OSS Vizier is a Python-based service for blackbox optimization and research. It allows you to setup an OSS Vizier Server that can host blackbox optimization algorithms for tuning objective functions and defining abstractions and utilities for implementing new optimization algorithms.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "AksIKBzZ-nre"
+      },
+      "source": [
+        "### Objective\n",
+        "\n",
+        "In this tutorial, you learn how to use `Vertex AI Vizier` to optimize a multi-objective study and convert the code to OSS Vizier.\n",
+        "\n",
+        "The goal is to __`minimize`__ the objective metric:\n",
+        "   ```\n",
+        "   y1 = r*sin(theta)\n",
+        "   ```\n",
+        "\n",
+        "and simultaneously __`maximize`__ the objective metric:\n",
+        "   ```\n",
+        "   y2 = r*cos(theta)\n",
+        "   ```\n",
+        "\n",
+        "so that you will evaluate over the parameter space:\n",
+        "\n",
+        "   - __`r`__ in [0,1],\n",
+        "\n",
+        "   - __`theta`__ in [0, pi/2]\n",
+        "\n",
+        "### Costs\n",
+        "\n",
+        "This tutorial uses billable components of Google Cloud:\n",
+        "\n",
+        "* Vertex AI\n",
+        "\n",
+        "Learn about [Vertex AI\n",
+        "pricing](https://cloud.google.com/vertex-ai/pricing) and use the [Pricing\n",
+        "Calculator](https://cloud.google.com/products/calculator/)\n",
+        "to generate a cost estimate based on your projected usage.\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "iMHz63rPbq6P"
+      },
+      "source": [
+        "## Installation\n",
+        "\n",
+        "Install the packages required for executing this notebook."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "b6f3dc43494b"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "# Configure the environment for the Vertex AI Workbench notebook.\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
+        "\n",
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install google-vizier==0.0.4\n",
+        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "64d24b4fab2c"
+      },
+      "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": "O8AIwN0abq6U"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "\n",
+        "if not os.getenv(\"IS_TESTING\"):\n",
+        "    # Restart the kernel after pip installs\n",
+        "    import IPython\n",
+        "\n",
+        "    app = IPython.Application.instance()\n",
+        "    app.kernel.do_shutdown(True)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "before_you_begin:nogpu"
+      },
+      "source": [
+        "## Before you begin\n",
+        "\n",
+        "### GPU runtime\n",
+        "\n",
+        "This tutorial does not require a GPU runtime.\n",
+        "\n",
+        "### Set up your Google Cloud project\n",
+        "\n",
+        "**The following steps are required, regardless of your notebook environment.**\n",
+        "\n",
+        "1. [Select or create a Google Cloud project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
+        "\n",
+        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
+        "\n",
+        "3. [Enable the Vertex AI APIs, Compute Engine APIs, and Cloud Storage.](https://console.cloud.google.com/flows/enableapi?apiid=ml.googleapis.com,compute_component,storage-component.googleapis.com)\n",
+        "\n",
+        "4. [The Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Google Cloud Notebook.\n",
+        "\n",
+        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
+        "Cloud SDK uses the right project for all the commands in this notebook.\n",
+        "\n",
+        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "set_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "PROJECT_ID = \"[your-project-id]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "autoset_project_id"
+      },
+      "outputs": [],
+      "source": [
+        "if PROJECT_ID == \"\" or PROJECT_ID is None or PROJECT_ID == \"[your-project-id]\":\n",
+        "    # Get your Google Cloud project id from gcloud\n",
+        "    shell_output = ! gcloud config list --format 'value(core.project)' 2>/dev/null\n",
+        "    PROJECT_ID = shell_output[0]\n",
+        "    print(\"Project ID:\", PROJECT_ID)"
+      ]
+    },
+    {
+      "cell_type": "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": "04933ed28eef"
+      },
+      "outputs": [],
+      "source": [
+        "REGION = \"[your-region]\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "jvNx3KyF2Ou0"
+      },
+      "outputs": [],
+      "source": [
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "h0SMyUsC-mzi"
+      },
+      "source": [
+        "### Authenticate your Google Cloud account\n",
+        "\n",
+        "**If you are using Vertex AI Workbench Notebook**, your environment is already authenticated. Skip this step.\n",
+        "\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
+        "\n",
+        "**Otherwise**, follow these steps:\n",
+        "\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
+        "\n",
+        "2. Click **Create service account**.\n",
+        "\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
+        "\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
+        "\n",
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "iTQY9g4mRo6r"
+      },
+      "outputs": [],
+      "source": [
+        "# If you are running this notebook in Colab, run this cell and follow the\n",
+        "# instructions to authenticate your Google Cloud 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 Google Cloud\n",
+        "    # account.\n",
+        "    elif not os.getenv(\"IS_TESTING\"):\n",
+        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Dax2zrpTi2Xy"
+      },
+      "source": [
+        "### Import libraries and define constants"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "xD60d6Q0i2X0"
+      },
+      "outputs": [],
+      "source": [
+        "import datetime\n",
+        "import math"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "CWuu4wmki2X3"
+      },
+      "source": [
+        "## Tutorial\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KyEjqIdnad0w"
+      },
+      "source": [
+        "This section defines some parameters to create the study and optimize the objective function.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "8HCgeF8had77"
+      },
+      "outputs": [],
+      "source": [
+        "# 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",
+        ")\n",
+        "\n",
+        "print(\"REGION: {}\".format(REGION))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "8NBduXsEaRKr"
+      },
+      "source": [
+        "### Define the parameters\n",
+        "\n",
+        "The following is a sample study configuration, built as a hierarchical python dictionary. It is already filled out. Run the cell to configure the study.\n",
+        "\n",
+        "__`USE_VERTEX_VIZIER`__: Uses Vertex Vizier SDK to do the optimization if True. Use OSS Vizier otherwise.\n",
+        "\n",
+        "__`SUGGESTION_COUNT`__: The number of suggestions (trials) requested in a single request.\n",
+        "\n",
+        "__`MAX_NUM_ITERATIONS`__: The number of iterations to explore before stopping. It is set to 4 to shorten the time to run the code, so don't expect convergence. For convergence, it would likely need to be about 20.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "E1VNJ4YBznhR"
+      },
+      "outputs": [],
+      "source": [
+        "USE_VERTEX_VIZIER = True  # @param {type:\"boolean\"}\n",
+        "\n",
+        "MAX_NUM_ITERATIONS = 4  # @param {type:\"integer\"}\n",
+        "\n",
+        "SUGGESTION_COUNT = 2  # @param {type:\"integer\"}\n",
+        "\n",
+        "OWNER = \"owner\"  # @param {type:\"string\"}\n",
+        "\n",
+        "SERVICE_ENDPOINT = \"127.0.0.1:8888\"  # @param {type:\"string\"}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4_Yvt-7Z8_re"
+      },
+      "source": [
+        "### Import the package and define `create_study` for different sources\n",
+        "\n",
+        "In Vertex Vizier, `project` and `location` are already specified and `Study.create_or_load` is called to create a study. You need to input the owner of your study and the server address in the format [ip:port]. To bring up the OSS Vizier server, please follow the [instructions](https://oss-vizier.readthedocs.io/) on the OSS Vizier website."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "0sAHZn1406VR"
+      },
+      "outputs": [],
+      "source": [
+        "if USE_VERTEX_VIZIER:\n",
+        "    from google.cloud import aiplatform\n",
+        "    from google.cloud.aiplatform.vizier import Study, pyvizier\n",
+        "\n",
+        "    def create_study(project, location, display_name, problem):\n",
+        "        aiplatform.init(project=project, location=location)\n",
+        "        study = Study.create_or_load(display_name=display_name, problem=problem)\n",
+        "        return study\n",
+        "\n",
+        "else:\n",
+        "    from vizier.service import clients, pyvizier\n",
+        "\n",
+        "    def create_study(project, location, display_name, problem):\n",
+        "        clients.environment_variables.service_endpoint = SERVICE_ENDPOINT\n",
+        "        study = clients.Study.from_study_config(\n",
+        "            problem, owner=OWNER, study_id=STUDY_DISPLAY_NAME\n",
+        "        )\n",
+        "        return study"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "guvkcQe_-zQf"
+      },
+      "source": [
+        "### Metric evaluation functions\n",
+        "\n",
+        "Next, define some functions to evaluate the two objective metrics.\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Fjfk5_c900Oz"
+      },
+      "outputs": [],
+      "source": [
+        "# r * sin(theta)\n",
+        "def Metric1Evaluation(r, theta):\n",
+        "    \"\"\"Evaluate the first metric on the trial.\"\"\"\n",
+        "    return r * math.sin(theta)\n",
+        "\n",
+        "\n",
+        "# r * cos(theta)\n",
+        "def Metric2Evaluation(r, theta):\n",
+        "    \"\"\"Evaluate the second metric on the trial.\"\"\"\n",
+        "    return r * math.cos(theta)\n",
+        "\n",
+        "\n",
+        "def CreateMetrics(r, theta):\n",
+        "    # Evaluate both objective metrics for this trial\n",
+        "    y1 = Metric1Evaluation(r, theta)\n",
+        "    y2 = Metric2Evaluation(r, theta)\n",
+        "    print(\n",
+        "        \"[r = {}, theta = {}] => y1 = r*sin(theta) = {}, y2 = r*cos(theta) = {}\".format(\n",
+        "            r, theta, y1, y2\n",
+        "        )\n",
+        "    )\n",
+        "    measurement = pyvizier.Measurement()\n",
+        "    measurement.metrics[\"y1\"] = y1\n",
+        "    measurement.metrics[\"y2\"] = y2\n",
+        "\n",
+        "    # Return the results for this trial\n",
+        "    return measurement"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "2DgUIEpZ-_fJ"
+      },
+      "source": [
+        "### Optimization\n",
+        "\n",
+        "The following code defines a study with parameters and metrics, evaluates the metric information based on the suggestions from Vizier, and reports the metrics value back. After a few rounds of iteration, you can get optimal trials by calling `optimal_trials()`. The code is adapt to both Vertex Vizier and OSS Vizier."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "s-AHfPOASXXW"
+      },
+      "outputs": [],
+      "source": [
+        "problem = pyvizier.StudyConfig()\n",
+        "problem.algorithm = pyvizier.Algorithm.RANDOM_SEARCH\n",
+        "\n",
+        "# Objective Metrics\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",
+        "# 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)\n",
+        "\n",
+        "study = create_study(\n",
+        "    project=PROJECT_ID,\n",
+        "    location=REGION,\n",
+        "    display_name=STUDY_DISPLAY_NAME,\n",
+        "    problem=problem,\n",
+        ")\n",
+        "\n",
+        "for _ in range(MAX_NUM_ITERATIONS):\n",
+        "    trials = study.suggest(count=SUGGESTION_COUNT)\n",
+        "    for trial in trials:\n",
+        "        materialize_trial = trial.materialize()\n",
+        "        measurement = CreateMetrics(\n",
+        "            materialize_trial.parameters.get_value(\"r\"),\n",
+        "            materialize_trial.parameters.get_value(\"theta\"),\n",
+        "        )\n",
+        "        trial.add_measurement(measurement=measurement)\n",
+        "        trial.complete(measurement=measurement)\n",
+        "\n",
+        "optimal_trials = study.optimal_trials()\n",
+        "print(\"optimal_trials: {}\".format(optimal_trials))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "KAxfq9Fri2YV"
+      },
+      "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. You can also manually delete resources that you created by running the following code."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "zQlLDfvlzYde"
+      },
+      "outputs": [],
+      "source": [
+        "study.delete()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "collapsed_sections": [],
+      "name": "conversions_vertex_vizier_and_open_source_vizier.ipynb",
+      "toc_visible": true
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

notebooks/official/experiments/build_model_experimentation_lineage_with_prebuild_code.ipynb

@@ -689,6 +689,7 @@
         "# Training\n",
         "TRAIN_EXECUTION_NAME = \"train\"\n",
         "TARGET = \"category\"\n",
+        "TARGET_LABELS = [\"b\", \"t\", \"e\", \"m\"]\n",
         "FEATURES = \"title\"\n",
         "TEST_SIZE = 0.2\n",
         "SEED = 8\n",
@@ -974,7 +975,8 @@
         "import joblib\n",
         "import pandas as pd\n",
         "from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer\n",
-        "from sklearn.metrics import accuracy_score, precision_score, recall_score\n",
+        "from sklearn.metrics import (accuracy_score, confusion_matrix, precision_score,\n",
+        "                             recall_score)\n",
         "from sklearn.model_selection import train_test_split\n",
         "from sklearn.naive_bayes import MultinomialNB\n",
         "from sklearn.pipeline import Pipeline\n",
@@ -1049,13 +1051,17 @@
         "    y_pred = model.predict(X_test)\n",
         "\n",
         "    # Store evaluation metrics\n",
-        "    # Store evaluation metrics\n",
-        "    metrics = {\n",
+        "    summary_metrics = {\n",
         "        \"accuracy\": round(accuracy_score(y_test, y_pred), 5),\n",
         "        \"precision\": round(precision_score(y_test, y_pred, average=\"weighted\"), 5),\n",
         "        \"recall\": round(recall_score(y_test, y_pred, average=\"weighted\"), 5),\n",
         "    }\n",
-        "    return metrics\n",
+        "    classification_metrics = {\n",
+        "        \"matrix\": confusion_matrix(y_test, y_pred, labels=TARGET_LABELS).tolist(),\n",
+        "        \"labels\": TARGET_LABELS,\n",
+        "    }\n",
+        "\n",
+        "    return summary_metrics, classification_metrics\n",
         "\n",
         "\n",
         "def save_model(model: Pipeline, save_path: str) -> int:\n",
@@ -1138,13 +1144,20 @@
         "\n",
         "    # Evaluate model\n",
         "    logging.info(\"Evaluate model.\")\n",
-        "    model_metrics = evaluate_model(trained_pipeline, x_val, y_val)\n",
+        "    summary_metrics, classification_metrics = evaluate_model(\n",
+        "        trained_pipeline, x_val, y_val\n",
+        "    )\n",
         "\n",
         "    # Log training metrics and store model artifact ----------------------------\n",
         "\n",
         "    # Log training metrics\n",
         "    logging.info(\"Log training metrics.\")\n",
-        "    vertex_ai.log_metrics(model_metrics)\n",
+        "    vertex_ai.log_metrics(summary_metrics)\n",
+        "    vertex_ai.log_classification_metrics(\n",
+        "        labels=classification_metrics[\"labels\"],\n",
+        "        matrix=classification_metrics[\"matrix\"],\n",
+        "        display_name=\"my-confusion-matrix\",\n",
+        "    )\n",
         "\n",
         "    # Generate first ten predictions\n",
         "    logging.info(\"Generate prediction sample.\")\n",

notebooks/official/model_monitoring/model_monitoring.ipynb

@@ -975,7 +975,7 @@
         "# Sampling rate (optional, default=.8)\n",
         "LOG_SAMPLE_RATE = 0.8  # @param {type:\"number\"}\n",
         "\n",
-        "# Monitoring Interval in seconds (optional, default=1).\n",
+        "# Monitoring Interval in hours (optional, default=1).\n",
         "MONITOR_INTERVAL = 1  # @param {type:\"number\"}\n",
         "\n",
         "# URI to training dataset.\n",