fix: bucket

notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb

@@ -33,20 +33,21 @@
         "\n",
         "<table align=\"left\">\n",
         "  <td>\n",
-        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb\">\n",
+        "    <a href=\"https://colab.research.google.com/github/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/colab-logo-32px.png\" alt=\"Colab logo\"> Run in Colab\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb\">\n",
+        "    <a href=\"https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb\">\n",
         "      <img src=\"https://cloud.google.com/ml-engine/images/github-logo-32px.png\" alt=\"GitHub logo\">\n",
         "      View on GitHub\n",
         "    </a>\n",
         "  </td>\n",
         "  <td>\n",
-        "    <a href=\"https://console.cloud.google.com/vertex-ai/notebooks/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/master/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb\">\n",
+        "    <a href=\"https://console.cloud.google.com/vertex-ai/workbench/deploy-notebook?download_url=https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/official/pipelines/google_cloud_pipeline_components_automl_text.ipynb\">\n",
+        "      <img src=\"https://lh3.googleusercontent.com/UiNooY4LUgW_oTvpsNhPpQzsstV5W8F7rYgxgGBD85cWJoLmrOzhVs_ksK_vgx40SHs7jCqkTkCk=e14-rj-sc0xffffff-h130-w32\" alt=\"Vertex AI logo\">\n",
         "      Open in Vertex AI Workbench\n",
-        "    </a>\n",
+        "     </a>\n",
         "  </td>\n",
         "</table>\n",
         "<br/><br/><br/>"
@@ -82,14 +83,26 @@
       "source": [
         "### Objective\n",
         "\n",
-        "In this tutorial, you create an AutoML text classification using a pipeline with components from  `google_cloud_pipeline_components`.\n",
+        "In this tutorial, you learn to use `Vertex AI Pipelines` and `Google Cloud Pipeline Components` to build an `AutoML` text classification model.\n",
+        "\n",
+        "\n",
+        "This tutorial uses the following Google Cloud ML services:\n",
+        "\n",
+        "- `Vertex AI Pipelines`\n",
+        "- `Google Cloud Pipeline Components`\n",
+        "- `Vertex AutoML`\n",
+        "- `Vertex AI Model` resource\n",
+        "- `Vertex AI Endpoint` resource\n",
         "\n",
         "The steps performed include:\n",
         "\n",
-        "- Create a `Dataset` resource.\n",
-        "- Train an AutoML `Model` resource.\n",
-        "- Creates an `Endpoint` resource.\n",
-        "- Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Create a KFP pipeline:\n",
+        "    - Create a `Dataset` resource.\n",
+        "    - Train an AutoML text classification `Model` resource.\n",
+        "    - Create an `Endpoint` resource.\n",
+        "    - Deploys the `Model` resource to the `Endpoint` resource.\n",
+        "- Compile the KFP pipeline.\n",
+        "- Execute the KFP pipeline using `Vertex AI Pipelines`\n",
         "\n",
         "The components are [documented here](https://google-cloud-pipeline-components.readthedocs.io/en/latest/google_cloud_pipeline_components.aiplatform.html#module-google_cloud_pipeline_components.aiplatform)."
       ]
@@ -155,7 +168,7 @@
       "source": [
         "## Installation\n",
         "\n",
-        "Install the latest version of Vertex AI SDK for Python."
+        "Install the packages required for executing this notebook."
       ]
     },
     {
@@ -168,53 +181,20 @@
       "source": [
         "import os\n",
         "\n",
-        "# Google Cloud Notebook\n",
-        "if os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
-        "    USER_FLAG = \"--user\"\n",
-        "else:\n",
-        "    USER_FLAG = \"\"\n",
+        "# The Vertex AI Workbench Notebook product has specific requirements\n",
+        "IS_WORKBENCH_NOTEBOOK = os.getenv(\"DL_ANACONDA_HOME\") and not os.getenv(\"VIRTUAL_ENV\")\n",
+        "IS_USER_MANAGED_WORKBENCH_NOTEBOOK = os.path.exists(\n",
+        "    \"/opt/deeplearning/metadata/env_version\"\n",
+        ")\n",
         "\n",
-        "! pip3 install --upgrade google-cloud-aiplatform $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_storage"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-storage* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_storage"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install -U google-cloud-storage $USER_FLAG"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "source": [
-        "Install the latest GA version of *google-cloud-pipeline-components* library as well."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "install_gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade"
+        "# Vertex AI Notebook requires dependencies to be installed with '--user'\n",
+        "USER_FLAG = \"\"\n",
+        "if IS_WORKBENCH_NOTEBOOK:\n",
+        "    USER_FLAG = \"--user\"\n",
+        "\n",
+        "! pip3 install --upgrade google-cloud-aiplatform {USER_FLAG} -q\n",
+        "! pip3 install -U google-cloud-storage $USER_FLAG -q\n",
+        "! pip3 install $USER kfp google-cloud-pipeline-components --upgrade -q"
       ]
     },
     {
@@ -397,23 +377,30 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Google Cloud Notebook**, your environment is already authenticated. Skip this step.\n",
+        "**If you are using Vertex AI Workbench Notebook**, your environment is already authenticated. Skip this step.\n",
         "\n",
-        "**If you are using Colab**, run the cell below and follow the instructions when prompted to authenticate your account via oAuth.\n",
+        "**If you are using Colab**, run the cell below and follow the instructions\n",
+        "when prompted to authenticate your account via oAuth.\n",
         "\n",
         "**Otherwise**, follow these steps:\n",
         "\n",
-        "In the Cloud Console, go to the [Create service account key](https://console.cloud.google.com/apis/credentials/serviceaccountkey) page.\n",
+        "1. In the Cloud Console, go to the [**Create service account key**\n",
+        "   page](https://console.cloud.google.com/apis/credentials/serviceaccountkey).\n",
         "\n",
-        "**Click Create service account**.\n",
+        "2. Click **Create service account**.\n",
         "\n",
-        "In the **Service account name** field, enter a name, and click **Create**.\n",
+        "3. In the **Service account name** field, enter a name, and\n",
+        "   click **Create**.\n",
         "\n",
-        "In the **Grant this service account access to project** section, click the Role drop-down list. Type \"Vertex\" into the filter box, and select **Vertex Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
+        "4. In the **Grant this service account access to project** section, click the **Role** drop-down list. Type \"Vertex AI\"\n",
+        "into the filter box, and select\n",
+        "   **Vertex AI Administrator**. Type \"Storage Object Admin\" into the filter box, and select **Storage Object Admin**.\n",
         "\n",
-        "Click Create. A JSON file that contains your key downloads to your local environment.\n",
+        "5. Click *Create*. A JSON file that contains your key downloads to your\n",
+        "local environment.\n",
         "\n",
-        "Enter the path to your service account key as the GOOGLE_APPLICATION_CREDENTIALS variable in the cell below and run the cell."
+        "6. Enter the path to your service account key as the\n",
+        "`GOOGLE_APPLICATION_CREDENTIALS` variable in the cell below and run the cell."
       ]
     },
     {
@@ -432,8 +419,11 @@
         "import os\n",
         "import sys\n",
         "\n",
-        "# If on Google Cloud Notebook, then don't execute this code\n",
-        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\"):\n",
+        "# If on Vertex AI Workbench, then don't execute this code\n",
+        "IS_COLAB = \"google.colab\" in sys.modules\n",
+        "if not os.path.exists(\"/opt/deeplearning/metadata/env_version\") and not os.getenv(\n",
+        "    \"DL_ANACONDA_HOME\"\n",
+        "):\n",
         "    if \"google.colab\" in sys.modules:\n",
         "        from google.colab import auth as google_auth\n",
         "\n",
@@ -469,7 +459,8 @@
       },
       "outputs": [],
       "source": [
-        "BUCKET_NAME = \"gs://[your-bucket-name]\"  # @param {type:\"string\"}"
+        "BUCKET_NAME = \"[your-bucket-name]\"  # @param {type:\"string\"}\n",
+        "BUCKET_URI = f\"gs://{BUCKET_NAME}\""
       ]
     },
     {
@@ -480,8 +471,9 @@
       },
       "outputs": [],
       "source": [
-        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"gs://[your-bucket-name]\":\n",
-        "    BUCKET_NAME = \"gs://\" + PROJECT_ID + \"aip-\" + TIMESTAMP"
+        "if BUCKET_NAME == \"\" or BUCKET_NAME is None or BUCKET_NAME == \"[your-bucket-name]\":\n",
+        "    BUCKET_NAME = PROJECT_ID + \"aip-\" + TIMESTAMP\n",
+        "    BUCKET_URI = \"gs://\" + BUCKET_NAME"
       ]
     },
     {
@@ -501,7 +493,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil mb -l $REGION $BUCKET_NAME"
+        "! gsutil mb -l $REGION $BUCKET_URI"
       ]
     },
     {
@@ -521,7 +513,7 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil ls -al $BUCKET_NAME"
+        "! gsutil ls -al $BUCKET_URI"
       ]
     },
     {
@@ -559,9 +551,16 @@
         "    or SERVICE_ACCOUNT is None\n",
         "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
         "):\n",
-        "    # Get your GCP project id from gcloud\n",
-        "    shell_output = !gcloud auth list 2>/dev/null\n",
-        "    SERVICE_ACCOUNT = shell_output[2].strip()\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    if IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
         "    print(\"Service Account:\", SERVICE_ACCOUNT)"
       ]
     },
@@ -584,9 +583,9 @@
       },
       "outputs": [],
       "source": [
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_NAME\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
         "\n",
-        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_NAME"
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
       ]
     },
     {
@@ -609,7 +608,8 @@
       },
       "outputs": [],
       "source": [
-        "import google.cloud.aiplatform as aip"
+        "import google.cloud.aiplatform as aip\n",
+        "import kfp"
       ]
     },
     {
@@ -631,27 +631,7 @@
       },
       "outputs": [],
       "source": [
-        "PIPELINE_ROOT = \"{}/pipeline_root/happydb\".format(BUCKET_NAME)"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "additional_imports"
-      },
-      "source": [
-        "Additional imports."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "import_pipelines:gcpc"
-      },
-      "outputs": [],
-      "source": [
-        "import kfp"
+        "PIPELINE_ROOT = \"{}/pipeline_root/happydb\".format(BUCKET_URI)"
       ]
     },
     {
@@ -673,7 +653,7 @@
       },
       "outputs": [],
       "source": [
-        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_NAME)"
+        "aip.init(project=PROJECT_ID, staging_bucket=BUCKET_URI)"
       ]
     },
     {
@@ -937,8 +917,8 @@
         "except Exception as e:\n",
         "    print(e)\n",
         "\n",
-        "if delete_bucket and \"BUCKET_NAME\" in globals():\n",
-        "    ! gsutil rm -r $BUCKET_NAME"
+        "if delete_bucket or os.getenv(\"IS_TESTING\"):\n",
+        "    ! gsutil rm -r $BUCKET_URI"
       ]
     }
   ],