Merge pull request #1227 from sudarshan-SpringML/auto_tab_on_vertex_pipeline

Update the file automl_tabular_on_vertex_pipelines

notebooks/official/automl/automl_tabular_on_vertex_pipelines.ipynb

@@ -170,7 +170,7 @@
       },
       "outputs": [],
       "source": [
-        "!pip install -U google-cloud-pipeline-components -q"
+        "!pip install -U google-cloud-pipeline-components==1.0.25 -q"
       ]
     },
     {
@@ -333,7 +333,10 @@
       },
       "outputs": [],
       "source": [
-        "REGION = \"[your-region]\"  # @param {type: \"string\"}"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}\n",
+        "\n",
+        "if REGION == \"[your-region]\":\n",
+        "    REGION = \"us-central1\""
       ]
     },
     {
@@ -379,8 +382,11 @@
         "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",
@@ -388,10 +394,9 @@
         "\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. Alternatively, you may edit this notebook to authenticate using\n",
-        "    # gcloud.\n",
+        "    # account.\n",
         "    elif not os.getenv(\"IS_TESTING\"):\n",
-        "        %env GOOGLE_APPLICATION_CREDENTIALS ''"
+        "        %env GOOGLE_APPLICATION_CREDENTIALS '[your-service-account-key-path]'"
       ]
     },
     {
@@ -478,6 +483,77 @@
         "! gsutil ls -al $BUCKET_URI"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "44accda192d5"
+      },
+      "source": [
+        "#### Service Account\n",
+        "\n",
+        "You use a service account to create Vertex AI Pipeline jobs. If you do not want to use your project's Compute Engine service account, set `SERVICE_ACCOUNT` to another service account ID."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "e0c9c4f84849"
+      },
+      "outputs": [],
+      "source": [
+        "SERVICE_ACCOUNT = \"[your-service-account]\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "604ae09ab6d3"
+      },
+      "outputs": [],
+      "source": [
+        "if (\n",
+        "    SERVICE_ACCOUNT == \"\"\n",
+        "    or SERVICE_ACCOUNT is None\n",
+        "    or SERVICE_ACCOUNT == \"[your-service-account]\"\n",
+        "):\n",
+        "    # Get your service account from gcloud\n",
+        "    if not IS_COLAB:\n",
+        "        shell_output = !gcloud auth list 2>/dev/null\n",
+        "        SERVICE_ACCOUNT = shell_output[2].replace(\"*\", \"\").strip()\n",
+        "\n",
+        "    else:  # IS_COLAB:\n",
+        "        shell_output = ! gcloud projects describe  $PROJECT_ID\n",
+        "        project_number = shell_output[-1].split(\":\")[1].strip().replace(\"'\", \"\")\n",
+        "        SERVICE_ACCOUNT = f\"{project_number}-compute@developer.gserviceaccount.com\"\n",
+        "\n",
+        "    print(\"Service Account:\", SERVICE_ACCOUNT)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "d1ecb60964d5"
+      },
+      "source": [
+        "#### Set service account access for Vertex AI Pipelines\n",
+        "Run the following commands to grant your service account access to read and write pipeline artifacts in the bucket that you created in the previous step. You only need to run this step once per service account."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "a592f0a380c2"
+      },
+      "outputs": [],
+      "source": [
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectCreator $BUCKET_URI\n",
+        "\n",
+        "! gsutil iam ch serviceAccount:{SERVICE_ACCOUNT}:roles/storage.objectViewer $BUCKET_URI"
+      ]
+    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -836,6 +912,7 @@
         "\n",
         "job.run()\n",
         "\n",
+        "\n",
         "pipeline_task_details = job.gca_resource.job_detail.task_details\n",
         "\n",
         "if export_additional_model_without_custom_ops:\n",
@@ -877,6 +954,7 @@
         "stage_1_tuner_task = get_task_detail(\n",
         "    pipeline_task_details, \"automl-tabular-stage-1-tuner\"\n",
         ")\n",
+        "\n",
         "stage_1_tuning_result_artifact_uri = (\n",
         "    stage_1_tuner_task.outputs[\"tuning_result_output\"].artifacts[0].uri\n",
         ")"