fix: boilerplate reduction 21

notebooks/official/datasets/get_started_with_data_labeling.ipynb

@@ -147,23 +147,12 @@
       "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",
-        "! pip3 install --upgrade google-cloud-aiplatform \\\n",
-        "                         google-cloud-storage $USER_FLAG -q\n",
+        "! pip3 install --upgrade --quiet google-cloud-aiplatform \\\n",
+        "                                 google-cloud-storage \n",
         "\n",
         "if os.getenv(\"IS_TESTING\"):\n",
-        "    ! pip3 install --upgrade google-api-core==2.10 $USER_FLAG -q"
+        "    ! pip3 install --upgrade --quiet google-api-core==2.10 "
       ]
     },
     {
@@ -172,68 +161,38 @@
         "id": "restart"
       },
       "source": [
-        "### Restart the kernel\n",
-        "\n",
-        "Once you've installed the Vertex AI SDK and Google *cloud-storage*, you need to restart the notebook kernel so it can find the packages.\n"
+        "### Colab only: Uncomment the following cell to restart the kernel"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "GIwKc4pk_i_t"
+        "id": "D-ZBOjErv5mM"
       },
       "outputs": [],
       "source": [
-        "import os\n",
+        "# Automatically restart kernel after installs so that your environment can access the new packages\n",
+        "# import IPython\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)"
+        "# app = IPython.Application.instance()\n",
+        "# app.kernel.do_shutdown(True)"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "before_you_begin"
+        "id": "yfEglUHQk9S3"
       },
       "source": [
         "## Before you begin\n",
         "\n",
-        "### GPU run-time\n",
+        "### Set your project ID\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 GCP project\n",
-        "\n",
-        "**The following steps are required, regardless of your notebook environment.**\n",
-        "\n",
-        "1. [Select or create a GCP project](https://console.cloud.google.com/cloud-resource-manager). When you first create an account, you get a $300 free credit towards your compute/storage costs.\n",
-        "\n",
-        "2. [Make sure that billing is enabled for your project.](https://cloud.google.com/billing/docs/how-to/modify-project)\n",
-        "\n",
-        "3. [Enable the Vertex AI APIs and Compute Engine APIs.](https://console.cloud.google.com/flows/enableapi?apiid=aiplatform.googleapis.com,compute_component)\n",
-        "\n",
-        "4. [Google Cloud SDK](https://cloud.google.com/sdk) is already installed in Vertex AI Workbench Notebooks.\n",
-        "\n",
-        "5. Enter your project ID in the cell below. Then run the  cell to make sure the\n",
-        "Cloud SDK uses the right project for all the commands in this notebook.\n",
-        "\n",
-        "**Note**: Jupyter runs lines prefixed with `!` as shell commands, and it interpolates Python variables prefixed with `$` into these commands.\n"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "WReHDGG5g0XY"
-      },
-      "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`."
+        "**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)"
       ]
     },
     {
@@ -244,33 +203,10 @@
       },
       "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}"
       ]
     },
     {
@@ -281,54 +217,18 @@
       "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)."
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "6Xtp5tvK_i_y"
+        "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 onto the name of resources which will be created in this tutorial.\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "d70An-Mg_i_2"
-      },
-      "outputs": [],
-      "source": [
-        "from datetime import datetime\n",
-        "\n",
-        "TIMESTAMP = datetime.now().strftime(\"%Y%m%d%H%M%S\")"
+        "REGION = \"us-central1\"  # @param {type: \"string\"}"
       ]
     },
     {
@@ -381,80 +281,65 @@
       "source": [
         "### Authenticate your Google Cloud account\n",
         "\n",
-        "**If you are using Vertex AI Workbench Notebooks**, your environment is already\n",
-        "authenticated. \n",
+        "Depending on your Jupyter environment, you may have to manually authenticate. Follow the relevant instructions below.\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",
+        "**1. Vertex AI Workbench**\n",
+        "* Do nothing as you are already authenticated.\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."
+        "**2. Local JupyterLab instance, uncomment and run:**"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "chybg3Ap_i_2"
+        "id": "ce6043da7b33"
       },
       "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 ''"
+        "# ! gcloud auth login"
       ]
     },
     {
       "cell_type": "markdown",
       "metadata": {
-        "id": "bucket:batch_prediction"
+        "id": "0367eac06a10"
+      },
+      "source": [
+        "**3. Colab, uncomment and run:**"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "21ad4dbb4a61"
+      },
+      "outputs": [],
+      "source": [
+        "# from google.colab import auth\n",
+        "# auth.authenticate_user()"
+      ]
+    },
+    {
+      "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."
+      ]
+    },
+    {
+      "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",
-        "This tutorial is designed to use training data that is in a public Cloud Storage bucket and a local Cloud Storage bucket for your batch predictions. You may alternatively use your own training data that you have stored in a local Cloud Storage bucket.\n",
-        "\n",
-        "Set the name of your Cloud Storage bucket below. It must be unique across all Cloud Storage buckets.\n"
+        "Create a storage bucket to store intermediate artifacts such as datasets."
       ]
     },
     {
@@ -465,21 +350,7 @@
       },
       "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_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"
+        "BUCKET_URI = f\"gs://your-bucket-name-{PROJECT_ID}-unique\"  # @param {type:\"string\"}"
       ]
     },
     {
@@ -488,40 +359,20 @@
         "id": "create_bucket"
       },
       "source": [
-        "**Only if your bucket doesn't already exist**: Run the following cell to create your Cloud Storage bucket.\n"
+        "**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": "qPPrwWpO_i_6"
+        "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:\n"
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "fn744B7x_i_7"
-      },
-      "outputs": [],
-      "source": [
-        "! gsutil ls -al $BUCKET_URI"
-      ]
-    },
     {
       "cell_type": "markdown",
       "metadata": {
@@ -554,7 +405,6 @@
       "outputs": [],
       "source": [
         "import os\n",
-        "import sys\n",
         "import time\n",
         "\n",
         "import google.cloud.aiplatform as aip\n",
@@ -745,7 +595,7 @@
       },
       "outputs": [],
       "source": [
-        "dataset = aip.ImageDataset.create(\"labeling_\" + TIMESTAMP)\n",
+        "dataset = aip.ImageDataset.create(\"labeling\")\n",
         "print(dataset)"
       ]
     },
@@ -802,8 +652,8 @@
       "outputs": [],
       "source": [
         "specialist_pool = {\n",
-        "    \"name\": \"labeling_\" + TIMESTAMP,\n",
-        "    \"display_name\": \"labeling_\" + TIMESTAMP,\n",
+        "    \"name\": \"labeling\",\n",
+        "    \"display_name\": \"labeling\",\n",
         "    \"specialist_manager_emails\": [EMAIL],\n",
         "}\n",
         "\n",
@@ -863,7 +713,7 @@
         "inputs = ParseDict({\"annotation_specs\": [\"rose\"]}, Value())\n",
         "\n",
         "data_labeling_job = {\n",
-        "    \"display_name\": \"labeling_\" + TIMESTAMP,\n",
+        "    \"display_name\": \"labeling\",\n",
         "    \"datasets\": [dataset.resource_name],\n",
         "    \"labeler_count\": 1,\n",
         "    \"instruction_uri\": INSTRUCTION_FILE,\n",