Merge branch 'main' into ml_ops_6

notebooks/community/ml_ops/stage4/get_started_with_vertex_xai.ipynb

@@ -130,7 +130,9 @@
         "- Train an custom XGBoost tabular model.\n",
         "    - Manually set configuration metadata.\n",
         "    - Do an online prediction with explanations.\n",
-        "- Train an custom Scikit-learn tabular model.\n",
+        "- Train an custom scikit-learn tabular model.\n",
+        "    - Manually set configuration metadata.\n",
+        "    - Do an online prediction with explanations.\n",
         "\n",
         "Learn more about [Introduction to Vertex AI Explainable AI ](https://cloud.google.com/vertex-ai/docs/explainable-ai/overview)"
       ]
@@ -4969,7 +4971,7 @@
         "id": "xai_intro:sklearn"
       },
       "source": [
-        "## Explainable AI for Sciket-learn models\n",
+        "## Explainable AI for scikit-learn models\n",
         "\n",
         "To use Vertex Explainable AI with a scikit-learn tabular model, you must configure certain options when you create the `Model` resource that you plan to request explanations from, when you deploy the model, or when you submit a batch explanation job. To configure manually, you do the following:\n",
         "\n",
@@ -5039,18 +5041,29 @@
         "! touch custom/trainer/__init__.py"
       ]
     },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "taskpy_contents:scilearn,census,regressor"
+      },
+      "source": [
+        "#### Task.py contents\n",
+        "\n",
+        "In the next cell, you write the contents of the training script task.py."
+      ]
+    },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "taskpy_contents:scilearn,census"
+        "id": "taskpy_contents:scilearn,census,regressor"
       },
       "outputs": [],
       "source": [
         "%%writefile custom/trainer/task.py\n",
         "# Single Instance Training for Census Income\n",
         "\n",
-        "from sklearn.ensemble import RandomForestClassifier\n",
+        "from sklearn.ensemble import RandomForestRegressor\n",
         "import joblib\n",
         "from sklearn.feature_selection import SelectKBest\n",
         "from sklearn.pipeline import FeatureUnion\n",
@@ -5169,16 +5182,16 @@
         "# Combine all the features using FeatureUnion\n",
         "preprocess = FeatureUnion(categorical_pipelines)\n",
         "\n",
-        "# Create the classifier\n",
-        "classifier = RandomForestClassifier()\n",
+        "# Create the regressor\n",
+        "regressor = RandomForestRegressor()\n",
         "\n",
         "# Transform the features and fit them to the classifier\n",
-        "classifier.fit(preprocess.transform(train_features), train_labels)\n",
+        "regressor.fit(preprocess.transform(train_features), train_labels)\n",
         "\n",
         "# Create the overall model as a single pipeline\n",
         "pipeline = Pipeline([\n",
         "    ('union', preprocess),\n",
-        "    ('classifier', classifier)\n",
+        "    ('classifier', regressor)\n",
         "])\n",
         "\n",
         "# Split path into bucket and subdirectory\n",
@@ -5514,7 +5527,7 @@
         "    inputs={\n",
         "        \"features\": {\"index_feature_mapping\": COLUMNS, \"encoding\": \"BAG_OF_FEATURES\"}\n",
         "    },\n",
-        "    outputs={\"specifies\": {}},\n",
+        "    outputs={\"income\": {}},\n",
         ")\n",
         "\n",
         "MODEL_DIR = MODEL_DIR + \"/model\"\n",
@@ -5640,64 +5653,23 @@
       },
       "outputs": [],
       "source": [
-        "instance = [\n",
-        "    25,\n",
+        "INSTANCE = [\n",
+        "    31,\n",
         "    \"Private\",\n",
-        "    226802,\n",
-        "    \"11th\",\n",
-        "    7,\n",
+        "    45781,\n",
+        "    \"Masters\",\n",
+        "    14,\n",
         "    \"Never-married\",\n",
-        "    \"Machine-op-inspct\",\n",
-        "    \"Own-child\",\n",
-        "    \"Black\",\n",
-        "    \"Male\",\n",
+        "    \"Prof-specialty\",\n",
+        "    \"Not-in-family\",\n",
+        "    \"White\",\n",
+        "    \"Female\",\n",
+        "    14084,\n",
         "    0,\n",
-        "    0,\n",
-        "    40,\n",
+        "    50,\n",
         "    \"United-States\",\n",
         "]\n",
-        "instances = [instance]"
-      ]
-    },
-    {
-      "cell_type": "markdown",
-      "metadata": {
-        "id": "predict_request:mbsdk,custom,lbn"
-      },
-      "source": [
-        "### Make the prediction\n",
-        "\n",
-        "Now that your `Model` resource is deployed to an `Endpoint` resource, you can do online predictions by sending prediction requests to the `Endpoint` resource.\n",
-        "\n",
-        "#### Request\n",
-        "\n",
-        "The format of each instance is:\n",
-        "\n",
-        "    [feature_list]\n",
-        "\n",
-        "Since the predict() method can take multiple items (instances), send your single test item as a list of one test item.\n",
-        "\n",
-        "#### Response\n",
-        "\n",
-        "The response from the predict() call is a Python dictionary with the following entries:\n",
-        "\n",
-        "- `ids`: The internal assigned unique identifiers for each prediction request.\n",
-        "- `predictions`: The predicted confidence, between 0 and 1, per class label.\n",
-        "- `deployed_model_id`: The Vertex AI identifier for the deployed `Model` resource which did the predictions."
-      ]
-    },
-    {
-      "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "id": "predict_request:mbsdk,custom,lbn"
-      },
-      "outputs": [],
-      "source": [
-        "instances_list = [INSTANCE]\n",
-        "\n",
-        "prediction = endpoint.predict(instances_list)\n",
-        "print(prediction)"
+        "instances = [INSTANCE]"
       ]
     },
     {
@@ -5760,18 +5732,18 @@
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "examine_feature_attributions:mbsdk,iris"
+        "id": "examine_feature_attributions:mbsdk,sklearn"
       },
       "outputs": [],
       "source": [
         "from tabulate import tabulate\n",
         "\n",
-        "feature_names = [\"sepal_length\", \"sepal_width\", \"petal_length\", \"petal_width\"]\n",
+        "feature_names = COLUMNS\n",
         "attributions = prediction.explanations[0].attributions[0].feature_attributions\n",
         "\n",
         "rows = []\n",
         "for i, val in enumerate(feature_names):\n",
-        "    rows.append([val, INSTANCE[val], attributions[val]])\n",
+        "    rows.append([val, INSTANCE[i], attributions[val]])\n",
         "print(tabulate(rows, headers=[\"Feature name\", \"Feature value\", \"Attribution value\"]))"
       ]
     },