Update some sample notebooks to include dropped_features (microsoft#1911

) * update some notebooks to include dropped_features * update some notebooks to include dropped_features * update some notebooks to include dropped_features * remove unused changes * remove unused changes * address comments * address comment
sky-dust-intelligence · Jan 18, 2023 · 60d8870 · 60d8870
1 parent 9d24ea2
commit 60d8870
Show file tree

Hide file tree

Showing 2 changed files with 32 additions and 6 deletions.
diff --git a/notebooks/responsibleaidashboard/getting-started.ipynb b/notebooks/responsibleaidashboard/getting-started.ipynb
@@ -110,7 +110,9 @@
    "source": [
     "It is necessary to initialize a RAIInsights object upon which the different components can be loaded. `task_type` holds the string `'regression'` or `'classification'` depending on the developer's purpose.\n",
     "\n",
-    "Users can also specify categorical features via the `categorical_features` parameter."
+    "Users can also specify categorical features via the `categorical_features` parameter.\n",
+    "\n",
+    "Using the `FeatureMetadata` container, you can declare an `identity_feature`, and specify features to withhold from the model via the `dropped_features` parameter. The `FeatureMetadata` serves as an input argument for `RAIInsights`."
    ]
   },
   {
@@ -119,8 +121,13 @@
    "metadata": {},
    "source": [
     "```Python\n",
+    "from responsibleai.feature_metadata import FeatureMetadata\n",
+    "# Add 's1' as an identity feature, set 'age' as a dropped feature\n",
+    "feature_metadata = FeatureMetadata(identity_feature_name='s1', dropped_features=['age'])\n",
+    "\n",
     "task_type = 'regression'\n",
-    "rai_insights = RAIInsights(model, train_data, test_data, target_feature, task_type)\n",
+    "\n",
+    "rai_insights = RAIInsights(model, train_data, test_data, target_feature, task_type, categorical_features=[], feature_metadata=feature_metadata)\n",
     "```"
    ]
   },

diff --git a/notebooks/responsibleaidashboard/responsibleaidashboard-diabetes-decision-making.ipynb b/notebooks/responsibleaidashboard/responsibleaidashboard-diabetes-decision-making.ipynb
@@ -114,6 +114,25 @@
     "data.feature_names"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "46119282",
+   "metadata": {},
+   "source": [
+    "You may define `features_to_drop` and drop any features from `X_train`. The model will be trained without `features_to_drop`. If `features_to_drop` is not set, `X_train_after_drop` will be the same as `X_train`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3db1ef3b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "features_to_drop = []\n",
+    "X_train_after_drop = X_train.drop(features_to_drop, axis=1)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "59853607",
@@ -130,7 +149,7 @@
    "outputs": [],
    "source": [
     "model = RandomForestRegressor(random_state=0)\n",
-    "model.fit(X_train, y_train)"
+    "model.fit(X_train_after_drop, y_train)"
    ]
   },
   {
@@ -161,7 +180,7 @@
     "\n",
     "RAIInsights accepts the model, the train dataset, the test dataset, the target feature string, the task type string, and a list of strings of categorical feature names as its arguments.\n",
     "\n",
-    "You may also create the `FeatureMetadata` container and identify any feature of your choice as the `identity_feature`. The `FeatureMetadata` may also be passed into the `RAIInsights`."
+    "You may also create the `FeatureMetadata` container, identify any feature of your choice as the `identity_feature`, and specify dropped features via the `dropped_features` parameter. The `FeatureMetadata` may also be passed into the `RAIInsights`."
    ]
   },
   {
@@ -172,8 +191,8 @@
    "outputs": [],
    "source": [
     "from responsibleai.feature_metadata import FeatureMetadata\n",
-    "# Add 's1' as an identity feature\n",
-    "feature_metadata = FeatureMetadata(identity_feature_name='s1')\n",
+    "# Add 's1' as an identity feature, set features_to_drop as dropped features\n",
+    "feature_metadata = FeatureMetadata(identity_feature_name='s1', dropped_features=features_to_drop)\n",
     "rai_insights = RAIInsights(model, train_data, test_data, target_feature, 'regression',\n",
     "                           categorical_features=[], feature_metadata=feature_metadata)"
    ]