Merge pull request #351 from imatiach-msft/ilmat/update-raw-features-notebook

Update raw features explanation notebook

how-to-use-azureml/explain-model/explain-tabular-data-raw-features/explain-sklearn-raw-features.ipynb

@@ -29,6 +29,22 @@
     "4. Visualize the global and local explanations with the visualization dashboard."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This example needs sklearn-pandas. If it is not installed, uncomment and run the following line."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install sklearn-pandas"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -39,7 +55,7 @@
     "from sklearn.impute import SimpleImputer\n",
     "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
     "from sklearn.linear_model import LogisticRegression\n",
-    "from azureml.contrib.explain.model.tabular_explainer import TabularExplainer\n",
+    "from azureml.explain.model.tabular_explainer import TabularExplainer\n",
     "from sklearn_pandas import DataFrameMapper\n",
     "import pandas as pd\n",
     "import numpy as np"
@@ -101,16 +117,19 @@
     "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
     "from sklearn_pandas import DataFrameMapper\n",
     "\n",
-    "# Impute and standardize the numeric features\n",
-    "numeric_transformations = [([f], Pipeline(steps=[\n",
-    "    ('imputer', SimpleImputer(strategy='median')),\n",
-    "    ('scaler', StandardScaler())])) for f in numeric_features]\n",
-    "    \n",
-    "# One hot encode the categorical features    \n",
-    "categorical_transformations = [([f], OneHotEncoder(handle_unknown='ignore', sparse=False)) for f in categorical_features]\n",
+    "# Impute, standardize the numeric features and one-hot encode the categorical features.    \n",
     "\n",
+    "transformations = [\n",
+    "    ([\"age\", \"fare\"], Pipeline(steps=[\n",
+    "        ('imputer', SimpleImputer(strategy='median')),\n",
+    "        ('scaler', StandardScaler())\n",
+    "    ])),\n",
+    "    ([\"embarked\"], Pipeline(steps=[\n",
+    "        (\"imputer\", SimpleImputer(strategy='constant', fill_value='missing')), \n",
+    "        (\"encoder\", OneHotEncoder(sparse=False))])),\n",
+    "    ([\"sex\", \"pclass\"], OneHotEncoder(sparse=False))    \n",
+    "]\n",
     "\n",
-    "transformations = numeric_transformations + categorical_transformations\n",
     "\n",
     "# Append classifier to preprocessing pipeline.\n",
     "# Now we have a full prediction pipeline.\n",
@@ -231,13 +250,6 @@
    "source": [
     "ExplanationDashboard(global_explanation, model, x_test)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {