scikit-learn · thomasjpfan · Oct 31, 2019 · Jun 5, 2019 · Jun 5, 2019 · Jun 6, 2019
diff --git a/doc/whats_new/v0.22.rst b/doc/whats_new/v0.22.rst
@@ -370,6 +370,10 @@ Changelog
   :class:`ensemble.HistGradientBoostingRegressor`. :pr:`13769` by
   `Nicolas Hug`_.
 
+- |Enhancement| :func:`inspection.partial_dependence` accepts pandas DataFrame
+  and :class:`pipeline.Pipeline` containing :class:`compose.ColumnTransformer`.
+  :pr:`14028` by :user:`Guillaume Lemaitre <glemaitre>`.
+
 :mod:`sklearn.kernel_approximation`
 ...................................
 

diff --git a/examples/inspection/plot_partial_dependence.py b/examples/inspection/plot_partial_dependence.py
@@ -30,6 +30,7 @@
 
 from time import time
 import numpy as np
+import pandas as pd
 import matplotlib.pyplot as plt
 from mpl_toolkits.mplot3d import Axes3D
 
@@ -54,8 +55,8 @@
 # (here the average target, by default)
 
 cal_housing = fetch_california_housing()
-names = cal_housing.feature_names
-X, y = cal_housing.data, cal_housing.target
+X = pd.DataFrame(cal_housing.data, columns=cal_housing.feature_names)
+y = cal_housing.target
 
 y -= y.mean()
 
@@ -104,8 +105,9 @@
 tic = time()
 # We don't compute the 2-way PDP (5, 1) here, because it is a lot slower
 # with the brute method.
-features = [0, 5, 1, 2]
-plot_partial_dependence(est, X_train, features, feature_names=names,
+features = ['MedInc', 'AveOccup', 'HouseAge', 'AveRooms']
+plot_partial_dependence(est, X_train, features,
+                        feature_names=X_train.columns.tolist(),
                         n_jobs=3, grid_resolution=20)
 print("done in {:.3f}s".format(time() - tic))
 fig = plt.gcf()
@@ -143,8 +145,10 @@
 
 print('Computing partial dependence plots...')
 tic = time()
-features = [0, 5, 1, 2, (5, 1)]
-plot_partial_dependence(est, X_train, features, feature_names=names,
+features = ['MedInc', 'AveOccup', 'HouseAge', 'AveRooms',
+            ('AveOccup', 'HouseAge')]
+plot_partial_dependence(est, X_train, features,
+                        feature_names=X_train.columns.tolist(),
                         n_jobs=3, grid_resolution=20)
 print("done in {:.3f}s".format(time() - tic))
 fig = plt.gcf()
@@ -192,16 +196,16 @@
 
 fig = plt.figure()
 
-target_feature = (1, 5)
-pdp, axes = partial_dependence(est, X_train, target_feature,
+features = ('AveOccup', 'HouseAge')
+pdp, axes = partial_dependence(est, X_train, features=features,
                                grid_resolution=20)
 XX, YY = np.meshgrid(axes[0], axes[1])
 Z = pdp[0].T
 ax = Axes3D(fig)
 surf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1,
                        cmap=plt.cm.BuPu, edgecolor='k')
-ax.set_xlabel(names[target_feature[0]])
-ax.set_ylabel(names[target_feature[1]])
+ax.set_xlabel(features[0])
+ax.set_ylabel(features[1])
 ax.set_zlabel('Partial dependence')
 #  pretty init view
 ax.view_init(elev=22, azim=122)

diff --git a/examples/plot_partial_dependence_visualization_api.py b/examples/plot_partial_dependence_visualization_api.py
@@ -15,6 +15,7 @@
 """
 print(__doc__)
 
+import pandas as pd
 import matplotlib.pyplot as plt
 from sklearn.datasets import load_boston
 from sklearn.neural_network import MLPRegressor
@@ -32,8 +33,8 @@
 # housing price dataset.
 
 boston = load_boston()
-X, y = boston.data, boston.target
-feature_names = boston.feature_names
+X = pd.DataFrame(boston.data, columns=boston.feature_names)
+y = boston.target
 
 tree = DecisionTreeRegressor()
 mlp = make_pipeline(StandardScaler(),
@@ -55,7 +56,7 @@
 fig, ax = plt.subplots(figsize=(12, 6))
 ax.set_title("Decision Tree")
 tree_disp = plot_partial_dependence(tree, X, ["LSTAT", "RM"],
-                                    feature_names=feature_names, ax=ax)
+                                    feature_names=X.columns.tolist(), ax=ax)
 
 ##############################################################################
 # The partial depdendence curves can be plotted for the multi-layer perceptron.
@@ -65,7 +66,7 @@
 fig, ax = plt.subplots(figsize=(12, 6))
 ax.set_title("Multi-layer Perceptron")
 mlp_disp = plot_partial_dependence(mlp, X, ["LSTAT", "RM"],
-                                   feature_names=feature_names, ax=ax,
+                                   feature_names=X.columns.tolist(), ax=ax,
                                    line_kw={"c": "red"})
 
 ##############################################################################
@@ -134,7 +135,7 @@
 # the same axes. In this case, `tree_disp.axes_` is passed into the second
 # plot function.
 tree_disp = plot_partial_dependence(tree, X, ["LSTAT"],
-                                    feature_names=feature_names)
+                                    feature_names=X.columns.tolist())
 mlp_disp = plot_partial_dependence(mlp, X, ["LSTAT"],
-                                   feature_names=feature_names,
+                                   feature_names=X.columns.tolist(),
                                    ax=tree_disp.axes_, line_kw={"c": "red"})