Pushing the docs to dev/ for branch: master, commit 7ea78614829a144f2f82e94fca515722a0fc2ef3

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import load_boston\nfrom sklearn.neural_network import MLPRegressor\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.inspection import plot_partial_dependence"
+        "print(__doc__)\n\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom sklearn.datasets import load_boston\nfrom sklearn.neural_network import MLPRegressor\nfrom sklearn.preprocessing import StandardScaler\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.inspection import plot_partial_dependence"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "boston = load_boston()\nX, y = boston.data, boston.target\nfeature_names = boston.feature_names\n\ntree = DecisionTreeRegressor()\nmlp = make_pipeline(StandardScaler(),\n                    MLPRegressor(hidden_layer_sizes=(100, 100),\n                                 tol=1e-2, max_iter=500, random_state=0))\ntree.fit(X, y)\nmlp.fit(X, y)"
+        "boston = load_boston()\nX = pd.DataFrame(boston.data, columns=boston.feature_names)\ny = boston.target\n\ntree = DecisionTreeRegressor()\nmlp = make_pipeline(StandardScaler(),\n                    MLPRegressor(hidden_layer_sizes=(100, 100),\n                                 tol=1e-2, max_iter=500, random_state=0))\ntree.fit(X, y)\nmlp.fit(X, y)"
       ]
     },
     {
@@ -62,7 +62,7 @@
       },
       "outputs": [],
       "source": [
-        "fig, ax = plt.subplots(figsize=(12, 6))\nax.set_title(\"Decision Tree\")\ntree_disp = plot_partial_dependence(tree, X, [\"LSTAT\", \"RM\"],\n                                    feature_names=feature_names, ax=ax)"
+        "fig, ax = plt.subplots(figsize=(12, 6))\nax.set_title(\"Decision Tree\")\ntree_disp = plot_partial_dependence(tree, X, [\"LSTAT\", \"RM\"],\n                                    feature_names=X.columns.tolist(), ax=ax)"
       ]
     },
     {
@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "fig, ax = plt.subplots(figsize=(12, 6))\nax.set_title(\"Multi-layer Perceptron\")\nmlp_disp = plot_partial_dependence(mlp, X, [\"LSTAT\", \"RM\"],\n                                   feature_names=feature_names, ax=ax,\n                                   line_kw={\"c\": \"red\"})"
+        "fig, ax = plt.subplots(figsize=(12, 6))\nax.set_title(\"Multi-layer Perceptron\")\nmlp_disp = plot_partial_dependence(mlp, X, [\"LSTAT\", \"RM\"],\n                                   feature_names=X.columns.tolist(), ax=ax,\n                                   line_kw={\"c\": \"red\"})"
       ]
     },
     {
@@ -152,7 +152,7 @@
       },
       "outputs": [],
       "source": [
-        "tree_disp = plot_partial_dependence(tree, X, [\"LSTAT\"],\n                                    feature_names=feature_names)\nmlp_disp = plot_partial_dependence(mlp, X, [\"LSTAT\"],\n                                   feature_names=feature_names,\n                                   ax=tree_disp.axes_, line_kw={\"c\": \"red\"})"
+        "tree_disp = plot_partial_dependence(tree, X, [\"LSTAT\"],\n                                    feature_names=X.columns.tolist())\nmlp_disp = plot_partial_dependence(mlp, X, [\"LSTAT\"],\n                                   feature_names=X.columns.tolist(),\n                                   ax=tree_disp.axes_, line_kw={\"c\": \"red\"})"
       ]
     }
   ],

dev/_downloads/51a82a09a4aa0f703f69fb5d4f15104f/plot_partial_dependence_visualization_api.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nfrom time import time\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom mpl_toolkits.mplot3d import Axes3D\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import QuantileTransformer\nfrom sklearn.pipeline import make_pipeline\n\nfrom sklearn.inspection import partial_dependence\nfrom sklearn.inspection import plot_partial_dependence\nfrom sklearn.experimental import enable_hist_gradient_boosting  # noqa\nfrom sklearn.ensemble import HistGradientBoostingRegressor\nfrom sklearn.neural_network import MLPRegressor\nfrom sklearn.datasets import fetch_california_housing"
+        "print(__doc__)\n\nfrom time import time\nimport numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nfrom mpl_toolkits.mplot3d import Axes3D\n\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import QuantileTransformer\nfrom sklearn.pipeline import make_pipeline\n\nfrom sklearn.inspection import partial_dependence\nfrom sklearn.inspection import plot_partial_dependence\nfrom sklearn.experimental import enable_hist_gradient_boosting  # noqa\nfrom sklearn.ensemble import HistGradientBoostingRegressor\nfrom sklearn.neural_network import MLPRegressor\nfrom sklearn.datasets import fetch_california_housing"
       ]
     },
     {
@@ -44,7 +44,7 @@
       },
       "outputs": [],
       "source": [
-        "cal_housing = fetch_california_housing()\nnames = cal_housing.feature_names\nX, y = cal_housing.data, cal_housing.target\n\ny -= y.mean()\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1,\n                                                    random_state=0)"
+        "cal_housing = fetch_california_housing()\nX = pd.DataFrame(cal_housing.data, columns=cal_housing.feature_names)\ny = cal_housing.target\n\ny -= y.mean()\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1,\n                                                    random_state=0)"
       ]
     },
     {
@@ -80,7 +80,7 @@
       },
       "outputs": [],
       "source": [
-        "print('Computing partial dependence plots...')\ntic = time()\n# We don't compute the 2-way PDP (5, 1) here, because it is a lot slower\n# with the brute method.\nfeatures = [0, 5, 1, 2]\nplot_partial_dependence(est, X_train, features, feature_names=names,\n                        n_jobs=3, grid_resolution=20)\nprint(\"done in {:.3f}s\".format(time() - tic))\nfig = plt.gcf()\nfig.suptitle('Partial dependence of house value on non-___location features\\n'\n             'for the California housing dataset, with MLPRegressor')\nfig.subplots_adjust(hspace=0.3)"
+        "print('Computing partial dependence plots...')\ntic = time()\n# We don't compute the 2-way PDP (5, 1) here, because it is a lot slower\n# with the brute method.\nfeatures = ['MedInc', 'AveOccup', 'HouseAge', 'AveRooms']\nplot_partial_dependence(est, X_train, features,\n                        feature_names=X_train.columns.tolist(),\n                        n_jobs=3, grid_resolution=20)\nprint(\"done in {:.3f}s\".format(time() - tic))\nfig = plt.gcf()\nfig.suptitle('Partial dependence of house value on non-___location features\\n'\n             'for the California housing dataset, with MLPRegressor')\nfig.subplots_adjust(hspace=0.3)"
       ]
     },
     {
@@ -116,7 +116,7 @@
       },
       "outputs": [],
       "source": [
-        "print('Computing partial dependence plots...')\ntic = time()\nfeatures = [0, 5, 1, 2, (5, 1)]\nplot_partial_dependence(est, X_train, features, feature_names=names,\n                        n_jobs=3, grid_resolution=20)\nprint(\"done in {:.3f}s\".format(time() - tic))\nfig = plt.gcf()\nfig.suptitle('Partial dependence of house value on non-___location features\\n'\n             'for the California housing dataset, with Gradient Boosting')\nfig.subplots_adjust(wspace=0.4, hspace=0.3)"
+        "print('Computing partial dependence plots...')\ntic = time()\nfeatures = ['MedInc', 'AveOccup', 'HouseAge', 'AveRooms',\n            ('AveOccup', 'HouseAge')]\nplot_partial_dependence(est, X_train, features,\n                        feature_names=X_train.columns.tolist(),\n                        n_jobs=3, grid_resolution=20)\nprint(\"done in {:.3f}s\".format(time() - tic))\nfig = plt.gcf()\nfig.suptitle('Partial dependence of house value on non-___location features\\n'\n             'for the California housing dataset, with Gradient Boosting')\nfig.subplots_adjust(wspace=0.4, hspace=0.3)"
       ]
     },
     {
@@ -141,7 +141,7 @@
       },
       "outputs": [],
       "source": [
-        "fig = plt.figure()\n\ntarget_feature = (1, 5)\npdp, axes = partial_dependence(est, X_train, target_feature,\n                               grid_resolution=20)\nXX, YY = np.meshgrid(axes[0], axes[1])\nZ = pdp[0].T\nax = Axes3D(fig)\nsurf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1,\n                       cmap=plt.cm.BuPu, edgecolor='k')\nax.set_xlabel(names[target_feature[0]])\nax.set_ylabel(names[target_feature[1]])\nax.set_zlabel('Partial dependence')\n#  pretty init view\nax.view_init(elev=22, azim=122)\nplt.colorbar(surf)\nplt.suptitle('Partial dependence of house value on median\\n'\n             'age and average occupancy, with Gradient Boosting')\nplt.subplots_adjust(top=0.9)\n\nplt.show()"
+        "fig = plt.figure()\n\nfeatures = ('AveOccup', 'HouseAge')\npdp, axes = partial_dependence(est, X_train, features=features,\n                               grid_resolution=20)\nXX, YY = np.meshgrid(axes[0], axes[1])\nZ = pdp[0].T\nax = Axes3D(fig)\nsurf = ax.plot_surface(XX, YY, Z, rstride=1, cstride=1,\n                       cmap=plt.cm.BuPu, edgecolor='k')\nax.set_xlabel(features[0])\nax.set_ylabel(features[1])\nax.set_zlabel('Partial dependence')\n#  pretty init view\nax.view_init(elev=22, azim=122)\nplt.colorbar(surf)\nplt.suptitle('Partial dependence of house value on median\\n'\n             'age and average occupancy, with Gradient Boosting')\nplt.subplots_adjust(top=0.9)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/5a693c97e821586539ab9d250762742c/plot_partial_dependence.ipynb

@@ -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"})

dev/_downloads/781bb5a2dc85df6b75ee78d2eb118b0b/plot_partial_dependence_visualization_api.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)