Pushing the docs to dev/ for branch: master, commit a2ebb8cfd2d126ad8e6fb36e0bdadba7de8fcd9f

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "# Author: Tim Head <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nnp.random.seed(10)\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_classification\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.ensemble import (RandomTreesEmbedding, RandomForestClassifier,\n                              GradientBoostingClassifier)\nfrom sklearn.preprocessing import OneHotEncoder\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_curve\nfrom sklearn.pipeline import make_pipeline\n\nn_estimator = 10\nX, y = make_classification(n_samples=80000)\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)\n# It is important to train the ensemble of trees on a different subset\n# of the training data than the linear regression model to avoid\n# overfitting, in particular if the total number of leaves is\n# similar to the number of training samples\nX_train, X_train_lr, y_train, y_train_lr = train_test_split(X_train,\n                                                            y_train,\n                                                            test_size=0.5)\n\n# Unsupervised transformation based on totally random trees\nrt = RandomTreesEmbedding(max_depth=3, n_estimators=n_estimator,\n\trandom_state=0)\n\nrt_lm = LogisticRegression()\npipeline = make_pipeline(rt, rt_lm)\npipeline.fit(X_train, y_train)\ny_pred_rt = pipeline.predict_proba(X_test)[:, 1]\nfpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)\n\n# Supervised transformation based on random forests\nrf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)\nrf_enc = OneHotEncoder()\nrf_lm = LogisticRegression()\nrf.fit(X_train, y_train)\nrf_enc.fit(rf.apply(X_train))\nrf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)\n\ny_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]\nfpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)\n\ngrd = GradientBoostingClassifier(n_estimators=n_estimator)\ngrd_enc = OneHotEncoder()\ngrd_lm = LogisticRegression()\ngrd.fit(X_train, y_train)\ngrd_enc.fit(grd.apply(X_train)[:, :, 0])\ngrd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)\n\ny_pred_grd_lm = grd_lm.predict_proba(\n    grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]\nfpr_grd_lm, tpr_grd_lm, _ = roc_curve(y_test, y_pred_grd_lm)\n\n\n# The gradient boosted model by itself\ny_pred_grd = grd.predict_proba(X_test)[:, 1]\nfpr_grd, tpr_grd, _ = roc_curve(y_test, y_pred_grd)\n\n\n# The random forest model by itself\ny_pred_rf = rf.predict_proba(X_test)[:, 1]\nfpr_rf, tpr_rf, _ = roc_curve(y_test, y_pred_rf)\n\nplt.figure(1)\nplt.plot([0, 1], [0, 1], 'k--')\nplt.plot(fpr_rt_lm, tpr_rt_lm, label='RT + LR')\nplt.plot(fpr_rf, tpr_rf, label='RF')\nplt.plot(fpr_rf_lm, tpr_rf_lm, label='RF + LR')\nplt.plot(fpr_grd, tpr_grd, label='GBT')\nplt.plot(fpr_grd_lm, tpr_grd_lm, label='GBT + LR')\nplt.xlabel('False positive rate')\nplt.ylabel('True positive rate')\nplt.title('ROC curve')\nplt.legend(loc='best')\nplt.show()\n\nplt.figure(2)\nplt.xlim(0, 0.2)\nplt.ylim(0.8, 1)\nplt.plot([0, 1], [0, 1], 'k--')\nplt.plot(fpr_rt_lm, tpr_rt_lm, label='RT + LR')\nplt.plot(fpr_rf, tpr_rf, label='RF')\nplt.plot(fpr_rf_lm, tpr_rf_lm, label='RF + LR')\nplt.plot(fpr_grd, tpr_grd, label='GBT')\nplt.plot(fpr_grd_lm, tpr_grd_lm, label='GBT + LR')\nplt.xlabel('False positive rate')\nplt.ylabel('True positive rate')\nplt.title('ROC curve (zoomed in at top left)')\nplt.legend(loc='best')\nplt.show()"
+        "# Author: Tim Head <[email protected]>\n#\n# License: BSD 3 clause\n\nimport numpy as np\nnp.random.seed(10)\n\nimport matplotlib.pyplot as plt\n\nfrom sklearn.datasets import make_classification\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.ensemble import (RandomTreesEmbedding, RandomForestClassifier,\n                              GradientBoostingClassifier)\nfrom sklearn.preprocessing import CategoricalEncoder\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.metrics import roc_curve\nfrom sklearn.pipeline import make_pipeline\n\nn_estimator = 10\nX, y = make_classification(n_samples=80000)\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.5)\n# It is important to train the ensemble of trees on a different subset\n# of the training data than the linear regression model to avoid\n# overfitting, in particular if the total number of leaves is\n# similar to the number of training samples\nX_train, X_train_lr, y_train, y_train_lr = train_test_split(X_train,\n                                                            y_train,\n                                                            test_size=0.5)\n\n# Unsupervised transformation based on totally random trees\nrt = RandomTreesEmbedding(max_depth=3, n_estimators=n_estimator,\n\trandom_state=0)\n\nrt_lm = LogisticRegression()\npipeline = make_pipeline(rt, rt_lm)\npipeline.fit(X_train, y_train)\ny_pred_rt = pipeline.predict_proba(X_test)[:, 1]\nfpr_rt_lm, tpr_rt_lm, _ = roc_curve(y_test, y_pred_rt)\n\n# Supervised transformation based on random forests\nrf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)\nrf_enc = CategoricalEncoder()\nrf_lm = LogisticRegression()\nrf.fit(X_train, y_train)\nrf_enc.fit(rf.apply(X_train))\nrf_lm.fit(rf_enc.transform(rf.apply(X_train_lr)), y_train_lr)\n\ny_pred_rf_lm = rf_lm.predict_proba(rf_enc.transform(rf.apply(X_test)))[:, 1]\nfpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)\n\ngrd = GradientBoostingClassifier(n_estimators=n_estimator)\ngrd_enc = CategoricalEncoder()\ngrd_lm = LogisticRegression()\ngrd.fit(X_train, y_train)\ngrd_enc.fit(grd.apply(X_train)[:, :, 0])\ngrd_lm.fit(grd_enc.transform(grd.apply(X_train_lr)[:, :, 0]), y_train_lr)\n\ny_pred_grd_lm = grd_lm.predict_proba(\n    grd_enc.transform(grd.apply(X_test)[:, :, 0]))[:, 1]\nfpr_grd_lm, tpr_grd_lm, _ = roc_curve(y_test, y_pred_grd_lm)\n\n\n# The gradient boosted model by itself\ny_pred_grd = grd.predict_proba(X_test)[:, 1]\nfpr_grd, tpr_grd, _ = roc_curve(y_test, y_pred_grd)\n\n\n# The random forest model by itself\ny_pred_rf = rf.predict_proba(X_test)[:, 1]\nfpr_rf, tpr_rf, _ = roc_curve(y_test, y_pred_rf)\n\nplt.figure(1)\nplt.plot([0, 1], [0, 1], 'k--')\nplt.plot(fpr_rt_lm, tpr_rt_lm, label='RT + LR')\nplt.plot(fpr_rf, tpr_rf, label='RF')\nplt.plot(fpr_rf_lm, tpr_rf_lm, label='RF + LR')\nplt.plot(fpr_grd, tpr_grd, label='GBT')\nplt.plot(fpr_grd_lm, tpr_grd_lm, label='GBT + LR')\nplt.xlabel('False positive rate')\nplt.ylabel('True positive rate')\nplt.title('ROC curve')\nplt.legend(loc='best')\nplt.show()\n\nplt.figure(2)\nplt.xlim(0, 0.2)\nplt.ylim(0.8, 1)\nplt.plot([0, 1], [0, 1], 'k--')\nplt.plot(fpr_rt_lm, tpr_rt_lm, label='RT + LR')\nplt.plot(fpr_rf, tpr_rf, label='RF')\nplt.plot(fpr_rf_lm, tpr_rf_lm, label='RF + LR')\nplt.plot(fpr_grd, tpr_grd, label='GBT')\nplt.plot(fpr_grd_lm, tpr_grd_lm, label='GBT + LR')\nplt.xlabel('False positive rate')\nplt.ylabel('True positive rate')\nplt.title('ROC curve (zoomed in at top left)')\nplt.legend(loc='best')\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -34,7 +34,7 @@
 from sklearn.linear_model import LogisticRegression
 from sklearn.ensemble import (RandomTreesEmbedding, RandomForestClassifier,
                               GradientBoostingClassifier)
-from sklearn.preprocessing import OneHotEncoder
+from sklearn.preprocessing import CategoricalEncoder
 from sklearn.model_selection import train_test_split
 from sklearn.metrics import roc_curve
 from sklearn.pipeline import make_pipeline
@@ -62,7 +62,7 @@
 
 # Supervised transformation based on random forests
 rf = RandomForestClassifier(max_depth=3, n_estimators=n_estimator)
-rf_enc = OneHotEncoder()
+rf_enc = CategoricalEncoder()
 rf_lm = LogisticRegression()
 rf.fit(X_train, y_train)
 rf_enc.fit(rf.apply(X_train))
@@ -72,7 +72,7 @@
 fpr_rf_lm, tpr_rf_lm, _ = roc_curve(y_test, y_pred_rf_lm)
 
 grd = GradientBoostingClassifier(n_estimators=n_estimator)
-grd_enc = OneHotEncoder()
+grd_enc = CategoricalEncoder()
 grd_lm = LogisticRegression()
 grd.fit(X_train, y_train)
 grd_enc.fit(grd.apply(X_train)[:, :, 0])