Pushing the docs to dev/ for branch: master, commit 52aaf8269235d4965022b8ec970243bdcb59c9a7

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\n\nfrom sklearn.datasets import load_boston\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import Imputer\nfrom sklearn.model_selection import cross_val_score\n\nrng = np.random.RandomState(0)\n\ndataset = load_boston()\nX_full, y_full = dataset.data, dataset.target\nn_samples = X_full.shape[0]\nn_features = X_full.shape[1]\n\n# Estimate the score on the entire dataset, with no missing values\nestimator = RandomForestRegressor(random_state=0, n_estimators=100)\nscore = cross_val_score(estimator, X_full, y_full).mean()\nprint(\"Score with the entire dataset = %.2f\" % score)\n\n# Add missing values in 75% of the lines\nmissing_rate = 0.75\nn_missing_samples = int(np.floor(n_samples * missing_rate))\nmissing_samples = np.hstack((np.zeros(n_samples - n_missing_samples,\n                                      dtype=np.bool),\n                             np.ones(n_missing_samples,\n                                     dtype=np.bool)))\nrng.shuffle(missing_samples)\nmissing_features = rng.randint(0, n_features, n_missing_samples)\n\n# Estimate the score without the lines containing missing values\nX_filtered = X_full[~missing_samples, :]\ny_filtered = y_full[~missing_samples]\nestimator = RandomForestRegressor(random_state=0, n_estimators=100)\nscore = cross_val_score(estimator, X_filtered, y_filtered).mean()\nprint(\"Score without the samples containing missing values = %.2f\" % score)\n\n# Estimate the score after imputation of the missing values\nX_missing = X_full.copy()\nX_missing[np.where(missing_samples)[0], missing_features] = 0\ny_missing = y_full.copy()\nestimator = Pipeline([(\"imputer\", Imputer(missing_values=0,\n                                          strategy=\"mean\",\n                                          axis=0)),\n                      (\"forest\", RandomForestRegressor(random_state=0,\n                                                       n_estimators=100))])\nscore = cross_val_score(estimator, X_missing, y_missing).mean()\nprint(\"Score after imputation of the missing values = %.2f\" % score)"
+        "import numpy as np\n\nfrom sklearn.datasets import load_boston\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.pipeline import Pipeline\nfrom sklearn.preprocessing import Imputer\nfrom sklearn.model_selection import cross_val_score\n\nrng = np.random.RandomState(0)\n\ndataset = load_boston()\nX_full, y_full = dataset.data, dataset.target\nn_samples = X_full.shape[0]\nn_features = X_full.shape[1]\n\n# Estimate the score on the entire dataset, with no missing values\nestimator = RandomForestRegressor(random_state=0, n_estimators=100)\nscore = cross_val_score(estimator, X_full, y_full).mean()\nprint(\"Score with the entire dataset = %.2f\" % score)\n\n# Add missing values in 75% of the lines\nmissing_rate = 0.75\nn_missing_samples = int(np.floor(n_samples * missing_rate))\nmissing_samples = np.hstack((np.zeros(n_samples - n_missing_samples,\n                                      dtype=np.bool),\n                             np.ones(n_missing_samples,\n                                     dtype=np.bool)))\nrng.shuffle(missing_samples)\nmissing_features = rng.randint(0, n_features, n_missing_samples)\n\n# Estimate the score without the lines containing missing values\nX_filtered = X_full[~missing_samples, :]\ny_filtered = y_full[~missing_samples]\nestimator = RandomForestRegressor(random_state=0, n_estimators=100)\nscore = cross_val_score(estimator, X_filtered, y_filtered).mean()\nprint(\"Score without the samples containing missing values = %.2f\" % score)\n\n# Estimate the score after imputation of the missing values\nX_missing = X_full.copy()\nX_missing[np.where(missing_samples)[0], missing_features] = 0\ny_missing = y_full.copy()\nestimator = Pipeline([(\"imputer\", Imputer(missing_values=0,\n                                          strategy=\"mean\")),\n                      (\"forest\", RandomForestRegressor(random_state=0,\n                                                       n_estimators=100))])\nscore = cross_val_score(estimator, X_missing, y_missing).mean()\nprint(\"Score after imputation of the missing values = %.2f\" % score)"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -65,8 +65,7 @@
 X_missing[np.where(missing_samples)[0], missing_features] = 0
 y_missing = y_full.copy()
 estimator = Pipeline([("imputer", Imputer(missing_values=0,
-                                          strategy="mean",
-                                          axis=0)),
+                                          strategy="mean")),
                       ("forest", RandomForestRegressor(random_state=0,
                                                        n_estimators=100))])
 score = cross_val_score(estimator, X_missing, y_missing).mean()