Pushing the docs to dev/ for branch: master, commit 9a4bd3702d403b30a7fa1c88332a6261a470c41a

Author: sklearn-ci

dev/_downloads/3409d9766d352cc9f9b169d4a799a87a/auto_examples_python.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\n\n# To use this experimental feature, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.impute import IterativeImputer\nfrom sklearn.linear_model import BayesianRidge\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.ensemble import ExtraTreesRegressor\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.model_selection import cross_val_score\n\nN_SPLITS = 5\n\nrng = np.random.RandomState(0)\n\nX_full, y_full = fetch_california_housing(return_X_y=True)\n# ~2k samples is enough for the purpose of the example.\n# Remove the following two lines for a slower run with different error bars.\nX_full = X_full[::10]\ny_full = y_full[::10]\nn_samples, n_features = X_full.shape\n\n# Estimate the score on the entire dataset, with no missing values\nbr_estimator = BayesianRidge()\nscore_full_data = pd.DataFrame(\n    cross_val_score(\n        br_estimator, X_full, y_full, scoring='neg_mean_squared_error',\n        cv=N_SPLITS\n    ),\n    columns=['Full Data']\n)\n\n# Add a single missing value to each row\nX_missing = X_full.copy()\ny_missing = y_full\nmissing_samples = np.arange(n_samples)\nmissing_features = rng.choice(n_features, n_samples, replace=True)\nX_missing[missing_samples, missing_features] = np.nan\n\n# Estimate the score after imputation (mean and median strategies)\nscore_simple_imputer = pd.DataFrame()\nfor strategy in ('mean', 'median'):\n    estimator = make_pipeline(\n        SimpleImputer(missing_values=np.nan, strategy=strategy),\n        br_estimator\n    )\n    score_simple_imputer[strategy] = cross_val_score(\n        estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n        cv=N_SPLITS\n    )\n\n# Estimate the score after iterative imputation of the missing values\n# with different estimators\nestimators = [\n    BayesianRidge(),\n    DecisionTreeRegressor(max_features='sqrt', random_state=0),\n    ExtraTreesRegressor(n_estimators=10, random_state=0),\n    KNeighborsRegressor(n_neighbors=15)\n]\nscore_iterative_imputer = pd.DataFrame()\nfor impute_estimator in estimators:\n    estimator = make_pipeline(\n        IterativeImputer(random_state=0, estimator=impute_estimator),\n        br_estimator\n    )\n    score_iterative_imputer[impute_estimator.__class__.__name__] = \\\n        cross_val_score(\n            estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n            cv=N_SPLITS\n        )\n\nscores = pd.concat(\n    [score_full_data, score_simple_imputer, score_iterative_imputer],\n    keys=['Original', 'SimpleImputer', 'IterativeImputer'], axis=1\n)\n\n# plot boston results\nfig, ax = plt.subplots(figsize=(13, 6))\nmeans = -scores.mean()\nerrors = scores.std()\nmeans.plot.barh(xerr=errors, ax=ax)\nax.set_title('California Housing Regression with Different Imputation Methods')\nax.set_xlabel('MSE (smaller is better)')\nax.set_yticks(np.arange(means.shape[0]))\nax.set_yticklabels([\" w/ \".join(label) for label in means.index.tolist()])\nplt.tight_layout(pad=1)\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\n\n# To use this experimental feature, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.impute import IterativeImputer\nfrom sklearn.linear_model import BayesianRidge\nfrom sklearn.tree import DecisionTreeRegressor\nfrom sklearn.ensemble import ExtraTreesRegressor\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.model_selection import cross_val_score\n\nN_SPLITS = 5\n\nrng = np.random.RandomState(0)\n\nX_full, y_full = fetch_california_housing(return_X_y=True)\n# ~2k samples is enough for the purpose of the example.\n# Remove the following two lines for a slower run with different error bars.\nX_full = X_full[::10]\ny_full = y_full[::10]\nn_samples, n_features = X_full.shape\n\n# Estimate the score on the entire dataset, with no missing values\nbr_estimator = BayesianRidge()\nscore_full_data = pd.DataFrame(\n    cross_val_score(\n        br_estimator, X_full, y_full, scoring='neg_mean_squared_error',\n        cv=N_SPLITS\n    ),\n    columns=['Full Data']\n)\n\n# Add a single missing value to each row\nX_missing = X_full.copy()\ny_missing = y_full\nmissing_samples = np.arange(n_samples)\nmissing_features = rng.choice(n_features, n_samples, replace=True)\nX_missing[missing_samples, missing_features] = np.nan\n\n# Estimate the score after imputation (mean and median strategies)\nscore_simple_imputer = pd.DataFrame()\nfor strategy in ('mean', 'median'):\n    estimator = make_pipeline(\n        SimpleImputer(missing_values=np.nan, strategy=strategy),\n        br_estimator\n    )\n    score_simple_imputer[strategy] = cross_val_score(\n        estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n        cv=N_SPLITS\n    )\n\n# Estimate the score after iterative imputation of the missing values\n# with different estimators\nestimators = [\n    BayesianRidge(),\n    DecisionTreeRegressor(max_features='sqrt', random_state=0),\n    ExtraTreesRegressor(n_estimators=10, random_state=0),\n    KNeighborsRegressor(n_neighbors=15)\n]\nscore_iterative_imputer = pd.DataFrame()\nfor impute_estimator in estimators:\n    estimator = make_pipeline(\n        IterativeImputer(random_state=0, estimator=impute_estimator),\n        br_estimator\n    )\n    score_iterative_imputer[impute_estimator.__class__.__name__] = \\\n        cross_val_score(\n            estimator, X_missing, y_missing, scoring='neg_mean_squared_error',\n            cv=N_SPLITS\n        )\n\nscores = pd.concat(\n    [score_full_data, score_simple_imputer, score_iterative_imputer],\n    keys=['Original', 'SimpleImputer', 'IterativeImputer'], axis=1\n)\n\n# plot california housing results\nfig, ax = plt.subplots(figsize=(13, 6))\nmeans = -scores.mean()\nerrors = scores.std()\nmeans.plot.barh(xerr=errors, ax=ax)\nax.set_title('California Housing Regression with Different Imputation Methods')\nax.set_xlabel('MSE (smaller is better)')\nax.set_yticks(np.arange(means.shape[0]))\nax.set_yticklabels([\" w/ \".join(label) for label in means.index.tolist()])\nplt.tight_layout(pad=1)\nplt.show()"
       ]
     }
   ],

dev/_downloads/5d93da33b794785877d0c01122dd0716/plot_iterative_imputer_variants_comparison.ipynb

@@ -119,7 +119,7 @@
     keys=['Original', 'SimpleImputer', 'IterativeImputer'], axis=1
 )
 
-# plot boston results
+# plot california housing results
 fig, ax = plt.subplots(figsize=(13, 6))
 means = -scores.mean()
 errors = scores.std()