Pushing the docs to dev/ for branch: master, commit 1675e77e3e41ca287a451bc65e37a2eba5ca1e39

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\nimport pandas as pd\n\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.get_values()])\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 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.get_values()])\nplt.tight_layout(pad=1)\nplt.show()"
       ]
     }
   ],

dev/_downloads/auto_examples_python.zip

@@ -42,6 +42,8 @@
 import matplotlib.pyplot as plt
 import pandas as pd
 
+# To use this experimental feature, we need to explicitly ask for it:
+from sklearn.experimental import enable_iterative_imputer  # noqa
 from sklearn.datasets import fetch_california_housing
 from sklearn.impute import SimpleImputer
 from sklearn.impute import IterativeImputer

dev/_downloads/plot_iterative_imputer_variants_comparison.ipynb

@@ -26,7 +26,7 @@
       },
       "outputs": [],
       "source": [
-        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nfrom sklearn.datasets import load_diabetes\nfrom sklearn.datasets import load_boston\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.pipeline import make_pipeline, make_union\nfrom sklearn.impute import SimpleImputer, IterativeImputer, MissingIndicator\nfrom sklearn.model_selection import cross_val_score\n\nrng = np.random.RandomState(0)\n\nN_SPLITS = 5\nREGRESSOR = RandomForestRegressor(random_state=0, n_estimators=100)\n\n\ndef get_scores_for_imputer(imputer, X_missing, y_missing):\n    estimator = make_pipeline(\n        make_union(imputer, MissingIndicator(missing_values=0)),\n        REGRESSOR)\n    impute_scores = cross_val_score(estimator, X_missing, y_missing,\n                                    scoring='neg_mean_squared_error',\n                                    cv=N_SPLITS)\n    return impute_scores\n\n\ndef get_results(dataset):\n    X_full, y_full = dataset.data, dataset.target\n    n_samples = X_full.shape[0]\n    n_features = X_full.shape[1]\n\n    # Estimate the score on the entire dataset, with no missing values\n    full_scores = cross_val_score(REGRESSOR, X_full, y_full,\n                                  scoring='neg_mean_squared_error',\n                                  cv=N_SPLITS)\n\n    # Add missing values in 75% of the lines\n    missing_rate = 0.75\n    n_missing_samples = int(np.floor(n_samples * missing_rate))\n    missing_samples = np.hstack((np.zeros(n_samples - n_missing_samples,\n                                          dtype=np.bool),\n                                 np.ones(n_missing_samples,\n                                         dtype=np.bool)))\n    rng.shuffle(missing_samples)\n    missing_features = rng.randint(0, n_features, n_missing_samples)\n    X_missing = X_full.copy()\n    X_missing[np.where(missing_samples)[0], missing_features] = 0\n    y_missing = y_full.copy()\n\n    # Estimate the score after replacing missing values by 0\n    imputer = SimpleImputer(missing_values=0,\n                            strategy='constant',\n                            fill_value=0)\n    zero_impute_scores = get_scores_for_imputer(imputer, X_missing, y_missing)\n\n    # Estimate the score after imputation (mean strategy) of the missing values\n    imputer = SimpleImputer(missing_values=0, strategy=\"mean\")\n    mean_impute_scores = get_scores_for_imputer(imputer, X_missing, y_missing)\n\n    # Estimate the score after iterative imputation of the missing values\n    imputer = IterativeImputer(missing_values=0,\n                               random_state=0,\n                               n_nearest_features=5)\n    iterative_impute_scores = get_scores_for_imputer(imputer,\n                                                     X_missing,\n                                                     y_missing)\n\n    return ((full_scores.mean(), full_scores.std()),\n            (zero_impute_scores.mean(), zero_impute_scores.std()),\n            (mean_impute_scores.mean(), mean_impute_scores.std()),\n            (iterative_impute_scores.mean(), iterative_impute_scores.std()))\n\n\nresults_diabetes = np.array(get_results(load_diabetes()))\nmses_diabetes = results_diabetes[:, 0] * -1\nstds_diabetes = results_diabetes[:, 1]\n\nresults_boston = np.array(get_results(load_boston()))\nmses_boston = results_boston[:, 0] * -1\nstds_boston = results_boston[:, 1]\n\nn_bars = len(mses_diabetes)\nxval = np.arange(n_bars)\n\nx_labels = ['Full data',\n            'Zero imputation',\n            'Mean Imputation',\n            'Multivariate Imputation']\ncolors = ['r', 'g', 'b', 'orange']\n\n# plot diabetes results\nplt.figure(figsize=(12, 6))\nax1 = plt.subplot(121)\nfor j in xval:\n    ax1.barh(j, mses_diabetes[j], xerr=stds_diabetes[j],\n             color=colors[j], alpha=0.6, align='center')\n\nax1.set_title('Imputation Techniques with Diabetes Data')\nax1.set_xlim(left=np.min(mses_diabetes) * 0.9,\n             right=np.max(mses_diabetes) * 1.1)\nax1.set_yticks(xval)\nax1.set_xlabel('MSE')\nax1.invert_yaxis()\nax1.set_yticklabels(x_labels)\n\n# plot boston results\nax2 = plt.subplot(122)\nfor j in xval:\n    ax2.barh(j, mses_boston[j], xerr=stds_boston[j],\n             color=colors[j], alpha=0.6, align='center')\n\nax2.set_title('Imputation Techniques with Boston Data')\nax2.set_yticks(xval)\nax2.set_xlabel('MSE')\nax2.invert_yaxis()\nax2.set_yticklabels([''] * n_bars)\n\nplt.show()"
+        "print(__doc__)\n\nimport numpy as np\nimport matplotlib.pyplot as plt\n\n# To use the experimental IterativeImputer, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa\nfrom sklearn.datasets import load_diabetes\nfrom sklearn.datasets import load_boston\nfrom sklearn.ensemble import RandomForestRegressor\nfrom sklearn.pipeline import make_pipeline, make_union\nfrom sklearn.impute import SimpleImputer, IterativeImputer, MissingIndicator\nfrom sklearn.model_selection import cross_val_score\n\nrng = np.random.RandomState(0)\n\nN_SPLITS = 5\nREGRESSOR = RandomForestRegressor(random_state=0, n_estimators=100)\n\n\ndef get_scores_for_imputer(imputer, X_missing, y_missing):\n    estimator = make_pipeline(\n        make_union(imputer, MissingIndicator(missing_values=0)),\n        REGRESSOR)\n    impute_scores = cross_val_score(estimator, X_missing, y_missing,\n                                    scoring='neg_mean_squared_error',\n                                    cv=N_SPLITS)\n    return impute_scores\n\n\ndef get_results(dataset):\n    X_full, y_full = dataset.data, dataset.target\n    n_samples = X_full.shape[0]\n    n_features = X_full.shape[1]\n\n    # Estimate the score on the entire dataset, with no missing values\n    full_scores = cross_val_score(REGRESSOR, X_full, y_full,\n                                  scoring='neg_mean_squared_error',\n                                  cv=N_SPLITS)\n\n    # Add missing values in 75% of the lines\n    missing_rate = 0.75\n    n_missing_samples = int(np.floor(n_samples * missing_rate))\n    missing_samples = np.hstack((np.zeros(n_samples - n_missing_samples,\n                                          dtype=np.bool),\n                                 np.ones(n_missing_samples,\n                                         dtype=np.bool)))\n    rng.shuffle(missing_samples)\n    missing_features = rng.randint(0, n_features, n_missing_samples)\n    X_missing = X_full.copy()\n    X_missing[np.where(missing_samples)[0], missing_features] = 0\n    y_missing = y_full.copy()\n\n    # Estimate the score after replacing missing values by 0\n    imputer = SimpleImputer(missing_values=0,\n                            strategy='constant',\n                            fill_value=0)\n    zero_impute_scores = get_scores_for_imputer(imputer, X_missing, y_missing)\n\n    # Estimate the score after imputation (mean strategy) of the missing values\n    imputer = SimpleImputer(missing_values=0, strategy=\"mean\")\n    mean_impute_scores = get_scores_for_imputer(imputer, X_missing, y_missing)\n\n    # Estimate the score after iterative imputation of the missing values\n    imputer = IterativeImputer(missing_values=0,\n                               random_state=0,\n                               n_nearest_features=5)\n    iterative_impute_scores = get_scores_for_imputer(imputer,\n                                                     X_missing,\n                                                     y_missing)\n\n    return ((full_scores.mean(), full_scores.std()),\n            (zero_impute_scores.mean(), zero_impute_scores.std()),\n            (mean_impute_scores.mean(), mean_impute_scores.std()),\n            (iterative_impute_scores.mean(), iterative_impute_scores.std()))\n\n\nresults_diabetes = np.array(get_results(load_diabetes()))\nmses_diabetes = results_diabetes[:, 0] * -1\nstds_diabetes = results_diabetes[:, 1]\n\nresults_boston = np.array(get_results(load_boston()))\nmses_boston = results_boston[:, 0] * -1\nstds_boston = results_boston[:, 1]\n\nn_bars = len(mses_diabetes)\nxval = np.arange(n_bars)\n\nx_labels = ['Full data',\n            'Zero imputation',\n            'Mean Imputation',\n            'Multivariate Imputation']\ncolors = ['r', 'g', 'b', 'orange']\n\n# plot diabetes results\nplt.figure(figsize=(12, 6))\nax1 = plt.subplot(121)\nfor j in xval:\n    ax1.barh(j, mses_diabetes[j], xerr=stds_diabetes[j],\n             color=colors[j], alpha=0.6, align='center')\n\nax1.set_title('Imputation Techniques with Diabetes Data')\nax1.set_xlim(left=np.min(mses_diabetes) * 0.9,\n             right=np.max(mses_diabetes) * 1.1)\nax1.set_yticks(xval)\nax1.set_xlabel('MSE')\nax1.invert_yaxis()\nax1.set_yticklabels(x_labels)\n\n# plot boston results\nax2 = plt.subplot(122)\nfor j in xval:\n    ax2.barh(j, mses_boston[j], xerr=stds_boston[j],\n             color=colors[j], alpha=0.6, align='center')\n\nax2.set_title('Imputation Techniques with Boston Data')\nax2.set_yticks(xval)\nax2.set_xlabel('MSE')\nax2.invert_yaxis()\nax2.set_yticklabels([''] * n_bars)\n\nplt.show()"
       ]
     }
   ],

dev/_downloads/plot_iterative_imputer_variants_comparison.py

@@ -23,6 +23,8 @@
 import numpy as np
 import matplotlib.pyplot as plt
 
+# To use the experimental IterativeImputer, we need to explicitly ask for it:
+from sklearn.experimental import enable_iterative_imputer  # noqa
 from sklearn.datasets import load_diabetes
 from sklearn.datasets import load_boston
 from sklearn.ensemble import RandomForestRegressor