Pushing the docs to dev/ for branch: master, commit b8d1226d69bc4930d73c83394d2fee22dfe7ce2c

Author: sklearn-ci

dev/_downloads/auto_examples_jupyter.zip

@@ -0,0 +1,54 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "outputs": [],
+      "source": [
+        "%matplotlib inline"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "\n# Imputing missing values with variants of IterativeImputer\n\n\nThe :class:`sklearn.impute.IterativeImputer` class is very flexible - it can be\nused with a variety of estimators to do round-robin regression, treating every\nvariable as an output in turn.\n\nIn this example we compare some estimators for the purpose of missing feature\nimputation with :class:`sklearn.imputeIterativeImputer`::\n\n    :class:`~sklearn.linear_model.BayesianRidge`: regularized linear regression\n    :class:`~sklearn.tree.DecisionTreeRegressor`: non-linear regression\n    :class:`~sklearn.ensemble.ExtraTreesRegressor`: similar to missForest in R\n    :class:`~sklearn.neighbors.KNeighborsRegressor`: comparable to other KNN\n    imputation approaches\n\nOf particular interest is the ability of\n:class:`sklearn.impute.IterativeImputer` to mimic the behavior of missForest, a\npopular imputation package for R. In this example, we have chosen to use\n:class:`sklearn.ensemble.ExtraTreesRegressor` instead of\n:class:`sklearn.ensemble.RandomForestRegressor` (as in missForest) due to its\nincreased speed.\n\nNote that :class:`sklearn.neighbors.KNeighborsRegressor` is different from KNN\nimputation, which learns from samples with missing values by using a distance\nmetric that accounts for missing values, rather than imputing them.\n\nThe goal is to compare different estimators to see which one is best for the\n:class:`sklearn.impute.IterativeImputer` when using a\n:class:`sklearn.linear_model.BayesianRidge` estimator on the California housing\ndataset with a single value randomly removed from each row.\n\nFor this particular pattern of missing values we see that\n:class:`sklearn.ensemble.ExtraTreesRegressor` and\n:class:`sklearn.linear_model.BayesianRidge` give the best results.\n\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "collapsed": false
+      },
+      "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)\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, n_jobs=-1, random_state=0),\n    KNeighborsRegressor(n_neighbors=15)\n]\nscore_iterative_imputer = pd.DataFrame()\nfor estimator in estimators:\n    estimator = make_pipeline(\n        IterativeImputer(random_state=0, estimator=estimator),\n        br_estimator\n    )\n    score_iterative_imputer[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()"
+      ]
+    }
+  ],
+  "metadata": {
+    "kernelspec": {
+      "display_name": "Python 3",
+      "language": "python",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.6.8"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

dev/_downloads/auto_examples_python.zip

@@ -0,0 +1,126 @@
+"""
+=========================================================
+Imputing missing values with variants of IterativeImputer
+=========================================================
+
+The :class:`sklearn.impute.IterativeImputer` class is very flexible - it can be
+used with a variety of estimators to do round-robin regression, treating every
+variable as an output in turn.
+
+In this example we compare some estimators for the purpose of missing feature
+imputation with :class:`sklearn.imputeIterativeImputer`::
+
+    :class:`~sklearn.linear_model.BayesianRidge`: regularized linear regression
+    :class:`~sklearn.tree.DecisionTreeRegressor`: non-linear regression
+    :class:`~sklearn.ensemble.ExtraTreesRegressor`: similar to missForest in R
+    :class:`~sklearn.neighbors.KNeighborsRegressor`: comparable to other KNN
+    imputation approaches
+
+Of particular interest is the ability of
+:class:`sklearn.impute.IterativeImputer` to mimic the behavior of missForest, a
+popular imputation package for R. In this example, we have chosen to use
+:class:`sklearn.ensemble.ExtraTreesRegressor` instead of
+:class:`sklearn.ensemble.RandomForestRegressor` (as in missForest) due to its
+increased speed.
+
+Note that :class:`sklearn.neighbors.KNeighborsRegressor` is different from KNN
+imputation, which learns from samples with missing values by using a distance
+metric that accounts for missing values, rather than imputing them.
+
+The goal is to compare different estimators to see which one is best for the
+:class:`sklearn.impute.IterativeImputer` when using a
+:class:`sklearn.linear_model.BayesianRidge` estimator on the California housing
+dataset with a single value randomly removed from each row.
+
+For this particular pattern of missing values we see that
+:class:`sklearn.ensemble.ExtraTreesRegressor` and
+:class:`sklearn.linear_model.BayesianRidge` give the best results.
+"""
+print(__doc__)
+
+import numpy as np
+import matplotlib.pyplot as plt
+import pandas as pd
+
+from sklearn.datasets import fetch_california_housing
+from sklearn.impute import SimpleImputer
+from sklearn.impute import IterativeImputer
+from sklearn.linear_model import BayesianRidge
+from sklearn.tree import DecisionTreeRegressor
+from sklearn.ensemble import ExtraTreesRegressor
+from sklearn.neighbors import KNeighborsRegressor
+from sklearn.pipeline import make_pipeline
+from sklearn.model_selection import cross_val_score
+
+N_SPLITS = 5
+
+rng = np.random.RandomState(0)
+
+X_full, y_full = fetch_california_housing(return_X_y=True)
+n_samples, n_features = X_full.shape
+
+# Estimate the score on the entire dataset, with no missing values
+br_estimator = BayesianRidge()
+score_full_data = pd.DataFrame(
+    cross_val_score(
+        br_estimator, X_full, y_full, scoring='neg_mean_squared_error',
+        cv=N_SPLITS
+    ),
+    columns=['Full Data']
+)
+
+# Add a single missing value to each row
+X_missing = X_full.copy()
+y_missing = y_full
+missing_samples = np.arange(n_samples)
+missing_features = rng.choice(n_features, n_samples, replace=True)
+X_missing[missing_samples, missing_features] = np.nan
+
+# Estimate the score after imputation (mean and median strategies)
+score_simple_imputer = pd.DataFrame()
+for strategy in ('mean', 'median'):
+    estimator = make_pipeline(
+        SimpleImputer(missing_values=np.nan, strategy=strategy),
+        br_estimator
+    )
+    score_simple_imputer[strategy] = cross_val_score(
+        estimator, X_missing, y_missing, scoring='neg_mean_squared_error',
+        cv=N_SPLITS
+    )
+
+# Estimate the score after iterative imputation of the missing values
+# with different estimators
+estimators = [
+    BayesianRidge(),
+    DecisionTreeRegressor(max_features='sqrt', random_state=0),
+    ExtraTreesRegressor(n_estimators=10, n_jobs=-1, random_state=0),
+    KNeighborsRegressor(n_neighbors=15)
+]
+score_iterative_imputer = pd.DataFrame()
+for estimator in estimators:
+    estimator = make_pipeline(
+        IterativeImputer(random_state=0, estimator=estimator),
+        br_estimator
+    )
+    score_iterative_imputer[estimator.__class__.__name__] = \
+        cross_val_score(
+            estimator, X_missing, y_missing, scoring='neg_mean_squared_error',
+            cv=N_SPLITS
+        )
+
+scores = pd.concat(
+    [score_full_data, score_simple_imputer, score_iterative_imputer],
+    keys=['Original', 'SimpleImputer', 'IterativeImputer'], axis=1
+)
+
+# plot boston results
+fig, ax = plt.subplots(figsize=(13, 6))
+means = -scores.mean()
+errors = scores.std()
+means.plot.barh(xerr=errors, ax=ax)
+ax.set_title('California Housing Regression with Different Imputation Methods')
+ax.set_xlabel('MSE (smaller is better)')
+ax.set_yticks(np.arange(means.shape[0]))
+ax.set_yticklabels([" w/ ".join(label) for label in means.index.get_values()])
+plt.tight_layout(pad=1)
+plt.show()