Pushing the docs to dev/ for branch: main, commit 9f8668182ab1492923057aca05ce6f2de38af02d

Author: sklearn-ci

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -4,7 +4,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "\n# Imputing missing values with variants of IterativeImputer\n\n.. currentmodule:: sklearn\n\nThe :class:`~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:`~impute.IterativeImputer`:\n\n* :class:`~linear_model.BayesianRidge`: regularized linear regression\n* :class:`~ensemble.RandomForestRegressor`: Forests of randomized trees regression\n* :func:`~pipeline.make_pipeline` (:class:`~kernel_approximation.Nystroem`,\n  :class:`~linear_model.Ridge`): a pipeline with the expansion of a degree 2\n  polynomial kernel and regularized linear regression\n* :class:`~neighbors.KNeighborsRegressor`: comparable to other KNN\n  imputation approaches\n\nOf particular interest is the ability of\n:class:`~impute.IterativeImputer` to mimic the behavior of missForest, a\npopular imputation package for R.\n\nNote that :class:`~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:`~impute.IterativeImputer` when using a\n:class:`~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:`~linear_model.BayesianRidge` and\n:class:`~ensemble.RandomForestRegressor` give the best results.\n\nIt should be noted that some estimators such as\n:class:`~ensemble.HistGradientBoostingRegressor` can natively deal with\nmissing features and are often recommended over building pipelines with\ncomplex and costly missing values imputation strategies.\n"
+        "\n# Imputing missing values with variants of IterativeImputer\n\n.. currentmodule:: sklearn\n\nThe :class:`~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:`~impute.IterativeImputer`:\n\n* :class:`~linear_model.BayesianRidge`: regularized linear regression\n* :class:`~ensemble.RandomForestRegressor`: forests of randomized trees regression\n* :func:`~pipeline.make_pipeline` (:class:`~kernel_approximation.Nystroem`,\n  :class:`~linear_model.Ridge`): a pipeline with the expansion of a degree 2\n  polynomial kernel and regularized linear regression\n* :class:`~neighbors.KNeighborsRegressor`: comparable to other KNN\n  imputation approaches\n\nOf particular interest is the ability of\n:class:`~impute.IterativeImputer` to mimic the behavior of missForest, a\npopular imputation package for R.\n\nNote that :class:`~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:`~impute.IterativeImputer` when using a\n:class:`~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:`~linear_model.BayesianRidge` and\n:class:`~ensemble.RandomForestRegressor` give the best results.\n\nIt should be noted that some estimators such as\n:class:`~ensemble.HistGradientBoostingRegressor` can natively deal with\nmissing features and are often recommended over building pipelines with\ncomplex and costly missing values imputation strategies.\n"
       ]
     },
     {
@@ -15,7 +15,7 @@
       },
       "outputs": [],
       "source": [
-        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.ensemble import RandomForestRegressor\n\n# To use this experimental feature, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa: F401\nfrom sklearn.impute import IterativeImputer, SimpleImputer\nfrom sklearn.kernel_approximation import Nystroem\nfrom sklearn.linear_model import BayesianRidge, Ridge\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.pipeline import make_pipeline\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\", 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), br_estimator\n    )\n    score_simple_imputer[strategy] = cross_val_score(\n        estimator, X_missing, y_missing, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\n# Estimate the score after iterative imputation of the missing values\n# with different estimators\nestimators = [\n    BayesianRidge(),\n    RandomForestRegressor(\n        # We tuned the hyperparameters of the RandomForestRegressor to get a good\n        # enough predictive performance for a restricted execution time.\n        n_estimators=4,\n        max_depth=10,\n        bootstrap=True,\n        max_samples=0.5,\n        n_jobs=2,\n        random_state=0,\n    ),\n    make_pipeline(\n        Nystroem(kernel=\"polynomial\", degree=2, random_state=0), Ridge(alpha=1e3)\n    ),\n    KNeighborsRegressor(n_neighbors=15),\n]\nscore_iterative_imputer = pd.DataFrame()\n# iterative imputer is sensible to the tolerance and\n# dependent on the estimator used internally.\n# we tuned the tolerance to keep this example run with limited computational\n# resources while not changing the results too much compared to keeping the\n# stricter default value for the tolerance parameter.\ntolerances = (1e-3, 1e-1, 1e-1, 1e-2)\nfor impute_estimator, tol in zip(estimators, tolerances):\n    estimator = make_pipeline(\n        IterativeImputer(\n            random_state=0, estimator=impute_estimator, max_iter=25, tol=tol\n        ),\n        br_estimator,\n    )\n    score_iterative_imputer[impute_estimator.__class__.__name__] = cross_val_score(\n        estimator, X_missing, y_missing, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\nscores = pd.concat(\n    [score_full_data, score_simple_imputer, score_iterative_imputer],\n    keys=[\"Original\", \"SimpleImputer\", \"IterativeImputer\"],\n    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()"
+        "# Authors: The scikit-learn developers\n# SPDX-License-Identifier: BSD-3-Clause\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn.datasets import fetch_california_housing\nfrom sklearn.ensemble import RandomForestRegressor\n\n# To use this experimental feature, we need to explicitly ask for it:\nfrom sklearn.experimental import enable_iterative_imputer  # noqa: F401\nfrom sklearn.impute import IterativeImputer, SimpleImputer\nfrom sklearn.kernel_approximation import Nystroem\nfrom sklearn.linear_model import BayesianRidge, Ridge\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.neighbors import KNeighborsRegressor\nfrom sklearn.pipeline import make_pipeline\nfrom sklearn.preprocessing import RobustScaler\n\nN_SPLITS = 5\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\ndef compute_score_for(X, y, imputer=None):\n    # We scale data before imputation and training a target estimator,\n    # because our target estimator and some of the imputers assume\n    # that the features have similar scales.\n    if imputer is None:\n        estimator = make_pipeline(RobustScaler(), BayesianRidge())\n    else:\n        estimator = make_pipeline(RobustScaler(), imputer, BayesianRidge())\n    return cross_val_score(\n        estimator, X, y, scoring=\"neg_mean_squared_error\", cv=N_SPLITS\n    )\n\n\n# Estimate the score on the entire dataset, with no missing values\nscore_full_data = pd.DataFrame(\n    compute_score_for(X_full, y_full),\n    columns=[\"Full Data\"],\n)\n\n# Add a single missing value to each row\nrng = np.random.RandomState(0)\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    score_simple_imputer[strategy] = compute_score_for(\n        X_missing, y_missing, SimpleImputer(strategy=strategy)\n    )\n\n# Estimate the score after iterative imputation of the missing values\n# with different estimators\nnamed_estimators = [\n    (\"Bayesian Ridge\", BayesianRidge()),\n    (\n        \"Random Forest\",\n        RandomForestRegressor(\n            # We tuned the hyperparameters of the RandomForestRegressor to get a good\n            # enough predictive performance for a restricted execution time.\n            n_estimators=5,\n            max_depth=10,\n            bootstrap=True,\n            max_samples=0.5,\n            n_jobs=2,\n            random_state=0,\n        ),\n    ),\n    (\n        \"Nystroem + Ridge\",\n        make_pipeline(\n            Nystroem(kernel=\"polynomial\", degree=2, random_state=0), Ridge(alpha=1e4)\n        ),\n    ),\n    (\n        \"k-NN\",\n        KNeighborsRegressor(n_neighbors=10),\n    ),\n]\nscore_iterative_imputer = pd.DataFrame()\n# Iterative imputer is sensitive to the tolerance and\n# dependent on the estimator used internally.\n# We tuned the tolerance to keep this example run with limited computational\n# resources while not changing the results too much compared to keeping the\n# stricter default value for the tolerance parameter.\ntolerances = (1e-3, 1e-1, 1e-1, 1e-2)\nfor (name, impute_estimator), tol in zip(named_estimators, tolerances):\n    score_iterative_imputer[name] = compute_score_for(\n        X_missing,\n        y_missing,\n        IterativeImputer(\n            random_state=0, estimator=impute_estimator, max_iter=40, tol=tol\n        ),\n    )\n\nscores = pd.concat(\n    [score_full_data, score_simple_imputer, score_iterative_imputer],\n    keys=[\"Original\", \"SimpleImputer\", \"IterativeImputer\"],\n    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/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -13,7 +13,7 @@
 imputation with :class:`~impute.IterativeImputer`:
 
 * :class:`~linear_model.BayesianRidge`: regularized linear regression
-* :class:`~ensemble.RandomForestRegressor`: Forests of randomized trees regression
+* :class:`~ensemble.RandomForestRegressor`: forests of randomized trees regression
 * :func:`~pipeline.make_pipeline` (:class:`~kernel_approximation.Nystroem`,
   :class:`~linear_model.Ridge`): a pipeline with the expansion of a degree 2
   polynomial kernel and regularized linear regression
@@ -62,28 +62,39 @@
 from sklearn.model_selection import cross_val_score
 from sklearn.neighbors import KNeighborsRegressor
 from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import RobustScaler
 
 N_SPLITS = 5
 
-rng = np.random.RandomState(0)
-
 X_full, y_full = fetch_california_housing(return_X_y=True)
 # ~2k samples is enough for the purpose of the example.
 # Remove the following two lines for a slower run with different error bars.
 X_full = X_full[::10]
 y_full = y_full[::10]
 n_samples, n_features = X_full.shape
 
+
+def compute_score_for(X, y, imputer=None):
+    # We scale data before imputation and training a target estimator,
+    # because our target estimator and some of the imputers assume
+    # that the features have similar scales.
+    if imputer is None:
+        estimator = make_pipeline(RobustScaler(), BayesianRidge())
+    else:
+        estimator = make_pipeline(RobustScaler(), imputer, BayesianRidge())
+    return cross_val_score(
+        estimator, X, y, scoring="neg_mean_squared_error", cv=N_SPLITS
+    )
+
+
 # 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
-    ),
+    compute_score_for(X_full, y_full),
     columns=["Full Data"],
 )
 
 # Add a single missing value to each row
+rng = np.random.RandomState(0)
 X_missing = X_full.copy()
 y_missing = y_full
 missing_samples = np.arange(n_samples)
@@ -93,48 +104,52 @@
 # 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
+    score_simple_imputer[strategy] = compute_score_for(
+        X_missing, y_missing, SimpleImputer(strategy=strategy)
     )
 
 # Estimate the score after iterative imputation of the missing values
 # with different estimators
-estimators = [
-    BayesianRidge(),
-    RandomForestRegressor(
-        # We tuned the hyperparameters of the RandomForestRegressor to get a good
-        # enough predictive performance for a restricted execution time.
-        n_estimators=4,
-        max_depth=10,
-        bootstrap=True,
-        max_samples=0.5,
-        n_jobs=2,
-        random_state=0,
+named_estimators = [
+    ("Bayesian Ridge", BayesianRidge()),
+    (
+        "Random Forest",
+        RandomForestRegressor(
+            # We tuned the hyperparameters of the RandomForestRegressor to get a good
+            # enough predictive performance for a restricted execution time.
+            n_estimators=5,
+            max_depth=10,
+            bootstrap=True,
+            max_samples=0.5,
+            n_jobs=2,
+            random_state=0,
+        ),
     ),
-    make_pipeline(
-        Nystroem(kernel="polynomial", degree=2, random_state=0), Ridge(alpha=1e3)
+    (
+        "Nystroem + Ridge",
+        make_pipeline(
+            Nystroem(kernel="polynomial", degree=2, random_state=0), Ridge(alpha=1e4)
+        ),
+    ),
+    (
+        "k-NN",
+        KNeighborsRegressor(n_neighbors=10),
     ),
-    KNeighborsRegressor(n_neighbors=15),
 ]
 score_iterative_imputer = pd.DataFrame()
-# iterative imputer is sensible to the tolerance and
+# Iterative imputer is sensitive to the tolerance and
 # dependent on the estimator used internally.
-# we tuned the tolerance to keep this example run with limited computational
+# We tuned the tolerance to keep this example run with limited computational
 # resources while not changing the results too much compared to keeping the
 # stricter default value for the tolerance parameter.
 tolerances = (1e-3, 1e-1, 1e-1, 1e-2)
-for impute_estimator, tol in zip(estimators, tolerances):
-    estimator = make_pipeline(
+for (name, impute_estimator), tol in zip(named_estimators, tolerances):
+    score_iterative_imputer[name] = compute_score_for(
+        X_missing,
+        y_missing,
         IterativeImputer(
-            random_state=0, estimator=impute_estimator, max_iter=25, tol=tol
+            random_state=0, estimator=impute_estimator, max_iter=40, tol=tol
         ),
-        br_estimator,
-    )
-    score_iterative_imputer[impute_estimator.__class__.__name__] = cross_val_score(
-        estimator, X_missing, y_missing, scoring="neg_mean_squared_error", cv=N_SPLITS
     )
 
 scores = pd.concat(