Pushing the docs to dev/ for branch: main, commit b98dc797c480b1b9495f918e201d45ee07f29feb

Author: sklearn-ci

dev/_downloads/02192f99342d6d1323161978b6c80bfc/plot_ols_ridge.zip

@@ -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\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\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()"
       ]
     }
   ],