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()"
       ]
     }
   ],

dev/_downloads/02fe21a1f5d14bd1ebbe34aa905d9bf6/plot_multilabel.zip

@@ -29,7 +29,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom sklearn.cluster import HDBSCAN\nfrom sklearn.datasets import load_digits\nfrom sklearn.metrics import v_measure_score\n\nX, true_labels = load_digits(return_X_y=True)\nprint(f\"number of digits: {len(np.unique(true_labels))}\")\n\nhdbscan = HDBSCAN(min_cluster_size=15).fit(X)\nnon_noisy_labels = hdbscan.labels_[hdbscan.labels_ != -1]\nprint(f\"number of clusters found: {len(np.unique(non_noisy_labels))}\")\n\nprint(v_measure_score(true_labels[hdbscan.labels_ != -1], non_noisy_labels))"
+        "import numpy as np\n\nfrom sklearn.cluster import HDBSCAN\nfrom sklearn.datasets import load_digits\nfrom sklearn.metrics import v_measure_score\n\nX, true_labels = load_digits(return_X_y=True)\nprint(f\"number of digits: {len(np.unique(true_labels))}\")\n\nhdbscan = HDBSCAN(min_cluster_size=15).fit(X)\nnon_noisy_labels = hdbscan.labels_[hdbscan.labels_ != -1]\nprint(f\"number of clusters found: {len(np.unique(non_noisy_labels))}\")\n\nprint(v_measure_score(true_labels[hdbscan.labels_ != -1], non_noisy_labels))"
       ]
     },
     {
@@ -47,7 +47,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom sklearn.preprocessing import TargetEncoder\n\nX = np.array([[\"cat\"] * 30 + [\"dog\"] * 20 + [\"snake\"] * 38], dtype=object).T\ny = [90.3] * 30 + [20.4] * 20 + [21.2] * 38\n\nenc = TargetEncoder(random_state=0)\nX_trans = enc.fit_transform(X, y)\n\nenc.encodings_"
+        "import numpy as np\n\nfrom sklearn.preprocessing import TargetEncoder\n\nX = np.array([[\"cat\"] * 30 + [\"dog\"] * 20 + [\"snake\"] * 38], dtype=object).T\ny = [90.3] * 30 + [20.4] * 20 + [21.2] * 38\n\nenc = TargetEncoder(random_state=0)\nX_trans = enc.fit_transform(X, y)\n\nenc.encodings_"
       ]
     },
     {
@@ -65,7 +65,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom sklearn.tree import DecisionTreeClassifier\n\nX = np.array([0, 1, 6, np.nan]).reshape(-1, 1)\ny = [0, 0, 1, 1]\n\ntree = DecisionTreeClassifier(random_state=0).fit(X, y)\ntree.predict(X)"
+        "import numpy as np\n\nfrom sklearn.tree import DecisionTreeClassifier\n\nX = np.array([0, 1, 6, np.nan]).reshape(-1, 1)\ny = [0, 0, 1, 1]\n\ntree = DecisionTreeClassifier(random_state=0).fit(X, y)\ntree.predict(X)"
       ]
     },
     {
@@ -101,7 +101,7 @@
       },
       "outputs": [],
       "source": [
-        "import numpy as np\nfrom sklearn.model_selection import cross_val_score\nfrom sklearn.datasets import make_low_rank_matrix\nfrom sklearn.ensemble import HistGradientBoostingRegressor\n\nn_samples, n_features = 500, 10\nrng = np.random.RandomState(0)\nX = make_low_rank_matrix(n_samples, n_features, random_state=rng)\ncoef = rng.uniform(low=-10, high=20, size=n_features)\ny = rng.gamma(shape=2, scale=np.exp(X @ coef) / 2)\ngbdt = HistGradientBoostingRegressor(loss=\"gamma\")\ncross_val_score(gbdt, X, y).mean()"
+        "import numpy as np\n\nfrom sklearn.datasets import make_low_rank_matrix\nfrom sklearn.ensemble import HistGradientBoostingRegressor\nfrom sklearn.model_selection import cross_val_score\n\nn_samples, n_features = 500, 10\nrng = np.random.RandomState(0)\nX = make_low_rank_matrix(n_samples, n_features, random_state=rng)\ncoef = rng.uniform(low=-10, high=20, size=n_features)\ny = rng.gamma(shape=2, scale=np.exp(X @ coef) / 2)\ngbdt = HistGradientBoostingRegressor(loss=\"gamma\")\ncross_val_score(gbdt, X, y).mean()"
       ]
     },
     {
@@ -119,7 +119,7 @@
       },
       "outputs": [],
       "source": [
-        "from sklearn.preprocessing import OrdinalEncoder\nimport numpy as np\n\nX = np.array(\n    [[\"dog\"] * 5 + [\"cat\"] * 20 + [\"rabbit\"] * 10 + [\"snake\"] * 3], dtype=object\n).T\nenc = OrdinalEncoder(min_frequency=6).fit(X)\nenc.infrequent_categories_"
+        "import numpy as np\n\nfrom sklearn.preprocessing import OrdinalEncoder\n\nX = np.array(\n    [[\"dog\"] * 5 + [\"cat\"] * 20 + [\"rabbit\"] * 10 + [\"snake\"] * 3], dtype=object\n).T\nenc = OrdinalEncoder(min_frequency=6).fit(X)\nenc.infrequent_categories_"
       ]
     }
   ],

dev/_downloads/0358b1921962fd7c6f5a94c5abc91476/plot_hashing_vs_dict_vectorizer.zip

@@ -1,4 +1,4 @@
-# ruff: noqa
+# ruff: noqa: CPY001, E501
 """
 =======================================
 Release Highlights for scikit-learn 1.2
@@ -31,9 +31,10 @@
 # (some examples) <https://youtu.be/5bCg8VfX2x8>`__.
 
 import numpy as np
-from sklearn.datasets import load_iris
-from sklearn.preprocessing import StandardScaler, KBinsDiscretizer
+
 from sklearn.compose import ColumnTransformer
+from sklearn.datasets import load_iris
+from sklearn.preprocessing import KBinsDiscretizer, StandardScaler
 
 X, y = load_iris(as_frame=True, return_X_y=True)
 sepal_cols = ["sepal length (cm)", "sepal width (cm)"]
@@ -78,6 +79,7 @@
 # :class:`~metrics.PredictionErrorDisplay` provides a way to analyze regression
 # models in a qualitative manner.
 import matplotlib.pyplot as plt
+
 from sklearn.metrics import PredictionErrorDisplay
 
 fig, axs = plt.subplots(nrows=1, ncols=2, figsize=(12, 5))
@@ -109,8 +111,8 @@
 X = X.select_dtypes(["number", "category"]).drop(columns=["body"])
 
 # %%
-from sklearn.preprocessing import OrdinalEncoder
 from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import OrdinalEncoder
 
 categorical_features = ["pclass", "sex", "embarked"]
 model = make_pipeline(

dev/_downloads/038d1885eb5f5ea53aca42da3031fe38/plot_document_clustering.zip

@@ -10,7 +10,7 @@
 the `set_output` method or globally by setting `set_config(transform_output="pandas")`.
 For details, see
 `SLEP018 <https://scikit-learn-enhancement-proposals.readthedocs.io/en/latest/slep018/proposal.html>`__.
-"""  # noqa
+"""  # noqa: CPY001
 
 # %%
 # First, we load the iris dataset as a DataFrame to demonstrate the `set_output` API.

dev/_downloads/03c018a16384c69f3a89e473650d57ee/plot_svm_margin.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\nfrom scipy.stats import randint\n\nfrom sklearn import datasets\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.experimental import enable_halving_search_cv  # noqa\nfrom sklearn.model_selection import HalvingRandomSearchCV"
+        "# 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\nfrom scipy.stats import randint\n\nfrom sklearn import datasets\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.experimental import enable_halving_search_cv  # noqa: F401\nfrom sklearn.model_selection import HalvingRandomSearchCV"
       ]
     },
     {