scikit-learn · adrinjalali · Apr 28, 2025 · Apr 18, 2025 · Apr 18, 2025 · Apr 18, 2025
diff --git a/benchmarks/bench_plot_fastkmeans.py b/benchmarks/bench_plot_fastkmeans.py
@@ -97,8 +97,8 @@ def compute_bench_2(chunks):
 
 
 if __name__ == "__main__":
-    from mpl_toolkits.mplot3d import axes3d  # noqa register the 3d projection
     import matplotlib.pyplot as plt
+    from mpl_toolkits.mplot3d import axes3d  # register the 3d projection  # noqa: F401
 
     samples_range = np.linspace(50, 150, 5).astype(int)
     features_range = np.linspace(150, 50000, 5).astype(int)

diff --git a/benchmarks/bench_plot_lasso_path.py b/benchmarks/bench_plot_lasso_path.py
@@ -80,8 +80,8 @@ def compute_bench(samples_range, features_range):
 
 
 if __name__ == "__main__":
-    from mpl_toolkits.mplot3d import axes3d  # noqa register the 3d projection
     import matplotlib.pyplot as plt
+    from mpl_toolkits.mplot3d import axes3d  # register the 3d projection # noqa: F401
 
     samples_range = np.linspace(10, 2000, 5).astype(int)
     features_range = np.linspace(10, 2000, 5).astype(int)

diff --git a/benchmarks/bench_plot_svd.py b/benchmarks/bench_plot_svd.py
@@ -54,8 +54,8 @@ def compute_bench(samples_range, features_range, n_iter=3, rank=50):
 
 
 if __name__ == "__main__":
-    from mpl_toolkits.mplot3d import axes3d  # noqa register the 3d projection
     import matplotlib.pyplot as plt
+    from mpl_toolkits.mplot3d import axes3d  # register the 3d projection  # noqa: F401
 
     samples_range = np.linspace(2, 1000, 4).astype(int)
     features_range = np.linspace(2, 1000, 4).astype(int)

diff --git a/doc/api_reference.py b/doc/api_reference.py
@@ -1349,4 +1349,4 @@ def _get_submodule(module_name, submodule_name):
 }
 """
 
-DEPRECATED_API_REFERENCE = {}  # type: ignore
+DEPRECATED_API_REFERENCE = {}  # type: ignore[var-annotated]
diff --git a/doc/conf.py b/doc/conf.py
@@ -769,8 +769,10 @@ def reset_sklearn_config(gallery_conf, fname):
 
 # enable experimental module so that experimental estimators can be
 # discovered properly by sphinx
-from sklearn.experimental import enable_iterative_imputer  # noqa
-from sklearn.experimental import enable_halving_search_cv  # noqa
+from sklearn.experimental import (  # noqa: F401
+    enable_halving_search_cv,
+    enable_iterative_imputer,
+)
 
 
 def make_carousel_thumbs(app, exception):

diff --git a/doc/conftest.py b/doc/conftest.py
@@ -41,7 +41,7 @@ def setup_working_with_text_data():
 
 def setup_loading_other_datasets():
     try:
-        import pandas  # noqa
+        import pandas  # noqa: F401
     except ImportError:
         raise SkipTest("Skipping loading_other_datasets.rst, pandas not installed")
 
@@ -56,43 +56,43 @@ def setup_loading_other_datasets():
 
 def setup_compose():
     try:
-        import pandas  # noqa
+        import pandas  # noqa: F401
     except ImportError:
         raise SkipTest("Skipping compose.rst, pandas not installed")
 
 
 def setup_impute():
     try:
-        import pandas  # noqa
+        import pandas  # noqa: F401
     except ImportError:
         raise SkipTest("Skipping impute.rst, pandas not installed")
 
 
 def setup_grid_search():
     try:
-        import pandas  # noqa
+        import pandas  # noqa: F401
     except ImportError:
         raise SkipTest("Skipping grid_search.rst, pandas not installed")
 
 
 def setup_preprocessing():
     try:
-        import pandas  # noqa
+        import pandas  # noqa: F401
     except ImportError:
         raise SkipTest("Skipping preprocessing.rst, pandas not installed")
 
 
 def skip_if_matplotlib_not_installed(fname):
     try:
-        import matplotlib  # noqa
+        import matplotlib  # noqa: F401
     except ImportError:
         basename = os.path.basename(fname)
         raise SkipTest(f"Skipping doctests for {basename}, matplotlib not installed")
 
 
 def skip_if_cupy_not_installed(fname):
     try:
-        import cupy  # noqa
+        import cupy  # noqa: F401
     except ImportError:
         basename = os.path.basename(fname)
         raise SkipTest(f"Skipping doctests for {basename}, cupy not installed")

diff --git a/examples/ensemble/plot_gradient_boosting_quantile.py b/examples/ensemble/plot_gradient_boosting_quantile.py
@@ -241,11 +241,12 @@ def coverage_fraction(y, y_low, y_high):
 # cross-validation on the pinball loss with alpha=0.05:
 
 # %%
-from sklearn.experimental import enable_halving_search_cv  # noqa
-from sklearn.model_selection import HalvingRandomSearchCV
-from sklearn.metrics import make_scorer
 from pprint import pprint
 
+from sklearn.experimental import enable_halving_search_cv  # noqa: F401
+from sklearn.metrics import make_scorer
+from sklearn.model_selection import HalvingRandomSearchCV
+
 param_grid = dict(
     learning_rate=[0.05, 0.1, 0.2],
     max_depth=[2, 5, 10],

diff --git a/examples/impute/plot_iterative_imputer_variants_comparison.py b/examples/impute/plot_iterative_imputer_variants_comparison.py
@@ -55,7 +55,7 @@
 from sklearn.ensemble import RandomForestRegressor
 
 # To use this experimental feature, we need to explicitly ask for it:
-from sklearn.experimental import enable_iterative_imputer  # noqa
+from sklearn.experimental import enable_iterative_imputer  # noqa: F401
 from sklearn.impute import IterativeImputer, SimpleImputer
 from sklearn.kernel_approximation import Nystroem
 from sklearn.linear_model import BayesianRidge, Ridge

diff --git a/examples/impute/plot_missing_values.py b/examples/impute/plot_missing_values.py
@@ -92,7 +92,7 @@ def add_missing_values(X_full, y_full):
 from sklearn.ensemble import RandomForestRegressor
 
 # To use the experimental IterativeImputer, we need to explicitly ask for it:
-from sklearn.experimental import enable_iterative_imputer  # noqa
+from sklearn.experimental import enable_iterative_imputer  # noqa: F401
 from sklearn.impute import IterativeImputer, KNNImputer, SimpleImputer
 from sklearn.model_selection import cross_val_score
 from sklearn.pipeline import make_pipeline

diff --git a/examples/miscellaneous/plot_set_output.py b/examples/miscellaneous/plot_set_output.py
@@ -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.

diff --git a/examples/model_selection/plot_successive_halving_heatmap.py b/examples/model_selection/plot_successive_halving_heatmap.py
@@ -18,7 +18,7 @@
 import pandas as pd
 
 from sklearn import datasets
-from sklearn.experimental import enable_halving_search_cv  # noqa
+from sklearn.experimental import enable_halving_search_cv  # noqa: F401
 from sklearn.model_selection import GridSearchCV, HalvingGridSearchCV
 from sklearn.svm import SVC
 

diff --git a/examples/model_selection/plot_successive_halving_iterations.py b/examples/model_selection/plot_successive_halving_iterations.py
@@ -20,7 +20,7 @@
 
 from sklearn import datasets
 from sklearn.ensemble import RandomForestClassifier
-from sklearn.experimental import enable_halving_search_cv  # noqa
+from sklearn.experimental import enable_halving_search_cv  # noqa: F401
 from sklearn.model_selection import HalvingRandomSearchCV
 
 # %%

diff --git a/examples/release_highlights/plot_release_highlights_0_23_0.py b/examples/release_highlights/plot_release_highlights_0_23_0.py
@@ -1,4 +1,4 @@
-# ruff: noqa
+# ruff: noqa: CPY001
 """
 ========================================
 Release Highlights for scikit-learn 0.23
@@ -35,9 +35,10 @@
 # 'poisson' loss as well.
 
 import numpy as np
-from sklearn.model_selection import train_test_split
-from sklearn.linear_model import PoissonRegressor
+
 from sklearn.ensemble import HistGradientBoostingRegressor
+from sklearn.linear_model import PoissonRegressor
+from sklearn.model_selection import train_test_split
 
 n_samples, n_features = 1000, 20
 rng = np.random.RandomState(0)
@@ -63,11 +64,11 @@
 # this feature.
 
 from sklearn import set_config
-from sklearn.pipeline import make_pipeline
-from sklearn.preprocessing import OneHotEncoder, StandardScaler
-from sklearn.impute import SimpleImputer
 from sklearn.compose import make_column_transformer
+from sklearn.impute import SimpleImputer
 from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import OneHotEncoder, StandardScaler
 
 set_config(display="diagram")
 
@@ -94,12 +95,13 @@
 # parallelism instead of relying on joblib, so the `n_jobs` parameter has no
 # effect anymore. For more details on how to control the number of threads,
 # please refer to our :ref:`parallelism` notes.
-import scipy
 import numpy as np
-from sklearn.model_selection import train_test_split
+import scipy
+
 from sklearn.cluster import KMeans
 from sklearn.datasets import make_blobs
 from sklearn.metrics import completeness_score
+from sklearn.model_selection import train_test_split
 
 rng = np.random.RandomState(0)
 X, y = make_blobs(random_state=rng)
@@ -126,11 +128,12 @@
 # example, see :ref:`sphx_glr_auto_examples_ensemble_plot_hgbt_regression.py`.
 import numpy as np
 from matplotlib import pyplot as plt
-from sklearn.model_selection import train_test_split
+
+from sklearn.ensemble import HistGradientBoostingRegressor
 
 # from sklearn.inspection import plot_partial_dependence
 from sklearn.inspection import PartialDependenceDisplay
-from sklearn.ensemble import HistGradientBoostingRegressor
+from sklearn.model_selection import train_test_split
 
 n_samples = 500
 rng = np.random.RandomState(0)
@@ -173,10 +176,11 @@
 # The two linear regressors :class:`~sklearn.linear_model.Lasso` and
 # :class:`~sklearn.linear_model.ElasticNet` now support sample weights.
 
-from sklearn.model_selection import train_test_split
+import numpy as np
+
 from sklearn.datasets import make_regression
 from sklearn.linear_model import Lasso
-import numpy as np
+from sklearn.model_selection import train_test_split
 
 n_samples, n_features = 1000, 20
 rng = np.random.RandomState(0)

diff --git a/examples/release_highlights/plot_release_highlights_0_24_0.py b/examples/release_highlights/plot_release_highlights_0_24_0.py
@@ -1,4 +1,4 @@
-# ruff: noqa
+# ruff: noqa: CPY001, E501
 """
 ========================================
 Release Highlights for scikit-learn 0.24
@@ -51,10 +51,11 @@
 
 import numpy as np
 from scipy.stats import randint
-from sklearn.experimental import enable_halving_search_cv  # noqa
-from sklearn.model_selection import HalvingRandomSearchCV
-from sklearn.ensemble import RandomForestClassifier
+
 from sklearn.datasets import make_classification
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.experimental import enable_halving_search_cv  # noqa: F401
+from sklearn.model_selection import HalvingRandomSearchCV
 
 rng = np.random.RandomState(0)
 
@@ -118,6 +119,7 @@
 # Read more in the :ref:`User guide <self_training>`.
 
 import numpy as np
+
 from sklearn import datasets
 from sklearn.semi_supervised import SelfTrainingClassifier
 from sklearn.svm import SVC
@@ -140,9 +142,9 @@
 # (backward selection), based on a cross-validated score maximization.
 # See the :ref:`User Guide <sequential_feature_selection>`.
 
+from sklearn.datasets import load_iris
 from sklearn.feature_selection import SequentialFeatureSelector
 from sklearn.neighbors import KNeighborsClassifier
-from sklearn.datasets import load_iris
 
 X, y = load_iris(return_X_y=True, as_frame=True)
 feature_names = X.columns
@@ -163,11 +165,11 @@
 # :class:`~sklearn.preprocessing.PolynomialFeatures`.
 
 from sklearn.datasets import fetch_covtype
-from sklearn.pipeline import make_pipeline
-from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import MinMaxScaler
 from sklearn.kernel_approximation import PolynomialCountSketch
 from sklearn.linear_model import LogisticRegression
+from sklearn.model_selection import train_test_split
+from sklearn.pipeline import make_pipeline
+from sklearn.preprocessing import MinMaxScaler
 
 X, y = fetch_covtype(return_X_y=True)
 pipe = make_pipeline(
@@ -194,8 +196,8 @@
 # prediction on a feature for each sample separately, with one line per sample.
 # See the :ref:`User Guide <individual_conditional>`
 
-from sklearn.ensemble import RandomForestRegressor
 from sklearn.datasets import fetch_california_housing
+from sklearn.ensemble import RandomForestRegressor
 
 # from sklearn.inspection import plot_partial_dependence
 from sklearn.inspection import PartialDependenceDisplay
@@ -232,10 +234,11 @@
 # splitting criterion. Setting `criterion="poisson"` might be a good choice
 # if your target is a count or a frequency.
 
-from sklearn.tree import DecisionTreeRegressor
-from sklearn.model_selection import train_test_split
 import numpy as np
 
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeRegressor
+
 n_samples, n_features = 1000, 20
 rng = np.random.RandomState(0)
 X = rng.randn(n_samples, n_features)

diff --git a/examples/release_highlights/plot_release_highlights_1_0_0.py b/examples/release_highlights/plot_release_highlights_1_0_0.py
@@ -1,4 +1,4 @@
-# ruff: noqa
+# ruff: noqa: CPY001
 """
 =======================================
 Release Highlights for scikit-learn 1.0
@@ -89,6 +89,7 @@
 # refer to the :ref:`User Guide <spline_transformer>`.
 
 import numpy as np
+
 from sklearn.preprocessing import SplineTransformer
 
 X = np.arange(5).reshape(5, 1)
@@ -147,9 +148,10 @@
 # is used to check that the column names of the dataframe passed in
 # non-:term:`fit`, such as :term:`predict`, are consistent with features in
 # :term:`fit`:
-from sklearn.preprocessing import StandardScaler
 import pandas as pd
 
+from sklearn.preprocessing import StandardScaler
+
 X = pd.DataFrame([[1, 2, 3], [4, 5, 6]], columns=["a", "b", "c"])
 scalar = StandardScaler().fit(X)
 scalar.feature_names_in_
@@ -162,9 +164,10 @@
 # will be added to all other transformers in future releases. Additionally,
 # :meth:`compose.ColumnTransformer.get_feature_names_out` is available to
 # combine feature names of its transformers:
+import pandas as pd
+
 from sklearn.compose import ColumnTransformer
 from sklearn.preprocessing import OneHotEncoder
-import pandas as pd
 
 X = pd.DataFrame({"pet": ["dog", "cat", "fish"], "age": [3, 7, 1]})
 preprocessor = ColumnTransformer(
-Original file line number
+Diff line change
@@ Expand Up / @@ -1349,4 +1349,4 @@ def _get_submodule(module_name, submodule_name): @@
     }
     """
-    DEPRECATED_API_REFERENCE = {}  # type: ignore
+    DEPRECATED_API_REFERENCE = {}  # type: ignore[var-annotated]