scikit-learn · adrinjalali · Mar 18, 2025 · Jan 21, 2025 · Jan 21, 2025 · Jan 23, 2025
diff --git a/build_tools/circle/list_versions.py b/build_tools/circle/list_versions.py
@@ -71,10 +71,8 @@ def get_file_size(version):
     "Web-based documentation is available for versions listed below:\n",
 ]
 
-ROOT_URL = (
-    "https://api.github.com/repos/scikit-learn/scikit-learn.github.io/contents/"  # noqa
-)
-RAW_FMT = "https://raw.githubusercontent.com/scikit-learn/scikit-learn.github.io/master/%s/index.html"  # noqa
+ROOT_URL = "https://api.github.com/repos/scikit-learn/scikit-learn.github.io/contents/"
+RAW_FMT = "https://raw.githubusercontent.com/scikit-learn/scikit-learn.github.io/master/%s/index.html"
 VERSION_RE = re.compile(r"scikit-learn ([\w\.\-]+) documentation</title>")
 NAMED_DIRS = ["dev", "stable"]
 

diff --git a/build_tools/update_environments_and_lock_files.py b/build_tools/update_environments_and_lock_files.py
@@ -643,9 +643,9 @@ def write_pip_lock_file(build_metadata):
 
     json_output = execute_command(["conda", "info", "--json"])
     conda_info = json.loads(json_output)
-    environment_folder = [
+    environment_folder = next(
         each for each in conda_info["envs"] if each.endswith(environment_name)
-    ][0]
+    )
     environment_path = Path(environment_folder)
     pip_compile_path = environment_path / "bin" / "pip-compile"
 

diff --git a/examples/ensemble/plot_forest_hist_grad_boosting_comparison.py b/examples/ensemble/plot_forest_hist_grad_boosting_comparison.py
@@ -143,7 +143,7 @@
 for idx, result in enumerate(results):
     cv_results = result["cv_results"].round(3)
     model_name = result["model"]
-    param_name = list(param_grids[model_name].keys())[0]
+    param_name = next(iter(param_grids[model_name].keys()))
     cv_results[param_name] = cv_results["param_" + param_name]
     cv_results["model"] = model_name
 

diff --git a/examples/linear_model/plot_sgdocsvm_vs_ocsvm.py b/examples/linear_model/plot_sgdocsvm_vs_ocsvm.py
@@ -17,7 +17,7 @@
 benefits of such an approximation in terms of computation time but rather to
 show that we obtain similar results on a toy dataset.
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

diff --git a/examples/model_selection/plot_grid_search_stats.py b/examples/model_selection/plot_grid_search_stats.py
@@ -230,8 +230,8 @@ def compute_corrected_ttest(differences, df, n_train, n_test):
 
 n = differences.shape[0]  # number of test sets
 df = n - 1
-n_train = len(list(cv.split(X, y))[0][0])
-n_test = len(list(cv.split(X, y))[0][1])
+n_train = len(next(iter(cv.split(X, y)))[0])
+n_test = len(next(iter(cv.split(X, y)))[1])
 
 t_stat, p_val = compute_corrected_ttest(differences, df, n_train, n_test)
 print(f"Corrected t-value: {t_stat:.3f}\nCorrected p-value: {p_val:.3f}")

diff --git a/examples/neighbors/plot_species_kde.py b/examples/neighbors/plot_species_kde.py
@@ -33,7 +33,7 @@
   <http://rob.schapire.net/papers/ecolmod.pdf>`_
   S. J. Phillips, R. P. Anderson, R. E. Schapire - Ecological Modelling,
   190:231-259, 2006.
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

diff --git a/pyproject.toml b/pyproject.toml
@@ -148,7 +148,7 @@ preview = true
 # This enables us to use the explicit preview rules that we want only
 explicit-preview-rules = true
 # all rules can be found here: https://beta.ruff.rs/docs/rules/
-select = ["E", "F", "W", "I", "CPY001"]
+select = ["E", "F", "W", "I", "CPY001", "RUF"]
 ignore=[
     # space before : (needed for how black formats slicing)
     "E203",
@@ -163,6 +163,13 @@ ignore=[
     # F841 is in preview (july 2024), and we don't care much about it.
     # Local variable ... is assigned to but never used
     "F841",
+    # some RUF rules trigger too many changes
+    "RUF002",
+    "RUF003",
+    "RUF005",
+    "RUF012",
+    "RUF015",
+    "RUF021",
 ]
 
 [tool.ruff.lint.flake8-copyright]

diff --git a/sklearn/_loss/__init__.py b/sklearn/_loss/__init__.py
@@ -20,14 +20,14 @@
 )
 
 __all__ = [
-    "HalfSquaredError",
     "AbsoluteError",
-    "PinballLoss",
-    "HuberLoss",
-    "HalfPoissonLoss",
+    "HalfBinomialLoss",
     "HalfGammaLoss",
+    "HalfMultinomialLoss",
+    "HalfPoissonLoss",
+    "HalfSquaredError",
     "HalfTweedieLoss",
     "HalfTweedieLossIdentity",
-    "HalfBinomialLoss",
-    "HalfMultinomialLoss",
+    "HuberLoss",
+    "PinballLoss",
 ]
diff --git a/sklearn/cluster/__init__.py b/sklearn/cluster/__init__.py
@@ -26,21 +26,24 @@
 from ._spectral import SpectralClustering, spectral_clustering
 
 __all__ = [
+    "DBSCAN",
+    "HDBSCAN",
+    "OPTICS",
     "AffinityPropagation",
     "AgglomerativeClustering",
     "Birch",
-    "DBSCAN",
-    "OPTICS",
-    "cluster_optics_dbscan",
-    "cluster_optics_xi",
-    "compute_optics_graph",
-    "KMeans",
     "BisectingKMeans",
     "FeatureAgglomeration",
+    "KMeans",
     "MeanShift",
     "MiniBatchKMeans",
+    "SpectralBiclustering",
     "SpectralClustering",
+    "SpectralCoclustering",
     "affinity_propagation",
+    "cluster_optics_dbscan",
+    "cluster_optics_xi",
+    "compute_optics_graph",
     "dbscan",
     "estimate_bandwidth",
     "get_bin_seeds",
@@ -50,7 +53,4 @@
     "mean_shift",
     "spectral_clustering",
     "ward_tree",
-    "SpectralBiclustering",
-    "SpectralCoclustering",
-    "HDBSCAN",
 ]
diff --git a/sklearn/cluster/_bicluster.py b/sklearn/cluster/_bicluster.py
@@ -18,7 +18,7 @@
 from ..utils.validation import assert_all_finite, validate_data
 from ._kmeans import KMeans, MiniBatchKMeans
 
-__all__ = ["SpectralCoclustering", "SpectralBiclustering"]
+__all__ = ["SpectralBiclustering", "SpectralCoclustering"]
 
 
 def _scale_normalize(X):

diff --git a/sklearn/compose/__init__.py b/sklearn/compose/__init__.py
@@ -17,7 +17,7 @@
 
 __all__ = [
     "ColumnTransformer",
-    "make_column_transformer",
     "TransformedTargetRegressor",
     "make_column_selector",
+    "make_column_transformer",
 ]
diff --git a/sklearn/compose/_column_transformer.py b/sklearn/compose/_column_transformer.py
@@ -50,7 +50,7 @@
     check_is_fitted,
 )
 
-__all__ = ["ColumnTransformer", "make_column_transformer", "make_column_selector"]
+__all__ = ["ColumnTransformer", "make_column_selector", "make_column_transformer"]
 
 
 _ERR_MSG_1DCOLUMN = (
@@ -1352,10 +1352,8 @@ def _is_empty_column_selection(column):
     if hasattr(column, "dtype") and np.issubdtype(column.dtype, np.bool_):
         return not column.any()
     elif hasattr(column, "__len__"):
-        return (
-            len(column) == 0
-            or all(isinstance(col, bool) for col in column)
-            and not any(column)
+        return len(column) == 0 or (
+            all(isinstance(col, bool) for col in column) and not any(column)
         )
     else:
         return False

diff --git a/sklearn/compose/tests/test_column_transformer.py b/sklearn/compose/tests/test_column_transformer.py
@@ -361,7 +361,7 @@ def test_column_transformer_empty_columns(pandas, column_selection, callable_col
         X = X_array
 
     if callable_column:
-        column = lambda X: column_selection  # noqa
+        column = lambda X: column_selection
     else:
         column = column_selection
 

diff --git a/sklearn/conftest.py b/sklearn/conftest.py
@@ -185,7 +185,7 @@ def pytest_collection_modifyitems(config, items):
             marker = pytest.mark.xfail(
                 reason=(
                     "know failure. See "
-                    "https://github.com/scikit-learn/scikit-learn/issues/17797"  # noqa
+                    "https://github.com/scikit-learn/scikit-learn/issues/17797"
                 )
             )
             item.add_marker(marker)

diff --git a/sklearn/covariance/__init__.py b/sklearn/covariance/__init__.py
@@ -27,13 +27,13 @@
 )
 
 __all__ = [
+    "OAS",
     "EllipticEnvelope",
     "EmpiricalCovariance",
     "GraphicalLasso",
     "GraphicalLassoCV",
     "LedoitWolf",
     "MinCovDet",
-    "OAS",
     "ShrunkCovariance",
     "empirical_covariance",
     "fast_mcd",

diff --git a/sklearn/cross_decomposition/__init__.py b/sklearn/cross_decomposition/__init__.py
@@ -5,4 +5,4 @@
 
 from ._pls import CCA, PLSSVD, PLSCanonical, PLSRegression
 
-__all__ = ["PLSCanonical", "PLSRegression", "PLSSVD", "CCA"]
+__all__ = ["CCA", "PLSSVD", "PLSCanonical", "PLSRegression"]
diff --git a/sklearn/cross_decomposition/_pls.py b/sklearn/cross_decomposition/_pls.py
@@ -27,7 +27,7 @@
 from ..utils.fixes import parse_version, sp_version
 from ..utils.validation import FLOAT_DTYPES, check_is_fitted, validate_data
 
-__all__ = ["PLSCanonical", "PLSRegression", "PLSSVD"]
+__all__ = ["PLSSVD", "PLSCanonical", "PLSRegression"]
 
 
 if sp_version >= parse_version("1.7"):

diff --git a/sklearn/datasets/__init__.py b/sklearn/datasets/__init__.py
@@ -61,22 +61,22 @@
     "dump_svmlight_file",
     "fetch_20newsgroups",
     "fetch_20newsgroups_vectorized",
+    "fetch_california_housing",
+    "fetch_covtype",
     "fetch_file",
+    "fetch_kddcup99",
     "fetch_lfw_pairs",
     "fetch_lfw_people",
     "fetch_olivetti_faces",
-    "fetch_species_distributions",
-    "fetch_california_housing",
-    "fetch_covtype",
-    "fetch_rcv1",
-    "fetch_kddcup99",
     "fetch_openml",
+    "fetch_rcv1",
+    "fetch_species_distributions",
     "get_data_home",
+    "load_breast_cancer",
     "load_diabetes",
     "load_digits",
     "load_files",
     "load_iris",
-    "load_breast_cancer",
     "load_linnerud",
     "load_sample_image",
     "load_sample_images",
@@ -85,9 +85,9 @@
     "load_wine",
     "make_biclusters",
     "make_blobs",
+    "make_checkerboard",
     "make_circles",
     "make_classification",
-    "make_checkerboard",
     "make_friedman1",
     "make_friedman2",
     "make_friedman3",

diff --git a/sklearn/datasets/_kddcup99.py b/sklearn/datasets/_kddcup99.py
@@ -376,7 +376,7 @@ def _fetch_brute_kddcup99(
         except Exception as e:
             raise OSError(
                 "The cache for fetch_kddcup99 is invalid, please delete "
-                f"{str(kddcup_dir)} and run the fetch_kddcup99 again"
+                f"{kddcup_dir} and run the fetch_kddcup99 again"
             ) from e
 
     elif download_if_missing:

diff --git a/sklearn/datasets/_openml.py b/sklearn/datasets/_openml.py
@@ -20,7 +20,7 @@
 import numpy as np
 
 from ..utils import Bunch
-from ..utils._optional_dependencies import check_pandas_support  # noqa
+from ..utils._optional_dependencies import check_pandas_support
 from ..utils._param_validation import (
     Integral,
     Interval,

diff --git a/sklearn/datasets/_svmlight_format_io.py b/sklearn/datasets/_svmlight_format_io.py
@@ -384,10 +384,8 @@ def get_data():
         for f in files
     ]
 
-    if (
-        zero_based is False
-        or zero_based == "auto"
-        and all(len(tmp[1]) and np.min(tmp[1]) > 0 for tmp in r)
+    if zero_based is False or (
+        zero_based == "auto" and all(len(tmp[1]) and np.min(tmp[1]) > 0 for tmp in r)
     ):
         for _, indices, _, _, _ in r:
             indices -= 1

diff --git a/sklearn/datasets/tests/test_kddcup99.py b/sklearn/datasets/tests/test_kddcup99.py
@@ -82,7 +82,7 @@ def test_corrupted_file_error_message(fetch_kddcup99_fxt, tmp_path):
 
     msg = (
         "The cache for fetch_kddcup99 is invalid, please "
-        f"delete {str(kddcup99_dir)} and run the fetch_kddcup99 again"
+        f"delete {kddcup99_dir} and run the fetch_kddcup99 again"
     )
 
     with pytest.raises(OSError, match=msg):

diff --git a/sklearn/decomposition/__init__.py b/sklearn/decomposition/__init__.py
@@ -31,24 +31,24 @@
 from ._truncated_svd import TruncatedSVD
 
 __all__ = [
+    "NMF",
+    "PCA",
     "DictionaryLearning",
+    "FactorAnalysis",
     "FastICA",
     "IncrementalPCA",
     "KernelPCA",
+    "LatentDirichletAllocation",
     "MiniBatchDictionaryLearning",
     "MiniBatchNMF",
     "MiniBatchSparsePCA",
-    "NMF",
-    "PCA",
     "SparseCoder",
     "SparsePCA",
+    "TruncatedSVD",
     "dict_learning",
     "dict_learning_online",
     "fastica",
     "non_negative_factorization",
     "randomized_svd",
     "sparse_encode",
-    "FactorAnalysis",
-    "TruncatedSVD",
-    "LatentDirichletAllocation",
 ]
diff --git a/sklearn/decomposition/_fastica.py b/sklearn/decomposition/_fastica.py
@@ -25,7 +25,7 @@
 from ..utils._param_validation import Interval, Options, StrOptions, validate_params
 from ..utils.validation import check_is_fitted, validate_data
 
-__all__ = ["fastica", "FastICA"]
+__all__ = ["FastICA", "fastica"]
 
 
 def _gs_decorrelation(w, W, j):

diff --git a/sklearn/decomposition/tests/test_fastica.py b/sklearn/decomposition/tests/test_fastica.py
@@ -80,7 +80,7 @@ def test_fastica_simple(add_noise, global_random_seed, global_dtype):
         pytest.xfail(
             "FastICA instability with Ubuntu Atlas build with float32 "
             "global_dtype. For more details, see "
-            "https://github.com/scikit-learn/scikit-learn/issues/24131#issuecomment-1208091119"  # noqa
+            "https://github.com/scikit-learn/scikit-learn/issues/24131#issuecomment-1208091119"
         )
 
     # Test the FastICA algorithm on very simple data.

diff --git a/sklearn/ensemble/__init__.py b/sklearn/ensemble/__init__.py
@@ -23,23 +23,23 @@
 from ._weight_boosting import AdaBoostClassifier, AdaBoostRegressor
 
 __all__ = [
+    "AdaBoostClassifier",
+    "AdaBoostRegressor",
+    "BaggingClassifier",
+    "BaggingRegressor",
     "BaseEnsemble",
-    "RandomForestClassifier",
-    "RandomForestRegressor",
-    "RandomTreesEmbedding",
     "ExtraTreesClassifier",
     "ExtraTreesRegressor",
-    "BaggingClassifier",
-    "BaggingRegressor",
-    "IsolationForest",
     "GradientBoostingClassifier",
     "GradientBoostingRegressor",
-    "AdaBoostClassifier",
-    "AdaBoostRegressor",
-    "VotingClassifier",
-    "VotingRegressor",
-    "StackingClassifier",
-    "StackingRegressor",
     "HistGradientBoostingClassifier",
     "HistGradientBoostingRegressor",
+    "IsolationForest",
+    "RandomForestClassifier",
+    "RandomForestRegressor",
+    "RandomTreesEmbedding",
+    "StackingClassifier",
+    "StackingRegressor",
+    "VotingClassifier",
+    "VotingRegressor",
 ]
Original file line number	Diff line number	Diff line change
Expand Up		@@ -5,4 +5,4 @@

		from ._pls import CCA, PLSSVD, PLSCanonical, PLSRegression

		__all__ = ["PLSCanonical", "PLSRegression", "PLSSVD", "CCA"]
		__all__ = ["CCA", "PLSSVD", "PLSCanonical", "PLSRegression"]