scikit-learn · lesteve · Apr 15, 2025 · Mar 18, 2025 · Mar 18, 2025 · Mar 18, 2025
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -11,7 +11,7 @@ jobs:
           command: |
             source build_tools/shared.sh
             # Include pytest compatibility with mypy
-            pip install pytest $(get_dep ruff min) $(get_dep mypy min) $(get_dep black min) cython-lint
+            pip install pytest $(get_dep ruff min) $(get_dep mypy min) cython-lint
       - run:
           name: linting
           command: ./build_tools/linting.sh

diff --git a/.github/workflows/arm-unit-tests.yml b/.github/workflows/arm-unit-tests.yml
@@ -27,7 +27,7 @@ jobs:
         run: |
           source build_tools/shared.sh
           # Include pytest compatibility with mypy
-          pip install pytest $(get_dep ruff min) $(get_dep mypy min) $(get_dep black min) cython-lint
+          pip install pytest $(get_dep ruff min) $(get_dep mypy min) cython-lint
       - name: Run linters
         run: ./build_tools/linting.sh
       - name: Run Meson OpenMP checks

diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -34,11 +34,10 @@ jobs:
           curl https://raw.githubusercontent.com/${{ github.repository }}/main/build_tools/shared.sh --retry 5 -o ./build_tools/shared.sh
           source build_tools/shared.sh
           # Include pytest compatibility with mypy
-          pip install pytest $(get_dep ruff min) $(get_dep mypy min) $(get_dep black min) cython-lint
+          pip install pytest $(get_dep ruff min) $(get_dep mypy min)
           # we save the versions of the linters to be used in the error message later.
           python -c "from importlib.metadata import version; print(f\"ruff={version('ruff')}\")" >> /tmp/versions.txt
           python -c "from importlib.metadata import version; print(f\"mypy={version('mypy')}\")" >> /tmp/versions.txt
-          python -c "from importlib.metadata import version; print(f\"black={version('black')}\")" >> /tmp/versions.txt
           python -c "from importlib.metadata import version; print(f\"cython-lint={version('cython-lint')}\")" >> /tmp/versions.txt
 
       - name: Run linting

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -7,14 +7,11 @@ repos:
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.11.0
+    rev: v0.11.2
     hooks:
     -   id: ruff
         args: ["--fix", "--output-format=full"]
--   repo: https://github.com/psf/black
-    rev: 24.3.0
-    hooks:
-    -   id: black
+    -   id: ruff-format
 -   repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.15.0
     hooks:

diff --git a/README.rst b/README.rst
@@ -1,6 +1,6 @@
 .. -*- mode: rst -*-
 
-|Azure| |Codecov| |CircleCI| |Nightly wheels| |Black| |PythonVersion| |PyPi| |DOI| |Benchmark|
+|Azure| |Codecov| |CircleCI| |Nightly wheels| |Ruff| |PythonVersion| |PyPi| |DOI| |Benchmark|
 
 .. |Azure| image:: https://dev.azure.com/scikit-learn/scikit-learn/_apis/build/status/scikit-learn.scikit-learn?branchName=main
    :target: https://dev.azure.com/scikit-learn/scikit-learn/_build/latest?definitionId=1&branchName=main
@@ -14,15 +14,15 @@
 .. |Nightly wheels| image:: https://github.com/scikit-learn/scikit-learn/workflows/Wheel%20builder/badge.svg?event=schedule
    :target: https://github.com/scikit-learn/scikit-learn/actions?query=workflow%3A%22Wheel+builder%22+event%3Aschedule
 
+.. |Ruff| image:: https://img.shields.io/badge/code%20style-ruff-000000.svg
+   :target: https://github.com/astral-sh/ruff
+
 .. |PythonVersion| image:: https://img.shields.io/pypi/pyversions/scikit-learn.svg
    :target: https://pypi.org/project/scikit-learn/
 
 .. |PyPi| image:: https://img.shields.io/pypi/v/scikit-learn
    :target: https://pypi.org/project/scikit-learn
 
-.. |Black| image:: https://img.shields.io/badge/code%20style-black-000000.svg
-   :target: https://github.com/psf/black
-
 .. |DOI| image:: https://zenodo.org/badge/21369/scikit-learn/scikit-learn.svg
    :target: https://zenodo.org/badge/latestdoi/21369/scikit-learn/scikit-learn
 

diff --git a/azure-pipelines.yml b/azure-pipelines.yml
@@ -35,7 +35,7 @@ jobs:
     - bash: |
         source build_tools/shared.sh
         # Include pytest compatibility with mypy
-        pip install pytest $(get_dep ruff min) $(get_dep mypy min) $(get_dep black min) cython-lint
+        pip install pytest $(get_dep ruff min) $(get_dep mypy min) cython-lint
       displayName: Install linters
     - bash: |
         ./build_tools/linting.sh

diff --git a/benchmarks/bench_hist_gradient_boosting_adult.py b/benchmarks/bench_hist_gradient_boosting_adult.py
@@ -46,7 +46,7 @@ def predict(est, data_test, target_test):
     toc = time()
     roc_auc = roc_auc_score(target_test, predicted_proba_test[:, 1])
     acc = accuracy_score(target_test, predicted_test)
-    print(f"predicted in {toc - tic:.3f}s, ROC AUC: {roc_auc:.4f}, ACC: {acc :.4f}")
+    print(f"predicted in {toc - tic:.3f}s, ROC AUC: {roc_auc:.4f}, ACC: {acc:.4f}")
 
 
 data = fetch_openml(data_id=179, as_frame=True)  # adult dataset

diff --git a/benchmarks/bench_hist_gradient_boosting_higgsboson.py b/benchmarks/bench_hist_gradient_boosting_higgsboson.py
@@ -74,7 +74,7 @@ def predict(est, data_test, target_test):
     toc = time()
     roc_auc = roc_auc_score(target_test, predicted_proba_test[:, 1])
     acc = accuracy_score(target_test, predicted_test)
-    print(f"predicted in {toc - tic:.3f}s, ROC AUC: {roc_auc:.4f}, ACC: {acc :.4f}")
+    print(f"predicted in {toc - tic:.3f}s, ROC AUC: {roc_auc:.4f}, ACC: {acc:.4f}")
 
 
 df = load_data()

diff --git a/build_tools/get_comment.py b/build_tools/get_comment.py
@@ -55,9 +55,7 @@ def get_step_message(log, start, end, title, message, details):
     if end not in log:
         return ""
     res = (
-        "-----------------------------------------------\n"
-        f"### {title}\n\n"
-        f"{message}\n\n"
+        f"-----------------------------------------------\n### {title}\n\n{message}\n\n"
     )
     if details:
         res += (
@@ -92,33 +90,31 @@ def get_message(log_file, repo, pr_number, sha, run_id, details, versions):
 
     message = ""
 
-    # black
+    # ruff check
     message += get_step_message(
         log,
-        start="### Running black ###",
-        end="Problems detected by black",
-        title="`black`",
+        start="### Running the ruff linter ###",
+        end="Problems detected by ruff check",
+        title="`ruff check`",
         message=(
-            "`black` detected issues. Please run `black .` locally and push "
-            "the changes. Here you can see the detected issues. Note that "
-            "running black might also fix some of the issues which might be "
-            "detected by `ruff`. Note that the installed `black` version is "
-            f"`black={versions['black']}`."
+            "`ruff` detected issues. Please run "
+            "`ruff check --fix --output-format=full` locally, fix the remaining "
+            "issues, and push the changes. Here you can see the detected issues. Note "
+            f"that the installed `ruff` version is `ruff={versions['ruff']}`."
         ),
         details=details,
     )
 
-    # ruff
+    # ruff format
     message += get_step_message(
         log,
-        start="### Running ruff ###",
-        end="Problems detected by ruff",
-        title="`ruff`",
+        start="### Running the ruff formatter ###",
+        end="Problems detected by ruff format",
+        title="`ruff format`",
         message=(
-            "`ruff` detected issues. Please run "
-            "`ruff check --fix --output-format=full` locally, fix the remaining "
-            "issues, and push the changes. Here you can see the detected issues. Note "
-            f"that the installed `ruff` version is `ruff={versions['ruff']}`."
+            "`ruff` detected issues. Please run `ruff format` locally and push "
+            "the changes. Here you can see the detected issues. Note that the "
+            f"installed `ruff` version is `ruff={versions['ruff']}`."
         ),
         details=details,
     )
@@ -239,7 +235,7 @@ def get_headers(token):
 def find_lint_bot_comments(repo, token, pr_number):
     """Get the comment from the linting bot."""
     # repo is in the form of "org/repo"
-    # API doc: https://docs.github.com/en/rest/issues/comments?apiVersion=2022-11-28#list-issue-comments  # noqa
+    # API doc: https://docs.github.com/en/rest/issues/comments?apiVersion=2022-11-28#list-issue-comments
     response = requests.get(
         f"https://api.github.com/repos/{repo}/issues/{pr_number}/comments",
         headers=get_headers(token),
@@ -274,15 +270,15 @@ def create_or_update_comment(comment, message, repo, pr_number, token):
     # repo is in the form of "org/repo"
     if comment is not None:
         print("updating existing comment")
-        # API doc: https://docs.github.com/en/rest/issues/comments?apiVersion=2022-11-28#update-an-issue-comment  # noqa
+        # API doc: https://docs.github.com/en/rest/issues/comments?apiVersion=2022-11-28#update-an-issue-comment
         response = requests.patch(
             f"https://api.github.com/repos/{repo}/issues/comments/{comment['id']}",
             headers=get_headers(token),
             json={"body": message},
         )
     else:
         print("creating new comment")
-        # API doc: https://docs.github.com/en/rest/issues/comments?apiVersion=2022-11-28#create-an-issue-comment  # noqa
+        # API doc: https://docs.github.com/en/rest/issues/comments?apiVersion=2022-11-28#create-an-issue-comment
         response = requests.post(
             f"https://api.github.com/repos/{repo}/issues/{pr_number}/comments",
             headers=get_headers(token),

diff --git a/build_tools/linting.sh b/build_tools/linting.sh
@@ -10,26 +10,25 @@ set -o pipefail
 
 global_status=0
 
-echo -e "### Running black ###\n"
-black --check --diff .
+echo -e "### Running the ruff linter ###\n"
+ruff check --output-format=full
 status=$?
-
 if [[ $status -eq 0 ]]
 then
-    echo -e "No problem detected by black\n"
+    echo -e "No problem detected by the ruff linter\n"
 else
-    echo -e "Problems detected by black, please run black and commit the result\n"
+    echo -e "Problems detected by ruff check, please fix them\n"
     global_status=1
 fi
 
-echo -e "### Running ruff ###\n"
-ruff check --output-format=full
+echo -e "### Running the ruff formatter ###\n"
+ruff format --diff
 status=$?
 if [[ $status -eq 0 ]]
 then
-    echo -e "No problem detected by ruff\n"
+    echo -e "No problem detected by the ruff formatter\n"
 else
-    echo -e "Problems detected by ruff, please fix them\n"
+    echo -e "Problems detected by ruff format, please run ruff format and commit the result\n"
     global_status=1
 fi
 

diff --git a/doc/developers/contributing.rst b/doc/developers/contributing.rst
@@ -269,7 +269,7 @@ how to set up your git repository:
 
    .. prompt:: bash
 
-        pip install pytest pytest-cov ruff mypy numpydoc black==24.3.0
+        pip install pytest pytest-cov ruff==0.11.2 mypy numpydoc
 
 .. _upstream:
 
@@ -1565,7 +1565,7 @@ make this task easier and faster (in no particular order).
     variable) in the code base.
 
 - Configure `git blame` to ignore the commit that migrated the code style to
-  `black`.
+  `black` and then `ruff`.
 
   .. prompt:: bash
 

diff --git a/examples/applications/plot_species_distribution_modeling.py b/examples/applications/plot_species_distribution_modeling.py
@@ -109,7 +109,7 @@ def create_species_bunch(species_name, train, test, coverages, xgrid, ygrid):
 
 
 def plot_species_distribution(
-    species=("bradypus_variegatus_0", "microryzomys_minutus_0")
+    species=("bradypus_variegatus_0", "microryzomys_minutus_0"),
 ):
     """
     Plot the species distribution.

diff --git a/examples/applications/plot_time_series_lagged_features.py b/examples/applications/plot_time_series_lagged_features.py
@@ -265,7 +265,7 @@ def consolidate_scores(cv_results, scores, metric):
     time = cv_results["fit_time"]
     scores["fit_time"].append(f"{time.mean():.2f} ± {time.std():.2f} s")
 
-    scores["loss"].append(f"quantile {int(quantile*100)}")
+    scores["loss"].append(f"quantile {int(quantile * 100)}")
     for key, value in cv_results.items():
         if key.startswith("test_"):
             metric = key.split("test_")[1]

diff --git a/examples/applications/plot_topics_extraction_with_nmf_lda.py b/examples/applications/plot_topics_extraction_with_nmf_lda.py
@@ -50,7 +50,7 @@ def plot_top_words(model, feature_names, n_top_words, title):
 
         ax = axes[topic_idx]
         ax.barh(top_features, weights, height=0.7)
-        ax.set_title(f"Topic {topic_idx +1}", fontdict={"fontsize": 30})
+        ax.set_title(f"Topic {topic_idx + 1}", fontdict={"fontsize": 30})
         ax.tick_params(axis="both", which="major", labelsize=20)
         for i in "top right left".split():
             ax.spines[i].set_visible(False)

diff --git a/examples/covariance/plot_mahalanobis_distances.py b/examples/covariance/plot_mahalanobis_distances.py
@@ -60,7 +60,7 @@
     Proceedings of the National Academy of Sciences of the United States
     of America, 17, 684-688.
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

diff --git a/examples/ensemble/plot_bias_variance.py b/examples/ensemble/plot_bias_variance.py
@@ -177,8 +177,8 @@ def generate(n_samples, noise, n_repeat=1):
 
     plt.subplot(2, n_estimators, n_estimators + n + 1)
     plt.plot(X_test, y_error, "r", label="$error(x)$")
-    plt.plot(X_test, y_bias, "b", label="$bias^2(x)$"),
-    plt.plot(X_test, y_var, "g", label="$variance(x)$"),
+    plt.plot(X_test, y_bias, "b", label="$bias^2(x)$")
+    plt.plot(X_test, y_var, "g", label="$variance(x)$")
     plt.plot(X_test, y_noise, "c", label="$noise(x)$")
 
     plt.xlim([-5, 5])

diff --git a/examples/feature_selection/plot_rfe_digits.py b/examples/feature_selection/plot_rfe_digits.py
@@ -16,7 +16,7 @@
 
     See also :ref:`sphx_glr_auto_examples_feature_selection_plot_rfe_with_cross_validation.py`
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

diff --git a/examples/feature_selection/plot_select_from_model_diabetes.py b/examples/feature_selection/plot_select_from_model_diabetes.py
@@ -40,7 +40,7 @@
 # were already standardized.
 # For a more complete example on the interpretations of the coefficients of
 # linear models, you may refer to
-# :ref:`sphx_glr_auto_examples_inspection_plot_linear_model_coefficient_interpretation.py`.  # noqa: E501
+# :ref:`sphx_glr_auto_examples_inspection_plot_linear_model_coefficient_interpretation.py`.
 import matplotlib.pyplot as plt
 import numpy as np
 

diff --git a/examples/linear_model/plot_tweedie_regression_insurance_claims.py b/examples/linear_model/plot_tweedie_regression_insurance_claims.py
@@ -606,8 +606,9 @@ def score_estimator(
             "predicted, frequency*severity model": np.sum(
                 exposure * glm_freq.predict(X) * glm_sev.predict(X)
             ),
-            "predicted, tweedie, power=%.2f"
-            % glm_pure_premium.power: np.sum(exposure * glm_pure_premium.predict(X)),
+            "predicted, tweedie, power=%.2f" % glm_pure_premium.power: np.sum(
+                exposure * glm_pure_premium.predict(X)
+            ),
         }
     )
 

diff --git a/examples/manifold/plot_lle_digits.py b/examples/manifold/plot_lle_digits.py
@@ -10,7 +10,6 @@
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause
 
-
 # %%
 # Load digits dataset
 # -------------------

diff --git a/examples/manifold/plot_manifold_sphere.py b/examples/manifold/plot_manifold_sphere.py
@@ -50,7 +50,7 @@
 t = random_state.rand(n_samples) * np.pi
 
 # Sever the poles from the sphere.
-indices = (t < (np.pi - (np.pi / 8))) & (t > ((np.pi / 8)))
+indices = (t < (np.pi - (np.pi / 8))) & (t > (np.pi / 8))
 colors = p[indices]
 x, y, z = (
     np.sin(t[indices]) * np.cos(p[indices]),

diff --git a/examples/miscellaneous/plot_partial_dependence_visualization_api.py b/examples/miscellaneous/plot_partial_dependence_visualization_api.py
@@ -11,7 +11,7 @@
 
     See also :ref:`sphx_glr_auto_examples_miscellaneous_plot_roc_curve_visualization_api.py`
 
-"""  # noqa: E501
+"""
 
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause

diff --git a/examples/model_selection/plot_likelihood_ratios.py b/examples/model_selection/plot_likelihood_ratios.py
@@ -40,7 +40,7 @@ class proportion than the target application.
 from sklearn.datasets import make_classification
 
 X, y = make_classification(n_samples=10_000, weights=[0.9, 0.1], random_state=0)
-print(f"Percentage of people carrying the disease: {100*y.mean():.2f}%")
+print(f"Percentage of people carrying the disease: {100 * y.mean():.2f}%")
 
 # %%
 # A machine learning model is built to diagnose if a person with some given

diff --git a/examples/model_selection/plot_roc.py b/examples/model_selection/plot_roc.py
@@ -152,9 +152,9 @@
 #
 # We can briefly demo the effect of :func:`numpy.ravel`:
 
-print(f"y_score:\n{y_score[0:2,:]}")
+print(f"y_score:\n{y_score[0:2, :]}")
 print()
-print(f"y_score.ravel():\n{y_score[0:2,:].ravel()}")
+print(f"y_score.ravel():\n{y_score[0:2, :].ravel()}")
 
 # %%
 # In a multi-class classification setup with highly imbalanced classes,
@@ -359,7 +359,7 @@
     plt.plot(
         fpr_grid,
         mean_tpr[ix],
-        label=f"Mean {label_a} vs {label_b} (AUC = {mean_score :.2f})",
+        label=f"Mean {label_a} vs {label_b} (AUC = {mean_score:.2f})",
         linestyle=":",
         linewidth=4,
     )

diff --git a/examples/text/plot_document_classification_20newsgroups.py b/examples/text/plot_document_classification_20newsgroups.py
@@ -356,7 +356,7 @@ def benchmark(clf, custom_name=False):
 # Notice that the most important hyperparameters values were tuned using a grid
 # search procedure not shown in this notebook for the sake of simplicity. See
 # the example script
-# :ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`  # noqa: E501
+# :ref:`sphx_glr_auto_examples_model_selection_plot_grid_search_text_feature_extraction.py`
 # for a demo on how such tuning can be done.
 
 from sklearn.ensemble import RandomForestClassifier

@@ -43,7 +43,7 @@ def get_min_version_with_wheel(package_name, python_version):
         for file_info in release_info:
             if (
                 file_info["packagetype"] == "bdist_wheel"
-                and f'cp{python_version.replace(".", "")}' in file_info["filename"]
+                and f"cp{python_version.replace('.', '')}" in file_info["filename"]
                 and not file_info["yanked"]
             ):
                 compatible_versions.append(ver)