Merge branch 'scikit-learn:main' into main

virchan · Jun 14, 2024 · 18d959f · 18d959f
2 parents a643556 + dc1cad2
commit 18d959f
Show file tree

Hide file tree

Showing 381 changed files with 691 additions and 523 deletions.
diff --git a/benchmarks/bench_covertype.py b/benchmarks/bench_covertype.py
@@ -43,7 +43,7 @@
 
 # Author: Peter Prettenhofer <peter.prettenhofer@gmail.com>
 #         Arnaud Joly <arnaud.v.joly@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import argparse
 import os

diff --git a/benchmarks/bench_mnist.py b/benchmarks/bench_mnist.py
@@ -28,7 +28,7 @@
 
 # Author: Issam H. Laradji
 #         Arnaud Joly <arnaud.v.joly@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import argparse
 import os

diff --git a/benchmarks/bench_plot_nmf.py b/benchmarks/bench_plot_nmf.py
@@ -5,7 +5,7 @@
 # Authors: Tom Dupre la Tour (benchmark)
 #          Chih-Jen Linn (original projected gradient NMF implementation)
 #          Anthony Di Franco (projected gradient, Python and NumPy port)
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import numbers
 import sys

diff --git a/benchmarks/bench_plot_parallel_pairwise.py b/benchmarks/bench_plot_parallel_pairwise.py
@@ -1,5 +1,5 @@
 # Author: Mathieu Blondel <mathieu@mblondel.org>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 import time
 
 import matplotlib.pyplot as plt

diff --git a/benchmarks/bench_plot_polynomial_kernel_approximation.py b/benchmarks/bench_plot_polynomial_kernel_approximation.py
@@ -40,7 +40,7 @@
 """
 
 # Author: Daniel Lopez-Sanchez <lope@usal.es>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # Load data manipulation functions
 # Will use this for timing results

diff --git a/benchmarks/bench_rcv1_logreg_convergence.py b/benchmarks/bench_rcv1_logreg_convergence.py
@@ -1,7 +1,7 @@
 # Authors: Tom Dupre la Tour <tom.dupre-la-tour@m4x.org>
 #          Olivier Grisel <olivier.grisel@ensta.org>
 #
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import gc
 import time

diff --git a/benchmarks/bench_sgd_regression.py b/benchmarks/bench_sgd_regression.py
@@ -1,5 +1,5 @@
 # Author: Peter Prettenhofer <peter.prettenhofer@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import gc
 from time import time

diff --git a/benchmarks/bench_tsne_mnist.py b/benchmarks/bench_tsne_mnist.py
@@ -5,7 +5,7 @@
 
 """
 
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import argparse
 import json

diff --git a/doc/modules/array_api.rst b/doc/modules/array_api.rst
@@ -112,11 +112,15 @@ base estimator also does:
 Metrics
 -------
 
+- :func:`sklearn.metrics.cluster.entropy`
 - :func:`sklearn.metrics.accuracy_score`
 - :func:`sklearn.metrics.d2_tweedie_score`
+- :func:`sklearn.metrics.max_error`
 - :func:`sklearn.metrics.mean_absolute_error`
+- :func:`sklearn.metrics.mean_gamma_deviance`
 - :func:`sklearn.metrics.mean_squared_error`
 - :func:`sklearn.metrics.mean_tweedie_deviance`
+- :func:`sklearn.metrics.pairwise.additive_chi2_kernel`
 - :func:`sklearn.metrics.pairwise.cosine_similarity`
 - :func:`sklearn.metrics.pairwise.paired_cosine_distances`
 - :func:`sklearn.metrics.r2_score`

diff --git a/doc/whats_new/v1.5.rst b/doc/whats_new/v1.5.rst
@@ -23,6 +23,12 @@ Version 1.5.1
 Changelog
 ---------
 
+Changes impacting many modules
+------------------------------
+
+- |Fix| Fixed a regression causing a dead-lock at import time in some settings.
+  :pr:`29235` by :user:`Jérémie du Boisberranger <jeremiedbb>`.
+
 :mod:`sklearn.metrics`
 ......................
 

diff --git a/doc/whats_new/v1.6.rst b/doc/whats_new/v1.6.rst
@@ -32,14 +32,17 @@ See :ref:`array_api` for more details.
 
 **Functions:**
 
+- :func:`sklearn.metrics.cluster.entropy` :pr:`29141` by :user:`Yaroslav Korobko <Tialo>`;
 - :func:`sklearn.metrics.d2_tweedie_score` :pr:`29207` by :user:`Emily Chen <EmilyXinyi>`;
+- :func:`sklearn.metrics.max_error` :pr:`29212` by :user:`Edoardo Abati <EdAbati>`;
 - :func:`sklearn.metrics.mean_absolute_error` :pr:`27736` by :user:`Edoardo Abati <EdAbati>`;
+- :func:`sklearn.metrics.mean_gamma_deviance` :pr:`29239` by :usser:`Emily Chen <EmilyXinyi>`;
 - :func:`sklearn.metrics.mean_squared_error` :pr:`29142` by :user:`Yaroslav Korobko <Tialo>`;
 - :func:`sklearn.metrics.mean_tweedie_deviance` :pr:`28106` by :user:`Thomas Li <lithomas1>`;
-- :func:`sklearn.metrics.pairwise.cosine_similarity` :pr:`29014` by :user:`Edoardo Abati <EdAbati>`.
+- :func:`sklearn.metrics.pairwise.additive_chi2_kernel` :pr:`29144` by :user:`Yaroslav Korobko <Tialo>`;
+- :func:`sklearn.metrics.pairwise.cosine_similarity` :pr:`29014` by :user:`Edoardo Abati <EdAbati>`;
 - :func:`sklearn.metrics.pairwise.paired_cosine_distances` :pr:`29112` by :user:`Edoardo Abati <EdAbati>`.
 
-
 **Classes:**
 
 - :class:`preprocessing.LabelEncoder` now supports Array API compatible inputs.

diff --git a/examples/applications/plot_model_complexity_influence.py b/examples/applications/plot_model_complexity_influence.py
@@ -39,7 +39,7 @@
 # Authors: Eustache Diemert <eustache@diemert.fr>
 #          Maria Telenczuk <https://github.com/maikia>
 #          Guillaume Lemaitre <g.lemaitre58@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import time
 

diff --git a/examples/applications/plot_out_of_core_classification.py b/examples/applications/plot_out_of_core_classification.py
@@ -16,7 +16,7 @@
 
 # Authors: Eustache Diemert <eustache@diemert.fr>
 #          @FedericoV <https://github.com/FedericoV/>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import itertools
 import re

diff --git a/examples/applications/plot_outlier_detection_wine.py b/examples/applications/plot_outlier_detection_wine.py
@@ -24,7 +24,7 @@
 """
 
 # Author: Virgile Fritsch <virgile.fritsch@inria.fr>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # First example

diff --git a/examples/applications/plot_prediction_latency.py b/examples/applications/plot_prediction_latency.py
@@ -14,7 +14,7 @@
 """
 
 # Authors: Eustache Diemert <eustache@diemert.fr>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import gc
 import time

diff --git a/examples/applications/plot_species_distribution_modeling.py b/examples/applications/plot_species_distribution_modeling.py
@@ -39,7 +39,7 @@
 # Authors: Peter Prettenhofer <peter.prettenhofer@gmail.com>
 #          Jake Vanderplas <vanderplas@astro.washington.edu>
 #
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 from time import time
 

diff --git a/examples/applications/plot_stock_market.py b/examples/applications/plot_stock_market.py
@@ -11,7 +11,7 @@
 """
 
 # Author: Gael Varoquaux gael.varoquaux@normalesup.org
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # Retrieve the data from Internet

diff --git a/examples/applications/plot_tomography_l1_reconstruction.py b/examples/applications/plot_tomography_l1_reconstruction.py
@@ -37,7 +37,7 @@ class :class:`~sklearn.linear_model.Lasso`, that uses the coordinate descent
 """
 
 # Author: Emmanuelle Gouillart <emmanuelle.gouillart@nsup.org>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.pyplot as plt
 import numpy as np

diff --git a/examples/applications/plot_topics_extraction_with_nmf_lda.py b/examples/applications/plot_topics_extraction_with_nmf_lda.py
@@ -24,7 +24,7 @@
 # Author: Olivier Grisel <olivier.grisel@ensta.org>
 #         Lars Buitinck
 #         Chyi-Kwei Yau <chyikwei.yau@gmail.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 from time import time
 

diff --git a/examples/applications/wikipedia_principal_eigenvector.py b/examples/applications/wikipedia_principal_eigenvector.py
@@ -31,7 +31,7 @@
 """
 
 # Author: Olivier Grisel <olivier.grisel@ensta.org>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import os
 from bz2 import BZ2File

diff --git a/examples/bicluster/plot_spectral_biclustering.py b/examples/bicluster/plot_spectral_biclustering.py
@@ -19,7 +19,7 @@
 """
 
 # Author: Kemal Eren <kemal@kemaleren.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # Generate sample data

diff --git a/examples/bicluster/plot_spectral_coclustering.py b/examples/bicluster/plot_spectral_coclustering.py
@@ -16,7 +16,7 @@
 """
 
 # Author: Kemal Eren <kemal@kemaleren.com>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import numpy as np
 from matplotlib import pyplot as plt

diff --git a/examples/calibration/plot_calibration.py b/examples/calibration/plot_calibration.py
@@ -28,7 +28,7 @@
 # Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
 # Balazs Kegl <balazs.kegl@gmail.com>
 # Jan Hendrik Metzen <jhm@informatik.uni-bremen.de>
-# License: BSD Style.
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # Generate synthetic dataset

diff --git a/examples/calibration/plot_calibration_curve.py b/examples/calibration/plot_calibration_curve.py
@@ -14,7 +14,7 @@
 
 # Author: Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
 #         Jan Hendrik Metzen <jhm@informatik.uni-bremen.de>
-# License: BSD 3 clause.
+# SPDX-License-Identifier: BSD-3-Clause
 # %%
 # Dataset
 # -------

diff --git a/examples/calibration/plot_calibration_multiclass.py b/examples/calibration/plot_calibration_multiclass.py
@@ -28,7 +28,7 @@ class of an instance (red: class 1, green: class 2, blue: class 3).
 # the classifier but not calibrate the predicted probabilities.
 
 # Author: Jan Hendrik Metzen <jhm@informatik.uni-bremen.de>
-# License: BSD Style.
+# SPDX-License-Identifier: BSD-3-Clause
 
 import numpy as np
 

diff --git a/examples/calibration/plot_compare_calibration.py b/examples/calibration/plot_compare_calibration.py
@@ -18,7 +18,7 @@
 
 # %%
 # Author: Jan Hendrik Metzen <jhm@informatik.uni-bremen.de>
-# License: BSD 3 clause.
+# SPDX-License-Identifier: BSD-3-Clause
 #
 # Dataset
 # -------

diff --git a/examples/classification/plot_classification_probability.py b/examples/classification/plot_classification_probability.py
@@ -18,7 +18,7 @@
 """
 
 # Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.pyplot as plt
 import numpy as np

diff --git a/examples/classification/plot_classifier_comparison.py b/examples/classification/plot_classifier_comparison.py
@@ -22,7 +22,7 @@
 # Code source: Gaël Varoquaux
 #              Andreas Müller
 # Modified for documentation by Jaques Grobler
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.pyplot as plt
 import numpy as np

diff --git a/examples/classification/plot_digits_classification.py b/examples/classification/plot_digits_classification.py
@@ -9,7 +9,7 @@
 """
 
 # Author: Gael Varoquaux <gael dot varoquaux at normalesup dot org>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # Standard scientific Python imports
 import matplotlib.pyplot as plt

diff --git a/examples/cluster/plot_adjusted_for_chance_measures.py b/examples/cluster/plot_adjusted_for_chance_measures.py
@@ -17,7 +17,7 @@
 
 # Author: Olivier Grisel <olivier.grisel@ensta.org>
 #         Arturo Amor <david-arturo.amor-quiroz@inria.fr>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # Defining the list of metrics to evaluate

diff --git a/examples/cluster/plot_agglomerative_clustering.py b/examples/cluster/plot_agglomerative_clustering.py
@@ -25,7 +25,7 @@
 """
 
 # Authors: Gael Varoquaux, Nelle Varoquaux
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import time
 

diff --git a/examples/cluster/plot_agglomerative_clustering_metrics.py b/examples/cluster/plot_agglomerative_clustering_metrics.py
@@ -35,7 +35,7 @@
 """
 
 # Author: Gael Varoquaux
-# License: BSD 3-Clause or CC-0
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.patheffects as PathEffects
 import matplotlib.pyplot as plt

diff --git a/examples/cluster/plot_agglomerative_dendrogram.py b/examples/cluster/plot_agglomerative_dendrogram.py
@@ -1,5 +1,5 @@
 # Authors: Mathew Kallada, Andreas Mueller
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 """
 =========================================
 Plot Hierarchical Clustering Dendrogram

diff --git a/examples/cluster/plot_birch_vs_minibatchkmeans.py b/examples/cluster/plot_birch_vs_minibatchkmeans.py
@@ -23,7 +23,7 @@
 
 # Authors: Manoj Kumar <manojkumarsivaraj334@gmail.com
 #          Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 from itertools import cycle
 from time import time

diff --git a/examples/cluster/plot_cluster_iris.py b/examples/cluster/plot_cluster_iris.py
@@ -20,7 +20,7 @@
 
 # Code source: Gaël Varoquaux
 # Modified for documentation by Jaques Grobler
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.pyplot as plt
 

diff --git a/examples/cluster/plot_coin_segmentation.py b/examples/cluster/plot_coin_segmentation.py
@@ -23,7 +23,7 @@
 # Author: Gael Varoquaux <gael.varoquaux@normalesup.org>
 #         Brian Cheung
 #         Andrew Knyazev <Andrew.Knyazev@ucdenver.edu>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import time
 

diff --git a/examples/cluster/plot_coin_ward_segmentation.py b/examples/cluster/plot_coin_ward_segmentation.py
@@ -11,7 +11,7 @@
 
 # Author : Vincent Michel, 2010
 #          Alexandre Gramfort, 2011
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # Generate data

diff --git a/examples/cluster/plot_color_quantization.py b/examples/cluster/plot_color_quantization.py
@@ -23,7 +23,7 @@
 #          Olivier Grisel <olivier.grisel@ensta.org>
 #          Mathieu Blondel <mathieu@mblondel.org>
 #
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 from time import time
 

diff --git a/examples/cluster/plot_digits_agglomeration.py b/examples/cluster/plot_digits_agglomeration.py
@@ -10,7 +10,7 @@
 
 # Code source: Gaël Varoquaux
 # Modified for documentation by Jaques Grobler
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 import matplotlib.pyplot as plt
 import numpy as np

diff --git a/examples/cluster/plot_digits_linkage.py b/examples/cluster/plot_digits_linkage.py
@@ -28,7 +28,7 @@
 """
 
 # Authors: Gael Varoquaux
-# License: BSD 3 clause (C) INRIA 2014
+# SPDX-License-Identifier: BSD-3-Clause
 
 from time import time
 

diff --git a/examples/cluster/plot_face_compress.py b/examples/cluster/plot_face_compress.py
@@ -9,7 +9,7 @@
 
 # Authors: Gael Varoquaux
 #          Jaques Grobler
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 # Original image

diff --git a/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py b/examples/cluster/plot_feature_agglomeration_vs_univariate_selection.py
@@ -15,7 +15,7 @@
 """
 
 # Author: Alexandre Gramfort <alexandre.gramfort@inria.fr>
-# License: BSD 3 clause
+# SPDX-License-Identifier: BSD-3-Clause
 
 # %%
 import shutil