Merging main 080724

Signed-off-by: Adam Li <adam2392@gmail.com>

Author: adam2392

.github/workflows/cuda-ci.yml

@@ -42,4 +42,4 @@ jobs:
         run: |
           source "${HOME}/conda/etc/profile.d/conda.sh"
           conda activate sklearn
-          pytest -k 'array_api'
+          SCIPY_ARRAY_API=1 pytest -k 'array_api'

.github/workflows/wheels.yml

@@ -174,8 +174,8 @@ jobs:
           CIBW_CONFIG_SETTINGS_WINDOWS: "setup-args=--vsenv"
           CIBW_REPAIR_WHEEL_COMMAND_WINDOWS: bash build_tools/github/repair_windows_wheels.sh {wheel} {dest_dir}
           CIBW_BEFORE_TEST_WINDOWS: bash build_tools/github/build_minimal_windows_image.sh ${{ matrix.python }}
-          CIBW_TEST_REQUIRES: pytest
           CIBW_BEFORE_TEST: bash {project}/build_tools/wheels/cibw_before_test.sh
+          CIBW_TEST_REQUIRES: pytest pandas
           CIBW_TEST_COMMAND: bash {project}/build_tools/wheels/test_wheels.sh
           CIBW_TEST_COMMAND_WINDOWS: bash {project}/build_tools/github/test_windows_wheels.sh ${{ matrix.python }}
           CIBW_BUILD_VERBOSITY: 1

.gitignore

@@ -21,6 +21,7 @@ doc/css/*
 !doc/css/.gitkeep
 doc/modules/generated/
 doc/datasets/generated/
+doc/developers/maintainer.rst
 doc/index.rst
 doc/min_dependency_table.rst
 doc/min_dependency_substitutions.rst
@@ -87,31 +88,5 @@ _configtest.o.d
 # virtualenv from advanced installation guide
 sklearn-env/
 
-# files generated from a template
-sklearn/_loss/_loss.pyx
-sklearn/utils/_seq_dataset.pyx
-sklearn/utils/_seq_dataset.pxd
-sklearn/utils/_weight_vector.pyx
-sklearn/utils/_weight_vector.pxd
-sklearn/linear_model/_sag_fast.pyx
-sklearn/linear_model/_sgd_fast.pyx
-sklearn/metrics/_dist_metrics.pyx
-sklearn/metrics/_dist_metrics.pxd
-sklearn/metrics/_pairwise_distances_reduction/_argkmin.pxd
-sklearn/metrics/_pairwise_distances_reduction/_argkmin.pyx
-sklearn/metrics/_pairwise_distances_reduction/_argkmin_classmode.pyx
-sklearn/metrics/_pairwise_distances_reduction/_base.pxd
-sklearn/metrics/_pairwise_distances_reduction/_base.pyx
-sklearn/metrics/_pairwise_distances_reduction/_datasets_pair.pxd
-sklearn/metrics/_pairwise_distances_reduction/_datasets_pair.pyx
-sklearn/metrics/_pairwise_distances_reduction/_middle_term_computer.pxd
-sklearn/metrics/_pairwise_distances_reduction/_middle_term_computer.pyx
-sklearn/metrics/_pairwise_distances_reduction/_radius_neighbors.pxd
-sklearn/metrics/_pairwise_distances_reduction/_radius_neighbors.pyx
-sklearn/metrics/_pairwise_distances_reduction/_radius_neighbors_classmode.pyx
-sklearn/neighbors/_ball_tree.pyx
-sklearn/neighbors/_binary_tree.pxi
-sklearn/neighbors/_kd_tree.pyx
-
 # Default JupyterLite content
 jupyterlite_contents

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ repos:
     -   id: trailing-whitespace
 -   repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.2.1
+    rev: v0.5.1
     hooks:
     -   id: ruff
         args: ["--fix", "--output-format=full"]

.spin/cmds.py

@@ -0,0 +1,29 @@
+import shutil
+import sys
+
+import click
+from spin.cmds import util
+
+
+@click.command()
+def clean():
+    """🪥 Clean build folder.
+
+    Very rarely needed since meson-python recompiles as needed when sklearn is
+    imported.
+
+    One known use case where "spin clean" is useful: avoid compilation errors
+    when switching from numpy<2 to numpy>=2 in the same conda environment or
+    virtualenv.
+    """
+    util.run([sys.executable, "-m", "pip", "uninstall", "scikit-learn", "-y"])
+    default_meson_build_dir = (
+        f"build/cp{sys.version_info.major}{sys.version_info.minor}"
+    )
+    click.secho(
+        f"removing default Meson build dir: {default_meson_build_dir}",
+        bold=True,
+        fg="bright_blue",
+    )
+
+    shutil.rmtree(default_meson_build_dir, ignore_errors=True)

azure-pipelines.yml

@@ -138,6 +138,7 @@ jobs:
         # Here we make sure, that they are still run on a regular basis.
         ${{ if eq(variables['Build.Reason'], 'Schedule') }}:
           SKLEARN_SKIP_NETWORK_TESTS: '0'
+        SCIPY_ARRAY_API: '1'
 
 # Check compilation with Ubuntu 22.04 LTS (Jammy Jellyfish) and scipy from conda-forge
 # By default the CI is sequential, where `Ubuntu_Jammy_Jellyfish` runs first and
@@ -197,10 +198,10 @@ jobs:
         not(contains(dependencies['git_commit']['outputs']['commit.message'], '[ci skip]'))
       )
     matrix:
-      # Linux + Python 3.9 build with OpenBLAS and without pandas
-      pymin_conda_defaults_openblas:
+      # Linux + Python 3.9 build with minimum supported version of dependencies
+      pymin_conda_forge_openblas_min_dependencies:
         DISTRIB: 'conda'
-        LOCK_FILE: './build_tools/azure/pymin_conda_defaults_openblas_linux-64_conda.lock'
+        LOCK_FILE: './build_tools/azure/pymin_conda_forge_openblas_min_dependencies_linux-64_conda.lock'
         # Enable debug Cython directives to capture IndexError exceptions in
         # combination with the -Werror::pytest.PytestUnraisableExceptionWarning
         # flag for pytest.
@@ -221,6 +222,7 @@ jobs:
         # makes sure that they are single threaded in each xdist subprocess.
         PYTEST_XDIST_VERSION: 'none'
         PIP_BUILD_ISOLATION: 'true'
+        SCIPY_ARRAY_API: '1'
 
 - template: build_tools/azure/posix-docker.yml
   parameters:
@@ -259,6 +261,7 @@ jobs:
         DISTRIB: 'conda'
         LOCK_FILE: './build_tools/azure/pylatest_conda_forge_mkl_osx-64_conda.lock'
         SKLEARN_TESTS_GLOBAL_RANDOM_SEED: '5'  # non-default seed
+        SCIPY_ARRAY_API: '1'
       pylatest_conda_mkl_no_openmp:
         DISTRIB: 'conda'
         LOCK_FILE: './build_tools/azure/pylatest_conda_mkl_no_openmp_osx-64_conda.lock'

benchmarks/bench_kernel_pca_solvers_time_vs_n_components.py

@@ -36,8 +36,6 @@
 of components (this takes more time).
 """
 
-# Authors: Sylvain MARIE, Schneider Electric
-
 import time
 
 import matplotlib.pyplot as plt

benchmarks/bench_plot_parallel_pairwise.py

@@ -1,5 +1,6 @@
 # Authors: The scikit-learn developers
 # SPDX-License-Identifier: BSD-3-Clause
+
 import time
 
 import matplotlib.pyplot as plt

build_tools/azure/debian_atlas_32bit_lock.txt

@@ -1,20 +1,20 @@
 #
-# This file is autogenerated by pip-compile with Python 3.9
+# This file is autogenerated by pip-compile with Python 3.11
 # by the following command:
 #
 #    pip-compile --output-file=build_tools/azure/debian_atlas_32bit_lock.txt build_tools/azure/debian_atlas_32bit_requirements.txt
 #
-attrs==23.2.0
+attrs==24.1.0
     # via pytest
-coverage==7.5.4
+coverage==7.6.1
     # via pytest-cov
 cython==3.0.10
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
 iniconfig==2.0.0
     # via pytest
 joblib==1.2.0
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
-meson==1.4.1
+meson==1.5.1
     # via meson-python
 meson-python==0.16.0
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
@@ -40,6 +40,4 @@ pytest-cov==2.9.0
 threadpoolctl==3.1.0
     # via -r build_tools/azure/debian_atlas_32bit_requirements.txt
 tomli==2.0.1
-    # via
-    #   meson-python
-    #   pytest
+    # via pytest

build_tools/azure/install.sh

@@ -85,14 +85,14 @@ python_environment_install_and_activate() {
         # install them from scientific-python-nightly-wheels
         dev_anaconda_url=https://pypi.anaconda.org/scientific-python-nightly-wheels/simple
         dev_packages="numpy scipy Cython"
-        pip install --pre --upgrade --timeout=60 --extra-index $dev_anaconda_url $dev_packages
+        pip install --pre --upgrade --timeout=60 --extra-index $dev_anaconda_url $dev_packages --only-binary :all:
     fi
 
     if [[ "$DISTRIB" == "conda-pip-scipy-dev" ]]; then
         echo "Installing development dependency wheels"
         dev_anaconda_url=https://pypi.anaconda.org/scientific-python-nightly-wheels/simple
         dev_packages="numpy scipy pandas Cython"
-        pip install --pre --upgrade --timeout=60 --extra-index $dev_anaconda_url $dev_packages
+        pip install --pre --upgrade --timeout=60 --extra-index $dev_anaconda_url $dev_packages --only-binary :all:
 
         check_packages_dev_version $dev_packages