scikit-learn · betatim · Aug 4, 2023 · May 17, 2023 · May 17, 2023 · May 17, 2023
diff --git a/.binder/requirements.txt b/.binder/requirements.txt
@@ -1,4 +1,4 @@
---find-links https://pypi.anaconda.org/scipy-wheels-nightly/simple/scikit-learn
+--find-links https://pypi.anaconda.org/scientific-python-nightly-wheels/simple/scikit-learn
 --pre
 matplotlib
 scikit-image

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 flake8 $(get_dep mypy min) $(get_dep black min)
+            pip install pytest ruff $(get_dep mypy min) $(get_dep black min) cython-lint
       - run:
           name: linting
           command: ./build_tools/linting.sh
@@ -24,9 +24,6 @@ jobs:
       - OPENBLAS_NUM_THREADS: 2
       - CONDA_ENV_NAME: testenv
       - LOCK_FILE: build_tools/circle/doc_min_dependencies_linux-64_conda.lock
-      # Sphinx race condition in doc-min-dependencies is causing job to stall
-      # Here we run the job serially
-      - SPHINX_NUMJOBS: 1
     steps:
       - checkout
       - run: ./build_tools/circle/checkout_merge_commit.sh

diff --git a/.codecov.yml b/.codecov.yml
@@ -28,4 +28,7 @@ codecov:
 ignore:
 - "sklearn/externals"
 - "sklearn/_build_utils"
+- "sklearn/__check_build"
+- "sklearn/_min_dependencies.py"
 - "**/setup.py"
+- "**/conftest.py"
diff --git a/.git-blame-ignore-revs b/.git-blame-ignore-revs
@@ -25,3 +25,9 @@
 
 # PR 22983: Update to Black 22.3.0
 d4aad64b1eb2e42e76f49db2ccfbe4b4660d092b
+
+# PR 26110: Update black to 23.3.0
+893d5accaf9d16f447645e704f85a216187564f7
+
+# PR 26649: Add isort and ruff rules
+42173fdb34b5aded79664e045cada719dfbe39dc
diff --git a/.github/scripts/label_title_regex.py b/.github/scripts/label_title_regex.py
@@ -1,10 +1,11 @@
 """Labels PRs based on title. Must be run in a github action with the
 pull_request_target event."""
-from github import Github
-import os
 import json
+import os
 import re
 
+from github import Github
+
 context_dict = json.loads(os.getenv("CONTEXT_GITHUB"))
 
 repo = context_dict["repository"]

diff --git a/.github/workflows/artifact-redirector.yml b/.github/workflows/artifact-redirector.yml
@@ -1,5 +1,12 @@
 name: CircleCI artifacts redirector
 on: [status]
+
+# Restrict the permissions granted to the use of secrets.GITHUB_TOKEN in this
+# github actions workflow:
+# https://docs.github.com/en/actions/security-guides/automatic-token-authentication
+permissions:
+  statuses: write
+
 jobs:
   circleci_artifacts_redirector_job:
     runs-on: ubuntu-latest
@@ -11,6 +18,7 @@ jobs:
         uses: larsoner/circleci-artifacts-redirector-action@master
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
+          api-token: ${{ secrets.CIRCLECI_TOKEN }}
           artifact-path: 0/doc/_changed.html
           circleci-jobs: doc
           job-title: Check the rendered docs here!
diff --git a/.github/workflows/assign.yml b/.github/workflows/assign.yml
@@ -4,6 +4,12 @@ on:
   issue_comment:
     types: created
 
+# Restrict the permissions granted to the use of secrets.GITHUB_TOKEN in this
+# github actions workflow:
+# https://docs.github.com/en/actions/security-guides/automatic-token-authentication
+permissions:
+  issues: write
+
 jobs:
   one:
     runs-on: ubuntu-latest

diff --git a/.github/workflows/labeler-module.yml b/.github/workflows/labeler-module.yml
@@ -3,11 +3,18 @@ on:
   pull_request_target:
     types: [opened]
 
+# Restrict the permissions granted to the use of secrets.GITHUB_TOKEN in this
+# github actions workflow:
+# https://docs.github.com/en/actions/security-guides/automatic-token-authentication
+permissions:
+  contents: read
+  pull-requests: write
+
 jobs:
   triage:
     runs-on: ubuntu-latest
     steps:
-    - uses: thomasjpfan/labeler@v2.5.0
+    - uses: thomasjpfan/labeler@v2.5.1
       continue-on-error: true
       if: github.repository == 'scikit-learn/scikit-learn'
       with:
@@ -18,7 +25,7 @@ jobs:
   triage_file_extensions:
     runs-on: ubuntu-latest
     steps:
-    - uses: thomasjpfan/labeler@v2.5.0
+    - uses: thomasjpfan/labeler@v2.5.1
       continue-on-error: true
       if: github.repository == 'scikit-learn/scikit-learn'
       with:

diff --git a/.github/workflows/labeler-title-regex.yml b/.github/workflows/labeler-title-regex.yml
@@ -3,6 +3,9 @@ on:
   pull_request_target:
     types: [opened, edited]
 
+# Restrict the permissions granted to the use of secrets.GITHUB_TOKEN in this
+# github actions workflow:
+# https://docs.github.com/en/actions/security-guides/automatic-token-authentication
 permissions:
   contents: read
   pull-requests: write

diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml
@@ -0,0 +1,103 @@
+# This linter job on GH actions is used to trigger the commenter bot
+# in bot-lint-comment.yml file. It stores the output of the linter to be used
+# by the commenter bot.
+name: linter
+
+on:
+  - pull_request_target
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+
+    # setting any permission will set everything else to none for GITHUB_TOKEN
+    permissions:
+      pull-requests: none
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: 3.11
+
+      - name: Install dependencies
+        run: |
+          source build_tools/shared.sh
+          # Include pytest compatibility with mypy
+          pip install pytest ruff $(get_dep mypy min) $(get_dep black min) cython-lint
+          # we save the versions of the linters to be used in the error message later.
+          python -c "from importlib.metadata import version; print(f\"ruff={version('ruff')}\")" >> /tmp/versions.txt
+          python -c "from importlib.metadata import version; print(f\"mypy={version('mypy')}\")" >> /tmp/versions.txt
+          python -c "from importlib.metadata import version; print(f\"black={version('black')}\")" >> /tmp/versions.txt
+          python -c "from importlib.metadata import version; print(f\"cython-lint={version('cython-lint')}\")" >> /tmp/versions.txt
+
+      - name: Run linting
+        id: lint-script
+        # We download the linting script from main, since this workflow is run
+        # from main itself.
+        run: |
+          curl https://raw.githubusercontent.com/${{ github.repository }}/main/build_tools/linting.sh --retry 5 -o ./build_tools/linting.sh
+          set +e
+          ./build_tools/linting.sh &> /tmp/linting_output.txt
+          cat /tmp/linting_output.txt
+
+      - name: Upload Artifact
+        if: always()
+        uses: actions/upload-artifact@v3
+        with:
+          name: lint-log
+          path: |
+            /tmp/linting_output.txt
+            /tmp/versions.txt
+          retention-days: 1
+
+  comment:
+    needs: lint
+    if: always()
+    runs-on: ubuntu-latest
+
+    # We need these permissions to be able to post / update comments
+    permissions:
+      pull-requests: write
+      issues: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Set up Python
+        uses: actions/setup-python@v3
+        with:
+          python-version: 3.11
+
+      - name: Install dependencies
+        run: python -m pip install requests
+
+      - name: Download artifact
+        id: download-artifact
+        uses: actions/download-artifact@v3
+        with:
+          name: lint-log
+
+      - name: Print log
+        run: cat linting_output.txt
+
+      - name: Process Comments
+        id: process-comments
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          PR_NUMBER: ${{ github.event.pull_request.number }}
+          BRANCH_SHA: ${{ github.event.pull_request.head.sha }}
+          RUN_ID: ${{ github.run_id }}
+          LOG_FILE: linting_output.txt
+          VERSIONS_FILE: versions.txt
+        run: python ./build_tools/get_comment.py
diff --git a/.github/workflows/publish_pypi.yml b/.github/workflows/publish_pypi.yml
@@ -13,6 +13,9 @@ on:
 jobs:
   publish:
     runs-on: ubuntu-latest
+    permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write
     steps:
     - uses: actions/checkout@v3
     - uses: actions/setup-python@v4
@@ -35,15 +38,10 @@ jobs:
       run: |
         python build_tools/github/check_wheels.py
     - name: Publish package to TestPyPI
-      uses: pypa/gh-action-pypi-publish@v1.4.1
+      uses: pypa/gh-action-pypi-publish@v1.8.5
       with:
-        user: __token__
-        password: ${{ secrets.TEST_PYPI_TOKEN }}
         repository_url: https://test.pypi.org/legacy/
       if: ${{ github.event.inputs.pypi_repo == 'testpypi' }}
     - name: Publish package to PyPI
-      uses: pypa/gh-action-pypi-publish@v1.4.1
-      with:
-        user: __token__
-        password: ${{ secrets.PYPI_TOKEN }}
+      uses: pypa/gh-action-pypi-publish@v1.8.5
       if: ${{ github.event.inputs.pypi_repo == 'pypi' }}
diff --git a/.github/workflows/twitter.yml b/.github/workflows/twitter.yml
diff --git a/.github/workflows/unassign.yml b/.github/workflows/unassign.yml
@@ -4,6 +4,12 @@ on:
   issues:
     types: unassigned
 
+# Restrict the permissions granted to the use of secrets.GITHUB_TOKEN in this
+# github actions workflow:
+# https://docs.github.com/en/actions/security-guides/automatic-token-authentication
+permissions:
+  issues: write
+
 jobs:
   one:
     runs-on: ubuntu-latest

diff --git a/.github/workflows/wheels.yml b/.github/workflows/wheels.yml
@@ -116,9 +116,7 @@ jobs:
         env:
           CONFTEST_PATH: ${{ github.workspace }}/conftest.py
           CONFTEST_NAME: conftest.py
-          CIBW_ENVIRONMENT: OMP_NUM_THREADS=2
-                            OPENBLAS_NUM_THREADS=2
-                            SKLEARN_SKIP_NETWORK_TESTS=1
+          CIBW_ENVIRONMENT: SKLEARN_SKIP_NETWORK_TESTS=1
                             SKLEARN_BUILD_PARALLEL=3
           CIBW_BUILD: cp${{ matrix.python }}-${{ matrix.platform_id }}
           CIBW_ARCHS: all
@@ -173,8 +171,6 @@ jobs:
       - name: Test source distribution
         run: bash build_tools/github/test_source.sh
         env:
-          OMP_NUM_THREADS: 2
-          OPENBLAS_NUM_THREADS: 2
           SKLEARN_SKIP_NETWORK_TESTS: 1
 
       - name: Store artifacts

diff --git a/.gitignore b/.gitignore
@@ -85,10 +85,12 @@ 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
@@ -97,3 +99,6 @@ 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
+
+# Default JupyterLite content
+jupyterlite_contents
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -6,17 +6,24 @@ repos:
     -   id: end-of-file-fixer
     -   id: trailing-whitespace
 -   repo: https://github.com/psf/black
-    rev: 22.3.0
+    rev: 23.3.0
     hooks:
     -   id: black
--   repo: https://github.com/pycqa/flake8
-    rev: 4.0.1
+-   repo: https://github.com/astral-sh/ruff-pre-commit
+    # Ruff version.
+    rev: v0.0.272
     hooks:
-    -   id: flake8
-        types: [file, python]
+    -   id: ruff
+        args: ["--fix", "--show-source"]
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v0.961
+    rev: v1.3.0
     hooks:
      -  id: mypy
         files: sklearn/
         additional_dependencies: [pytest==6.2.4]
+-   repo: https://github.com/MarcoGorelli/cython-lint
+    rev: v0.15.0
+    hooks:
+    # TODO: add the double-quote-cython-strings hook when it's usability has improved:
+    # possibility to pass a directory and use it as a check instead of auto-formatter.
+    -   id: cython-lint