Merge remote-tracking branch 'neurodata/submodulev3' into submodulev3

Author: SamuelCarliles3

.git-blame-ignore-revs

@@ -31,3 +31,6 @@ d4aad64b1eb2e42e76f49db2ccfbe4b4660d092b
 
 # PR 26649: Add isort and ruff rules
 42173fdb34b5aded79664e045cada719dfbe39dc
+
+# PR #28802: Update black to 24.3.0
+c4c546355667b070edd5c892b206aa4a97af9a0b

.github/dependabot.yml

@@ -0,0 +1,21 @@
+version: 2
+updates:
+  # Maintain dependencies for GitHub Actions as recommended in SPEC8:
+  # https://github.com/scientific-python/specs/pull/325
+  # At the time of writing, release critical workflows such as
+  # pypa/gh-action-pypi-publish should use hash-based versioning for security
+  # reasons. This strategy may be generalized to all other github actions
+  # in the future.
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+    groups:
+      actions:
+        patterns:
+          - "*"
+    labels:
+      - "Build / CI"
+      - "dependencies"
+    reviewers:
+      - "scikit-learn/core-devs"

.github/workflows/check-changelog.yml

@@ -16,7 +16,7 @@ jobs:
         run: |
           echo "PR_NUMBER=${{ github.event.pull_request.number }}" >> $GITHUB_ENV
           echo "TAGGED_MILESTONE=${{ github.event.pull_request.milestone.title }}" >> $GITHUB_ENV
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
         with:
           fetch-depth: '0'
       - name: Check the changelog entry

.github/workflows/check-sdist.yml

@@ -11,7 +11,7 @@ jobs:
 
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
           python-version: '3.9'

.github/workflows/cuda-gpu-ci.yml

@@ -0,0 +1,46 @@
+name: CUDA GPU
+on:
+  workflow_dispatch:
+    inputs:
+      pr_id:
+        description: Test the contents of this Pull Request
+        required: true
+
+permissions: read-all
+
+jobs:
+  tests:
+    runs-on:
+      group: cuda-gpu-runner-group
+    name: Run Array API unit tests
+    steps:
+      - uses: actions/setup-python@v5
+        with:
+          # XXX: The 3.12.4 release of Python on GitHub Actions is corrupted:
+          # https://github.com/actions/setup-python/issues/886
+          python-version: '3.12.3'
+      - name: Checkout main repository
+        uses: actions/checkout@v4
+      - run: |
+          git fetch origin +refs/pull/${{ inputs.pr_id }}/head:pr-${{ inputs.pr_id }}
+          git checkout pr-${{ inputs.pr_id }}
+          echo "Checked out commit $(git rev-parse HEAD)"
+      - name: Cache conda environment
+        id: cache-conda
+        uses: actions/cache@v4
+        with:
+          path: ~/conda
+          key: ${{ runner.os }}-build-${{ hashFiles('build_tools/github/create_gpu_environment.sh') }}-${{ hashFiles('build_tools/github/pylatest_conda_forge_cuda_array-api_linux-64_conda.lock') }}
+      - name: Install miniforge
+        if: ${{ steps.cache-conda.outputs.cache-hit != 'true' }}
+        run: bash build_tools/github/create_gpu_environment.sh
+      - name: Install scikit-learn
+        run: |
+          source "${HOME}/conda/etc/profile.d/conda.sh"
+          conda activate sklearn
+          pip install --verbose --no-build-isolation --config-settings editable-verbose=true --editable .
+      - name: Run array API tests
+        run: |
+          source "${HOME}/conda/etc/profile.d/conda.sh"
+          conda activate sklearn
+          pytest -k 'array_api'

.github/workflows/labeler-title-regex.yml

@@ -15,7 +15,7 @@ jobs:
   labeler:
     runs-on: ubuntu-20.04
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - uses: actions/setup-python@v5
       with:
         python-version: '3.9'

.github/workflows/lint.yml

@@ -20,7 +20,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           ref: ${{ github.event.pull_request.head.sha }}
 
@@ -52,7 +52,7 @@ jobs:
 
       - name: Upload Artifact
         if: always()
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: lint-log
           path: |
@@ -72,7 +72,7 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Set up Python
         uses: actions/setup-python@v5
@@ -84,7 +84,7 @@ jobs:
 
       - name: Download artifact
         id: download-artifact
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: lint-log
 

.github/workflows/publish_pypi.yml

@@ -18,7 +18,7 @@ jobs:
       # IMPORTANT: this permission is mandatory for trusted publishing
       id-token: write
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - uses: actions/setup-python@v5
       with:
         python-version: '3.8'
@@ -39,10 +39,13 @@ jobs:
       run: |
         python build_tools/github/check_wheels.py
     - name: Publish package to TestPyPI
-      uses: pypa/gh-action-pypi-publish@v1.8.5
+      uses: pypa/gh-action-pypi-publish@81e9d935c883d0b210363ab89cf05f3894778450 # v1.8.14
       with:
-        repository_url: https://test.pypi.org/legacy/
+        repository-url: https://test.pypi.org/legacy/
+        print-hash: true
       if: ${{ github.event.inputs.pypi_repo == 'testpypi' }}
     - name: Publish package to PyPI
-      uses: pypa/gh-action-pypi-publish@v1.8.5
+      uses: pypa/gh-action-pypi-publish@81e9d935c883d0b210363ab89cf05f3894778450 # v1.8.14
       if: ${{ github.event.inputs.pypi_repo == 'pypi' }}
+      with:
+        print-hash: true

.github/workflows/update-lock-files.yml

@@ -6,6 +6,10 @@ on:
   schedule:
     - cron: '0 5 * * 1'
 
+# XXX Set the right permissions, per step??
+# Can we set read only at the global level here and then elevate to write for some steps?
+#permissions: read-all
+
 jobs:
   update_lock_files:
     if: github.repository == 'scikit-learn/scikit-learn'
@@ -25,9 +29,8 @@ jobs:
           - name: cirrus-arm
             update_script_args: "--select-tag arm"
             additional_commit_message: "[cirrus arm]"
-          - name: pypy
-            update_script_args: "--select-tag pypy"
-            additional_commit_message: "[pypy]"
+          - name: array-api
+            update_script_args: "--select-tag cuda"
 
     steps:
       - uses: actions/checkout@v4
@@ -43,7 +46,7 @@ jobs:
 
       - name: Create Pull Request
         id: cpr
-        uses: peter-evans/create-pull-request@v5
+        uses: peter-evans/create-pull-request@v6
         with:
           token: ${{ secrets.BOT_GITHUB_TOKEN }}
           push-to-fork: scikit-learn-bot/scikit-learn
@@ -59,6 +62,14 @@ jobs:
             ### Note
             If the CI tasks fail, create a new branch based on this PR and add the required fixes to that branch.
 
+      # The CUDA workflow needs to be triggered explicitly as it uses an expensive runner
+      - name: Trigger additional tests
+        if: steps.cpr.outputs.pull-request-number != '' && matrix.name == 'array-api'
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          gh workflow run .github/workflows/cuda-gpu-ci.yml -f pr_id=${{steps.cpr.outputs.pull-request-number}}
+
       - name: Check Pull Request
         if: steps.cpr.outputs.pull-request-number != ''
         run: |

.github/workflows/update_tracking_issue.yml

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-latest
     if: github.repository == 'scikit-learn/scikit-learn' && github.event_name == 'schedule'
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
           python-version: '3.9'

.github/workflows/wheels.yml

@@ -32,7 +32,7 @@ jobs:
 
     steps:
       - name: Checkout scikit-learn
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
         with:
           ref: ${{ github.event.pull_request.head.sha }}
 
@@ -53,8 +53,6 @@ jobs:
       matrix:
         include:
           # Window 64 bit
-          # Note: windows-2019 is needed for older Python versions:
-          # https://github.com/scikit-learn/scikit-learn/issues/22530
           - os: windows-latest
             python: 39
             platform_id: win_amd64
@@ -90,16 +88,16 @@ jobs:
             manylinux_image: manylinux2014
 
           # MacOS x86_64
-          - os: macos-latest
+          - os: macos-12
             python: 39
             platform_id: macosx_x86_64
-          - os: macos-latest
+          - os: macos-12
             python: 310
             platform_id: macosx_x86_64
-          - os: macos-latest
+          - os: macos-12
             python: 311
             platform_id: macosx_x86_64
-          - os: macos-latest
+          - os: macos-12
             python: 312
             platform_id: macosx_x86_64
 
@@ -119,7 +117,7 @@ jobs:
 
     steps:
       - name: Checkout scikit-learn
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup Python
         uses: actions/setup-python@v5
@@ -177,8 +175,9 @@ jobs:
         run: bash build_tools/wheels/build_wheels.sh
 
       - name: Store artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
+          name: cibw-wheels-cp${{ matrix.python }}-${{ matrix.platform_id }}
           path: wheelhouse/*.whl
 
   update-tracker:
@@ -199,7 +198,7 @@ jobs:
 
     steps:
       - name: Checkout scikit-learn
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Setup Python
         uses: actions/setup-python@v5
@@ -217,8 +216,9 @@ jobs:
           SKLEARN_SKIP_NETWORK_TESTS: 1
 
       - name: Store artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
+          name: cibw-sdist
           path: dist/*.tar.gz
 
   # Upload the wheels and the source distribution
@@ -232,12 +232,14 @@ jobs:
 
     steps:
       - name: Checkout scikit-learn
-        uses: actions/checkout@v3
+        uses: actions/checkout@v4
 
       - name: Download artifacts
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
+          pattern: cibw-*
           path: dist
+          merge-multiple: true
 
       - name: Setup Python
         uses: actions/setup-python@v5

.gitignore

@@ -15,9 +15,13 @@ dist/
 MANIFEST
 doc/sg_execution_times.rst
 doc/_build/
+doc/api/*.rst
 doc/auto_examples/
+doc/css/*
+!doc/css/.gitkeep
 doc/modules/generated/
 doc/datasets/generated/
+doc/index.rst
 doc/min_dependency_table.rst
 doc/min_dependency_substitutions.rst
 *.pdf
@@ -55,6 +59,7 @@ examples/cluster/joblib
 reuters/
 benchmarks/bench_covertype_data/
 benchmarks/HIGGS.csv.gz
+bench_pca_solvers.csv
 
 *.prefs
 .pydevproject

.pre-commit-config.yaml

@@ -27,3 +27,10 @@ repos:
     # 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
+-   repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v2.7.1
+    hooks:
+    -   id: prettier
+        files: ^doc/scss/|^doc/js/scripts/
+        exclude: ^doc/js/scripts/vendor/
+        types_or: ["scss", "javascript"]