Merge remote-tracking branch 'upstream/main' into groupby-generic

Merge branch to update pull request

Author: acrossler

.github/workflows/broken-linkcheck.yml

@@ -6,7 +6,7 @@ on:
 
 jobs:
   cleanup:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
     if: github.repository_owner == 'pandas-dev'
     permissions:
       actions: write

.github/workflows/cache-cleanup-daily.yml

@@ -6,7 +6,8 @@ on:
 
 jobs:
   cleanup:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
+    if: github.repository_owner == 'pandas-dev'
     steps:
       - name: Clean Cache
         run: |

.github/workflows/cache-cleanup.yml

@@ -28,8 +28,8 @@ jobs:
 
     steps:
       - uses: actions/checkout@v5
-      - uses: github/codeql-action/init@v3
+      - uses: github/codeql-action/init@v4
         with:
           languages: ${{ matrix.language }}
-      - uses: github/codeql-action/autobuild@v3
-      - uses: github/codeql-action/analyze@v3
+      - uses: github/codeql-action/autobuild@v4
+      - uses: github/codeql-action/analyze@v4

.github/workflows/codeql.yml

@@ -9,15 +9,6 @@ permissions:
   pull-requests: write
 
 jobs:
-  issue_assign:
-    runs-on: ubuntu-24.04
-    if: (!github.event.issue.pull_request) && github.event.comment.body == 'take'
-    concurrency:
-      group: ${{ github.actor }}-issue-assign
-    steps:
-      - run: |
-          echo "Assigning issue ${{ github.event.issue.number }} to ${{ github.event.comment.user.login }}"
-          curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"assignees": ["${{ github.event.comment.user.login }}"]}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/assignees
   preview_docs:
     runs-on: ubuntu-24.04
     if: github.event.issue.pull_request && github.event.comment.body == '/preview'
@@ -28,64 +19,3 @@ jobs:
         with:
           previewer-server: "https://pandas.pydata.org/preview"
           artifact-job: "Doc Build and Upload"
-  asv_run:
-    runs-on: ubuntu-24.04
-    # TODO: Support more benchmarking options later, against different branches, against self, etc
-    if: github.event.issue.pull_request && startsWith(github.event.comment.body, '@github-actions benchmark')
-    defaults:
-      run:
-        shell: bash -el {0}
-    env:
-      ENV_FILE: environment.yml
-      COMMENT: ${{github.event.comment.body}}
-
-    concurrency:
-      # Set concurrency to prevent abuse(full runs are ~5.5 hours !!!)
-      # each user can only run one concurrent benchmark bot at a time
-      # We don't cancel in progress jobs, but if you want to benchmark multiple PRs, you're gonna have
-      # to wait
-      group: ${{ github.actor }}-asv
-      cancel-in-progress: false
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v5
-        with:
-          fetch-depth: 0
-
-        # Although asv sets up its own env, deps are still needed
-        # during discovery process
-      - name: Set up Conda
-        uses: ./.github/actions/setup-conda
-
-      - name: Run benchmarks
-        id: bench
-        continue-on-error: true # asv will exit code 1 for regressions
-        run: |
-          # extracting the regex, see https://stackoverflow.com/a/36798723
-          REGEX=$(echo "$COMMENT" | sed -n "s/^.*-b\s*\(\S*\).*$/\1/p")
-          cd asv_bench
-          asv check -E existing
-          git remote add upstream https://github.com/pandas-dev/pandas.git
-          git fetch upstream
-          asv machine --yes
-          asv continuous -f 1.1 -b $REGEX upstream/main HEAD
-          echo 'BENCH_OUTPUT<<EOF' >> $GITHUB_ENV
-          asv compare -f 1.1 upstream/main HEAD >> $GITHUB_ENV
-          echo 'EOF' >> $GITHUB_ENV
-          echo "REGEX=$REGEX" >> $GITHUB_ENV
-
-      - uses: actions/github-script@v8
-        env:
-          BENCH_OUTPUT: ${{env.BENCH_OUTPUT}}
-          REGEX: ${{env.REGEX}}
-        with:
-          script: |
-            const ENV_VARS = process.env
-            const run_url = `https://github.com/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`
-            github.rest.issues.createComment({
-              issue_number: context.issue.number,
-              owner: context.repo.owner,
-              repo: context.repo.repo,
-              body: '\nBenchmarks completed. View runner logs here.' + run_url + '\nRegex used: '+ 'regex ' + ENV_VARS["REGEX"] + '\n' + ENV_VARS["BENCH_OUTPUT"]
-            })

.github/workflows/comment-commands.yml

@@ -93,7 +93,7 @@ jobs:
       run: mv doc/build/html web/build/docs
 
     - name: Save website as an artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v5
       with:
         name: website
         path: web/build

.github/workflows/docbuild-and-upload.yml

@@ -181,8 +181,7 @@ jobs:
     timeout-minutes: 90
     strategy:
       matrix:
-        # Note: Don't use macOS latest since macos 14 appears to be arm64 only
-        os: [macos-13, macos-14, windows-latest]
+        os: [macos-15-intel, macos-15, windows-2025]
         env_file: [actions-311.yaml, actions-312.yaml, actions-313.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
@@ -322,7 +321,7 @@ jobs:
       fail-fast: false
       matrix:
         # Separate out macOS 13 and 14, since macOS 14 is arm64 only
-        os: [ubuntu-24.04, macOS-13, macOS-14, windows-latest]
+        os: [ubuntu-24.04, macOS-13, macOS-14, windows-2025]
 
     timeout-minutes: 90
 
@@ -399,7 +398,7 @@ jobs:
           pyodide build
 
       - name: Set up Node.js
-        uses: actions/setup-node@v5
+        uses: actions/setup-node@v6
         with:
           node-version: '20'
 

.github/workflows/unit-tests.yml

@@ -64,7 +64,7 @@ jobs:
           python -m pip install build
           python -m build --sdist
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: sdist
           path: ./dist/*
@@ -98,10 +98,9 @@ jobs:
         - [ubuntu-24.04, musllinux_x86_64]
         - [ubuntu-24.04-arm, manylinux_aarch64]
         - [ubuntu-24.04-arm, musllinux_aarch64]
-        - [macos-13, macosx_x86_64]
-        # Note: M1 images on Github Actions start from macOS 14
-        - [macos-14, macosx_arm64]
-        - [windows-2022, win_amd64]
+        - [macos-15-intel, macosx_x86_64]
+        - [macos-15, macosx_arm64]
+        - [windows-2025, win_amd64]
         - [windows-11-arm, win_arm64]
         python: [["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"], ["cp314", "3.14"], ["cp314t", "3.14"]]
         include:
@@ -139,7 +138,7 @@ jobs:
       # removes unnecessary files from the release
       - name: Download sdist (not macOS)
         #if: ${{ matrix.buildplat[1] != 'macosx_*' }}
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           name: sdist
           path: ./dist
@@ -162,7 +161,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v3.2.0
+        uses: pypa/cibuildwheel@v3.2.1
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
@@ -197,7 +196,7 @@ jobs:
         shell: bash -el {0}
         run: for whl in $(ls wheelhouse); do wheel unpack wheelhouse/$whl -d /tmp; done
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
           path: ./wheelhouse/*.whl
@@ -229,7 +228,7 @@ jobs:
       - build_sdist
       - build_wheels
 
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-24.04
 
     environment:
       name: pypi
@@ -239,10 +238,12 @@ jobs:
 
     steps:
       - name: Download all artefacts
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           path: dist          # everything lands in ./dist/**
 
+      # TODO: This step can be probably be achieved by actions/download-artifact@v6
+      # by specifying merge-multiple: true, and a glob pattern
       - name: Collect files
         run: |
           mkdir -p upload

.github/workflows/wheels.yml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.11
+    rev: v0.14.3
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -46,7 +46,7 @@ repos:
     -   id: codespell
         types_or: [python, rst, markdown, cython, c]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.16.7
+    rev: v0.18.1
     hooks:
     -   id: cython-lint
     -   id: double-quote-cython-strings
@@ -67,11 +67,11 @@ repos:
     -   id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
-    rev: 6.0.1
+    rev: 7.0.0
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.20.0
+    rev: v3.21.0
     hooks:
     -   id: pyupgrade
         args: [--py311-plus]
@@ -87,19 +87,19 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v1.0.0
+    rev: v1.0.1
     hooks:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v21.1.0
+    rev: v21.1.2
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.9.0
+    rev: v1.9.1
     hooks:
     - id: meson-fmt
       args: ['--inplace']

.pre-commit-config.yaml

@@ -179,7 +179,7 @@ If you are simply looking to start working with the pandas codebase, navigate to
 
 You can also triage issues which may include reproducing bug reports, or asking for vital information such as version numbers or reproduction instructions. If you would like to start triaging issues, one easy way to get started is to [subscribe to pandas on CodeTriage](https://www.codetriage.com/pandas-dev/pandas).
 
-Or maybe through using pandas you have an idea of your own or are looking for something in the documentation and thinking ‘this can be improved’...you can do something about it!
+Or maybe through using pandas you have an idea of your own or are looking for something in the documentation and thinking ‘this can be improved’... you can do something about it!
 
 Feel free to ask questions on the [mailing list](https://groups.google.com/forum/?fromgroups#!forum/pydata) or on [Slack](https://pandas.pydata.org/docs/dev/development/community.html?highlight=slack#community-slack).