Merge branch 'main' into test_numpy_complex2

Author: MichaelTiemannOSC

.circleci/config.yml

@@ -3,7 +3,7 @@ version: 2.1
 jobs:
   test-arm:
     machine:
-      image: ubuntu-2004:2022.04.1
+      image: default
     resource_class: arm.large
     environment:
       ENV_FILE: ci/deps/circle-310-arm64.yaml
@@ -46,7 +46,7 @@ jobs:
       cibw-build:
         type: string
     machine:
-      image: ubuntu-2004:2022.04.1
+      image: default
     resource_class: arm.large
     environment:
       TRIGGER_SOURCE: << pipeline.trigger_source >>

.github/actions/run-tests/action.yml

@@ -1,16 +1,9 @@
 name: Run tests and report results
-inputs:
-  preload:
-    description: Preload arguments for sanitizer
-    required: false
-  asan_options:
-    description: Arguments for Address Sanitizer (ASAN)
-    required: false
 runs:
   using: composite
   steps:
     - name: Test
-      run: ${{ inputs.asan_options }} ${{ inputs.preload }} ci/run_tests.sh
+      run: ci/run_tests.sh
       shell: bash -el {0}
 
     - name: Publish test results
@@ -20,11 +13,6 @@ runs:
         path: test-data.xml
       if: failure()
 
-    - name: Report Coverage
-      run: coverage report -m
-      shell: bash -el {0}
-      if: failure()
-
     - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v3
       with:

.github/workflows/code-checks.yml

@@ -86,7 +86,7 @@ jobs:
       if: ${{ steps.build.outcome == 'success' && always() }}
 
     - name: Typing + pylint
-      uses: pre-commit/action@v3.0.0
+      uses: pre-commit/action@v3.0.1
       with:
         extra_args: --verbose --hook-stage manual --all-files
       if: ${{ steps.build.outcome == 'success' && always() }}

.github/workflows/comment-commands.yml

@@ -24,12 +24,10 @@ jobs:
     concurrency:
       group: ${{ github.actor }}-preview-docs
     steps:
-      - run: |
-          if curl --output /dev/null --silent --head --fail "https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"; then
-            curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "Website preview of this PR available at: https://pandas.pydata.org/preview/${{ github.event.issue.number }}/"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
-          else
-            curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" -d '{"body": "No preview found for PR #${{ github.event.issue.number }}. Did the docs build complete?"}' https://api.github.com/repos/${{ github.repository }}/issues/${{ github.event.issue.number }}/comments
-          fi
+      - uses: pandas-dev/github-doc-previewer@v0.3.2
+        with:
+          previewer-server: "https://pandas.pydata.org/preview"
+          artifact-job: "Doc Build and Upload"
   asv_run:
     runs-on: ubuntu-22.04
     # TODO: Support more benchmarking options later, against different branches, against self, etc

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

@@ -90,10 +90,3 @@ jobs:
         name: website
         path: web/build
         retention-days: 14
-
-    - name: Trigger web/doc preview
-      run: curl -X POST https://pandas.pydata.org/preview/submit/$RUN_ID/$PR_ID/
-      env:
-        RUN_ID: ${{ github.run_id }}
-        PR_ID: ${{ github.event.pull_request.number }}
-      if: github.event_name == 'pull_request'

.github/workflows/package-checks.yml

@@ -24,7 +24,7 @@ jobs:
     runs-on: ubuntu-22.04
     strategy:
       matrix:
-        extra: ["test", "performance", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output-formatting", "clipboard", "compression", "consortium-standard", "all"]
+        extra: ["test", "pyarrow", "performance", "computation", "fss", "aws", "gcp", "excel", "parquet", "feather", "hdf5", "spss", "postgresql", "mysql", "sql-other", "html", "xml", "plot", "output-formatting", "clipboard", "compression", "all"]
       fail-fast: false
     name: Install Extras - ${{ matrix.extra }}
     concurrency:

.github/workflows/unit-tests.yml

@@ -57,63 +57,23 @@ jobs:
             # Also install zh_CN (its encoding is gb2312) but do not activate it.
             # It will be temporarily activated during tests with locale.setlocale
             extra_loc: "zh_CN"
-          - name: "Copy-on-Write 3.9"
-            env_file: actions-39.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.10"
-            env_file: actions-310.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.11"
-            env_file: actions-311.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.12"
-            env_file: actions-312.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "1"
-          - name: "Copy-on-Write 3.11 (warnings)"
-            env_file: actions-311.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "warn"
-          - name: "Copy-on-Write 3.10 (warnings)"
-            env_file: actions-310.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "warn"
-          - name: "Copy-on-Write 3.9 (warnings)"
-            env_file: actions-39.yaml
-            pattern: "not slow and not network and not single_cpu"
-            pandas_copy_on_write: "warn"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
             test_args: "--max-worker-restart 0"
           - name: "Numpy Dev"
             env_file: actions-311-numpydev.yaml
             pattern: "not slow and not network and not single_cpu"
-            # Currently restricted the warnings that error to Deprecation Warnings from numpy
-            # done since pyarrow isn't compatible with numpydev always
-            # TODO: work with pyarrow to revert this?
-            test_args: "-W error::DeprecationWarning:numpy -W error::FutureWarning:numpy"
+            test_args: "-W error::DeprecationWarning -W error::FutureWarning"
           - name: "Pyarrow Nightly"
             env_file: actions-311-pyarrownightly.yaml
             pattern: "not slow and not network and not single_cpu"
-          - name: "ASAN / UBSAN"
-            env_file: actions-311-sanitizers.yaml
-            pattern: "not slow and not network and not single_cpu and not skip_ubsan"
-            asan_options: "ASAN_OPTIONS=detect_leaks=0"
-            preload: LD_PRELOAD=$(gcc -print-file-name=libasan.so)
-            meson_args: --config-settings=setup-args="-Db_sanitize=address,undefined"
-            cflags_adds: -fno-sanitize-recover=all
-            pytest_workers: -1  # disable pytest-xdist as it swallows stderr from ASAN
       fail-fast: false
     name: ${{ matrix.name || format('ubuntu-latest {0}', matrix.env_file) }}
     env:
       PATTERN: ${{ matrix.pattern }}
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
-      PANDAS_COPY_ON_WRITE: ${{ matrix.pandas_copy_on_write || '0' }}
       PANDAS_CI: ${{ matrix.pandas_ci || '1' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: ${{ matrix.pytest_workers || 'auto' }}
@@ -123,7 +83,7 @@ jobs:
       QT_QPA_PLATFORM: offscreen
     concurrency:
       # https://github.community/t/concurrecy-not-work-for-push/183068/7
-      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}-${{ matrix.pandas_copy_on_write || '' }}
+      group: ${{ github.event_name == 'push' && github.run_number || github.ref }}-${{ matrix.env_file }}-${{ matrix.pattern }}-${{ matrix.extra_apt || '' }}}
       cancel-in-progress: true
 
     services:
@@ -193,18 +153,12 @@ jobs:
     - name: Test (not single_cpu)
       uses: ./.github/actions/run-tests
       if: ${{ matrix.name != 'Pypy' }}
-      with:
-        preload: ${{ matrix.preload }}
-        asan_options: ${{ matrix.asan_options }}
       env:
         # Set pattern to not single_cpu if not already set
         PATTERN: ${{ env.PATTERN == '' && 'not single_cpu' || matrix.pattern }}
 
     - name: Test (single_cpu)
       uses: ./.github/actions/run-tests
-      with:
-        preload: ${{ matrix.preload }}
-        asan_options: ${{ matrix.asan_options }}
       env:
         PATTERN: 'single_cpu'
         PYTEST_WORKERS: 0
@@ -214,7 +168,8 @@ jobs:
     timeout-minutes: 90
     strategy:
       matrix:
-        os: [macos-latest, windows-latest]
+        # Note: Don't use macOS latest since macos 14 appears to be arm64 only
+        os: [macos-13, macos-14, windows-latest]
         env_file: [actions-39.yaml, actions-310.yaml, actions-311.yaml, actions-312.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}
@@ -227,8 +182,7 @@ jobs:
       PANDAS_CI: 1
       PYTEST_TARGET: pandas
       PATTERN: "not slow and not db and not network and not single_cpu"
-      # GH 47443: PYTEST_WORKERS > 0 crashes Windows builds with memory related errors
-      PYTEST_WORKERS: ${{ matrix.os == 'macos-latest' && 'auto' || '0' }}
+      PYTEST_WORKERS: 'auto'
 
     steps:
       - name: Checkout
@@ -354,7 +308,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        os: [ubuntu-22.04, macOS-latest, windows-latest]
+        # Separate out macOS 13 and 14, since macOS 14 is arm64 only
+        os: [ubuntu-22.04, macOS-13, macOS-14, windows-latest]
 
     timeout-minutes: 90
 

.github/workflows/wheels.yml

@@ -94,7 +94,9 @@ jobs:
         buildplat:
         - [ubuntu-22.04, manylinux_x86_64]
         - [ubuntu-22.04, musllinux_x86_64]
-        - [macos-12, macosx_*]
+        - [macos-12, macosx_x86_64]
+        # Note: M1 images on Github Actions start from macOS 14
+        - [macos-14, macosx_arm64]
         - [windows-2022, win_amd64]
         # TODO: support PyPy?
         python: [["cp39", "3.9"], ["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"]]
@@ -128,7 +130,7 @@ jobs:
       # Python version used to build sdist doesn't matter
       # wheel will be built from sdist with the correct version
       - name: Unzip sdist (macOS)
-        if: ${{ matrix.buildplat[1] == 'macosx_*' }}
+        if: ${{ startsWith(matrix.buildplat[1], 'macosx') }}
         run: |
           tar -xzf ./dist/${{ env.sdist_name }} -C ./dist
 
@@ -139,18 +141,18 @@ jobs:
 
       - name: Build normal wheels
         if: ${{ (env.IS_SCHEDULE_DISPATCH != 'true' || env.IS_PUSH == 'true') }}
-        uses: pypa/cibuildwheel@v2.16.2
+        uses: pypa/cibuildwheel@v2.17.0
         with:
-         package-dir: ./dist/${{ matrix.buildplat[1] == 'macosx_*' && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
+         package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
           CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
 
       - name: Build nightly wheels (with NumPy pre-release)
         if: ${{ (env.IS_SCHEDULE_DISPATCH == 'true' && env.IS_PUSH != 'true') }}
-        uses: pypa/cibuildwheel@v2.16.2
+        uses: pypa/cibuildwheel@v2.17.0
         with:
-         package-dir: ./dist/${{ matrix.buildplat[1] == 'macosx_*' && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
+         package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
           # The nightly wheels should be build witht he NumPy 2.0 pre-releases
           # which requires the additional URL.
@@ -183,15 +185,15 @@ jobs:
           $TST_CMD = @"
           python -m pip install hypothesis>=6.46.1 pytest>=7.3.2 pytest-xdist>=2.2.0;
           python -m pip install `$(Get-Item pandas\wheelhouse\*.whl);
-          python -c `'import pandas as pd; pd.test(extra_args=[\"`\"--no-strict-data-files`\"\", \"`\"-m not clipboard and not single_cpu and not slow and not network and not db`\"\"])`';
+          python -c `'import pandas as pd; pd.test(extra_args=[`\"--no-strict-data-files`\", `\"-m not clipboard and not single_cpu and not slow and not network and not db`\"])`';
           "@
           # add rc to the end of the image name if the Python version is unreleased
           docker pull python:${{ matrix.python[1] == '3.12' && '3.12-rc' || format('{0}-windowsservercore', matrix.python[1]) }}
           docker run --env PANDAS_CI='1' -v ${PWD}:C:\pandas python:${{ matrix.python[1] == '3.12' && '3.12-rc' || format('{0}-windowsservercore', matrix.python[1]) }} powershell -Command $TST_CMD
 
       - uses: actions/upload-artifact@v4
         with:
-          name: ${{ matrix.python[0] }}-${{ startsWith(matrix.buildplat[1], 'macosx') && 'macosx' || matrix.buildplat[1] }}
+          name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
           path: ./wheelhouse/*.whl
 
       - name: Upload wheels & sdist