Resolving merge conflict

Author: astronights

.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/[email protected]
+        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/unit-tests.yml

@@ -73,18 +73,6 @@ jobs:
             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"
@@ -214,7 +202,8 @@ 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 +216,7 @@ 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 +342,8 @@ 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: ${{ (env.IS_SCHEDULE_DISPATCH != 'true' || env.IS_PUSH == 'true') }}
-        uses: pypa/[email protected].4
+        uses: pypa/[email protected].5
         with:
-         package-dir: ./dist/${{ 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: ${{ (env.IS_SCHEDULE_DISPATCH == 'true' && env.IS_PUSH != 'true') }}
-        uses: pypa/[email protected].4
+        uses: pypa/[email protected].5
         with:
-         package-dir: ./dist/${{ 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

.pre-commit-config.yaml

@@ -101,8 +101,6 @@ repos:
 -   repo: https://github.com/pre-commit/pygrep-hooks
     rev: v1.10.0
     hooks:
-      - id: python-check-blanket-noqa
-      - id: python-check-blanket-type-ignore
       - id: rst-backticks
       - id: rst-directive-colons
         types: [text]  # overwrite types: [rst]

asv_bench/asv.conf.json

@@ -41,7 +41,7 @@
     // pip (with all the conda available packages installed first,
     // followed by the pip installed packages).
     "matrix": {
-        "Cython": ["3.0.5"],
+        "Cython": ["3.0"],
         "matplotlib": [],
         "sqlalchemy": [],
         "scipy": [],

asv_bench/benchmarks/algos/isin.py

@@ -59,7 +59,8 @@ def setup(self, dtype):
         elif dtype in ["str", "string[python]", "string[pyarrow]"]:
             try:
                 self.series = Series(
-                    Index([f"i-{i}" for i in range(N)], dtype=object), dtype=dtype
+                    Index([f"i-{i}" for i in range(N)], dtype=object)._values,
+                    dtype=dtype,
                 )
             except ImportError as err:
                 raise NotImplementedError from err

asv_bench/benchmarks/frame_methods.py

@@ -593,8 +593,6 @@ def setup(self):
         N = 10000
         # this is the worst case, where every column has NaNs.
         arr = np.random.randn(N, 100)
-        # NB: we need to set values in array, not in df.values, otherwise
-        #  the benchmark will be misleading for ArrayManager
         arr[::2] = np.nan
 
         self.df = DataFrame(arr)

asv_bench/benchmarks/strings.py

@@ -19,7 +19,8 @@ class Dtypes:
     def setup(self, dtype):
         try:
             self.s = Series(
-                Index([f"i-{i}" for i in range(10000)], dtype=object), dtype=dtype
+                Index([f"i-{i}" for i in range(10000)], dtype=object)._values,
+                dtype=dtype,
             )
         except ImportError as err:
             raise NotImplementedError from err

ci/code_checks.sh

@@ -93,7 +93,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.TimedeltaIndex.ceil\
         pandas.PeriodIndex\
         pandas.PeriodIndex.strftime\
-        pandas.Series.clip\
         pandas.Series.rename_axis\
         pandas.Series.dt.to_period\
         pandas.Series.dt.tz_localize\
@@ -115,7 +114,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Series.plot.barh\
         pandas.Series.plot.line\
         pandas.Series.plot.pie\
-        pandas.DataFrame.clip\
         pandas.DataFrame.plot\
         pandas.DataFrame.plot.bar\
         pandas.DataFrame.plot.barh\
@@ -171,20 +169,14 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.Interval\
         pandas.Grouper\
         pandas.core.groupby.SeriesGroupBy.apply\
-        pandas.core.groupby.SeriesGroupBy.transform\
-        pandas.core.groupby.DataFrameGroupBy.transform\
         pandas.core.groupby.DataFrameGroupBy.nth\
         pandas.core.groupby.DataFrameGroupBy.rolling\
-        pandas.core.groupby.SeriesGroupBy.idxmax\
-        pandas.core.groupby.SeriesGroupBy.idxmin\
         pandas.core.groupby.SeriesGroupBy.nth\
         pandas.core.groupby.SeriesGroupBy.rolling\
         pandas.core.groupby.DataFrameGroupBy.hist\
         pandas.core.groupby.DataFrameGroupBy.plot\
-        pandas.core.groupby.SeriesGroupBy.plot\
-        pandas.core.window.rolling.Rolling.quantile\
-        pandas.core.window.expanding.Expanding.quantile\
-        pandas.api.extensions.ExtensionArray.argsort # There should be no backslash in the final line, please keep this comment in the last ignored function
+        pandas.core.groupby.DataFrameGroupBy.corrwith\
+        pandas.core.groupby.SeriesGroupBy.plot # There should be no backslash in the final line, please keep this comment in the last ignored function
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi