Merge remote-tracking branch 'upstream/main' into #60365-enforce-numpy-docstring-validation

Author: thedataninja1786

.gitattributes

@@ -85,4 +85,5 @@ pandas/tests/io/parser/data export-ignore
 
 # Include cibw script in sdist since it's needed for building wheels
 scripts/cibw_before_build.sh -export-ignore
-scripts/cibw_before_test.sh -export-ignore
+scripts/cibw_before_build_windows.sh -export-ignore
+scripts/cibw_before_test_windows.sh -export-ignore

.github/workflows/unit-tests.yml

@@ -387,8 +387,8 @@ jobs:
       - name: Build Environment
         run: |
           python --version
-          python -m pip install --upgrade pip setuptools wheel meson[ninja]==1.2.1 meson-python==0.13.1
-          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy cython
+          python -m pip install --upgrade pip setuptools wheel numpy meson[ninja]==1.2.1 meson-python==0.13.1
+          python -m pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple cython
           python -m pip install versioneer[toml]
           python -m pip install python-dateutil pytz tzdata hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0 pytest-cov
           python -m pip install -ve . --no-build-isolation --no-index --no-deps -Csetup-args="--werror"

.github/workflows/wheels.yml

@@ -111,10 +111,6 @@ jobs:
         - buildplat: [ubuntu-22.04, pyodide_wasm32]
           python: ["cp312", "3.12"]
           cibw_build_frontend: 'build'
-        # TODO: Build free-threaded wheels for Windows
-        exclude:
-        - buildplat: [windows-2022, win_amd64]
-          python: ["cp313t", "3.13"]
 
     env:
       IS_PUSH: ${{ github.event_name == 'push' && startsWith(github.ref, 'refs/tags/v') }}
@@ -156,7 +152,7 @@ jobs:
         run: echo "sdist_name=$(cd ./dist && ls -d */)" >> "$GITHUB_ENV"
 
       - name: Build wheels
-        uses: pypa/cibuildwheel@v2.21.3
+        uses: pypa/cibuildwheel@v2.22.0
         with:
          package-dir: ./dist/${{ startsWith(matrix.buildplat[1], 'macosx') && env.sdist_name || needs.build_sdist.outputs.sdist_file }}
         env:
@@ -181,20 +177,6 @@ jobs:
         shell: bash -el {0}
         run: for whl in $(ls wheelhouse); do wheel unpack wheelhouse/$whl -d /tmp; done
 
-      # Testing on windowsservercore instead of GHA runner to fail on missing DLLs
-      - name: Test Windows Wheels
-        if: ${{ matrix.buildplat[1] == 'win_amd64' }}
-        shell: pwsh
-        run: |
-          $TST_CMD = @"
-          python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
-          python -m pip install `$(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`\"])`';
-          "@
-          # add rc to the end of the image name if the Python version is unreleased
-          docker pull python:${{ matrix.python[1] == '3.13' && '3.13-rc' || format('{0}-windowsservercore', matrix.python[1]) }}
-          docker run --env PANDAS_CI='1' -v ${PWD}:C:\pandas python:${{ matrix.python[1] == '3.13' && '3.13-rc' || format('{0}-windowsservercore', matrix.python[1]) }} powershell -Command $TST_CMD
-
       - uses: actions/upload-artifact@v4
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.7.2
+    rev: v0.8.1
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -47,7 +47,7 @@ repos:
         types_or: [python, rst, markdown, cython, c]
         additional_dependencies: [tomli]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.16.2
+    rev: v0.16.6
     hooks:
     -   id: cython-lint
     -   id: double-quote-cython-strings
@@ -95,7 +95,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.3
+    rev: v19.1.4
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

MANIFEST.in

@@ -65,3 +65,5 @@ graft pandas/_libs/include
 
 # Include cibw script in sdist since it's needed for building wheels
 include scripts/cibw_before_build.sh
+include scripts/cibw_before_build_windows.sh
+include scripts/cibw_before_test_windows.sh

asv_bench/benchmarks/groupby.py

@@ -511,8 +511,7 @@ def setup(self, dtype, method, application, ncols, engine):
         # grouping on multiple columns
         # and we lack kernels for a bunch of methods
         if (
-            engine == "numba"
-            and method in _numba_unsupported_methods
+            (engine == "numba" and method in _numba_unsupported_methods)
             or ncols > 1
             or application == "transformation"
             or dtype == "datetime"

ci/code_checks.sh

@@ -73,44 +73,33 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.RangeIndex.from_range PR01,SA01" \
-        -i "pandas.Series.dt.freq GL08" \
         -i "pandas.Series.dt.unit GL08" \
         -i "pandas.Series.pad PR01,SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
-        -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
-        -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.types.is_re_compilable PR07,SA01" \
-        -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
-        -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
-        -i "pandas.arrays.IntervalArray.right SA01" \
         -i "pandas.arrays.NumpyExtensionArray SA01" \
-        -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
+<<<<<<< HEAD
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
+=======
+        -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
+>>>>>>> upstream/main
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
         -i "pandas.core.resample.Resampler.get_group RT03,SA01" \
-        -i "pandas.core.resample.Resampler.groups SA01" \
-        -i "pandas.core.resample.Resampler.indices SA01" \
         -i "pandas.core.resample.Resampler.max PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.mean SA01" \
         -i "pandas.core.resample.Resampler.min PR01,RT03,SA01" \
@@ -120,24 +109,12 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.resample.Resampler.std SA01" \
         -i "pandas.core.resample.Resampler.transform PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.var SA01" \
-        -i "pandas.errors.AttributeConflictWarning SA01" \
-        -i "pandas.errors.ChainedAssignmentError SA01" \
-        -i "pandas.errors.DataError SA01" \
-        -i "pandas.errors.DuplicateLabelError SA01" \
-        -i "pandas.errors.IntCastingNaNError SA01" \
-        -i "pandas.errors.InvalidIndexError SA01" \
         -i "pandas.errors.NullFrequencyError SA01" \
-        -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
-        -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
-        -i "pandas.errors.PossibleDataLossError SA01" \
         -i "pandas.errors.UndefinedVariableError PR01,SA01" \
-        -i "pandas.errors.UnsortedIndexError SA01" \
         -i "pandas.errors.ValueLabelTypeMismatch SA01" \
-        -i "pandas.infer_freq SA01" \
         -i "pandas.io.json.build_table_schema PR07,RT03,SA01" \
-        -i "pandas.io.stata.StataWriter.write_file SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \

doc/source/conf.py

@@ -242,7 +242,6 @@
     "external_links": [],
     "footer_start": ["pandas_footer", "sphinx-version"],
     "github_url": "https://github.com/pandas-dev/pandas",
-    "twitter_url": "https://twitter.com/pandas_dev",
     "analytics": {
         "plausible_analytics_domain": "pandas.pydata.org",
         "plausible_analytics_url": "https://views.scientific-python.org/js/script.js",
@@ -258,6 +257,11 @@
     # patch version doesn't compare as equal (e.g. 2.2.1 != 2.2.0 but it should be)
     "show_version_warning_banner": False,
     "icon_links": [
+        {
+            "name": "X",
+            "url": "https://x.com/pandas_dev",
+            "icon": "fa-brands fa-square-x-twitter",
+        },
         {
             "name": "Mastodon",
             "url": "https://fosstodon.org/@pandas_dev",

doc/source/development/contributing_docstring.rst

@@ -940,7 +940,7 @@ Finally, docstrings can also be appended to with the ``doc`` decorator.
 
 In this example, we'll create a parent docstring normally (this is like
 ``pandas.core.generic.NDFrame``). Then we'll have two children (like
-``pandas.core.series.Series`` and ``pandas.DataFrame``). We'll
+``pandas.Series`` and ``pandas.DataFrame``). We'll
 substitute the class names in this docstring.
 
 .. code-block:: python
@@ -995,5 +995,5 @@ mapping function names to docstrings. Wherever possible, we prefer using
 ``doc``, since the docstring-writing processes is slightly closer to normal.
 
 See ``pandas.core.generic.NDFrame.fillna`` for an example template, and
-``pandas.core.series.Series.fillna`` and ``pandas.core.generic.frame.fillna``
+``pandas.Series.fillna`` and ``pandas.core.generic.frame.fillna``
 for the filled versions.