Merge remote-tracking branch 'upstream/main' into 59877-clines

pandas-dev · Dec 1, 2024 · f4499cc · f4499cc
2 parents e671c3b + a4fc97e
commit f4499cc
Show file tree

Hide file tree

Showing 343 changed files with 5,211 additions and 2,635 deletions.
diff --git a/.gitattributes b/.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
diff --git a/.github/actions/build_pandas/action.yml b/.github/actions/build_pandas/action.yml
@@ -22,13 +22,6 @@ runs:
         fi
       shell: bash -el {0}
 
-    - name: Uninstall nomkl
-      run: |
-        if conda list nomkl | grep nomkl 1>/dev/null; then
-          conda remove nomkl -y
-        fi
-      shell: bash -el {0}
-
     - name: Build Pandas
       run: |
         if [[ ${{ inputs.editable }} == "true" ]]; then

diff --git a/.github/workflows/code-checks.yml b/.github/workflows/code-checks.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
 
 env:
   ENV_FILE: environment.yml

diff --git a/.github/workflows/docbuild-and-upload.yml b/.github/workflows/docbuild-and-upload.yml
@@ -4,13 +4,13 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
 
 env:
   ENV_FILE: environment.yml

diff --git a/.github/workflows/package-checks.yml b/.github/workflows/package-checks.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     types: [ labeled, opened, synchronize, reopened ]
 
 permissions:
@@ -67,7 +67,7 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Python
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-name: recipe-test
           create-args: >-

diff --git a/.github/workflows/unit-tests.yml b/.github/workflows/unit-tests.yml
@@ -4,11 +4,11 @@ on:
   push:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
   pull_request:
     branches:
       - main
-      - 2.2.x
+      - 2.3.x
     paths-ignore:
       - "doc/**"
       - "web/**"
@@ -86,7 +86,6 @@ jobs:
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}
-      NPY_PROMOTION_STATE: ${{ matrix.env_file == 'actions-311-numpydev.yaml' && 'weak' || 'legacy' }}
       # Clipboard tests
       QT_QPA_PLATFORM: offscreen
       REMOVE_PYARROW: ${{ matrix.name == 'Future infer strings (without pyarrow)' && '1' || '0' }}
@@ -388,8 +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"

diff --git a/.github/workflows/wheels.yml b/.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@v2.20.0
+        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:
@@ -165,7 +161,7 @@ jobs:
           CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
 
       - name: Set up Python
-        uses: mamba-org/setup-micromamba@v1
+        uses: mamba-org/setup-micromamba@v2
         with:
           environment-name: wheel-env
           # Use a fixed Python, since we might have an unreleased Python not
@@ -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] }}

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -2,9 +2,9 @@ minimum_pre_commit_version: 2.15.0
 exclude: ^LICENSES/|\.(html|csv|svg)$
 # reserve "manual" for relatively slow hooks which we still want to run in CI
 default_stages: [
-    commit,
-    merge-commit,
-    push,
+    pre-commit,
+    pre-merge-commit,
+    pre-push,
     prepare-commit-msg,
     commit-msg,
     post-checkout,
@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.0
+    rev: v0.7.2
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -34,7 +34,7 @@ repos:
     -   id: ruff-format
         exclude: ^scripts|^pandas/tests/frame/test_query_eval.py
 -   repo: https://github.com/jendrikseipp/vulture
-    rev: 'v2.11'
+    rev: 'v2.13'
     hooks:
       - id: vulture
         entry: python scripts/run_vulture.py
@@ -52,7 +52,7 @@ repos:
     -   id: cython-lint
     -   id: double-quote-cython-strings
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.6.0
+    rev: v5.0.0
     hooks:
     -   id: check-case-conflict
     -   id: check-toml
@@ -74,7 +74,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.16.0
+    rev: v3.19.0
     hooks:
     -   id: pyupgrade
         args: [--py310-plus]
@@ -90,12 +90,12 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v0.9.1
+    rev: v1.0.0
     hooks:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v18.1.8
+    rev: v19.1.3
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
@@ -112,7 +112,7 @@ repos:
         types: [python]
         stages: [manual]
         additional_dependencies: &pyright_dependencies
-        - [email protected].352
+        - [email protected].383
     -   id: pyright
         # note: assumes python env is setup and activated
         name: pyright reportGeneralTypeIssues

diff --git a/MANIFEST.in b/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
diff --git a/ci/code_checks.sh b/ci/code_checks.sh
@@ -73,136 +73,52 @@ 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.cat.add_categories PR01,PR02" \
-        -i "pandas.Series.cat.as_ordered PR01" \
-        -i "pandas.Series.cat.as_unordered PR01" \
-        -i "pandas.Series.cat.remove_categories PR01,PR02" \
-        -i "pandas.Series.cat.remove_unused_categories PR01" \
-        -i "pandas.Series.cat.rename_categories PR01,PR02" \
-        -i "pandas.Series.cat.reorder_categories PR01,PR02" \
-        -i "pandas.Series.cat.set_categories PR01,PR02" \
-        -i "pandas.Series.dt.as_unit PR01,PR02" \
-        -i "pandas.Series.dt.ceil PR01,PR02" \
-        -i "pandas.Series.dt.day_name PR01,PR02" \
-        -i "pandas.Series.dt.floor PR01,PR02" \
-        -i "pandas.Series.dt.freq GL08" \
-        -i "pandas.Series.dt.month_name PR01,PR02" \
-        -i "pandas.Series.dt.normalize PR01" \
-        -i "pandas.Series.dt.round PR01,PR02" \
-        -i "pandas.Series.dt.strftime PR01,PR02" \
-        -i "pandas.Series.dt.to_period PR01,PR02" \
-        -i "pandas.Series.dt.total_seconds PR01" \
-        -i "pandas.Series.dt.tz_convert PR01,PR02" \
-        -i "pandas.Series.dt.tz_localize PR01,PR02" \
         -i "pandas.Series.dt.unit GL08" \
         -i "pandas.Series.pad PR01,SA01" \
-        -i "pandas.Series.sparse.from_coo PR07,SA01" \
-        -i "pandas.Series.sparse.npoints SA01" \
         -i "pandas.Timedelta.max PR02" \
         -i "pandas.Timedelta.min PR02" \
         -i "pandas.Timedelta.resolution PR02" \
-        -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -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_dict_like PR07,SA01" \
-        -i "pandas.api.types.is_file_like PR07,SA01" \
-        -i "pandas.api.types.is_float PR01,SA01" \
-        -i "pandas.api.types.is_hashable PR01,RT03,SA01" \
-        -i "pandas.api.types.is_integer PR01,SA01" \
-        -i "pandas.api.types.is_iterator PR07,SA01" \
-        -i "pandas.api.types.is_named_tuple PR07,SA01" \
-        -i "pandas.api.types.is_re PR07,SA01" \
-        -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.DatetimeArray SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
-        -i "pandas.arrays.IntervalArray.left 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.__iter__ RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.agg RT03" \
-        -i "pandas.core.groupby.DataFrameGroupBy.aggregate RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
-        -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" \
-        -i "pandas.core.groupby.DataFrameGroupBy.ohlc SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.sem SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.agg RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.aggregate RT03" \
         -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.ohlc SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.sem SA01" \
-        -i "pandas.core.resample.Resampler.__iter__ RT03,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" \
-        -i "pandas.core.resample.Resampler.ohlc SA01" \
         -i "pandas.core.resample.Resampler.prod SA01" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \
         -i "pandas.core.resample.Resampler.sem SA01" \
         -i "pandas.core.resample.Resampler.std SA01" \
-        -i "pandas.core.resample.Resampler.sum 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.CSSWarning SA01" \
-        -i "pandas.errors.CategoricalConversionWarning SA01" \
-        -i "pandas.errors.ChainedAssignmentError SA01" \
-        -i "pandas.errors.ClosedFileError SA01" \
-        -i "pandas.errors.DataError SA01" \
-        -i "pandas.errors.DuplicateLabelError SA01" \
         -i "pandas.errors.IntCastingNaNError SA01" \
-        -i "pandas.errors.InvalidIndexError SA01" \
-        -i "pandas.errors.InvalidVersion SA01" \
         -i "pandas.errors.NullFrequencyError SA01" \
-        -i "pandas.errors.NumExprClobberingError SA01" \
         -i "pandas.errors.NumbaUtilError SA01" \
-        -i "pandas.errors.OptionError SA01" \
-        -i "pandas.errors.OutOfBoundsDatetime SA01" \
-        -i "pandas.errors.OutOfBoundsTimedelta SA01" \
         -i "pandas.errors.PerformanceWarning SA01" \
-        -i "pandas.errors.PossibleDataLossError SA01" \
-        -i "pandas.errors.PossiblePrecisionLoss SA01" \
-        -i "pandas.errors.SpecificationError SA01" \
         -i "pandas.errors.UndefinedVariableError PR01,SA01" \
-        -i "pandas.errors.UnsortedIndexError SA01" \
-        -i "pandas.errors.UnsupportedFunctionCall 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.StataReader.data_label SA01" \
-        -i "pandas.io.stata.StataReader.value_labels RT03,SA01" \
-        -i "pandas.io.stata.StataReader.variable_labels RT03,SA01" \
         -i "pandas.io.stata.StataWriter.write_file SA01" \
-        -i "pandas.json_normalize RT03,SA01" \
-        -i "pandas.period_range RT03,SA01" \
         -i "pandas.plotting.andrews_curves RT03,SA01" \
-        -i "pandas.plotting.lag_plot RT03,SA01" \
         -i "pandas.plotting.scatter_matrix PR07,SA01" \
-        -i "pandas.set_eng_float_format RT03,SA01" \
-        -i "pandas.testing.assert_extension_array_equal SA01" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
@@ -348,7 +264,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.Second.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Second.n GL08" \
         -i "pandas.tseries.offsets.Second.normalize GL08" \
-        -i "pandas.tseries.offsets.SemiMonthBegin SA01" \
         -i "pandas.tseries.offsets.SemiMonthBegin.day_of_month GL08" \
         -i "pandas.tseries.offsets.SemiMonthBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.SemiMonthBegin.n GL08" \

diff --git a/ci/deps/actions-310-minimum_versions.yaml b/ci/deps/actions-310-minimum_versions.yaml
@@ -7,9 +7,9 @@ dependencies:
   - python=3.10
 
   # build dependencies
-  - versioneer[toml]
+  - versioneer
   - cython>=0.29.33
-  - meson[ninja]=1.2.1
+  - meson=1.2.1
   - meson-python=0.13.1
 
   # test dependencies