Merge branch 'pandas-dev:main' into patch-1

Author: fawazahmed0

.gitattributes

@@ -68,7 +68,7 @@ ci export-ignore
 doc export-ignore
 gitpod export-ignore
 MANIFEST.in export-ignore
-scripts export-ignore
+scripts/** export-ignore
 typings export-ignore
 web export-ignore
 CITATION.cff export-ignore
@@ -82,3 +82,7 @@ setup.py export-ignore
 # csv_dir_path fixture checks the existence of the directory
 # exclude the whole directory to avoid running related tests in sdist
 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

.github/workflows/unit-tests.yml

@@ -57,6 +57,9 @@ 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: "Future infer strings"
+            env_file: actions-311.yaml
+            pandas_future_infer_string: "1"
           - name: "Pypy"
             env_file: actions-pypy-39.yaml
             pattern: "not slow and not network and not single_cpu"
@@ -75,6 +78,7 @@ jobs:
       LANG: ${{ matrix.lang || 'C.UTF-8' }}
       LC_ALL: ${{ matrix.lc_all || '' }}
       PANDAS_CI: '1'
+      PANDAS_FUTURE_INFER_STRING: ${{ matrix.pandas_future_infer_string || '0' }}
       TEST_ARGS: ${{ matrix.test_args || '' }}
       PYTEST_WORKERS: 'auto'
       PYTEST_TARGET: ${{ matrix.pytest_target || 'pandas' }}

.github/workflows/wheels.yml

@@ -99,14 +99,25 @@ jobs:
         - [macos-14, macosx_arm64]
         - [windows-2022, win_amd64]
         # TODO: support PyPy?
-        python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"]]
-
+        python: [["cp310", "3.10"], ["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"]]
+        include:
+        # TODO: Remove this plus installing build deps in cibw_before_build.sh
+        # and test deps in cibw_before_test.sh after pandas can be built with a released NumPy/Cython
+        - python: ["cp313", "3.13"]
+          cibw_build_frontend: 'pip; args: --no-build-isolation'
+        - python: ["cp313t", "3.13"]
+          cibw_build_frontend: 'pip; args: --no-build-isolation'
         # Build Pyodide wheels and upload them to Anaconda.org
         # NOTE: this job is similar to the one in unit-tests.yml except for the fact
         # that it uses cibuildwheel instead of a standard Pyodide xbuildenv setup.
-        include:
-          - buildplat: [ubuntu-22.04, pyodide_wasm32]
-            python: ["cp312", "3.12"]
+        - 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') }}
       IS_SCHEDULE_DISPATCH: ${{ github.event_name == 'schedule' || github.event_name == 'workflow_dispatch' }}
@@ -153,6 +164,7 @@ jobs:
         env:
           CIBW_PRERELEASE_PYTHONS: True
           CIBW_BUILD: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
+          CIBW_BUILD_FRONTEND: ${{ matrix.cibw_build_frontend || 'pip' }}
           CIBW_PLATFORM: ${{ matrix.buildplat[1] == 'pyodide_wasm32' && 'pyodide' || 'auto' }}
 
       - name: Set up Python
@@ -176,15 +188,17 @@ jobs:
       - name: Test Windows Wheels
         if: ${{ matrix.buildplat[1] == 'win_amd64' }}
         shell: pwsh
+        # TODO: Remove NumPy nightly install when there's a 3.13 wheel on PyPI
         run: |
           $TST_CMD = @"
           python -m pip install hypothesis>=6.84.0 pytest>=7.3.2 pytest-xdist>=3.4.0;
+          ${{ matrix.python[1] == '3.13' && 'python -m pip install -i https://pypi.anaconda.org/scientific-python-nightly-wheels/simple numpy;' }}
           python -m pip install `$(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] == '3.12' && '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 $TST_CMD
+          docker pull python:${{ 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:

MANIFEST.in

@@ -62,3 +62,7 @@ prune pandas/tests/io/parser/data
 # Selectively re-add *.cxx files that were excluded above
 graft pandas/_libs/src
 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_test.sh

README.md

@@ -96,7 +96,7 @@ The source code is currently hosted on GitHub at:
 https://github.com/pandas-dev/pandas
 
 Binary installers for the latest released version are available at the [Python
-Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://docs.conda.io/en/latest/).
+Package Index (PyPI)](https://pypi.org/project/pandas) and on [Conda](https://anaconda.org/conda-forge/pandas).
 
 ```sh
 # conda

ci/code_checks.sh

@@ -70,16 +70,10 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         --format=actions \
         -i ES01 `# For now it is ok if docstrings are missing the extended summary` \
         -i "pandas.Series.dt PR01" `# Accessors are implemented as classes, but we do not document the Parameters section` \
-        -i "pandas.MultiIndex.append PR07,SA01" \
-        -i "pandas.MultiIndex.copy PR07,RT03,SA01" \
         -i "pandas.MultiIndex.get_level_values SA01" \
-        -i "pandas.MultiIndex.get_loc PR07" \
         -i "pandas.MultiIndex.get_loc_level PR07" \
-        -i "pandas.MultiIndex.levshape SA01" \
         -i "pandas.MultiIndex.names SA01" \
-        -i "pandas.MultiIndex.remove_unused_levels RT03,SA01" \
         -i "pandas.MultiIndex.reorder_levels RT03,SA01" \
-        -i "pandas.MultiIndex.set_levels RT03,SA01" \
         -i "pandas.MultiIndex.sortlevel PR07,SA01" \
         -i "pandas.MultiIndex.to_frame RT03" \
         -i "pandas.NA SA01" \
@@ -223,7 +217,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timestamp.fromordinal SA01" \
         -i "pandas.Timestamp.fromtimestamp PR01,SA01" \
         -i "pandas.Timestamp.hour GL08" \
-        -i "pandas.Timestamp.isoweekday SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.microsecond GL08" \
         -i "pandas.Timestamp.min PR02" \
@@ -304,10 +297,8 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.api.types.is_re PR07,SA01" \
         -i "pandas.api.types.is_re_compilable PR07,SA01" \
         -i "pandas.api.types.is_sparse SA01" \
-        -i "pandas.api.types.is_string_dtype SA01" \
         -i "pandas.api.types.is_timedelta64_ns_dtype SA01" \
         -i "pandas.api.types.pandas_dtype PR07,RT03,SA01" \
-        -i "pandas.api.types.union_categoricals RT03,SA01" \
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.BooleanArray SA01" \
         -i "pandas.arrays.DatetimeArray SA01" \
@@ -330,7 +321,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.indices SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.max SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.median SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.min SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.nth PR02" \
         -i "pandas.core.groupby.DataFrameGroupBy.nunique SA01" \
@@ -349,7 +339,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_decreasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.is_monotonic_increasing SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.max SA01" \
-        -i "pandas.core.groupby.SeriesGroupBy.median SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.min SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.nth PR02" \
         -i "pandas.core.groupby.SeriesGroupBy.ohlc SA01" \
@@ -364,7 +353,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -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.median SA01" \
         -i "pandas.core.resample.Resampler.min PR01,RT03,SA01" \
         -i "pandas.core.resample.Resampler.ohlc SA01" \
         -i "pandas.core.resample.Resampler.prod SA01" \

doc/source/getting_started/comparison/comparison_with_sql.rst

@@ -505,7 +505,7 @@ DELETE
     DELETE FROM tips
     WHERE tip > 9;
 
-In pandas we select the rows that should remain instead of deleting them:
+In pandas we select the rows that should remain instead of deleting the rows that should be removed:
 
 .. ipython:: python
 

doc/source/user_guide/pyarrow.rst

@@ -159,9 +159,11 @@ PyArrow also provides IO reading functionality that has been integrated into sev
 functions provide an ``engine`` keyword that can dispatch to PyArrow to accelerate reading from an IO source.
 
 * :func:`read_csv`
+* :func:`read_feather`
 * :func:`read_json`
 * :func:`read_orc`
-* :func:`read_feather`
+* :func:`read_parquet`
+* :func:`read_table` (experimental)
 
 .. ipython:: python
 

doc/source/user_guide/style.ipynb

@@ -351,7 +351,7 @@
     "\n",
     "- Using [.set_table_styles()][table] to control broader areas of the table with specified internal CSS. Although table styles allow the flexibility to add CSS selectors and properties controlling all individual parts of the table, they are unwieldy for individual cell specifications. Also, note that table styles cannot be exported to Excel. \n",
     "- Using [.set_td_classes()][td_class] to directly link either external CSS classes to your data cells or link the internal CSS classes created by [.set_table_styles()][table]. See [here](#Setting-Classes-and-Linking-to-External-CSS). These cannot be used on column header rows or indexes, and also won't export to Excel. \n",
-    "- Using the [.apply()][apply] and [.map()][map] functions to add direct internal CSS to specific data cells. See [here](#Styler-Functions). As of v1.4.0 there are also methods that work directly on column header rows or indexes; [.apply_index()][applyindex] and [.map_index()][mapindex]. Note that only these methods add styles that will export to Excel. These methods work in a similar way to [DataFrame.apply()][dfapply] and [DataFrame.map()][dfmap].\n",
+    "- Using the [.apply()][apply] and [.map()][map] functions to add direct internal CSS to specific data cells. See [here](#Styler-Functions). As of v1.4.0 there are also methods that work directly on column header rows or indexes: [.apply_index()][applyindex] and [.map_index()][mapindex]. Note that only these methods add styles that will export to Excel. These methods work in a similar way to [DataFrame.apply()][dfapply] and [DataFrame.map()][dfmap].\n",
     "\n",
     "[table]: ../reference/api/pandas.io.formats.style.Styler.set_table_styles.rst\n",
     "[styler]: ../reference/api/pandas.io.formats.style.Styler.rst\n",

doc/source/user_guide/text.rst

@@ -204,7 +204,7 @@ and replacing any remaining whitespaces with underscores:
 
 .. warning::
 
-    The type of the Series is inferred and the allowed types (i.e. strings).
+    The type of the Series is inferred and is one among the allowed types (i.e. strings).
 
     Generally speaking, the ``.str`` accessor is intended to work only on strings. With very few
     exceptions, other uses are not supported, and may be disabled at a later point.