Merge branch 'main' into doc/clarify-categorical-map

Author: Talyahav17

.github/workflows/wheels.yml

@@ -13,6 +13,8 @@
 name: Wheel builder
 
 on:
+  release:
+    types: [published]
   schedule:
   # 3:27 UTC every day
   - cron: "27 3 * * *"
@@ -101,7 +103,7 @@ jobs:
         - [macos-14, macosx_arm64]
         - [windows-2022, win_amd64]
         - [windows-11-arm, win_arm64]
-        python: [["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"]]
+        python: [["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"], ["cp314", "3.14"], ["cp314t", "3.14"]]
         include:
         # 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
@@ -216,3 +218,41 @@ jobs:
           source ci/upload_wheels.sh
           set_upload_vars
           upload_wheels
+
+  publish:
+    if: >
+      github.repository == 'pandas-dev/pandas' &&
+      github.event_name == 'release' &&
+      startsWith(github.ref, 'refs/tags/v')
+
+    needs:
+      - build_sdist
+      - build_wheels
+
+    runs-on: ubuntu-latest
+
+    environment:
+      name: pypi
+    permissions:
+      id-token: write         # OIDC for Trusted Publishing
+      contents: read
+
+    steps:
+      - name: Download all artefacts
+        uses: actions/download-artifact@v4
+        with:
+          path: dist          # everything lands in ./dist/**
+
+      - name: Collect files
+        run: |
+          mkdir -p upload
+          # skip any wheel that contains 'pyodide'
+          find dist -name '*pyodide*.whl' -prune -o \
+                    -name '*.whl'   -exec mv {} upload/ \;
+          find dist -name '*.tar.gz' -exec mv {} upload/ \;
+
+      - name: Publish to **PyPI** (Trusted Publishing)
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          packages-dir: upload
+          skip-existing: true

doc/source/development/contributing_codebase.rst

@@ -214,7 +214,8 @@ With custom types and inference this is not always possible so exceptions are ma
 pandas-specific types
 ~~~~~~~~~~~~~~~~~~~~~
 
-Commonly used types specific to pandas will appear in `pandas._typing <https://github.com/pandas-dev/pandas/blob/main/pandas/_typing.py>`_ and you should use these where applicable. This module is private for now but ultimately this should be exposed to third party libraries who want to implement type checking against pandas.
+Commonly used types specific to pandas will appear in `pandas._typing <https://github.com/pandas-dev/pandas/blob/main/pandas/_typing.py>`__ and you should use these where applicable. This module is private and is meant for pandas development.
+Types that are meant for user consumption should be exposed in `pandas.api.typing.aliases <https://github.com/pandas-dev/pandas/blob/main/pandas/api/typing/aliases.py>`__ and ideally added to the `pandas-stubs <https://github.com/pandas-dev/pandas-stubs>`__ project.
 
 For example, quite a few functions in pandas accept a ``dtype`` argument. This can be expressed as a string like ``"object"``, a ``numpy.dtype`` like ``np.int64`` or even a pandas ``ExtensionDtype`` like ``pd.CategoricalDtype``. Rather than burden the user with having to constantly annotate all of those options, this can simply be imported and reused from the pandas._typing module
 

doc/source/development/maintaining.rst

@@ -451,9 +451,10 @@ which will be triggered when the tag is pushed.
    - Set as the latest release: Leave checked, unless releasing a patch release for an older version
      (e.g. releasing 1.4.5 after 1.5 has been released)
 
-5. Upload wheels to PyPI::
-
-    twine upload pandas/dist/pandas-<version>*.{whl,tar.gz} --skip-existing
+5. Verify wheels are uploaded automatically by GitHub Actions
+   via `**Trusted Publishing** <https://docs.pypi.org/trusted-publishers/>`__
+   when the GitHub `*Release* <https://docs.github.com/en/repositories/releasing-projects-on-github/about-releases>`__
+   is published. Do not run ``twine upload`` manually.
 
 6. The GitHub release will after some hours trigger an
    `automated conda-forge PR <https://github.com/conda-forge/pandas-feedstock/pulls>`_.

doc/source/getting_started/index.rst

@@ -527,7 +527,6 @@ Data sets often contain more than just numerical data. pandas provides a wide ra
                 </div>
             </div>
         </div>
-
     </div>
     </div>
 

doc/source/getting_started/intro_tutorials/03_subset_data.rst

@@ -54,6 +54,8 @@ I’m interested in the age of the Titanic passengers.
 To select a single column, use square brackets ``[]`` with the column
 name of the column of interest.
 
+For more explanation, see `Brackets in Python and pandas <https://python-public-policy.afeld.me/en/columbia/brackets.html>`__.
+
 .. raw:: html
 
         </li>

doc/source/reference/aliases.rst

@@ -0,0 +1,96 @@
+{{ header }}
+
+.. _api.typing.aliases:
+
+======================================
+pandas typing aliases
+======================================
+
+**************
+Typing aliases
+**************
+
+.. currentmodule:: pandas.api.typing.aliases
+
+The typing declarations in ``pandas/_typing.py`` are considered private, and used
+by pandas developers for type checking of the pandas code base.  For users, it is
+highly recommended to use the ``pandas-stubs`` package that represents the officially
+supported type declarations for users of pandas.
+They are documented here for users who wish to use these declarations in their
+own python code that calls pandas or expects certain results.
+
+.. warning::
+
+    Note that the definitions and use cases of these aliases are subject to change without notice in any major, minor, or patch release of pandas.
+
+Each of these aliases listed in the table below can be found by importing them from :py:mod:`pandas.api.typing.aliases`.
+
+==================================== ================================================================
+Alias                                Meaning
+==================================== ================================================================
+:py:type:`AggFuncType`               Type of functions that can be passed to :meth:`agg` methods
+:py:type:`AlignJoin`                 Argument type for ``join`` in :meth:`DataFrame.join`
+:py:type:`AnyAll`                    Argument type for ``how`` in :meth:`dropna`
+:py:type:`AnyArrayLike`              Used to represent :class:`ExtensionArray`, ``numpy`` arrays, :class:`Index` and :class:`Series`
+:py:type:`ArrayLike`                 Used to represent :class:`ExtensionArray`, ``numpy`` arrays
+:py:type:`AstypeArg`                 Argument type in :meth:`astype`
+:py:type:`Axes`                      :py:type:`AnyArrayLike` plus sequences (not strings) and ``range``
+:py:type:`Axis`                      Argument type for ``axis`` in many methods
+:py:type:`CSVEngine`                 Argument type for ``engine`` in :meth:`DataFrame.read_csv`
+:py:type:`ColspaceArgType`           Argument type for ``colspace`` in :meth:`DataFrame.to_html`
+:py:type:`CompressionOptions`        Argument type for ``compression`` in all I/O output methods except :meth:`DataFrame.to_parquet`
+:py:type:`CorrelationMethod`         Argument type for ``correlation`` in :meth:`corr`
+:py:type:`DropKeep`                  Argument type for ``keep`` in :meth:`drop_duplicates`
+:py:type:`Dtype`                     Types as objects that can be used to specify dtypes
+:py:type:`DtypeArg`                  Argument type for ``dtype`` in various methods
+:py:type:`DtypeBackend`              Argument type for ``dtype_backend`` in various methods
+:py:type:`DtypeObj`                  Numpy dtypes and Extension dtypes
+:py:type:`ExcelWriterIfSheetExists`  Argument type for ``if_sheet_exists`` in :class:`ExcelWriter`
+:py:type:`ExcelWriterMergeCells`     Argument type for ``merge_cells`` in :meth:`to_excel`
+:py:type:`FilePath`                  Type of paths for files for I/O methods
+:py:type:`FillnaOptions`             Argument type for ``method`` in various methods where NA values are filled
+:py:type:`FloatFormatType`           Argument type for ``float_format`` in :meth:`to_string`
+:py:type:`FormattersType`            Argument type for ``formatters`` in :meth:`to_string`
+:py:type:`FromDictOrient`            Argument type for ``orient`` in :meth:`DataFrame.from_dict`
+:py:type:`HTMLFlavors`               Argument type for ``flavor`` in :meth:`pandas.read_html`
+:py:type:`IgnoreRaise`               Argument type for ``errors`` in multiple methods
+:py:type:`IndexLabel`                Argument type for ``level`` in multiple methods
+:py:type:`InterpolateOptions`        Argument type for ``interpolate`` in :meth:`interpolate`
+:py:type:`JSONEngine`                Argument type for ``engine`` in :meth:`read_json`
+:py:type:`JSONSerializable`          Argument type for the return type of a callable for argument ``default_handler`` in :meth:`to_json`
+:py:type:`JoinHow`                   Argument type for ``how`` in :meth:`pandas.merge_ordered` and for ``join`` in :meth:`Series.align`
+:py:type:`JoinValidate`              Argument type for ``validate`` in :meth:`DataFrame.join`
+:py:type:`MergeHow`                  Argument type for ``how`` in :meth:`merge`
+:py:type:`MergeValidate`             Argument type for ``validate`` in :meth:`merge`
+:py:type:`NaPosition`                Argument type for ``na_position`` in :meth:`sort_index` and :meth:`sort_values`
+:py:type:`NsmallestNlargestKeep`     Argument type for ``keep`` in :meth:`nlargest` and :meth:`nsmallest`
+:py:type:`OpenFileErrors`            Argument type for ``errors`` in :meth:`to_hdf` and :meth:`to_csv`
+:py:type:`Ordered`                   Return type for :py:attr:`ordered`` in :class:`CategoricalDtype` and :class:`Categorical`
+:py:type:`ParquetCompressionOptions` Argument type for ``compression`` in :meth:`DataFrame.to_parquet`
+:py:type:`QuantileInterpolation`     Argument type for ``interpolation`` in :meth:`quantile`
+:py:type:`ReadBuffer`                Additional argument type corresponding to buffers for various file reading methods
+:py:type:`ReadCsvBuffer`             Additional argument type corresponding to buffers for :meth:`pandas.read_csv`
+:py:type:`ReadPickleBuffer`          Additional argument type corresponding to buffers for :meth:`pandas.read_pickle`
+:py:type:`ReindexMethod`             Argument type for ``reindex`` in :meth:`reindex`
+:py:type:`Scalar`                    Types that can be stored in :class:`Series` with non-object dtype
+:py:type:`SequenceNotStr`            Used for arguments that require sequences, but not plain strings
+:py:type:`SliceType`                 Argument types for ``start`` and ``end`` in :meth:`Index.slice_locs`
+:py:type:`SortKind`                  Argument type for ``kind`` in :meth:`sort_index` and :meth:`sort_values`
+:py:type:`StorageOptions`            Argument type for ``storage_options`` in various file output methods
+:py:type:`Suffixes`                  Argument type for ``suffixes`` in :meth:`merge`, :meth:`compare` and :meth:`merge_ordered`
+:py:type:`TakeIndexer`               Argument type for ``indexer`` and ``indices`` in :meth:`take`
+:py:type:`TimeAmbiguous`             Argument type for ``ambiguous`` in time operations
+:py:type:`TimeGrouperOrigin`         Argument type for ``origin`` in :meth:`resample` and :class:`TimeGrouper`
+:py:type:`TimeNonexistent`           Argument type for ``nonexistent`` in time operations
+:py:type:`TimeUnit`                  Time unit argument and return type for :py:attr:`unit`, arguments ``unit`` and ``date_unit``
+:py:type:`TimedeltaConvertibleTypes` Argument type for ``offset`` in :meth:`resample`, ``halflife`` in :meth:`ewm` and ``start`` and ``end`` in :meth:`pandas.timedelta_range`
+:py:type:`TimestampConvertibleTypes` Argument type for ``origin`` in :meth:`resample` and :meth:`pandas.to_datetime`
+:py:type:`ToStataByteorder`          Argument type for ``byteorder`` in :meth:`DataFrame.to_stata`
+:py:type:`ToTimestampHow`            Argument type for ``how`` in :meth:`to_timestamp` and ``convention`` in :meth:`resample`
+:py:type:`UpdateJoin`                Argument type for ``join`` in :meth:`DataFrame.update`
+:py:type:`UsecolsArgType`            Argument type for ``usecols`` in :meth:`pandas.read_clipboard`, :meth:`pandas.read_csv` and :meth:`pandas.read_excel`
+:py:type:`WindowingRankType`         Argument type for ``method`` in :meth:`rank`` in rolling and expanding window operations
+:py:type:`WriteBuffer`               Additional argument type corresponding to buffers for various file output methods
+:py:type:`WriteExcelBuffer`          Additional argument type corresponding to buffers for :meth:`to_excel`
+:py:type:`XMLParsers`                Argument type for ``parser`` in :meth:`DataFrame.to_xml` and :meth:`pandas.read_xml`
+==================================== ================================================================

doc/source/reference/index.rst

@@ -55,6 +55,7 @@ to be stable.
    extensions
    testing
    missing_value
+   aliases
 
 .. This is to prevent warnings in the doc build. We don't want to encourage
 .. these methods.

doc/source/whatsnew/v3.0.0.rst

@@ -220,11 +220,13 @@ Other enhancements
 - Implemented :meth:`Series.str.isascii` and :meth:`Series.str.isascii` (:issue:`59091`)
 - Improve the resulting dtypes in :meth:`DataFrame.where` and :meth:`DataFrame.mask` with :class:`ExtensionDtype` ``other`` (:issue:`62038`)
 - Improved deprecation message for offset aliases (:issue:`60820`)
+- Many type aliases are now exposed in the new submodule :py:mod:`pandas.api.typing.aliases` (:issue:`55231`)
 - Multiplying two :class:`DateOffset` objects will now raise a ``TypeError`` instead of a ``RecursionError`` (:issue:`59442`)
 - Restore support for reading Stata 104-format and enable reading 103-format dta files (:issue:`58554`)
 - Support passing a :class:`Iterable[Hashable]` input to :meth:`DataFrame.drop_duplicates` (:issue:`59237`)
 - Support reading Stata 102-format (Stata 1) dta files (:issue:`58978`)
 - Support reading Stata 110-format (Stata 7) dta files (:issue:`47176`)
+- Switched wheel upload to **PyPI Trusted Publishing** (OIDC) for release-tag pushes in ``wheels.yml``. (:issue:`61718`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_typing.py

@@ -133,8 +133,27 @@ def __reversed__(self) -> Iterator[_T_co]: ...
 
 PythonScalar: TypeAlias = str | float | bool
 DatetimeLikeScalar: TypeAlias = Union["Period", "Timestamp", "Timedelta"]
-PandasScalar: TypeAlias = Union["Period", "Timestamp", "Timedelta", "Interval"]
-Scalar: TypeAlias = PythonScalar | PandasScalar | np.datetime64 | np.timedelta64 | date
+
+# aligned with pandas-stubs - typical scalars found in Series.  Explicitly leaves
+# out object
+_IndexIterScalar: TypeAlias = Union[
+    str,
+    bytes,
+    date,
+    datetime,
+    timedelta,
+    np.datetime64,
+    np.timedelta64,
+    bool,
+    int,
+    float,
+    "Timestamp",
+    "Timedelta",
+]
+Scalar: TypeAlias = Union[
+    _IndexIterScalar, "Interval", complex, np.integer, np.floating, np.complexfloating
+]
+
 IntStrT = TypeVar("IntStrT", bound=int | str)
 
 # timestamp and timedelta convertible types
@@ -312,6 +331,9 @@ def closed(self) -> bool:
 CompressionOptions: TypeAlias = (
     Literal["infer", "gzip", "bz2", "zip", "xz", "zstd", "tar"] | CompressionDict | None
 )
+ParquetCompressionOptions: TypeAlias = (
+    Literal["snappy", "gzip", "brotli", "lz4", "zstd"] | None
+)
 
 # types in DataFrameFormatter
 FormattersType: TypeAlias = (

pandas/api/typing/aliases.py

@@ -0,0 +1,135 @@
+from pandas._typing import (
+    AggFuncType,
+    AlignJoin,
+    AnyAll,
+    AnyArrayLike,
+    ArrayLike,
+    AstypeArg,
+    Axes,
+    Axis,
+    ColspaceArgType,
+    CompressionOptions,
+    CorrelationMethod,
+    CSVEngine,
+    DropKeep,
+    Dtype,
+    DtypeArg,
+    DtypeBackend,
+    DtypeObj,
+    ExcelWriterIfSheetExists,
+    ExcelWriterMergeCells,
+    FilePath,
+    FillnaOptions,
+    FloatFormatType,
+    FormattersType,
+    FromDictOrient,
+    HTMLFlavors,
+    IgnoreRaise,
+    IndexLabel,
+    InterpolateOptions,
+    JoinHow,
+    JoinValidate,
+    JSONEngine,
+    JSONSerializable,
+    MergeHow,
+    MergeValidate,
+    NaPosition,
+    NsmallestNlargestKeep,
+    OpenFileErrors,
+    Ordered,
+    ParquetCompressionOptions,
+    QuantileInterpolation,
+    ReadBuffer,
+    ReadCsvBuffer,
+    ReadPickleBuffer,
+    ReindexMethod,
+    Scalar,
+    SequenceNotStr,
+    SliceType,
+    SortKind,
+    StorageOptions,
+    Suffixes,
+    TakeIndexer,
+    TimeAmbiguous,
+    TimedeltaConvertibleTypes,
+    TimeGrouperOrigin,
+    TimeNonexistent,
+    TimestampConvertibleTypes,
+    TimeUnit,
+    ToStataByteorder,
+    ToTimestampHow,
+    UpdateJoin,
+    UsecolsArgType,
+    WindowingRankType,
+    WriteBuffer,
+    WriteExcelBuffer,
+    XMLParsers,
+)
+
+__all__ = [
+    "AggFuncType",
+    "AlignJoin",
+    "AnyAll",
+    "AnyArrayLike",
+    "ArrayLike",
+    "AstypeArg",
+    "Axes",
+    "Axis",
+    "CSVEngine",
+    "ColspaceArgType",
+    "CompressionOptions",
+    "CorrelationMethod",
+    "DropKeep",
+    "Dtype",
+    "DtypeArg",
+    "DtypeBackend",
+    "DtypeObj",
+    "ExcelWriterIfSheetExists",
+    "ExcelWriterMergeCells",
+    "FilePath",
+    "FillnaOptions",
+    "FloatFormatType",
+    "FormattersType",
+    "FromDictOrient",
+    "HTMLFlavors",
+    "IgnoreRaise",
+    "IndexLabel",
+    "InterpolateOptions",
+    "JSONEngine",
+    "JSONSerializable",
+    "JoinHow",
+    "JoinValidate",
+    "MergeHow",
+    "MergeValidate",
+    "NaPosition",
+    "NsmallestNlargestKeep",
+    "OpenFileErrors",
+    "Ordered",
+    "ParquetCompressionOptions",
+    "QuantileInterpolation",
+    "ReadBuffer",
+    "ReadCsvBuffer",
+    "ReadPickleBuffer",
+    "ReindexMethod",
+    "Scalar",
+    "SequenceNotStr",
+    "SliceType",
+    "SortKind",
+    "StorageOptions",
+    "Suffixes",
+    "TakeIndexer",
+    "TimeAmbiguous",
+    "TimeGrouperOrigin",
+    "TimeNonexistent",
+    "TimeUnit",
+    "TimedeltaConvertibleTypes",
+    "TimestampConvertibleTypes",
+    "ToStataByteorder",
+    "ToTimestampHow",
+    "UpdateJoin",
+    "UsecolsArgType",
+    "WindowingRankType",
+    "WriteBuffer",
+    "WriteExcelBuffer",
+    "XMLParsers",
+]