Merge branch 'shiny-new-feature' of https://github.com/Chiwendaiyue/pandas into shiny-new-feature

Author: cloudboat

.github/workflows/docbuild-and-upload.yml

@@ -93,7 +93,7 @@ jobs:
       run: mv doc/build/html web/build/docs
 
     - name: Save website as an artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v5
       with:
         name: website
         path: web/build

.github/workflows/unit-tests.yml

@@ -181,8 +181,7 @@ jobs:
     timeout-minutes: 90
     strategy:
       matrix:
-        # Note: Don't use macOS latest since macos 14 appears to be arm64 only
-        os: [macos-13, macos-14, windows-2025]
+        os: [macos-15-intel, macos-15, windows-2025]
         env_file: [actions-311.yaml, actions-312.yaml, actions-313.yaml]
       fail-fast: false
     runs-on: ${{ matrix.os }}

.github/workflows/wheels.yml

@@ -64,7 +64,7 @@ jobs:
           python -m pip install build
           python -m build --sdist
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: sdist
           path: ./dist/*
@@ -98,10 +98,9 @@ jobs:
         - [ubuntu-24.04, musllinux_x86_64]
         - [ubuntu-24.04-arm, manylinux_aarch64]
         - [ubuntu-24.04-arm, musllinux_aarch64]
-        - [macos-13, macosx_x86_64]
-        # Note: M1 images on Github Actions start from macOS 14
-        - [macos-14, macosx_arm64]
-        - [windows-2022, win_amd64]
+        - [macos-15-intel, macosx_x86_64]
+        - [macos-15, macosx_arm64]
+        - [windows-2025, win_amd64]
         - [windows-11-arm, win_arm64]
         python: [["cp311", "3.11"], ["cp312", "3.12"], ["cp313", "3.13"], ["cp313t", "3.13"], ["cp314", "3.14"], ["cp314t", "3.14"]]
         include:
@@ -139,7 +138,7 @@ jobs:
       # removes unnecessary files from the release
       - name: Download sdist (not macOS)
         #if: ${{ matrix.buildplat[1] != 'macosx_*' }}
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           name: sdist
           path: ./dist
@@ -197,7 +196,7 @@ jobs:
         shell: bash -el {0}
         run: for whl in $(ls wheelhouse); do wheel unpack wheelhouse/$whl -d /tmp; done
 
-      - uses: actions/upload-artifact@v4
+      - uses: actions/upload-artifact@v5
         with:
           name: ${{ matrix.python[0] }}-${{ matrix.buildplat[1] }}
           path: ./wheelhouse/*.whl
@@ -239,11 +238,11 @@ jobs:
 
     steps:
       - name: Download all artefacts
-        uses: actions/download-artifact@v5
+        uses: actions/download-artifact@v6
         with:
           path: dist          # everything lands in ./dist/**
 
-      # TODO: This step can be probably be achieved by actions/download-artifact@v5
+      # TODO: This step can be probably be achieved by actions/download-artifact@v6
       # by specifying merge-multiple: true, and a glob pattern
       - name: Collect files
         run: |

asv_bench/benchmarks/ctors.py

@@ -23,7 +23,7 @@ def gen_of_str(arr):
 
 
 def arr_dict(arr):
-    return dict(zip(range(len(arr)), arr))
+    return dict(zip(range(len(arr)), arr, strict=True))
 
 
 def list_of_tuples(arr):

asv_bench/benchmarks/series_methods.py

@@ -16,7 +16,7 @@ def setup(self):
         self.idx = date_range(
             start=datetime(2015, 10, 26), end=datetime(2016, 1, 1), freq="50s"
         )
-        self.data = dict(zip(self.idx, range(len(self.idx))))
+        self.data = dict(zip(self.idx, range(len(self.idx)), strict=True))
         self.array = np.array([1, 2, 3])
         self.idx2 = Index(["a", "b", "c"])
 
@@ -407,7 +407,9 @@ def setup(self, num_to_replace):
         self.to_replace_list = np.random.choice(self.arr, num_to_replace)
         self.values_list = np.random.choice(self.arr1, num_to_replace)
 
-        self.replace_dict = dict(zip(self.to_replace_list, self.values_list))
+        self.replace_dict = dict(
+            zip(self.to_replace_list, self.values_list, strict=True)
+        )
 
     def time_replace_dict(self, num_to_replace):
         self.ser.replace(self.replace_dict)

doc/source/reference/aliases.rst

@@ -65,7 +65,7 @@ Alias                                Meaning
 :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:`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
@@ -89,7 +89,7 @@ Alias                                Meaning
 :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:`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/user_guide/io.rst

@@ -2366,52 +2366,7 @@ Read a URL with no options:
 
    The data from the above URL changes every Monday so the resulting data above may be slightly different.
 
-Read a URL while passing headers alongside the HTTP request:
-
-.. code-block:: ipython
-
-   In [322]: url = 'https://www.sump.org/notes/request/' # HTTP request reflector
-
-   In [323]: pd.read_html(url)
-   Out[323]:
-   [                   0                    1
-    0     Remote Socket:  51.15.105.256:51760
-    1  Protocol Version:             HTTP/1.1
-    2    Request Method:                  GET
-    3       Request URI:      /notes/request/
-    4     Request Query:                  NaN,
-    0   Accept-Encoding:             identity
-    1              Host:         www.sump.org
-    2        User-Agent:    Python-urllib/3.8
-    3        Connection:                close]
-
-   In [324]: headers = {
-      .....:    'User-Agent':'Mozilla Firefox v14.0',
-      .....:    'Accept':'application/json',
-      .....:    'Connection':'keep-alive',
-      .....:    'Auth':'Bearer 2*/f3+fe68df*4'
-      .....: }
-
-   In [325]: pd.read_html(url, storage_options=headers)
-   Out[325]:
-   [                   0                    1
-    0     Remote Socket:  51.15.105.256:51760
-    1  Protocol Version:             HTTP/1.1
-    2    Request Method:                  GET
-    3       Request URI:      /notes/request/
-    4     Request Query:                  NaN,
-    0        User-Agent: Mozilla Firefox v14.0
-    1    AcceptEncoding:   gzip,  deflate,  br
-    2            Accept:      application/json
-    3        Connection:             keep-alive
-    4              Auth:  Bearer 2*/f3+fe68df*4]
-
-.. note::
-
-   We see above that the headers we passed are reflected in the HTTP request.
-
-Read in the content of the file from the above URL and pass it to ``read_html``
-as a string:
+Read in HTML content from a file using ``read_html``:
 
 .. ipython:: python
 

doc/source/whatsnew/v3.0.0.rst

@@ -201,6 +201,7 @@ Other enhancements
 - :class:`Rolling` and :class:`Expanding` now support ``nunique`` (:issue:`26958`)
 - :class:`Rolling` and :class:`Expanding` now support aggregations ``first`` and ``last`` (:issue:`33155`)
 - :func:`read_parquet` accepts ``to_pandas_kwargs`` which are forwarded to :meth:`pyarrow.Table.to_pandas` which enables passing additional keywords to customize the conversion to pandas, such as ``maps_as_pydicts`` to read the Parquet map data type as python dictionaries (:issue:`56842`)
+- :func:`to_numeric` on big integers converts to ``object`` datatype with python integers when not coercing. (:issue:`51295`)
 - :meth:`.DataFrameGroupBy.transform`, :meth:`.SeriesGroupBy.transform`, :meth:`.DataFrameGroupBy.agg`, :meth:`.SeriesGroupBy.agg`, :meth:`.SeriesGroupBy.apply`, :meth:`.DataFrameGroupBy.apply` now support ``kurt`` (:issue:`40139`)
 - :meth:`DataFrame.apply` supports using third-party execution engines like the Bodo.ai JIT compiler (:issue:`60668`)
 - :meth:`DataFrame.iloc` and :meth:`Series.iloc` now support boolean masks in ``__getitem__`` for more consistent indexing behavior (:issue:`60994`)
@@ -220,6 +221,7 @@ Other enhancements
 - Added support to read and write from and to Apache Iceberg tables with the new :func:`read_iceberg` and :meth:`DataFrame.to_iceberg` functions (:issue:`61383`)
 - Errors occurring during SQL I/O will now throw a generic :class:`.DatabaseError` instead of the raw Exception type from the underlying driver manager library (:issue:`60748`)
 - Implemented :meth:`Series.str.isascii` and :meth:`Series.str.isascii` (:issue:`59091`)
+- Improve error reporting through outputting the first few duplicates when :func:`merge` validation fails (:issue:`62742`)
 - 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`)
@@ -516,6 +518,22 @@ If we had passed ``pd.Int64Dtype()`` or ``"int64[pyarrow]"`` for the dtype in th
 
 With ``"mode.nan_is_na"`` set to ``False``, ``ser.to_numpy()`` (and ``frame.values`` and ``np.asarray(obj)``) will convert to ``object`` dtype if :class:`NA` entries are present, where before they would coerce to ``NaN``.  To retain a float numpy dtype, explicitly pass ``na_value=np.nan`` to :meth:`Series.to_numpy`.
 
+The ``__module__`` attribute now points to public modules
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+The ``__module__`` attribute on functions and classes in the public API has been
+updated to refer to the preferred public module from which to access the object,
+rather than the module in which the object happens to be defined (:issue:`55178`).
+
+This produces more informative displays in the Python console for classes, e.g.,
+instead of ``<class 'pandas.core.frame.DataFrame'>`` you now see
+``<class 'pandas.DataFrame'>``, and in interactive tools such as IPython, e.g.,
+instead of ``<function pandas.io.parsers.readers.read_csv(...)>`` you now see
+``<function pandas.read_csv(...)>``.
+
+This may break code that relies on the previous ``__module__`` values (e.g.
+doctests inspecting the ``type()`` of a DataFrame object).
+
 .. _whatsnew_300.api_breaking.deps:
 
 Increased minimum version for Python
@@ -721,6 +739,7 @@ Other Deprecations
 - Deprecated backward-compatibility behavior for :meth:`DataFrame.select_dtypes` matching "str" dtype when ``np.object_`` is specified (:issue:`61916`)
 - Deprecated option "future.no_silent_downcasting", as it is no longer used. In a future version accessing this option will raise (:issue:`59502`)
 - Deprecated slicing on a :class:`Series` or :class:`DataFrame` with a :class:`DatetimeIndex` using a ``datetime.date`` object, explicitly cast to :class:`Timestamp` instead (:issue:`35830`)
+- Deprecated the 'inplace' keyword from :meth:`Resampler.interpolate`, as passing ``True`` raises ``AttributeError`` (:issue:`58690`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_300.prior_deprecations:
@@ -939,6 +958,7 @@ Bug fixes
 
 Categorical
 ^^^^^^^^^^^
+- Bug in :class:`Categorical` where constructing from a pandas :class:`Series` or :class:`Index` with ``dtype='object'`` did not preserve the categories' dtype as ``object``; now the ``categories.dtype`` is preserved as ``object`` for these cases, while numpy arrays and Python sequences with ``dtype='object'`` continue to infer the most specific dtype (for example, ``str`` if all elements are strings) (:issue:`61778`)
 - Bug in :func:`Series.apply` where ``nan`` was ignored for :class:`CategoricalDtype` (:issue:`59938`)
 - Bug in :func:`testing.assert_index_equal` raising ``TypeError`` instead of ``AssertionError`` for incomparable ``CategoricalIndex`` when ``check_categorical=True`` and ``exact=False`` (:issue:`61935`)
 - Bug in :meth:`Categorical.astype` where ``copy=False`` would still trigger a copy of the codes (:issue:`62000`)
@@ -963,6 +983,7 @@ Datetimelike
 - Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` does not raise on Custom business days frequencies bigger then "1C" (:issue:`58664`)
 - Bug in :meth:`DatetimeIndex.is_year_start` and :meth:`DatetimeIndex.is_quarter_start` returning ``False`` on double-digit frequencies (:issue:`58523`)
 - Bug in :meth:`DatetimeIndex.union` and :meth:`DatetimeIndex.intersection` when ``unit`` was non-nanosecond (:issue:`59036`)
+- Bug in :meth:`DatetimeIndex.where` and :meth:`TimedeltaIndex.where` failing to set ``freq=None`` in some cases (:issue:`24555`)
 - Bug in :meth:`Index.union` with a ``pyarrow`` timestamp dtype incorrectly returning ``object`` dtype (:issue:`58421`)
 - Bug in :meth:`Series.dt.microsecond` producing incorrect results for pyarrow backed :class:`Series`. (:issue:`59154`)
 - Bug in :meth:`Timestamp.normalize` and :meth:`DatetimeArray.normalize` returning incorrect results instead of raising on integer overflow for very small (distant past) values (:issue:`60583`)
@@ -979,7 +1000,6 @@ Datetimelike
 - Bug in constructing arrays with a timezone-aware :class:`ArrowDtype` from timezone-naive datetime objects incorrectly treating those as UTC times instead of wall times like :class:`DatetimeTZDtype` (:issue:`61775`)
 - Bug in setting scalar values with mismatched resolution into arrays with non-nanosecond ``datetime64``, ``timedelta64`` or :class:`DatetimeTZDtype` incorrectly truncating those scalars (:issue:`56410`)
 
-
 Timedelta
 ^^^^^^^^^
 - Accuracy improvement in :meth:`Timedelta.to_pytimedelta` to round microseconds consistently for large nanosecond based Timedelta (:issue:`57841`)
@@ -998,6 +1018,7 @@ Numeric
 ^^^^^^^
 - Bug in :func:`api.types.infer_dtype` returning "mixed" for complex and ``pd.NA`` mix (:issue:`61976`)
 - Bug in :func:`api.types.infer_dtype` returning "mixed-integer-float" for float and ``pd.NA`` mix (:issue:`61621`)
+- Bug in :meth:`DataFrame.combine_first` where Int64 and UInt64 integers with absolute value greater than ``2**53`` would lose precision after the operation. (:issue:`60128`)
 - Bug in :meth:`DataFrame.corr` where numerical precision errors resulted in correlations above ``1.0`` (:issue:`61120`)
 - Bug in :meth:`DataFrame.cov` raises a ``TypeError`` instead of returning potentially incorrect results or other errors (:issue:`53115`)
 - Bug in :meth:`DataFrame.quantile` where the column type was not preserved when ``numeric_only=True`` with a list-like ``q`` produced an empty result (:issue:`59035`)
@@ -1017,6 +1038,7 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`Series.str.replace` raising an error on valid group references (``\1``, ``\2``, etc.) on series converted to PyArrow backend dtype (:issue:`62653`)
 - Bug in :meth:`Series.str.zfill` raising ``AttributeError`` for :class:`ArrowDtype` (:issue:`61485`)
 - Bug in :meth:`Series.value_counts` would not respect ``sort=False`` for series having ``string`` dtype (:issue:`55224`)
 - Bug in multiplication with a :class:`StringDtype` incorrectly allowing multiplying by bools; explicitly cast to integers instead (:issue:`62595`)
@@ -1026,6 +1048,7 @@ Interval
 - :meth:`Index.is_monotonic_decreasing`, :meth:`Index.is_monotonic_increasing`, and :meth:`Index.is_unique` could incorrectly be ``False`` for an ``Index`` created from a slice of another ``Index``. (:issue:`57911`)
 - Bug in :class:`Index`, :class:`Series`, :class:`DataFrame` constructors when given a sequence of :class:`Interval` subclass objects casting them to :class:`Interval` (:issue:`46945`)
 - Bug in :func:`interval_range` where start and end numeric types were always cast to 64 bit (:issue:`57268`)
+- Bug in :meth:`IntervalIndex.get_indexer` and :meth:`IntervalIndex.drop` when one of the sides of the index is non-unique (:issue:`52245`)
 
 Indexing
 ^^^^^^^^
@@ -1092,7 +1115,7 @@ I/O
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``index_col`` is specified and ``na_values`` is a dict containing the key ``None``. (:issue:`57547`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``nrows`` and ``iterator`` are specified without specifying a ``chunksize``. (:issue:`59079`)
 - Bug in :meth:`read_csv` where the order of the ``na_values`` makes an inconsistency when ``na_values`` is a list non-string values. (:issue:`59303`)
-- Bug in :meth:`read_csv` with ``engine="c"`` reading big integers as strings. Now reads them as python integers. (:issue:`51295`)
+- Bug in :meth:`read_csv` with ``c`` and ``python`` engines reading big integers as strings. Now reads them as python integers. (:issue:`51295`)
 - Bug in :meth:`read_csv` with ``engine="c"`` reading large float numbers with preceding integers as strings. Now reads them as floats. (:issue:`51295`)
 - Bug in :meth:`read_csv` with ``engine="pyarrow"`` and ``dtype="Int64"`` losing precision (:issue:`56136`)
 - Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)
@@ -1132,6 +1155,7 @@ Groupby/resample/rolling
 - Bug in :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupby.groups` that would not respect groupby argument ``dropna`` (:issue:`55919`)
 - Bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
+- Bug in :meth:`.DataFrameGroupBy` reductions where non-Boolean values were allowed for the ``numeric_only`` argument; passing a non-Boolean value will now raise (:issue:`62778`)
 - Bug in :meth:`.Resampler.interpolate` on a :class:`DataFrame` with non-uniform sampling and/or indices not aligning with the resulting resampled index would result in wrong interpolation (:issue:`21351`)
 - Bug in :meth:`.Series.rolling` when used with a :class:`.BaseIndexer` subclass and computing min/max (:issue:`46726`)
 - Bug in :meth:`DataFrame.ewm` and :meth:`Series.ewm` when passed ``times`` and aggregation functions other than mean (:issue:`51695`)
@@ -1188,6 +1212,7 @@ ExtensionArray
 - Bug in comparison between object with :class:`ArrowDtype` and incompatible-dtyped (e.g. string vs bool) incorrectly raising instead of returning all-``False`` (for ``==``) or all-``True`` (for ``!=``) (:issue:`59505`)
 - Bug in constructing pandas data structures when passing into ``dtype`` a string of the type followed by ``[pyarrow]`` while PyArrow is not installed would raise ``NameError`` rather than ``ImportError`` (:issue:`57928`)
 - Bug in various :class:`DataFrame` reductions for pyarrow temporal dtypes returning incorrect dtype when result was null (:issue:`59234`)
+- Fixed flex arithmetic with :class:`ExtensionArray` operands raising when ``fill_value`` was passed. (:issue:`62467`)
 
 Styler
 ^^^^^^

pandas/_libs/arrays.pyx

@@ -100,6 +100,10 @@ cdef class NDArrayBacked:
                 if len(state) == 1 and isinstance(state[0], dict):
                     self.__setstate__(state[0])
                     return
+                elif len(state) == 2:
+                    # GH#62820: Handle missing attrs dict during auto-unpickling
+                    self.__setstate__((*state, {}))
+                    return
                 raise NotImplementedError(state)  # pragma: no cover
 
             data, dtype = state[:2]