Merge branch 'main' into main

Author: sanjanam1998

ci/code_checks.sh

@@ -73,10 +73,12 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
         -i "pandas.errors.IncompatibleFrequency SA01,SS06,EX01" \
+        -i "pandas.errors.InvalidVersion GL08" \
         -i "pandas.api.extensions.ExtensionArray.value_counts EX01,RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.plot PR02" \
-        -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
-        -i "pandas.core.resample.Resampler.quantile PR01,PR07" \
+        -i "pandas.api.typing.DataFrameGroupBy.plot PR02" \
+        -i "pandas.api.typing.SeriesGroupBy.plot PR02" \
+        -i "pandas.api.typing.Resampler.quantile PR01,PR07" \
+        -i "pandas.arrays.NumpyExtensionArray GL08" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
         -i "pandas.tseries.offsets.BHalfYearBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BHalfYearBegin.n GL08" \

doc/source/reference/groupby.rst

@@ -5,7 +5,7 @@
 =======
 GroupBy
 =======
-.. currentmodule:: pandas.core.groupby
+.. currentmodule:: pandas.api.typing
 
 :class:`pandas.api.typing.DataFrameGroupBy` and :class:`pandas.api.typing.SeriesGroupBy`
 instances are returned by groupby calls :func:`pandas.DataFrame.groupby` and
@@ -40,7 +40,7 @@ Function application helper
 
    NamedAgg
 
-.. currentmodule:: pandas.core.groupby
+.. currentmodule:: pandas.api.typing
 
 Function application
 --------------------

doc/source/reference/resampling.rst

@@ -5,7 +5,7 @@
 ==========
 Resampling
 ==========
-.. currentmodule:: pandas.core.resample
+.. currentmodule:: pandas.api.typing
 
 :class:`pandas.api.typing.Resampler` instances are returned by
 resample calls: :func:`pandas.DataFrame.resample`, :func:`pandas.Series.resample`.

doc/source/reference/window.rst

@@ -17,7 +17,7 @@ calls: :func:`pandas.DataFrame.ewm` and :func:`pandas.Series.ewm`.
 
 Rolling window functions
 ------------------------
-.. currentmodule:: pandas.core.window.rolling
+.. currentmodule:: pandas.api.typing
 
 .. autosummary::
    :toctree: api/
@@ -48,7 +48,8 @@ Rolling window functions
 
 Weighted window functions
 -------------------------
-.. currentmodule:: pandas.core.window.rolling
+.. currentmodule:: pandas.api.typing
+
 
 .. autosummary::
    :toctree: api/
@@ -62,7 +63,8 @@ Weighted window functions
 
 Expanding window functions
 --------------------------
-.. currentmodule:: pandas.core.window.expanding
+.. currentmodule:: pandas.api.typing
+
 
 .. autosummary::
    :toctree: api/
@@ -93,7 +95,8 @@ Expanding window functions
 
 Exponentially-weighted window functions
 ---------------------------------------
-.. currentmodule:: pandas.core.window.ewm
+.. currentmodule:: pandas.api.typing
+
 
 .. autosummary::
    :toctree: api/

doc/source/user_guide/10min.rst

@@ -318,7 +318,9 @@ Setting a new column automatically aligns the data by the indexes:
 
 .. ipython:: python
 
-   s1 = pd.Series([1, 2, 3, 4, 5, 6], index=pd.date_range("20130102", periods=6))
+   s1 = pd.Series(
+      [1, 2, 3, 4, 5, 6],
+      index=pd.date_range("20130102", periods=6))
    s1
    df["F"] = s1
 

doc/source/user_guide/basics.rst

@@ -2372,11 +2372,18 @@ integers:
 
    df.select_dtypes(include=["number", "bool"], exclude=["unsignedinteger"])
 
-To select string columns you must use the ``object`` dtype:
+To select string columns include ``str``:
 
 .. ipython:: python
 
-   df.select_dtypes(include=["object"])
+   df.select_dtypes(include=[str])
+
+.. note::
+
+    This is a change in pandas 3.0. Previously strings were stored in ``object``
+    dtype columns, so would be selected with ``include=[object]``. See
+    :ref:`the migration guide <string_migration.select_dtypes>` for details on
+    how to write code that works with both versions.
 
 To see all the child dtypes of a generic ``dtype`` like ``numpy.number`` you
 can define a function that returns a tree of child dtypes:

doc/source/user_guide/enhancingperf.rst

@@ -455,7 +455,7 @@ by evaluate arithmetic and boolean expression all at once for large :class:`~pan
    :func:`~pandas.eval` is many orders of magnitude slower for
    smaller expressions or objects than plain Python. A good rule of thumb is
    to only use :func:`~pandas.eval` when you have a
-   :class:`~pandas.core.frame.DataFrame` with more than 10,000 rows.
+   :class:`~pandas.DataFrame` with more than 10,000 rows.
 
 Supported syntax
 ~~~~~~~~~~~~~~~~

doc/source/user_guide/migration-3-strings.rst

@@ -195,6 +195,8 @@ This is actually compatible with pandas 2.x as well, since in pandas < 3,
    of also stringifying missing values in pandas 2.x. See the section
    :ref:`string_migration_guide-astype_str` for more details.
 
+.. _string_migration.select_dtypes:
+
 For selecting string columns with :meth:`~DataFrame.select_dtypes` in a pandas
 2.x and 3.x compatible way, it is not possible to use ``"str"``. While this
 works for pandas 3.x, it raises an error in pandas 2.x.

doc/source/whatsnew/v3.0.0.rst

@@ -717,6 +717,7 @@ Other Deprecations
 - Deprecated using ``epoch`` date format in :meth:`DataFrame.to_json` and :meth:`Series.to_json`, use ``iso`` instead. (:issue:`57063`)
 - Deprecated allowing ``fill_value`` that cannot be held in the original dtype (excepting NA values for integer and bool dtypes) in :meth:`Series.unstack` and :meth:`DataFrame.unstack` (:issue:`12189`, :issue:`53868`)
 - Deprecated allowing ``fill_value`` that cannot be held in the original dtype (excepting NA values for integer and bool dtypes) in :meth:`Series.shift` and :meth:`DataFrame.shift` (:issue:`53802`)
+- 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`)
 
@@ -797,6 +798,7 @@ Other Removals
 - Enforce deprecation in :func:`testing.assert_series_equal` and :func:`testing.assert_frame_equal` with object dtype and mismatched null-like values, which are now considered not-equal (:issue:`18463`)
 - Enforce banning of upcasting in in-place setitem-like operations (:issue:`59007`) (see `PDEP6 <https://pandas.pydata.org/pdeps/0006-ban-upcasting.html>`_)
 - Enforced deprecation ``all`` and ``any`` reductions with ``datetime64``, :class:`DatetimeTZDtype`, and :class:`PeriodDtype` dtypes (:issue:`58029`)
+- Enforced deprecation allowing non-``bool`` and NA values for ``na`` in :meth:`.str.contains`, :meth:`.str.startswith`, and :meth:`.str.endswith` (:issue:`59615`)
 - Enforced deprecation disallowing ``float`` "periods" in :func:`date_range`, :func:`period_range`, :func:`timedelta_range`, :func:`interval_range`,  (:issue:`56036`)
 - Enforced deprecation disallowing parsing datetimes with mixed time zones unless user passes ``utc=True`` to :func:`to_datetime` (:issue:`57275`)
 - Enforced deprecation in :meth:`Series.value_counts` and :meth:`Index.value_counts` with object dtype performing dtype inference on the ``.index`` of the result (:issue:`56161`)
@@ -1002,6 +1004,7 @@ Numeric
 - Bug in :meth:`Series.dot` returning ``object`` dtype for :class:`ArrowDtype` and nullable-dtype data (:issue:`61375`)
 - Bug in :meth:`Series.std` and :meth:`Series.var` when using complex-valued data (:issue:`61645`)
 - Bug in ``np.matmul`` with :class:`Index` inputs raising a ``TypeError`` (:issue:`57079`)
+- Bug in arithmetic operations between objects with numpy-nullable dtype and :class:`ArrowDtype` incorrectly raising (:issue:`58602`)
 
 Conversion
 ^^^^^^^^^^
@@ -1057,6 +1060,7 @@ MultiIndex
 - :func:`MultiIndex.get_level_values` accessing a :class:`DatetimeIndex` does not carry the frequency attribute along (:issue:`58327`, :issue:`57949`)
 - Bug in :class:`DataFrame` arithmetic operations in case of unaligned MultiIndex columns (:issue:`60498`)
 - Bug in :class:`DataFrame` arithmetic operations with :class:`Series` in case of unaligned MultiIndex (:issue:`61009`)
+- Bug in :meth:`MultiIndex.union` raising when indexes have duplicates with differing names (:issue:`62059`)
 - Bug in :meth:`MultiIndex.from_tuples` causing wrong output with input of type tuples having NaN values (:issue:`60695`, :issue:`60988`)
 - Bug in :meth:`DataFrame.__setitem__` where column alignment logic would reindex the assigned value with an empty index, incorrectly setting all values to ``NaN``.(:issue:`61841`)
 - Bug in :meth:`DataFrame.reindex` and :meth:`Series.reindex` where reindexing :class:`Index` to a :class:`MultiIndex` would incorrectly set all values to ``NaN``.(:issue:`60923`)

meson.build

@@ -18,6 +18,9 @@ versioneer = files('generate_version.py')
 
 add_project_arguments('-DNPY_NO_DEPRECATED_API=0', language: 'c')
 add_project_arguments('-DNPY_NO_DEPRECATED_API=0', language: 'cpp')
+# Enables settings __module__ on cdef classes
+# https://github.com/cython/cython/issues/7231
+add_project_arguments('-DCYTHON_USE_TYPE_SPECS=1', language: 'c')
 
 # Allow supporting older numpys than the version compiled against
 # Set the define to the min supported version of numpy for pandas