Merge remote-tracking branch 'upstream/main' into regr_transpose_ea

# Conflicts:
#	doc/source/whatsnew/v2.2.1.rst

Author: rhshadrach

ci/code_checks.sh

@@ -65,8 +65,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (EX01, EX03, EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT02, RT04, RT05, SA02, SA03, SA04, SS01, SS02, SS03, SS04, SS05, SS06)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX01,EX03,EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT02,RT04,RT05,SA02,SA03,SA04,SS01,SS02,SS03,SS04,SS05,SS06
+    MSG='Validate docstrings (EX01, EX03, EX04, GL01, GL02, GL03, GL04, GL05, GL06, GL07, GL09, GL10, PR03, PR04, PR05, PR06, PR08, PR09, PR10, RT01, RT02, RT04, RT05, SA02, SA03, SA04, SA05, SS01, SS02, SS03, SS04, SS05, SS06)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=EX01,EX03,EX04,GL01,GL02,GL03,GL04,GL05,GL06,GL07,GL09,GL10,PR03,PR04,PR05,PR06,PR08,PR09,PR10,RT01,RT02,RT04,RT05,SA02,SA03,SA04,SA05,SS01,SS02,SS03,SS04,SS05,SS06
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Partially validate docstrings (PR02)' ;  echo $MSG
@@ -3182,14 +3182,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         pandas.util.hash_pandas_object # There should be no backslash in the final line, please keep this comment in the last ignored function
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
-    MSG='Partially validate docstrings (SA05)' ;  echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=actions --errors=SA05 --ignore_functions \
-        pandas.core.groupby.SeriesGroupBy.first\
-        pandas.core.groupby.SeriesGroupBy.last\
-        pandas.core.window.expanding.Expanding.aggregate\
-        pandas.core.window.rolling.Rolling.aggregate # There should be no backslash in the final line, please keep this comment in the last ignored function
-    RET=$(($RET + $?)) ; echo $MSG "DONE"
-
 fi
 
 ### DOCUMENTATION NOTEBOOKS ###

doc/source/conf.py

@@ -431,7 +431,7 @@
         "index",
         "pandas.tex",
         "pandas: powerful Python data analysis toolkit",
-        "Wes McKinney and the Pandas Development Team",
+        "Wes McKinney and the pandas Development Team",
         "manual",
     )
 ]

doc/source/development/contributing_codebase.rst

@@ -253,7 +253,7 @@ Testing type hints in code using pandas
 
 .. warning::
 
-    * Pandas is not yet a py.typed library (:pep:`561`)!
+    * pandas is not yet a py.typed library (:pep:`561`)!
       The primary purpose of locally declaring pandas as a py.typed library is to test and
       improve the pandas-builtin type annotations.
 

doc/source/development/contributing_documentation.rst

@@ -14,7 +14,7 @@ experts. If something in the docs doesn't make sense to you, updating the
 relevant section after you figure it out is a great way to ensure it will help
 the next person. Please visit the `issues page <https://github.com/pandas-dev/pandas/issues?page=1&q=is%3Aopen+sort%3Aupdated-desc+label%3ADocs>`__
 for a full list of issues that are currently open regarding the
-Pandas documentation.
+pandas documentation.
 
 
 

doc/source/development/debugging_extensions.rst

@@ -6,7 +6,7 @@
 Debugging C extensions
 ======================
 
-Pandas uses Cython and C/C++ `extension modules <https://docs.python.org/3/extending/extending.html>`_ to optimize performance. Unfortunately, the standard Python debugger does not allow you to step into these extensions. Cython extensions can be debugged with the `Cython debugger <https://docs.cython.org/en/latest/src/userguide/debugging.html>`_ and C/C++ extensions can be debugged using the tools shipped with your platform's compiler.
+pandas uses Cython and C/C++ `extension modules <https://docs.python.org/3/extending/extending.html>`_ to optimize performance. Unfortunately, the standard Python debugger does not allow you to step into these extensions. Cython extensions can be debugged with the `Cython debugger <https://docs.cython.org/en/latest/src/userguide/debugging.html>`_ and C/C++ extensions can be debugged using the tools shipped with your platform's compiler.
 
 For Python developers with limited or no C/C++ experience this can seem a daunting task. Core developer Will Ayd has written a 3 part blog series to help guide you from the standard Python debugger into these other tools:
 

doc/source/development/maintaining.rst

@@ -430,7 +430,7 @@ Release
     git checkout <branch>
     git pull --ff-only upstream <branch>
     git clean -xdf
-    git commit --allow-empty --author="Pandas Development Team <[email protected]>" -m "RLS: <version>"
+    git commit --allow-empty --author="pandas Development Team <[email protected]>" -m "RLS: <version>"
     git tag -a v<version> -m "Version <version>"  # NOTE that the tag is v1.5.2 with "v" not 1.5.2
     git push upstream <branch> --follow-tags
 
@@ -460,7 +460,7 @@ which will be triggered when the tag is pushed.
 4. Create a `new GitHub release <https://github.com/pandas-dev/pandas/releases/new>`_:
 
    - Tag: ``<version>``
-   - Title: ``Pandas <version>``
+   - Title: ``pandas <version>``
    - Description: Copy the description of the last release of the same kind (release candidate, major/minor or patch release)
    - Files: ``pandas-<version>.tar.gz`` source distribution just generated
    - Set as a pre-release: Only check for a release candidate

doc/source/user_guide/10min.rst

@@ -19,7 +19,7 @@ Customarily, we import as follows:
 Basic data structures in pandas
 -------------------------------
 
-Pandas provides two types of classes for handling data:
+pandas provides two types of classes for handling data:
 
 1. :class:`Series`: a one-dimensional labeled array holding data of any type
     such as integers, strings, Python objects etc.

doc/source/user_guide/categorical.rst

@@ -245,7 +245,8 @@ Equality semantics
 
 Two instances of :class:`~pandas.api.types.CategoricalDtype` compare equal
 whenever they have the same categories and order. When comparing two
-unordered categoricals, the order of the ``categories`` is not considered.
+unordered categoricals, the order of the ``categories`` is not considered. Note
+that categories with different dtypes are not the same.
 
 .. ipython:: python
 
@@ -263,6 +264,16 @@ All instances of ``CategoricalDtype`` compare equal to the string ``'category'``
 
    c1 == "category"
 
+Notice that the ``categories_dtype`` should be considered, especially when comparing with
+two empty ``CategoricalDtype`` instances.
+
+.. ipython:: python
+
+    c2 = pd.Categorical(np.array([], dtype=object))
+    c3 = pd.Categorical(np.array([], dtype=float))
+
+    c2.dtype == c3.dtype
+
 Description
 -----------
 

doc/source/user_guide/io.rst

@@ -1044,7 +1044,7 @@ Writing CSVs to binary file objects
 
 ``df.to_csv(..., mode="wb")`` allows writing a CSV to a file object
 opened binary mode. In most cases, it is not necessary to specify
-``mode`` as Pandas will auto-detect whether the file object is
+``mode`` as pandas will auto-detect whether the file object is
 opened in text or binary mode.
 
 .. ipython:: python
@@ -1604,7 +1604,7 @@ Specifying ``iterator=True`` will also return the ``TextFileReader`` object:
 Specifying the parser engine
 ''''''''''''''''''''''''''''
 
-Pandas currently supports three engines, the C engine, the python engine, and an experimental
+pandas currently supports three engines, the C engine, the python engine, and an experimental
 pyarrow engine (requires the ``pyarrow`` package). In general, the pyarrow engine is fastest
 on larger workloads and is equivalent in speed to the C engine on most other workloads.
 The python engine tends to be slower than the pyarrow and C engines on most workloads. However,
@@ -3910,7 +3910,7 @@ The look and feel of Excel worksheets created from pandas can be modified using
 
 .. note::
 
-    As of Pandas 3.0, by default spreadsheets created with the ``to_excel`` method
+    As of pandas 3.0, by default spreadsheets created with the ``to_excel`` method
     will not contain any styling. Users wishing to bold text, add bordered styles,
     etc in a worksheet output by ``to_excel`` can do so by using :meth:`Styler.to_excel`
     to create styled excel files. For documentation on styling spreadsheets, see

doc/source/whatsnew/v0.11.0.rst

@@ -12,7 +12,7 @@ Data have had quite a number of additions, and Dtype support is now full-fledged
 There are also a number of important API changes that long-time pandas users should
 pay close attention to.
 
-There is a new section in the documentation, :ref:`10 Minutes to Pandas <10min>`,
+There is a new section in the documentation, :ref:`10 Minutes to pandas <10min>`,
 primarily geared to new users.
 
 There is a new section in the documentation, :ref:`Cookbook <cookbook>`, a collection

doc/source/whatsnew/v1.3.1.rst

@@ -14,7 +14,7 @@ including other versions of pandas.
 
 Fixed regressions
 ~~~~~~~~~~~~~~~~~
-- Pandas could not be built on PyPy (:issue:`42355`)
+- pandas could not be built on PyPy (:issue:`42355`)
 - :class:`DataFrame` constructed with an older version of pandas could not be unpickled (:issue:`42345`)
 - Performance regression in constructing a :class:`DataFrame` from a dictionary of dictionaries (:issue:`42248`)
 - Fixed regression in :meth:`DataFrame.agg` dropping values when the DataFrame had an Extension Array dtype, a duplicate index, and ``axis=1`` (:issue:`42380`)

doc/source/whatsnew/v1.4.0.rst

@@ -607,7 +607,7 @@ Deprecated Int64Index, UInt64Index & Float64Index
 
 :class:`Int64Index`, :class:`UInt64Index` and :class:`Float64Index` have been
 deprecated in favor of the base :class:`Index` class and will be removed in
-Pandas 2.0 (:issue:`43028`).
+pandas 2.0 (:issue:`43028`).
 
 For constructing a numeric index, you can use the base :class:`Index` class
 instead specifying the data type (which will also work on older pandas

doc/source/whatsnew/v1.5.0.rst

@@ -63,7 +63,7 @@ We recommend installing the latest version of PyArrow to access the most recentl
 DataFrame interchange protocol implementation
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Pandas now implement the DataFrame interchange API spec.
+pandas now implement the DataFrame interchange API spec.
 See the full details on the API at https://data-apis.org/dataframe-protocol/latest/index.html
 
 The protocol consists of two parts:

doc/source/whatsnew/v2.0.0.rst

@@ -57,7 +57,7 @@ can it now take all numpy numeric dtypes, i.e.
     pd.Index([1, 2, 3], dtype=np.uint16)
     pd.Index([1, 2, 3], dtype=np.float32)
 
-The ability for :class:`Index` to hold the numpy numeric dtypes has meant some changes in Pandas
+The ability for :class:`Index` to hold the numpy numeric dtypes has meant some changes in pandas
 functionality. In particular, operations that previously were forced to create 64-bit indexes,
 can now create indexes with lower bit sizes, e.g. 32-bit indexes.
 

doc/source/whatsnew/v2.1.0.rst

@@ -67,7 +67,7 @@ DataFrame reductions preserve extension dtypes
 
 In previous versions of pandas, the results of DataFrame reductions
 (:meth:`DataFrame.sum` :meth:`DataFrame.mean` etc.) had NumPy dtypes, even when the DataFrames
-were of extension dtypes. Pandas can now keep the dtypes when doing reductions over DataFrame
+were of extension dtypes. pandas can now keep the dtypes when doing reductions over DataFrame
 columns with a common dtype (:issue:`52788`).
 
 *Old Behavior*

doc/source/whatsnew/v2.2.1.rst

@@ -24,12 +24,14 @@ Fixed regressions
 - Fixed regression in :meth:`CategoricalIndex.difference` raising ``KeyError`` when other contains null values other than NaN (:issue:`57318`)
 - Fixed regression in :meth:`DataFrame.groupby` raising ``ValueError`` when grouping by a :class:`Series` in some cases (:issue:`57276`)
 - Fixed regression in :meth:`DataFrame.loc` raising ``IndexError`` for non-unique, masked dtype indexes where result has more than 10,000 rows (:issue:`57027`)
+- Fixed regression in :meth:`DataFrame.loc` which was unnecessarily throwing "incompatible dtype warning" when expanding with partial row indexer and multiple columns (see `PDEP6 <https://pandas.pydata.org/pdeps/0006-ban-upcasting.html>`_) (:issue:`56503`)
 - Fixed regression in :meth:`DataFrame.map` with ``na_action="ignore"`` not being respected for NumPy nullable and :class:`ArrowDtypes` (:issue:`57316`)
 - Fixed regression in :meth:`DataFrame.merge` raising ``ValueError`` for certain types of 3rd-party extension arrays (:issue:`57316`)
 - Fixed regression in :meth:`DataFrame.shift` raising ``AssertionError`` for ``axis=1`` and empty :class:`DataFrame` (:issue:`57301`)
 - Fixed regression in :meth:`DataFrame.sort_index` not producing a stable sort for a index with duplicates (:issue:`57151`)
 - Fixed regression in :meth:`DataFrame.to_dict` with ``orient='list'`` and datetime or timedelta types returning integers (:issue:`54824`)
 - Fixed regression in :meth:`DataFrame.to_json` converting nullable integers to floats (:issue:`57224`)
+- Fixed regression in :meth:`DataFrame.to_sql` when ``method="multi"`` is passed and the dialect type is not Oracle (:issue:`57310`)
 - Fixed regression in :meth:`DataFrame.transpose` with nullable extension dtypes not having F-contiguous data potentially causing exceptions when used (:issue:`57315`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` ignoring the ``skipna`` argument (:issue:`57040`)
 - Fixed regression in :meth:`DataFrameGroupBy.idxmin`, :meth:`DataFrameGroupBy.idxmax`, :meth:`SeriesGroupBy.idxmin`, :meth:`SeriesGroupBy.idxmax` where values containing the minimum or maximum value for the dtype could produce incorrect results (:issue:`57040`)

doc/source/whatsnew/v3.0.0.rst

@@ -102,6 +102,7 @@ Deprecations
 ~~~~~~~~~~~~
 - Deprecated :meth:`Timestamp.utcfromtimestamp`, use ``Timestamp.fromtimestamp(ts, "UTC")`` instead (:issue:`56680`)
 - Deprecated :meth:`Timestamp.utcnow`, use ``Timestamp.now("UTC")`` instead (:issue:`56680`)
+- Deprecated allowing non-keyword arguments in :meth:`Series.to_string` except ``buf``. (:issue:`57280`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/_libs/algos_take_helper.pxi.in

@@ -184,6 +184,17 @@ def take_2d_axis1_{{name}}_{{dest}}(ndarray[{{c_type_in}}, ndim=2] values,
 
     fv = fill_value
 
+    {{if c_type_in == c_type_out != "object"}}
+    with nogil:
+        for i in range(n):
+            for j in range(k):
+                idx = indexer[j]
+                if idx == -1:
+                    out[i, j] = fv
+                else:
+                    out[i, j] = values[i, idx]
+
+    {{else}}
     for i in range(n):
         for j in range(k):
             idx = indexer[j]
@@ -195,6 +206,7 @@ def take_2d_axis1_{{name}}_{{dest}}(ndarray[{{c_type_in}}, ndim=2] values,
                 {{else}}
                 out[i, j] = values[i, idx]
                 {{endif}}
+    {{endif}}
 
 
 @cython.wraparound(False)

pandas/_typing.py

@@ -118,6 +118,7 @@
     Concatenate: Any = None
 
 HashableT = TypeVar("HashableT", bound=Hashable)
+HashableT2 = TypeVar("HashableT2", bound=Hashable)
 MutableMappingT = TypeVar("MutableMappingT", bound=MutableMapping)
 
 # array-like

pandas/core/base.py

@@ -8,7 +8,6 @@
 from typing import (
     TYPE_CHECKING,
     Any,
-    Callable,
     Generic,
     Literal,
     cast,
@@ -105,7 +104,7 @@ class PandasObject(DirNamesMixin):
     _cache: dict[str, Any]
 
     @property
-    def _constructor(self) -> Callable[..., Self]:
+    def _constructor(self) -> type[Self]:
         """
         Class constructor (for this class it's just `__class__`).
         """
@@ -1356,7 +1355,7 @@ def searchsorted(
             sorter=sorter,
         )
 
-    def drop_duplicates(self, *, keep: DropKeep = "first"):
+    def drop_duplicates(self, *, keep: DropKeep = "first") -> Self:
         duplicated = self._duplicated(keep=keep)
         # error: Value of type "IndexOpsMixin" is not indexable
         return self[~duplicated]  # type: ignore[index]

pandas/core/dtypes/missing.py

@@ -646,6 +646,20 @@ def infer_fill_value(val):
     return np.nan
 
 
+def construct_1d_array_from_inferred_fill_value(
+    value: object, length: int
+) -> ArrayLike:
+    # Find our empty_value dtype by constructing an array
+    #  from our value and doing a .take on it
+    from pandas.core.algorithms import take_nd
+    from pandas.core.construction import sanitize_array
+    from pandas.core.indexes.base import Index
+
+    arr = sanitize_array(value, Index(range(1)), copy=False)
+    taker = -1 * np.ones(length, dtype=np.intp)
+    return take_nd(arr, taker)
+
+
 def maybe_fill(arr: np.ndarray) -> np.ndarray:
     """
     Fill numpy.ndarray with NaN, unless we have a integer or boolean dtype.