Merge branch 'main' of https://github.com/sanggon6107/pandas into fix-loc-dtype

Author: sanggon6107

Dockerfile

@@ -13,5 +13,5 @@ COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
 RUN git config --global --add safe.directory /home/pandas
 
-ENV SHELL "/bin/bash"
+ENV SHELL="/bin/bash"
 CMD ["/bin/bash"]

asv_bench/benchmarks/rolling.py

@@ -10,7 +10,19 @@ class Methods:
         ["DataFrame", "Series"],
         [("rolling", {"window": 10}), ("rolling", {"window": 1000}), ("expanding", {})],
         ["int", "float"],
-        ["median", "mean", "max", "min", "std", "count", "skew", "kurt", "sum", "sem"],
+        [
+            "median",
+            "mean",
+            "max",
+            "min",
+            "std",
+            "count",
+            "skew",
+            "kurt",
+            "sum",
+            "sem",
+            "nunique",
+        ],
     )
     param_names = ["constructor", "window_kwargs", "dtype", "method"]
 

ci/code_checks.sh

@@ -83,6 +83,16 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.plot PR02" \
         -i "pandas.core.resample.Resampler.quantile PR01,PR07" \
         -i "pandas.tseries.offsets.BDay PR02,SA01" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.n GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.normalize GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.rule_code GL08" \
+        -i "pandas.tseries.offsets.BHalfYearBegin.startingMonth GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.n GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.normalize GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.rule_code GL08" \
+        -i "pandas.tseries.offsets.BHalfYearEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.is_on_offset GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.n GL08" \
         -i "pandas.tseries.offsets.BQuarterBegin.normalize GL08" \
@@ -185,6 +195,16 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.tseries.offsets.FY5253Quarter.variation GL08" \
         -i "pandas.tseries.offsets.FY5253Quarter.weekday GL08" \
         -i "pandas.tseries.offsets.FY5253Quarter.year_has_extra_week GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.n GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.normalize GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.rule_code GL08" \
+        -i "pandas.tseries.offsets.HalfYearBegin.startingMonth GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.is_on_offset GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.n GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.normalize GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.rule_code GL08" \
+        -i "pandas.tseries.offsets.HalfYearEnd.startingMonth GL08" \
         -i "pandas.tseries.offsets.Hour.is_on_offset GL08" \
         -i "pandas.tseries.offsets.Hour.n GL08" \
         -i "pandas.tseries.offsets.Hour.normalize GL08" \

doc/source/getting_started/overview.rst

@@ -174,3 +174,4 @@ License
 -------
 
 .. literalinclude:: ../../../LICENSE
+   :language: none

doc/source/reference/offset_frequency.rst

@@ -776,6 +776,146 @@ Methods
     QuarterBegin.is_year_start
     QuarterBegin.is_year_end
 
+BHalfYearEnd
+------------
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearEnd
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearEnd.freqstr
+    BHalfYearEnd.kwds
+    BHalfYearEnd.name
+    BHalfYearEnd.nanos
+    BHalfYearEnd.normalize
+    BHalfYearEnd.rule_code
+    BHalfYearEnd.n
+    BHalfYearEnd.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearEnd.copy
+    BHalfYearEnd.is_on_offset
+    BHalfYearEnd.is_month_start
+    BHalfYearEnd.is_month_end
+    BHalfYearEnd.is_quarter_start
+    BHalfYearEnd.is_quarter_end
+    BHalfYearEnd.is_year_start
+    BHalfYearEnd.is_year_end
+
+BHalfYearBegin
+--------------
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearBegin
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearBegin.freqstr
+    BHalfYearBegin.kwds
+    BHalfYearBegin.name
+    BHalfYearBegin.nanos
+    BHalfYearBegin.normalize
+    BHalfYearBegin.rule_code
+    BHalfYearBegin.n
+    BHalfYearBegin.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    BHalfYearBegin.copy
+    BHalfYearBegin.is_on_offset
+    BHalfYearBegin.is_month_start
+    BHalfYearBegin.is_month_end
+    BHalfYearBegin.is_quarter_start
+    BHalfYearBegin.is_quarter_end
+    BHalfYearBegin.is_year_start
+    BHalfYearBegin.is_year_end
+
+HalfYearEnd
+-----------
+.. autosummary::
+   :toctree: api/
+
+    HalfYearEnd
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearEnd.freqstr
+    HalfYearEnd.kwds
+    HalfYearEnd.name
+    HalfYearEnd.nanos
+    HalfYearEnd.normalize
+    HalfYearEnd.rule_code
+    HalfYearEnd.n
+    HalfYearEnd.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearEnd.copy
+    HalfYearEnd.is_on_offset
+    HalfYearEnd.is_month_start
+    HalfYearEnd.is_month_end
+    HalfYearEnd.is_quarter_start
+    HalfYearEnd.is_quarter_end
+    HalfYearEnd.is_year_start
+    HalfYearEnd.is_year_end
+
+HalfYearBegin
+-------------
+.. autosummary::
+   :toctree: api/
+
+    HalfYearBegin
+
+Properties
+~~~~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearBegin.freqstr
+    HalfYearBegin.kwds
+    HalfYearBegin.name
+    HalfYearBegin.nanos
+    HalfYearBegin.normalize
+    HalfYearBegin.rule_code
+    HalfYearBegin.n
+    HalfYearBegin.startingMonth
+
+Methods
+~~~~~~~
+.. autosummary::
+   :toctree: api/
+
+    HalfYearBegin.copy
+    HalfYearBegin.is_on_offset
+    HalfYearBegin.is_month_start
+    HalfYearBegin.is_month_end
+    HalfYearBegin.is_quarter_start
+    HalfYearBegin.is_quarter_end
+    HalfYearBegin.is_year_start
+    HalfYearBegin.is_year_end
+
 BYearEnd
 --------
 .. autosummary::

doc/source/reference/window.rst

@@ -42,6 +42,7 @@ Rolling window functions
    Rolling.quantile
    Rolling.sem
    Rolling.rank
+   Rolling.nunique
 
 .. _api.functions_window:
 
@@ -86,6 +87,7 @@ Expanding window functions
    Expanding.quantile
    Expanding.sem
    Expanding.rank
+   Expanding.nunique
 
 .. _api.functions_ewm:
 

doc/source/user_guide/io.rst

@@ -18,10 +18,10 @@ The pandas I/O API is a set of top level ``reader`` functions accessed like
     :widths: 30, 100, 60, 60
 
     text,`CSV <https://en.wikipedia.org/wiki/Comma-separated_values>`__, :ref:`read_csv<io.read_csv_table>`, :ref:`to_csv<io.store_in_csv>`
-    text,Fixed-Width Text File, :ref:`read_fwf<io.fwf_reader>` , NA
+    text,Fixed-Width Text File, :ref:`read_fwf<io.fwf_reader>`, NA
     text,`JSON <https://www.json.org/>`__, :ref:`read_json<io.json_reader>`, :ref:`to_json<io.json_writer>`
     text,`HTML <https://en.wikipedia.org/wiki/HTML>`__, :ref:`read_html<io.read_html>`, :ref:`to_html<io.html>`
-    text,`LaTeX <https://en.wikipedia.org/wiki/LaTeX>`__, :ref:`Styler.to_latex<io.latex>` , NA
+    text,`LaTeX <https://en.wikipedia.org/wiki/LaTeX>`__, NA, :ref:`Styler.to_latex<io.latex>`
     text,`XML <https://www.w3.org/standards/xml/core>`__, :ref:`read_xml<io.read_xml>`, :ref:`to_xml<io.xml>`
     text, Local clipboard, :ref:`read_clipboard<io.clipboard>`, :ref:`to_clipboard<io.clipboard>`
     binary,`MS Excel <https://en.wikipedia.org/wiki/Microsoft_Excel>`__ , :ref:`read_excel<io.excel_reader>`, :ref:`to_excel<io.excel_writer>`

doc/source/user_guide/timeseries.rst

@@ -891,6 +891,10 @@ into ``freq`` keyword arguments. The available date offsets and associated frequ
     :class:`~pandas.tseries.offsets.BQuarterEnd`, ``'BQE``, "business quarter end"
     :class:`~pandas.tseries.offsets.BQuarterBegin`, ``'BQS'``, "business quarter begin"
     :class:`~pandas.tseries.offsets.FY5253Quarter`, ``'REQ'``, "retail (aka 52-53 week) quarter"
+    :class:`~pandas.tseries.offsets.HalfYearEnd`, ``'HYE'``, "calendar half year end"
+    :class:`~pandas.tseries.offsets.HalfYearBegin`, ``'HYS'``, "calendar half year begin"
+    :class:`~pandas.tseries.offsets.BHalfYearEnd`, ``'BHYE``, "business half year end"
+    :class:`~pandas.tseries.offsets.BHalfYearBegin`, ``'BHYS'``, "business half year begin"
     :class:`~pandas.tseries.offsets.YearEnd`, ``'YE'``, "calendar year end"
     :class:`~pandas.tseries.offsets.YearBegin`, ``'YS'`` or ``'BYS'``,"calendar year begin"
     :class:`~pandas.tseries.offsets.BYearEnd`, ``'BYE'``, "business year end"

doc/source/whatsnew/v2.3.0.rst

@@ -37,6 +37,7 @@ Other enhancements
   updated to work correctly with NumPy >= 2 (:issue:`57739`)
 - :meth:`Series.str.decode` result now has ``StringDtype`` when ``future.infer_string`` is True (:issue:`60709`)
 - :meth:`~Series.to_hdf` and :meth:`~DataFrame.to_hdf` now round-trip with ``StringDtype``  (:issue:`60663`)
+- Improved ``repr`` of :class:`.NumpyExtensionArray` to account for NEP51 (:issue:`61085`)
 - The :meth:`Series.str.decode` has gained the argument ``dtype`` to control the dtype of the result (:issue:`60940`)
 - The :meth:`~Series.cumsum`, :meth:`~Series.cummin`, and :meth:`~Series.cummax` reductions are now implemented for ``StringDtype`` columns (:issue:`60633`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)
@@ -118,6 +119,7 @@ Conversion
 
 Strings
 ^^^^^^^
+- Bug in :meth:`DataFrame.sum` with ``axis=1``, :meth:`.DataFrameGroupBy.sum` or :meth:`.SeriesGroupBy.sum` with ``skipna=True``, and :meth:`.Resampler.sum` on :class:`StringDtype` with all NA values resulted in ``0`` and is now the empty string ``""`` (:issue:`60229`)
 - Bug in :meth:`Series.__pos__` and :meth:`DataFrame.__pos__` did not raise for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`60710`)
 - Bug in :meth:`Series.rank` for :class:`StringDtype` with ``storage="pyarrow"`` incorrectly returning integer results in case of ``method="average"`` and raising an error if it would truncate results (:issue:`59768`)
 - Bug in :meth:`Series.replace` with :class:`StringDtype` when replacing with a non-string value was not upcasting to ``object`` dtype (:issue:`60282`)

doc/source/whatsnew/v3.0.0.rst

@@ -61,7 +61,9 @@ Other enhancements
 - :meth:`Series.cummin` and :meth:`Series.cummax` now supports :class:`CategoricalDtype` (:issue:`52335`)
 - :meth:`Series.plot` now correctly handle the ``ylabel`` parameter for pie charts, allowing for explicit control over the y-axis label (:issue:`58239`)
 - :meth:`DataFrame.plot.scatter` argument ``c`` now accepts a column of strings, where rows with the same string are colored identically (:issue:`16827` and :issue:`16485`)
+- :class:`ArrowDtype` now supports ``pyarrow.JsonType`` (:issue:`60958`)
 - :class:`DataFrameGroupBy` and :class:`SeriesGroupBy` methods ``sum``, ``mean``, ``median``, ``prod``, ``min``, ``max``, ``std``, ``var`` and ``sem`` now accept ``skipna`` parameter (:issue:`15675`)
+- :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`)
 - :meth:`.DataFrameGroupBy.transform`, :meth:`.SeriesGroupBy.transform`, :meth:`.DataFrameGroupBy.agg`, :meth:`.SeriesGroupBy.agg`, :meth:`.SeriesGroupBy.apply`, :meth:`.DataFrameGroupBy.apply` now support ``kurt`` (:issue:`40139`)
@@ -694,8 +696,10 @@ Interval
 Indexing
 ^^^^^^^^
 - Bug in :meth:`DataFrame.__getitem__` returning modified columns when called with ``slice`` in Python 3.12 (:issue:`57500`)
+- Bug in :meth:`DataFrame.__getitem__` when slicing a :class:`DataFrame` with many rows raised an ``OverflowError`` (:issue:`59531`)
 - Bug in :meth:`DataFrame.from_records` throwing a ``ValueError`` when passed an empty list in ``index`` (:issue:`58594`)
 - Bug in :meth:`DataFrame.loc` with inconsistent behavior of loc-set with 2 given indexes to Series (:issue:`59933`)
+- Bug in :meth:`Index.get_indexer` and similar methods when ``NaN`` is located at or after position 128 (:issue:`58924`)
 - Bug in :meth:`MultiIndex.insert` when a new value inserted to a datetime-like level gets cast to ``NaT`` and fails indexing (:issue:`60388`)
 - Bug in printing :attr:`Index.names` and :attr:`MultiIndex.levels` would not escape single quotes (:issue:`60190`)
 
@@ -712,12 +716,13 @@ 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.from_tuples` causing wrong output with input of type tuples having NaN values (:issue:`60695`, :issue:`60988`)
 
 I/O
 ^^^
 - Bug in :class:`DataFrame` and :class:`Series` ``repr`` of :py:class:`collections.abc.Mapping`` elements. (:issue:`57915`)
 - Bug in :meth:`.DataFrame.to_json` when ``"index"`` was a value in the :attr:`DataFrame.column` and :attr:`Index.name` was ``None``. Now, this will fail with a ``ValueError`` (:issue:`58925`)
+- Bug in :meth:`.io.common.is_fsspec_url` not recognizing chained fsspec URLs (:issue:`48978`)
 - Bug in :meth:`DataFrame._repr_html_` which ignored the ``"display.float_format"`` option (:issue:`59876`)
 - Bug in :meth:`DataFrame.from_records` where ``columns`` parameter with numpy structured array was not reordering and filtering out the columns (:issue:`59717`)
 - Bug in :meth:`DataFrame.to_dict` raises unnecessary ``UserWarning`` when columns are not unique and ``orient='tight'``. (:issue:`58281`)
@@ -778,6 +783,7 @@ Reshaping
 ^^^^^^^^^
 - Bug in :func:`qcut` where values at the quantile boundaries could be incorrectly assigned (:issue:`59355`)
 - Bug in :meth:`DataFrame.combine_first` not preserving the column order (:issue:`60427`)
+- Bug in :meth:`DataFrame.explode` producing incorrect result for :class:`pyarrow.large_list` type (:issue:`61091`)
 - Bug in :meth:`DataFrame.join` inconsistently setting result index name (:issue:`55815`)
 - Bug in :meth:`DataFrame.join` when a :class:`DataFrame` with a :class:`MultiIndex` would raise an ``AssertionError`` when :attr:`MultiIndex.names` contained ``None``. (:issue:`58721`)
 - Bug in :meth:`DataFrame.merge` where merging on a column containing only ``NaN`` values resulted in an out-of-bounds array access (:issue:`59421`)
@@ -786,6 +792,7 @@ Reshaping
 - Bug in :meth:`DataFrame.pivot_table` incorrectly subaggregating results when called without an ``index`` argument (:issue:`58722`)
 - Bug in :meth:`DataFrame.stack` with the new implementation where ``ValueError`` is raised when ``level=[]`` (:issue:`60740`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)
+- Bug in :meth:`concat` where concatenating DataFrame and Series with ``ignore_index = True`` drops the series name (:issue:`60723`, :issue:`56257`)
 
 Sparse
 ^^^^^^