Merge branch 'main' into Test_issue_57930

Author: MCRE-BE

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.6.9
+    rev: v0.7.2
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -74,7 +74,7 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v3.17.0
+    rev: v3.19.0
     hooks:
     -   id: pyupgrade
         args: [--py310-plus]
@@ -95,7 +95,7 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v19.1.1
+    rev: v19.1.3
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include

doc/source/getting_started/comparison/comparison_with_r.rst

@@ -405,7 +405,7 @@ In Python, this list would be a list of tuples, so
    a = list(enumerate(list(range(1, 5)) + [np.NAN]))
    pd.DataFrame(a)
 
-For more details and examples see :ref:`the Into to Data Structures
+For more details and examples see :ref:`the Intro to Data Structures
 documentation <dsintro>`.
 
 meltdf

doc/source/whatsnew/v2.3.0.rst

@@ -32,6 +32,9 @@ enhancement1
 Other enhancements
 ^^^^^^^^^^^^^^^^^^
 
+- The semantics for the ``copy`` keyword in ``__array__`` methods (i.e. called
+  when using ``np.array()`` or ``np.asarray()`` on pandas objects) has been
+  updated to work correctly with NumPy >= 2 (:issue:`57739`)
 - The :meth:`~Series.sum` reduction is now implemented for ``StringDtype`` columns (:issue:`59853`)
 -
 
@@ -130,7 +133,7 @@ MultiIndex
 
 I/O
 ^^^
--
+- :meth:`DataFrame.to_excel` was storing decimals as strings instead of numbers (:issue:`49598`)
 -
 
 Period
@@ -170,7 +173,8 @@ Styler
 
 Other
 ^^^^^
--
+- Fixed usage of ``inspect`` when the optional dependencies ``pyarrow`` or ``jinja2``
+  are not installed (:issue:`60196`)
 -
 
 .. ---------------------------------------------------------------------------

doc/source/whatsnew/v3.0.0.rst

@@ -613,6 +613,7 @@ Categorical
 Datetimelike
 ^^^^^^^^^^^^
 - Bug in :attr:`is_year_start` where a DateTimeIndex constructed via a date_range with frequency 'MS' wouldn't have the correct year or quarter start attributes (:issue:`57377`)
+- Bug in :class:`DataFrame` raising ``ValueError`` when ``dtype`` is ``timedelta64`` and ``data`` is a list containing ``None`` (:issue:`60064`)
 - Bug in :class:`Timestamp` constructor failing to raise when ``tz=None`` is explicitly specified in conjunction with timezone-aware ``tzinfo`` or data (:issue:`48688`)
 - Bug in :func:`date_range` where the last valid timestamp would sometimes not be produced (:issue:`56134`)
 - Bug in :func:`date_range` where using a negative frequency value would not include all points between the start and end values (:issue:`56147`)
@@ -710,6 +711,7 @@ Period
 Plotting
 ^^^^^^^^
 - Bug in :meth:`.DataFrameGroupBy.boxplot` failed when there were multiple groupings (:issue:`14701`)
+- Bug in :meth:`DataFrame.plot.bar` with ``stacked=True`` where labels on stacked bars with zero-height segments were incorrectly positioned at the base instead of the label position of the previous segment (:issue:`59429`)
 - Bug in :meth:`DataFrame.plot.line` raising ``ValueError`` when set both color and a ``dict`` style (:issue:`59461`)
 - Bug in :meth:`DataFrame.plot` that causes a shift to the right when the frequency multiplier is greater than one. (:issue:`57587`)
 - Bug in :meth:`Series.plot` with ``kind="pie"`` with :class:`ArrowDtype` (:issue:`59192`)
@@ -771,7 +773,9 @@ Other
 - Bug in :meth:`DataFrame.apply` where passing ``engine="numba"`` ignored ``args`` passed to the applied function (:issue:`58712`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which caused an exception when using NumPy attributes via ``@`` notation, e.g., ``df.eval("@np.floor(a)")``. (:issue:`58041`)
 - Bug in :meth:`DataFrame.eval` and :meth:`DataFrame.query` which did not allow to use ``tan`` function. (:issue:`55091`)
+- Bug in :meth:`DataFrame.query` where using duplicate column names led to a ``TypeError``. (:issue:`59950`)
 - Bug in :meth:`DataFrame.query` which raised an exception or produced incorrect results when expressions contained backtick-quoted column names containing the hash character ``#``, backticks, or characters that fall outside the ASCII range (U+0001..U+007F). (:issue:`59285`) (:issue:`49633`)
+- Bug in :meth:`DataFrame.shift` where passing a ``freq`` on a DataFrame with no columns did not shift the index correctly. (:issue:`60102`)
 - Bug in :meth:`DataFrame.sort_index` when passing ``axis="columns"`` and ``ignore_index=True`` and ``ascending=False`` not returning a :class:`RangeIndex` columns (:issue:`57293`)
 - Bug in :meth:`DataFrame.transform` that was returning the wrong order unless the index was monotonically increasing. (:issue:`57069`)
 - Bug in :meth:`DataFrame.where` where using a non-bool type array in the function would return a ``ValueError`` instead of a ``TypeError`` (:issue:`56330`)

pandas/_libs/tslibs/period.pyx

@@ -114,6 +114,7 @@ from pandas._libs.tslibs.offsets import (
     INVALID_FREQ_ERR_MSG,
     BDay,
 )
+from pandas.util._decorators import set_module
 
 cdef:
     enum:
@@ -2830,6 +2831,7 @@ cdef class _Period(PeriodMixin):
         return period_format(self.ordinal, base, fmt)
 
 
+@set_module("pandas")
 class Period(_Period):
     """
     Represents a period of time.

pandas/_libs/tslibs/timedeltas.pyx

@@ -1,6 +1,7 @@
 import collections
 import warnings
 
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 
 cimport cython
@@ -1854,7 +1855,7 @@ cdef class _Timedelta(timedelta):
 
 # Python front end to C extension type _Timedelta
 # This serves as the box for timedelta64
-
+@set_module("pandas")
 class Timedelta(_Timedelta):
     """
     Represents a duration, the difference between two dates or times.
@@ -1916,7 +1917,7 @@ class Timedelta(_Timedelta):
     --------
     Here we initialize Timedelta object with both value and unit
 
-    >>> td = pd.Timedelta(1, "d")
+    >>> td = pd.Timedelta(1, "D")
     >>> td
     Timedelta('1 days 00:00:00')
 

pandas/_libs/tslibs/timestamps.pyx

@@ -50,6 +50,7 @@ import datetime as dt
 from pandas._libs.tslibs cimport ccalendar
 from pandas._libs.tslibs.base cimport ABCTimestamp
 
+from pandas.util._decorators import set_module
 from pandas.util._exceptions import find_stack_level
 
 from pandas._libs.tslibs.conversion cimport (
@@ -1648,7 +1649,7 @@ cdef class _Timestamp(ABCTimestamp):
 # Python front end to C extension type _Timestamp
 # This serves as the box for datetime64
 
-
+@set_module("pandas")
 class Timestamp(_Timestamp):
     """
     Pandas replacement for python datetime.datetime object.
@@ -2926,7 +2927,7 @@ timedelta}, default 'raise'
         --------
         >>> ts = pd.Timestamp(1584226800, unit='s', tz='Europe/Stockholm')
         >>> ts.tz
-        <DstTzInfo 'Europe/Stockholm' CET+1:00:00 STD>
+        zoneinfo.ZoneInfo(key='Europe/Stockholm')
         """
         return self.tzinfo
 

pandas/_testing/__init__.py

@@ -501,6 +501,8 @@ def shares_memory(left, right) -> bool:
     if isinstance(left, MultiIndex):
         return shares_memory(left._codes, right)
     if isinstance(left, (Index, Series)):
+        if isinstance(right, (Index, Series)):
+            return shares_memory(left._values, right._values)
         return shares_memory(left._values, right)
 
     if isinstance(left, NDArrayBackedExtensionArray):

pandas/conftest.py

@@ -600,7 +600,7 @@ def multiindex_year_month_day_dataframe_random_data():
     """
     tdf = DataFrame(
         np.random.default_rng(2).standard_normal((100, 4)),
-        columns=Index(list("ABCD"), dtype=object),
+        columns=Index(list("ABCD")),
         index=date_range("2000-01-01", periods=100, freq="B"),
     )
     ymd = tdf.groupby([lambda x: x.year, lambda x: x.month, lambda x: x.day]).sum()
@@ -787,7 +787,7 @@ def string_series() -> Series:
     """
     return Series(
         np.arange(30, dtype=np.float64) * 1.1,
-        index=Index([f"i_{i}" for i in range(30)], dtype=object),
+        index=Index([f"i_{i}" for i in range(30)]),
         name="series",
     )
 
@@ -798,7 +798,7 @@ def object_series() -> Series:
     Fixture for Series of dtype object with Index of unique strings
     """
     data = [f"foo_{i}" for i in range(30)]
-    index = Index([f"bar_{i}" for i in range(30)], dtype=object)
+    index = Index([f"bar_{i}" for i in range(30)])
     return Series(data, index=index, name="objects", dtype=object)
 
 
@@ -890,8 +890,8 @@ def int_frame() -> DataFrame:
     """
     return DataFrame(
         np.ones((30, 4), dtype=np.int64),
-        index=Index([f"foo_{i}" for i in range(30)], dtype=object),
-        columns=Index(list("ABCD"), dtype=object),
+        index=Index([f"foo_{i}" for i in range(30)]),
+        columns=Index(list("ABCD")),
     )
 
 

pandas/core/arrays/arrow/accessors.py

@@ -46,7 +46,7 @@ def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
 
     def _validate(self, data) -> None:
         dtype = data.dtype
-        if not isinstance(dtype, ArrowDtype):
+        if pa_version_under10p1 or not isinstance(dtype, ArrowDtype):
             # Raise AttributeError so that inspect can handle non-struct Series.
             raise AttributeError(self._validation_msg.format(dtype=dtype))