Merge remote-tracking branch 'upstream/main' into bug-read_csv-tarfile

Author: KevsterAmp

ci/code_checks.sh

@@ -90,9 +90,7 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.arrays.ArrowExtensionArray PR07,SA01" \
         -i "pandas.arrays.IntegerArray SA01" \
         -i "pandas.arrays.IntervalArray.length SA01" \
-        -i "pandas.arrays.IntervalArray.right SA01" \
         -i "pandas.arrays.NumpyExtensionArray SA01" \
-        -i "pandas.arrays.SparseArray PR07,SA01" \
         -i "pandas.arrays.TimedeltaArray PR07,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \

doc/source/development/contributing_docstring.rst

@@ -940,7 +940,7 @@ Finally, docstrings can also be appended to with the ``doc`` decorator.
 
 In this example, we'll create a parent docstring normally (this is like
 ``pandas.core.generic.NDFrame``). Then we'll have two children (like
-``pandas.core.series.Series`` and ``pandas.DataFrame``). We'll
+``pandas.Series`` and ``pandas.DataFrame``). We'll
 substitute the class names in this docstring.
 
 .. code-block:: python
@@ -995,5 +995,5 @@ mapping function names to docstrings. Wherever possible, we prefer using
 ``doc``, since the docstring-writing processes is slightly closer to normal.
 
 See ``pandas.core.generic.NDFrame.fillna`` for an example template, and
-``pandas.core.series.Series.fillna`` and ``pandas.core.generic.frame.fillna``
+``pandas.Series.fillna`` and ``pandas.core.generic.frame.fillna``
 for the filled versions.

doc/source/whatsnew/v2.3.0.rst

@@ -133,7 +133,7 @@ MultiIndex
 
 I/O
 ^^^
--
+- :meth:`DataFrame.to_excel` was storing decimals as strings instead of numbers (:issue:`49598`)
 -
 
 Period

doc/source/whatsnew/v3.0.0.rst

@@ -481,7 +481,7 @@ Other Removals
 - Enforced deprecation of :meth:`Series.interpolate` and :meth:`DataFrame.interpolate` for object-dtype (:issue:`57820`)
 - Enforced deprecation of :meth:`offsets.Tick.delta`, use ``pd.Timedelta(obj)`` instead (:issue:`55498`)
 - Enforced deprecation of ``axis=None`` acting the same as ``axis=0`` in the DataFrame reductions ``sum``, ``prod``, ``std``, ``var``, and ``sem``, passing ``axis=None`` will now reduce over both axes; this is particularly the case when doing e.g. ``numpy.sum(df)`` (:issue:`21597`)
-- Enforced deprecation of ``core.internals`` members ``Block``, ``ExtensionBlock``, and ``DatetimeTZBlock`` (:issue:`58467`)
+- Enforced deprecation of ``core.internals`` member ``DatetimeTZBlock`` (:issue:`58467`)
 - Enforced deprecation of ``date_parser`` in :func:`read_csv`, :func:`read_table`, :func:`read_fwf`, and :func:`read_excel` in favour of ``date_format`` (:issue:`50601`)
 - Enforced deprecation of ``keep_date_col`` keyword in :func:`read_csv` (:issue:`55569`)
 - Enforced deprecation of ``quantile`` keyword in :meth:`.Rolling.quantile` and :meth:`.Expanding.quantile`, renamed to ``q`` instead. (:issue:`52550`)
@@ -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`)

environment.yml

@@ -77,7 +77,7 @@ dependencies:
 
   # code checks
   - flake8=7.1.0  # run in subprocess over docstring examples
-  - mypy=1.11.2  # pre-commit uses locally installed mypy
+  - mypy=1.13.0  # pre-commit uses locally installed mypy
   - tokenize-rt  # scripts/check_for_inconsistent_pandas_namespace.py
   - pre-commit>=4.0.1
 

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

@@ -7,7 +7,6 @@
 from typing import (
     TYPE_CHECKING,
     ContextManager,
-    cast,
 )
 
 import numpy as np
@@ -21,8 +20,6 @@
 
 from pandas.compat import pa_version_under10p1
 
-from pandas.core.dtypes.common import is_string_dtype
-
 import pandas as pd
 from pandas import (
     ArrowDtype,
@@ -77,8 +74,8 @@
     with_csv_dialect,
 )
 from pandas.core.arrays import (
+    ArrowExtensionArray,
     BaseMaskedArray,
-    ExtensionArray,
     NumpyExtensionArray,
 )
 from pandas.core.arrays._mixins import NDArrayBackedExtensionArray
@@ -92,7 +89,6 @@
         NpDtype,
     )
 
-    from pandas.core.arrays import ArrowExtensionArray
 
 UNSIGNED_INT_NUMPY_DTYPES: list[NpDtype] = ["uint8", "uint16", "uint32", "uint64"]
 UNSIGNED_INT_EA_DTYPES: list[Dtype] = ["UInt8", "UInt16", "UInt32", "UInt64"]
@@ -501,6 +497,8 @@ 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):
@@ -510,24 +508,18 @@ def shares_memory(left, right) -> bool:
     if isinstance(left, pd.core.arrays.IntervalArray):
         return shares_memory(left._left, right) or shares_memory(left._right, right)
 
-    if (
-        isinstance(left, ExtensionArray)
-        and is_string_dtype(left.dtype)
-        and left.dtype.storage == "pyarrow"  # type: ignore[attr-defined]
-    ):
-        # https://github.com/pandas-dev/pandas/pull/43930#discussion_r736862669
-        left = cast("ArrowExtensionArray", left)
-        if (
-            isinstance(right, ExtensionArray)
-            and is_string_dtype(right.dtype)
-            and right.dtype.storage == "pyarrow"  # type: ignore[attr-defined]
-        ):
-            right = cast("ArrowExtensionArray", right)
+    if isinstance(left, ArrowExtensionArray):
+        if isinstance(right, ArrowExtensionArray):
+            # https://github.com/pandas-dev/pandas/pull/43930#discussion_r736862669
             left_pa_data = left._pa_array
             right_pa_data = right._pa_array
             left_buf1 = left_pa_data.chunk(0).buffers()[1]
             right_buf1 = right_pa_data.chunk(0).buffers()[1]
-            return left_buf1 == right_buf1
+            return left_buf1.address == right_buf1.address
+        else:
+            # if we have one one ArrowExtensionArray and one other array, assume
+            # they can only share memory if they share the same numpy buffer
+            return np.shares_memory(left, right)
 
     if isinstance(left, BaseMaskedArray) and isinstance(right, BaseMaskedArray):
         # By convention, we'll say these share memory if they share *either*

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")),
     )