Merge remote-tracking branch 'upstream/main' into series-sum-attrs

Author: fbourgey

.github/workflows/unit-tests.yml

@@ -380,7 +380,7 @@ jobs:
           fetch-depth: 0
 
       - name: Set up Python Free-threading Version
-        uses: deadsnakes/action@v3.1.0
+        uses: deadsnakes/action@v3.2.0
         with:
           python-version: 3.13-dev
           nogil: true

ci/code_checks.sh

@@ -73,12 +73,9 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.NA SA01" \
         -i "pandas.Period.freq GL08" \
         -i "pandas.Period.ordinal GL08" \
-        -i "pandas.Period.to_timestamp SA01" \
         -i "pandas.PeriodDtype.freq SA01" \
         -i "pandas.RangeIndex.from_range PR01,SA01" \
-        -i "pandas.RangeIndex.start SA01" \
         -i "pandas.RangeIndex.step SA01" \
-        -i "pandas.RangeIndex.stop SA01" \
         -i "pandas.Series.cat.add_categories PR01,PR02" \
         -i "pandas.Series.cat.as_ordered PR01" \
         -i "pandas.Series.cat.as_unordered PR01" \
@@ -93,10 +90,8 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Series.dt.floor PR01,PR02" \
         -i "pandas.Series.dt.freq GL08" \
         -i "pandas.Series.dt.month_name PR01,PR02" \
-        -i "pandas.Series.dt.nanoseconds SA01" \
         -i "pandas.Series.dt.normalize PR01" \
         -i "pandas.Series.dt.round PR01,PR02" \
-        -i "pandas.Series.dt.seconds SA01" \
         -i "pandas.Series.dt.strftime PR01,PR02" \
         -i "pandas.Series.dt.to_period PR01,PR02" \
         -i "pandas.Series.dt.total_seconds PR01" \
@@ -114,24 +109,13 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.Timedelta.resolution PR02" \
         -i "pandas.Timedelta.to_timedelta64 SA01" \
         -i "pandas.Timedelta.total_seconds SA01" \
-        -i "pandas.Timedelta.view SA01" \
-        -i "pandas.TimedeltaIndex.nanoseconds SA01" \
-        -i "pandas.TimedeltaIndex.seconds SA01" \
         -i "pandas.TimedeltaIndex.to_pytimedelta RT03,SA01" \
         -i "pandas.Timestamp.max PR02" \
         -i "pandas.Timestamp.min PR02" \
         -i "pandas.Timestamp.nanosecond GL08" \
         -i "pandas.Timestamp.resolution PR02" \
         -i "pandas.Timestamp.tzinfo GL08" \
         -i "pandas.Timestamp.year GL08" \
-        -i "pandas.api.extensions.ExtensionArray.interpolate PR01,SA01" \
-        -i "pandas.api.types.is_bool PR01,SA01" \
-        -i "pandas.api.types.is_categorical_dtype SA01" \
-        -i "pandas.api.types.is_complex PR01,SA01" \
-        -i "pandas.api.types.is_complex_dtype SA01" \
-        -i "pandas.api.types.is_datetime64_dtype SA01" \
-        -i "pandas.api.types.is_datetime64_ns_dtype SA01" \
-        -i "pandas.api.types.is_datetime64tz_dtype SA01" \
         -i "pandas.api.types.is_dict_like PR07,SA01" \
         -i "pandas.api.types.is_extension_array_dtype SA01" \
         -i "pandas.api.types.is_file_like PR07,SA01" \
@@ -165,7 +149,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.DataFrameGroupBy.agg RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.aggregate RT03" \
         -i "pandas.core.groupby.DataFrameGroupBy.boxplot PR07,RT03,SA01" \
-        -i "pandas.core.groupby.DataFrameGroupBy.filter SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.groups SA01" \
         -i "pandas.core.groupby.DataFrameGroupBy.hist RT03" \
@@ -181,7 +164,6 @@ if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
         -i "pandas.core.groupby.SeriesGroupBy.__iter__ RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.agg RT03" \
         -i "pandas.core.groupby.SeriesGroupBy.aggregate RT03" \
-        -i "pandas.core.groupby.SeriesGroupBy.filter PR01,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.get_group RT03,SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.groups SA01" \
         -i "pandas.core.groupby.SeriesGroupBy.indices SA01" \

doc/source/whatsnew/v2.3.0.rst

@@ -103,8 +103,9 @@ Conversion
 Strings
 ^^^^^^^
 - Bug in :meth:`Series.str.replace` when ``n < 0`` for :class:`StringDtype` with ``storage="pyarrow"`` (:issue:`59628`)
+- Bug in ``ser.str.slice`` with negative ``step`` with :class:`ArrowDtype` and :class:`StringDtype` with ``storage="pyarrow"`` giving incorrect results (:issue:`59710`)
 - Bug in the ``center`` method on :class:`Series` and :class:`Index` object ``str`` accessors with pyarrow-backed dtype not matching the python behavior in corner cases with an odd number of fill characters (:issue:`54792`)
-
+-
 
 Interval
 ^^^^^^^^

doc/source/whatsnew/v3.0.0.rst

@@ -55,6 +55,7 @@ Other enhancements
 - :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`)
 - :meth:`pandas.concat` will raise a ``ValueError`` when ``ignore_index=True`` and ``keys`` is not ``None`` (:issue:`59274`)
+- :meth:`str.get_dummies` now accepts a  ``dtype`` parameter to specify the dtype of the resulting DataFrame (:issue:`47872`)
 - Multiplying two :class:`DateOffset` objects will now raise a ``TypeError`` instead of a ``RecursionError`` (:issue:`59442`)
 - Restore support for reading Stata 104-format and enable reading 103-format dta files (:issue:`58554`)
 - Support passing a :class:`Iterable[Hashable]` input to :meth:`DataFrame.drop_duplicates` (:issue:`59237`)
@@ -668,6 +669,7 @@ Reshaping
 - 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`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when ``sort=False`` (:issue:`54987`, :issue:`55516`)
+- Bug in :meth:`DataFrame.pivot_table` incorrectly subaggregating results when called without an ``index`` argument (:issue:`58722`)
 - Bug in :meth:`DataFrame.unstack` producing incorrect results when manipulating empty :class:`DataFrame` with an :class:`ExtentionDtype` (:issue:`59123`)
 
 Sparse

pandas/_libs/lib.pyx

@@ -733,7 +733,9 @@ cpdef ndarray[object] ensure_string_array(
     convert_na_value : bool, default True
         If False, existing na values will be used unchanged in the new array.
     copy : bool, default True
-        Whether to ensure that a new array is returned.
+        Whether to ensure that a new array is returned. When True, a new array
+        is always returned. When False, a new array is only returned when needed
+        to avoid mutating the input array.
     skipna : bool, default True
         Whether or not to coerce nulls to their stringified form
         (e.g. if False, NaN becomes 'nan').
@@ -762,11 +764,15 @@ cpdef ndarray[object] ensure_string_array(
 
     result = np.asarray(arr, dtype="object")
 
-    if copy and (result is arr or np.shares_memory(arr, result)):
-        # GH#54654
-        result = result.copy()
-    elif not copy and result is arr:
-        already_copied = False
+    if result is arr or np.may_share_memory(arr, result):
+        # if np.asarray(..) did not make a copy of the input arr, we still need
+        #  to do that to avoid mutating the input array
+        # GH#54654: share_memory check is needed for rare cases where np.asarray
+        #  returns a new object without making a copy of the actual data
+        if copy:
+            result = result.copy()
+        else:
+            already_copied = False
     elif not copy and not result.flags.writeable:
         # Weird edge case where result is a view
         already_copied = False
@@ -1123,10 +1129,21 @@ def is_bool(obj: object) -> bool:
     """
     Return True if given object is boolean.
 
+    Parameters
+    ----------
+    obj : object
+        Object to check.
+
     Returns
     -------
     bool
 
+    See Also
+    --------
+    api.types.is_scalar : Check if the input is a scalar.
+    api.types.is_integer : Check if the input is an integer.
+    api.types.is_float : Check if the input is a float.
+
     Examples
     --------
     >>> pd.api.types.is_bool(True)
@@ -1142,10 +1159,22 @@ def is_complex(obj: object) -> bool:
     """
     Return True if given object is complex.
 
+    Parameters
+    ----------
+    obj : object
+        Object to check.
+
     Returns
     -------
     bool
 
+    See Also
+    --------
+    api.types.is_complex_dtype: Check whether the provided array or
+                                dtype is of a complex dtype.
+    api.types.is_number: Check if the object is a number.
+    api.types.is_integer: Return True if given object is integer.
+
     Examples
     --------
     >>> pd.api.types.is_complex(1 + 1j)

pandas/_libs/tslibs/period.pyx

@@ -2001,6 +2001,12 @@ cdef class _Period(PeriodMixin):
         -------
         Timestamp
 
+        See Also
+        --------
+        Timestamp : A class representing a single point in time.
+        Period : Represents a span of time with a fixed frequency.
+        PeriodIndex.to_timestamp : Convert a `PeriodIndex` to a `DatetimeIndex`.
+
         Examples
         --------
         >>> period = pd.Period('2023-1-1', freq='D')

pandas/_libs/tslibs/timedeltas.pyx

@@ -1458,11 +1458,26 @@ cdef class _Timedelta(timedelta):
         """
         Array view compatibility.
 
+        This method allows you to reinterpret the underlying data of a Timedelta
+        object as a different dtype. The `view` method provides a way to reinterpret
+        the internal representation of the `Timedelta` object without modifying its
+        data. This is particularly useful when you need to work with the underlying
+        data directly, such as for performance optimizations or interfacing with
+        low-level APIs. The returned value is typically the number of nanoseconds
+        since the epoch, represented as an integer or another specified dtype.
+
         Parameters
         ----------
         dtype : str or dtype
             The dtype to view the underlying data as.
 
+        See Also
+        --------
+        numpy.ndarray.view : Returns a view of an array with the same data.
+        Timedelta.to_numpy : Converts the Timedelta to a NumPy timedelta64.
+        Timedelta.total_seconds : Returns the total duration of the Timedelta
+            object in seconds.
+
         Examples
         --------
         >>> td = pd.Timedelta('3D')

pandas/conftest.py

@@ -1272,6 +1272,34 @@ def string_dtype(request):
     return request.param
 
 
+@pytest.fixture(
+    params=[
+        ("python", pd.NA),
+        pytest.param(("pyarrow", pd.NA), marks=td.skip_if_no("pyarrow")),
+        pytest.param(("pyarrow", np.nan), marks=td.skip_if_no("pyarrow")),
+        ("python", np.nan),
+    ],
+    ids=[
+        "string=string[python]",
+        "string=string[pyarrow]",
+        "string=str[pyarrow]",
+        "string=str[python]",
+    ],
+)
+def string_dtype_no_object(request):
+    """
+    Parametrized fixture for string dtypes.
+    * 'string[python]' (NA variant)
+    * 'string[pyarrow]' (NA variant)
+    * 'str' (NaN variant, with pyarrow)
+    * 'str' (NaN variant, without pyarrow)
+    """
+    # need to instantiate the StringDtype here instead of in the params
+    # to avoid importing pyarrow during test collection
+    storage, na_value = request.param
+    return pd.StringDtype(storage, na_value)
+
+
 @pytest.fixture(
     params=[
         "string[python]",

pandas/core/arrays/_arrow_string_mixins.py

@@ -3,13 +3,16 @@
 from functools import partial
 from typing import (
     TYPE_CHECKING,
+    Any,
     Literal,
 )
 
 import numpy as np
 
 from pandas.compat import (
     pa_version_under10p1,
+    pa_version_under11p0,
+    pa_version_under13p0,
     pa_version_under17p0,
 )
 
@@ -20,7 +23,7 @@
     import pyarrow.compute as pc
 
 if TYPE_CHECKING:
-    from collections.abc import Sized
+    from collections.abc import Callable
 
     from pandas._typing import (
         Scalar,
@@ -29,7 +32,7 @@
 
 
 class ArrowStringArrayMixin:
-    _pa_array: Sized
+    _pa_array: pa.ChunkedArray
 
     def __init__(self, *args, **kwargs) -> None:
         raise NotImplementedError
@@ -42,6 +45,9 @@ def _convert_int_result(self, result):
         # Convert an integer-dtype result to the appropriate result type
         raise NotImplementedError
 
+    def _apply_elementwise(self, func: Callable) -> list[list[Any]]:
+        raise NotImplementedError
+
     def _str_pad(
         self,
         width: int,
@@ -88,13 +94,29 @@ def _str_get(self, i: int) -> Self:
         selected = pc.utf8_slice_codeunits(
             self._pa_array, start=start, stop=stop, step=step
         )
-        null_value = pa.scalar(
-            None,
-            type=self._pa_array.type,  # type: ignore[attr-defined]
-        )
+        null_value = pa.scalar(None, type=self._pa_array.type)
         result = pc.if_else(not_out_of_bounds, selected, null_value)
         return type(self)(result)
 
+    def _str_slice(
+        self, start: int | None = None, stop: int | None = None, step: int | None = None
+    ) -> Self:
+        if pa_version_under11p0:
+            # GH#59724
+            result = self._apply_elementwise(lambda val: val[start:stop:step])
+            return type(self)(pa.chunked_array(result, type=self._pa_array.type))
+        if start is None:
+            if step is not None and step < 0:
+                # GH#59710
+                start = -1
+            else:
+                start = 0
+        if step is None:
+            step = 1
+        return type(self)(
+            pc.utf8_slice_codeunits(self._pa_array, start=start, stop=stop, step=step)
+        )
+
     def _str_slice_replace(
         self, start: int | None = None, stop: int | None = None, repl: str | None = None
     ) -> Self:
@@ -205,3 +227,37 @@ def _str_contains(
         if not isna(na):  # pyright: ignore [reportGeneralTypeIssues]
             result = result.fill_null(na)
         return self._convert_bool_result(result)
+
+    def _str_find(self, sub: str, start: int = 0, end: int | None = None):
+        if (
+            pa_version_under13p0
+            and not (start != 0 and end is not None)
+            and not (start == 0 and end is None)
+        ):
+            # GH#59562
+            res_list = self._apply_elementwise(lambda val: val.find(sub, start, end))
+            return self._convert_int_result(pa.chunked_array(res_list))
+
+        if (start == 0 or start is None) and end is None:
+            result = pc.find_substring(self._pa_array, sub)
+        else:
+            if sub == "":
+                # GH#56792
+                res_list = self._apply_elementwise(
+                    lambda val: val.find(sub, start, end)
+                )
+                return self._convert_int_result(pa.chunked_array(res_list))
+            if start is None:
+                start_offset = 0
+                start = 0
+            elif start < 0:
+                start_offset = pc.add(start, pc.utf8_length(self._pa_array))
+                start_offset = pc.if_else(pc.less(start_offset, 0), 0, start_offset)
+            else:
+                start_offset = start
+            slices = pc.utf8_slice_codeunits(self._pa_array, start, stop=end)
+            result = pc.find_substring(slices, sub)
+            found = pc.not_equal(result, pa.scalar(-1, type=result.type))
+            offset_result = pc.add(result, start_offset)
+            result = pc.if_else(found, offset_result, -1)
+        return self._convert_int_result(result)

pandas/core/arrays/arrow/_arrow_utils.py

@@ -1,27 +1,8 @@
 from __future__ import annotations
 
-import warnings
-
 import numpy as np
 import pyarrow
 
-from pandas._config.config import get_option
-
-from pandas.errors import PerformanceWarning
-from pandas.util._exceptions import find_stack_level
-
-
-def fallback_performancewarning(version: str | None = None) -> None:
-    """
-    Raise a PerformanceWarning for falling back to ExtensionArray's
-    non-pyarrow method
-    """
-    if get_option("performance_warnings"):
-        msg = "Falling back on a non-pyarrow code path which may decrease performance."
-        if version is not None:
-            msg += f" Upgrade to pyarrow >={version} to possibly suppress this warning."
-        warnings.warn(msg, PerformanceWarning, stacklevel=find_stack_level())
-
 
 def pyarrow_array_to_numpy_and_mask(
     arr, dtype: np.dtype