done

lib/python3.11/site-packages/pandas/core/arrays/__init__.py

@@ -0,0 +1,43 @@
+from pandas.core.arrays.arrow import ArrowExtensionArray
+from pandas.core.arrays.base import (
+    ExtensionArray,
+    ExtensionOpsMixin,
+    ExtensionScalarOpsMixin,
+)
+from pandas.core.arrays.boolean import BooleanArray
+from pandas.core.arrays.categorical import Categorical
+from pandas.core.arrays.datetimes import DatetimeArray
+from pandas.core.arrays.floating import FloatingArray
+from pandas.core.arrays.integer import IntegerArray
+from pandas.core.arrays.interval import IntervalArray
+from pandas.core.arrays.masked import BaseMaskedArray
+from pandas.core.arrays.numpy_ import NumpyExtensionArray
+from pandas.core.arrays.period import (
+    PeriodArray,
+    period_array,
+)
+from pandas.core.arrays.sparse import SparseArray
+from pandas.core.arrays.string_ import StringArray
+from pandas.core.arrays.string_arrow import ArrowStringArray
+from pandas.core.arrays.timedeltas import TimedeltaArray
+
+__all__ = [
+    "ArrowExtensionArray",
+    "ExtensionArray",
+    "ExtensionOpsMixin",
+    "ExtensionScalarOpsMixin",
+    "ArrowStringArray",
+    "BaseMaskedArray",
+    "BooleanArray",
+    "Categorical",
+    "DatetimeArray",
+    "FloatingArray",
+    "IntegerArray",
+    "IntervalArray",
+    "NumpyExtensionArray",
+    "PeriodArray",
+    "period_array",
+    "SparseArray",
+    "StringArray",
+    "TimedeltaArray",
+]

lib/python3.11/site-packages/pandas/core/arrays/_arrow_string_mixins.py

@@ -0,0 +1,362 @@
+from __future__ import annotations
+
+from functools import partial
+import re
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas.compat import (
+    pa_version_under10p1,
+    pa_version_under11p0,
+    pa_version_under13p0,
+    pa_version_under17p0,
+)
+
+if not pa_version_under10p1:
+    import pyarrow as pa
+    import pyarrow.compute as pc
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
+    from pandas._typing import (
+        Scalar,
+        Self,
+    )
+
+
+class ArrowStringArrayMixin:
+    _pa_array: pa.ChunkedArray
+
+    def __init__(self, *args, **kwargs) -> None:
+        raise NotImplementedError
+
+    def _convert_bool_result(self, result, na=lib.no_default, method_name=None):
+        # Convert a bool-dtype result to the appropriate result type
+        raise NotImplementedError
+
+    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_len(self):
+        result = pc.utf8_length(self._pa_array)
+        return self._convert_int_result(result)
+
+    def _str_lower(self) -> Self:
+        return type(self)(pc.utf8_lower(self._pa_array))
+
+    def _str_upper(self) -> Self:
+        return type(self)(pc.utf8_upper(self._pa_array))
+
+    def _str_strip(self, to_strip=None) -> Self:
+        if to_strip is None:
+            result = pc.utf8_trim_whitespace(self._pa_array)
+        else:
+            result = pc.utf8_trim(self._pa_array, characters=to_strip)
+        return type(self)(result)
+
+    def _str_lstrip(self, to_strip=None) -> Self:
+        if to_strip is None:
+            result = pc.utf8_ltrim_whitespace(self._pa_array)
+        else:
+            result = pc.utf8_ltrim(self._pa_array, characters=to_strip)
+        return type(self)(result)
+
+    def _str_rstrip(self, to_strip=None) -> Self:
+        if to_strip is None:
+            result = pc.utf8_rtrim_whitespace(self._pa_array)
+        else:
+            result = pc.utf8_rtrim(self._pa_array, characters=to_strip)
+        return type(self)(result)
+
+    def _str_pad(
+        self,
+        width: int,
+        side: Literal["left", "right", "both"] = "left",
+        fillchar: str = " ",
+    ):
+        if side == "left":
+            pa_pad = pc.utf8_lpad
+        elif side == "right":
+            pa_pad = pc.utf8_rpad
+        elif side == "both":
+            if pa_version_under17p0:
+                # GH#59624 fall back to object dtype
+                from pandas import array as pd_array
+
+                obj_arr = self.astype(object, copy=False)  # type: ignore[attr-defined]
+                obj = pd_array(obj_arr, dtype=object)
+                result = obj._str_pad(width, side, fillchar)  # type: ignore[attr-defined]
+                return type(self)._from_sequence(result, dtype=self.dtype)  # type: ignore[attr-defined]
+            else:
+                # GH#54792
+                # https://github.com/apache/arrow/issues/15053#issuecomment-2317032347
+                lean_left = (width % 2) == 0
+                pa_pad = partial(pc.utf8_center, lean_left_on_odd_padding=lean_left)
+        else:
+            raise ValueError(
+                f"Invalid side: {side}. Side must be one of 'left', 'right', 'both'"
+            )
+        return type(self)(pa_pad(self._pa_array, width=width, padding=fillchar))
+
+    def _str_get(self, i: int):
+        lengths = pc.utf8_length(self._pa_array)
+        if i >= 0:
+            out_of_bounds = pc.greater_equal(i, lengths)
+            start = i
+            stop = i + 1
+            step = 1
+        else:
+            out_of_bounds = pc.greater(-i, lengths)
+            start = i
+            stop = i - 1
+            step = -1
+        not_out_of_bounds = pc.invert(out_of_bounds.fill_null(True))
+        selected = pc.utf8_slice_codeunits(
+            self._pa_array, start=start, stop=stop, step=step
+        )
+        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
+    ):
+        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
+    ):
+        if repl is None:
+            repl = ""
+        if start is None:
+            start = 0
+        if stop is None:
+            stop = np.iinfo(np.int64).max
+        return type(self)(pc.utf8_replace_slice(self._pa_array, start, stop, repl))
+
+    def _str_replace(
+        self,
+        pat: str | re.Pattern,
+        repl: str | Callable,
+        n: int = -1,
+        case: bool = True,
+        flags: int = 0,
+        regex: bool = True,
+    ) -> Self:
+        if isinstance(pat, re.Pattern) or callable(repl) or not case or flags:
+            raise NotImplementedError(
+                "replace is not supported with a re.Pattern, callable repl, "
+                "case=False, or flags!=0"
+            )
+
+        func = pc.replace_substring_regex if regex else pc.replace_substring
+        # https://github.com/apache/arrow/issues/39149
+        # GH 56404, unexpected behavior with negative max_replacements with pyarrow.
+        pa_max_replacements = None if n < 0 else n
+        result = func(
+            self._pa_array,
+            pattern=pat,
+            replacement=repl,
+            max_replacements=pa_max_replacements,
+        )
+        return type(self)(result)
+
+    def _str_capitalize(self) -> Self:
+        return type(self)(pc.utf8_capitalize(self._pa_array))
+
+    def _str_title(self):
+        return type(self)(pc.utf8_title(self._pa_array))
+
+    def _str_swapcase(self):
+        return type(self)(pc.utf8_swapcase(self._pa_array))
+
+    def _str_removeprefix(self, prefix: str):
+        if not pa_version_under13p0:
+            starts_with = pc.starts_with(self._pa_array, pattern=prefix)
+            removed = pc.utf8_slice_codeunits(self._pa_array, len(prefix))
+            result = pc.if_else(starts_with, removed, self._pa_array)
+            return type(self)(result)
+        predicate = lambda val: val.removeprefix(prefix)
+        result = self._apply_elementwise(predicate)
+        return type(self)(pa.chunked_array(result))
+
+    def _str_removesuffix(self, suffix: str):
+        ends_with = pc.ends_with(self._pa_array, pattern=suffix)
+        removed = pc.utf8_slice_codeunits(self._pa_array, 0, stop=-len(suffix))
+        result = pc.if_else(ends_with, removed, self._pa_array)
+        return type(self)(result)
+
+    def _str_startswith(
+        self, pat: str | tuple[str, ...], na: Scalar | lib.NoDefault = lib.no_default
+    ):
+        if isinstance(pat, str):
+            result = pc.starts_with(self._pa_array, pattern=pat)
+        else:
+            if len(pat) == 0:
+                # For empty tuple we return null for missing values and False
+                #  for valid values.
+                result = pc.if_else(pc.is_null(self._pa_array), None, False)
+            else:
+                result = pc.starts_with(self._pa_array, pattern=pat[0])
+
+                for p in pat[1:]:
+                    result = pc.or_(result, pc.starts_with(self._pa_array, pattern=p))
+        return self._convert_bool_result(result, na=na, method_name="startswith")
+
+    def _str_endswith(
+        self, pat: str | tuple[str, ...], na: Scalar | lib.NoDefault = lib.no_default
+    ):
+        if isinstance(pat, str):
+            result = pc.ends_with(self._pa_array, pattern=pat)
+        else:
+            if len(pat) == 0:
+                # For empty tuple we return null for missing values and False
+                #  for valid values.
+                result = pc.if_else(pc.is_null(self._pa_array), None, False)
+            else:
+                result = pc.ends_with(self._pa_array, pattern=pat[0])
+
+                for p in pat[1:]:
+                    result = pc.or_(result, pc.ends_with(self._pa_array, pattern=p))
+        return self._convert_bool_result(result, na=na, method_name="endswith")
+
+    def _str_isalnum(self):
+        result = pc.utf8_is_alnum(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isalpha(self):
+        result = pc.utf8_is_alpha(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isdecimal(self):
+        result = pc.utf8_is_decimal(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isdigit(self):
+        result = pc.utf8_is_digit(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_islower(self):
+        result = pc.utf8_is_lower(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isnumeric(self):
+        result = pc.utf8_is_numeric(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isspace(self):
+        result = pc.utf8_is_space(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_istitle(self):
+        result = pc.utf8_is_title(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_isupper(self):
+        result = pc.utf8_is_upper(self._pa_array)
+        return self._convert_bool_result(result)
+
+    def _str_contains(
+        self,
+        pat,
+        case: bool = True,
+        flags: int = 0,
+        na: Scalar | lib.NoDefault = lib.no_default,
+        regex: bool = True,
+    ):
+        if flags:
+            raise NotImplementedError(f"contains not implemented with {flags=}")
+
+        if regex:
+            pa_contains = pc.match_substring_regex
+        else:
+            pa_contains = pc.match_substring
+        result = pa_contains(self._pa_array, pat, ignore_case=not case)
+        return self._convert_bool_result(result, na=na, method_name="contains")
+
+    def _str_match(
+        self,
+        pat: str | re.Pattern,
+        case: bool = True,
+        flags: int = 0,
+        na: Scalar | lib.NoDefault = lib.no_default,
+    ):
+        if isinstance(pat, re.Pattern):
+            # GH#61952
+            pat = pat.pattern
+        if isinstance(pat, str) and not pat.startswith("^"):
+            pat = f"^{pat}"
+        return self._str_contains(pat, case, flags, na, regex=True)
+
+    def _str_fullmatch(
+        self,
+        pat: str | re.Pattern,
+        case: bool = True,
+        flags: int = 0,
+        na: Scalar | lib.NoDefault = lib.no_default,
+    ):
+        if isinstance(pat, re.Pattern):
+            # GH#61952
+            pat = pat.pattern
+        if isinstance(pat, str) and (not pat.endswith("$") or pat.endswith("\\$")):
+            pat = f"{pat}$"
+        return self._str_match(pat, case, flags, na)
+
+    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)

lib/python3.11/site-packages/pandas/core/arrays/_mixins.py

@@ -0,0 +1,544 @@
+from __future__ import annotations
+
+from functools import wraps
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Literal,
+    cast,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas._libs.arrays import NDArrayBacked
+from pandas._libs.tslibs import is_supported_dtype
+from pandas._typing import (
+    ArrayLike,
+    AxisInt,
+    Dtype,
+    F,
+    FillnaOptions,
+    PositionalIndexer2D,
+    PositionalIndexerTuple,
+    ScalarIndexer,
+    Self,
+    SequenceIndexer,
+    Shape,
+    TakeIndexer,
+    npt,
+)
+from pandas.errors import AbstractMethodError
+from pandas.util._decorators import doc
+from pandas.util._validators import (
+    validate_bool_kwarg,
+    validate_fillna_kwargs,
+    validate_insert_loc,
+)
+
+from pandas.core.dtypes.common import pandas_dtype
+from pandas.core.dtypes.dtypes import (
+    DatetimeTZDtype,
+    ExtensionDtype,
+    PeriodDtype,
+)
+from pandas.core.dtypes.missing import array_equivalent
+
+from pandas.core import missing
+from pandas.core.algorithms import (
+    take,
+    unique,
+    value_counts_internal as value_counts,
+)
+from pandas.core.array_algos.quantile import quantile_with_mask
+from pandas.core.array_algos.transforms import shift
+from pandas.core.arrays.base import ExtensionArray
+from pandas.core.construction import extract_array
+from pandas.core.indexers import check_array_indexer
+from pandas.core.sorting import nargminmax
+
+if TYPE_CHECKING:
+    from collections.abc import Sequence
+
+    from pandas._typing import (
+        NumpySorter,
+        NumpyValueArrayLike,
+    )
+
+    from pandas import Series
+
+
+def ravel_compat(meth: F) -> F:
+    """
+    Decorator to ravel a 2D array before passing it to a cython operation,
+    then reshape the result to our own shape.
+    """
+
+    @wraps(meth)
+    def method(self, *args, **kwargs):
+        if self.ndim == 1:
+            return meth(self, *args, **kwargs)
+
+        flags = self._ndarray.flags
+        flat = self.ravel("K")
+        result = meth(flat, *args, **kwargs)
+        order = "F" if flags.f_contiguous else "C"
+        return result.reshape(self.shape, order=order)
+
+    return cast(F, method)
+
+
+class NDArrayBackedExtensionArray(NDArrayBacked, ExtensionArray):
+    """
+    ExtensionArray that is backed by a single NumPy ndarray.
+    """
+
+    _ndarray: np.ndarray
+
+    # scalar used to denote NA value inside our self._ndarray, e.g. -1
+    #  for Categorical, iNaT for Period. Outside of object dtype,
+    #  self.isna() should be exactly locations in self._ndarray with
+    #  _internal_fill_value.
+    _internal_fill_value: Any
+
+    def _box_func(self, x):
+        """
+        Wrap numpy type in our dtype.type if necessary.
+        """
+        return x
+
+    def _validate_scalar(self, value):
+        # used by NDArrayBackedExtensionIndex.insert
+        raise AbstractMethodError(self)
+
+    # ------------------------------------------------------------------------
+
+    def view(self, dtype: Dtype | None = None) -> ArrayLike:
+        # We handle datetime64, datetime64tz, timedelta64, and period
+        #  dtypes here. Everything else we pass through to the underlying
+        #  ndarray.
+        if dtype is None or dtype is self.dtype:
+            return self._from_backing_data(self._ndarray)
+
+        if isinstance(dtype, type):
+            # we sometimes pass non-dtype objects, e.g np.ndarray;
+            #  pass those through to the underlying ndarray
+            return self._ndarray.view(dtype)
+
+        dtype = pandas_dtype(dtype)
+        arr = self._ndarray
+
+        if isinstance(dtype, PeriodDtype):
+            cls = dtype.construct_array_type()
+            return cls(arr.view("i8"), dtype=dtype)
+        elif isinstance(dtype, DatetimeTZDtype):
+            dt_cls = dtype.construct_array_type()
+            dt64_values = arr.view(f"M8[{dtype.unit}]")
+            return dt_cls._simple_new(dt64_values, dtype=dtype)
+        elif lib.is_np_dtype(dtype, "M") and is_supported_dtype(dtype):
+            from pandas.core.arrays import DatetimeArray
+
+            dt64_values = arr.view(dtype)
+            return DatetimeArray._simple_new(dt64_values, dtype=dtype)
+
+        elif lib.is_np_dtype(dtype, "m") and is_supported_dtype(dtype):
+            from pandas.core.arrays import TimedeltaArray
+
+            td64_values = arr.view(dtype)
+            return TimedeltaArray._simple_new(td64_values, dtype=dtype)
+
+        # error: Argument "dtype" to "view" of "_ArrayOrScalarCommon" has incompatible
+        # type "Union[ExtensionDtype, dtype[Any]]"; expected "Union[dtype[Any], None,
+        # type, _SupportsDType, str, Union[Tuple[Any, int], Tuple[Any, Union[int,
+        # Sequence[int]]], List[Any], _DTypeDict, Tuple[Any, Any]]]"
+        return arr.view(dtype=dtype)  # type: ignore[arg-type]
+
+    def take(
+        self,
+        indices: TakeIndexer,
+        *,
+        allow_fill: bool = False,
+        fill_value: Any = None,
+        axis: AxisInt = 0,
+    ) -> Self:
+        if allow_fill:
+            fill_value = self._validate_scalar(fill_value)
+
+        new_data = take(
+            self._ndarray,
+            indices,
+            allow_fill=allow_fill,
+            fill_value=fill_value,
+            axis=axis,
+        )
+        return self._from_backing_data(new_data)
+
+    # ------------------------------------------------------------------------
+
+    def equals(self, other) -> bool:
+        if type(self) is not type(other):
+            return False
+        if self.dtype != other.dtype:
+            return False
+        return bool(array_equivalent(self._ndarray, other._ndarray, dtype_equal=True))
+
+    @classmethod
+    def _from_factorized(cls, values, original):
+        assert values.dtype == original._ndarray.dtype
+        return original._from_backing_data(values)
+
+    def _values_for_argsort(self) -> np.ndarray:
+        return self._ndarray
+
+    def _values_for_factorize(self):
+        return self._ndarray, self._internal_fill_value
+
+    def _hash_pandas_object(
+        self, *, encoding: str, hash_key: str, categorize: bool
+    ) -> npt.NDArray[np.uint64]:
+        from pandas.core.util.hashing import hash_array
+
+        values = self._ndarray
+        return hash_array(
+            values, encoding=encoding, hash_key=hash_key, categorize=categorize
+        )
+
+    # Signature of "argmin" incompatible with supertype "ExtensionArray"
+    def argmin(self, axis: AxisInt = 0, skipna: bool = True):  # type: ignore[override]
+        # override base class by adding axis keyword
+        validate_bool_kwarg(skipna, "skipna")
+        if not skipna and self._hasna:
+            raise NotImplementedError
+        return nargminmax(self, "argmin", axis=axis)
+
+    # Signature of "argmax" incompatible with supertype "ExtensionArray"
+    def argmax(self, axis: AxisInt = 0, skipna: bool = True):  # type: ignore[override]
+        # override base class by adding axis keyword
+        validate_bool_kwarg(skipna, "skipna")
+        if not skipna and self._hasna:
+            raise NotImplementedError
+        return nargminmax(self, "argmax", axis=axis)
+
+    def unique(self) -> Self:
+        new_data = unique(self._ndarray)
+        return self._from_backing_data(new_data)
+
+    @classmethod
+    @doc(ExtensionArray._concat_same_type)
+    def _concat_same_type(
+        cls,
+        to_concat: Sequence[Self],
+        axis: AxisInt = 0,
+    ) -> Self:
+        if not lib.dtypes_all_equal([x.dtype for x in to_concat]):
+            dtypes = {str(x.dtype) for x in to_concat}
+            raise ValueError("to_concat must have the same dtype", dtypes)
+
+        return super()._concat_same_type(to_concat, axis=axis)
+
+    @doc(ExtensionArray.searchsorted)
+    def searchsorted(
+        self,
+        value: NumpyValueArrayLike | ExtensionArray,
+        side: Literal["left", "right"] = "left",
+        sorter: NumpySorter | None = None,
+    ) -> npt.NDArray[np.intp] | np.intp:
+        npvalue = self._validate_setitem_value(value)
+        return self._ndarray.searchsorted(npvalue, side=side, sorter=sorter)
+
+    @doc(ExtensionArray.shift)
+    def shift(self, periods: int = 1, fill_value=None):
+        # NB: shift is always along axis=0
+        axis = 0
+        fill_value = self._validate_scalar(fill_value)
+        new_values = shift(self._ndarray, periods, axis, fill_value)
+
+        return self._from_backing_data(new_values)
+
+    def __setitem__(self, key, value) -> None:
+        key = check_array_indexer(self, key)
+        value = self._validate_setitem_value(value)
+        self._ndarray[key] = value
+
+    def _validate_setitem_value(self, value):
+        return value
+
+    @overload
+    def __getitem__(self, key: ScalarIndexer) -> Any:
+        ...
+
+    @overload
+    def __getitem__(
+        self,
+        key: SequenceIndexer | PositionalIndexerTuple,
+    ) -> Self:
+        ...
+
+    def __getitem__(
+        self,
+        key: PositionalIndexer2D,
+    ) -> Self | Any:
+        if lib.is_integer(key):
+            # fast-path
+            result = self._ndarray[key]
+            if self.ndim == 1:
+                return self._box_func(result)
+            return self._from_backing_data(result)
+
+        # error: Incompatible types in assignment (expression has type "ExtensionArray",
+        # variable has type "Union[int, slice, ndarray]")
+        key = extract_array(key, extract_numpy=True)  # type: ignore[assignment]
+        key = check_array_indexer(self, key)
+        result = self._ndarray[key]
+        if lib.is_scalar(result):
+            return self._box_func(result)
+
+        result = self._from_backing_data(result)
+        return result
+
+    def _fill_mask_inplace(
+        self, method: str, limit: int | None, mask: npt.NDArray[np.bool_]
+    ) -> None:
+        # (for now) when self.ndim == 2, we assume axis=0
+        func = missing.get_fill_func(method, ndim=self.ndim)
+        func(self._ndarray.T, limit=limit, mask=mask.T)
+
+    def _pad_or_backfill(
+        self,
+        *,
+        method: FillnaOptions,
+        limit: int | None = None,
+        limit_area: Literal["inside", "outside"] | None = None,
+        copy: bool = True,
+    ) -> Self:
+        mask = self.isna()
+        if mask.any():
+            # (for now) when self.ndim == 2, we assume axis=0
+            func = missing.get_fill_func(method, ndim=self.ndim)
+
+            npvalues = self._ndarray.T
+            if copy:
+                npvalues = npvalues.copy()
+            func(npvalues, limit=limit, limit_area=limit_area, mask=mask.T)
+            npvalues = npvalues.T
+
+            if copy:
+                new_values = self._from_backing_data(npvalues)
+            else:
+                new_values = self
+
+        else:
+            if copy:
+                new_values = self.copy()
+            else:
+                new_values = self
+        return new_values
+
+    @doc(ExtensionArray.fillna)
+    def fillna(
+        self, value=None, method=None, limit: int | None = None, copy: bool = True
+    ) -> Self:
+        value, method = validate_fillna_kwargs(
+            value, method, validate_scalar_dict_value=False
+        )
+
+        mask = self.isna()
+        # error: Argument 2 to "check_value_size" has incompatible type
+        # "ExtensionArray"; expected "ndarray"
+        value = missing.check_value_size(
+            value, mask, len(self)  # type: ignore[arg-type]
+        )
+
+        if mask.any():
+            if method is not None:
+                # (for now) when self.ndim == 2, we assume axis=0
+                func = missing.get_fill_func(method, ndim=self.ndim)
+                npvalues = self._ndarray.T
+                if copy:
+                    npvalues = npvalues.copy()
+                func(npvalues, limit=limit, mask=mask.T)
+                npvalues = npvalues.T
+
+                # TODO: NumpyExtensionArray didn't used to copy, need tests
+                #  for this
+                new_values = self._from_backing_data(npvalues)
+            else:
+                # fill with value
+                if copy:
+                    new_values = self.copy()
+                else:
+                    new_values = self[:]
+                new_values[mask] = value
+        else:
+            # We validate the fill_value even if there is nothing to fill
+            if value is not None:
+                self._validate_setitem_value(value)
+
+            if not copy:
+                new_values = self[:]
+            else:
+                new_values = self.copy()
+        return new_values
+
+    # ------------------------------------------------------------------------
+    # Reductions
+
+    def _wrap_reduction_result(self, axis: AxisInt | None, result):
+        if axis is None or self.ndim == 1:
+            return self._box_func(result)
+        return self._from_backing_data(result)
+
+    # ------------------------------------------------------------------------
+    # __array_function__ methods
+
+    def _putmask(self, mask: npt.NDArray[np.bool_], value) -> None:
+        """
+        Analogue to np.putmask(self, mask, value)
+
+        Parameters
+        ----------
+        mask : np.ndarray[bool]
+        value : scalar or listlike
+
+        Raises
+        ------
+        TypeError
+            If value cannot be cast to self.dtype.
+        """
+        value = self._validate_setitem_value(value)
+
+        np.putmask(self._ndarray, mask, value)
+
+    def _where(self: Self, mask: npt.NDArray[np.bool_], value) -> Self:
+        """
+        Analogue to np.where(mask, self, value)
+
+        Parameters
+        ----------
+        mask : np.ndarray[bool]
+        value : scalar or listlike
+
+        Raises
+        ------
+        TypeError
+            If value cannot be cast to self.dtype.
+        """
+        value = self._validate_setitem_value(value)
+
+        res_values = np.where(mask, self._ndarray, value)
+        if res_values.dtype != self._ndarray.dtype:
+            raise AssertionError(
+                # GH#56410
+                "Something has gone wrong, please report a bug at "
+                "github.com/pandas-dev/pandas/"
+            )
+        return self._from_backing_data(res_values)
+
+    # ------------------------------------------------------------------------
+    # Index compat methods
+
+    def insert(self, loc: int, item) -> Self:
+        """
+        Make new ExtensionArray inserting new item at location. Follows
+        Python list.append semantics for negative values.
+
+        Parameters
+        ----------
+        loc : int
+        item : object
+
+        Returns
+        -------
+        type(self)
+        """
+        loc = validate_insert_loc(loc, len(self))
+
+        code = self._validate_scalar(item)
+
+        new_vals = np.concatenate(
+            (
+                self._ndarray[:loc],
+                np.asarray([code], dtype=self._ndarray.dtype),
+                self._ndarray[loc:],
+            )
+        )
+        return self._from_backing_data(new_vals)
+
+    # ------------------------------------------------------------------------
+    # Additional array methods
+    #  These are not part of the EA API, but we implement them because
+    #  pandas assumes they're there.
+
+    def value_counts(self, dropna: bool = True) -> Series:
+        """
+        Return a Series containing counts of unique values.
+
+        Parameters
+        ----------
+        dropna : bool, default True
+            Don't include counts of NA values.
+
+        Returns
+        -------
+        Series
+        """
+        if self.ndim != 1:
+            raise NotImplementedError
+
+        from pandas import (
+            Index,
+            Series,
+        )
+
+        if dropna:
+            # error: Unsupported operand type for ~ ("ExtensionArray")
+            values = self[~self.isna()]._ndarray  # type: ignore[operator]
+        else:
+            values = self._ndarray
+
+        result = value_counts(values, sort=False, dropna=dropna)
+
+        index_arr = self._from_backing_data(np.asarray(result.index._data))
+        index = Index(index_arr, name=result.index.name)
+        return Series(result._values, index=index, name=result.name, copy=False)
+
+    def _quantile(
+        self,
+        qs: npt.NDArray[np.float64],
+        interpolation: str,
+    ) -> Self:
+        # TODO: disable for Categorical if not ordered?
+
+        mask = np.asarray(self.isna())
+        arr = self._ndarray
+        fill_value = self._internal_fill_value
+
+        res_values = quantile_with_mask(arr, mask, fill_value, qs, interpolation)
+        if res_values.dtype == self._ndarray.dtype:
+            return self._from_backing_data(res_values)
+        else:
+            # e.g. test_quantile_empty we are empty integer dtype and res_values
+            #  has floating dtype
+            # TODO: technically __init__ isn't defined here.
+            #  Should we raise NotImplementedError and handle this on NumpyEA?
+            return type(self)(res_values)  # type: ignore[call-arg]
+
+    # ------------------------------------------------------------------------
+    # numpy-like methods
+
+    @classmethod
+    def _empty(cls, shape: Shape, dtype: ExtensionDtype) -> Self:
+        """
+        Analogous to np.empty(shape, dtype=dtype)
+
+        Parameters
+        ----------
+        shape : tuple[int]
+        dtype : ExtensionDtype
+        """
+        # The base implementation uses a naive approach to find the dtype
+        #  for the backing ndarray
+        arr = cls._from_sequence([], dtype=dtype)
+        backing = np.empty(shape, dtype=arr._ndarray.dtype)
+        return arr._from_backing_data(backing)

lib/python3.11/site-packages/pandas/core/arrays/_ranges.py

@@ -0,0 +1,207 @@
+"""
+Helper functions to generate range-like data for DatetimeArray
+(and possibly TimedeltaArray/PeriodArray)
+"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from pandas._libs.lib import i8max
+from pandas._libs.tslibs import (
+    BaseOffset,
+    OutOfBoundsDatetime,
+    Timedelta,
+    Timestamp,
+    iNaT,
+)
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+
+def generate_regular_range(
+    start: Timestamp | Timedelta | None,
+    end: Timestamp | Timedelta | None,
+    periods: int | None,
+    freq: BaseOffset,
+    unit: str = "ns",
+) -> npt.NDArray[np.intp]:
+    """
+    Generate a range of dates or timestamps with the spans between dates
+    described by the given `freq` DateOffset.
+
+    Parameters
+    ----------
+    start : Timedelta, Timestamp or None
+        First point of produced date range.
+    end : Timedelta, Timestamp or None
+        Last point of produced date range.
+    periods : int or None
+        Number of periods in produced date range.
+    freq : Tick
+        Describes space between dates in produced date range.
+    unit : str, default "ns"
+        The resolution the output is meant to represent.
+
+    Returns
+    -------
+    ndarray[np.int64]
+        Representing the given resolution.
+    """
+    istart = start._value if start is not None else None
+    iend = end._value if end is not None else None
+    freq.nanos  # raises if non-fixed frequency
+    td = Timedelta(freq)
+    b: int
+    e: int
+    try:
+        td = td.as_unit(unit, round_ok=False)
+    except ValueError as err:
+        raise ValueError(
+            f"freq={freq} is incompatible with unit={unit}. "
+            "Use a lower freq or a higher unit instead."
+        ) from err
+    stride = int(td._value)
+
+    if periods is None and istart is not None and iend is not None:
+        b = istart
+        # cannot just use e = Timestamp(end) + 1 because arange breaks when
+        # stride is too large, see GH10887
+        e = b + (iend - b) // stride * stride + stride // 2 + 1
+    elif istart is not None and periods is not None:
+        b = istart
+        e = _generate_range_overflow_safe(b, periods, stride, side="start")
+    elif iend is not None and periods is not None:
+        e = iend + stride
+        b = _generate_range_overflow_safe(e, periods, stride, side="end")
+    else:
+        raise ValueError(
+            "at least 'start' or 'end' should be specified if a 'period' is given."
+        )
+
+    with np.errstate(over="raise"):
+        # If the range is sufficiently large, np.arange may overflow
+        #  and incorrectly return an empty array if not caught.
+        try:
+            values = np.arange(b, e, stride, dtype=np.int64)
+        except FloatingPointError:
+            xdr = [b]
+            while xdr[-1] != e:
+                xdr.append(xdr[-1] + stride)
+            values = np.array(xdr[:-1], dtype=np.int64)
+    return values
+
+
+def _generate_range_overflow_safe(
+    endpoint: int, periods: int, stride: int, side: str = "start"
+) -> int:
+    """
+    Calculate the second endpoint for passing to np.arange, checking
+    to avoid an integer overflow.  Catch OverflowError and re-raise
+    as OutOfBoundsDatetime.
+
+    Parameters
+    ----------
+    endpoint : int
+        nanosecond timestamp of the known endpoint of the desired range
+    periods : int
+        number of periods in the desired range
+    stride : int
+        nanoseconds between periods in the desired range
+    side : {'start', 'end'}
+        which end of the range `endpoint` refers to
+
+    Returns
+    -------
+    other_end : int
+
+    Raises
+    ------
+    OutOfBoundsDatetime
+    """
+    # GH#14187 raise instead of incorrectly wrapping around
+    assert side in ["start", "end"]
+
+    i64max = np.uint64(i8max)
+    msg = f"Cannot generate range with {side}={endpoint} and periods={periods}"
+
+    with np.errstate(over="raise"):
+        # if periods * strides cannot be multiplied within the *uint64* bounds,
+        #  we cannot salvage the operation by recursing, so raise
+        try:
+            addend = np.uint64(periods) * np.uint64(np.abs(stride))
+        except FloatingPointError as err:
+            raise OutOfBoundsDatetime(msg) from err
+
+    if np.abs(addend) <= i64max:
+        # relatively easy case without casting concerns
+        return _generate_range_overflow_safe_signed(endpoint, periods, stride, side)
+
+    elif (endpoint > 0 and side == "start" and stride > 0) or (
+        endpoint < 0 < stride and side == "end"
+    ):
+        # no chance of not-overflowing
+        raise OutOfBoundsDatetime(msg)
+
+    elif side == "end" and endpoint - stride <= i64max < endpoint:
+        # in _generate_regular_range we added `stride` thereby overflowing
+        #  the bounds.  Adjust to fix this.
+        return _generate_range_overflow_safe(
+            endpoint - stride, periods - 1, stride, side
+        )
+
+    # split into smaller pieces
+    mid_periods = periods // 2
+    remaining = periods - mid_periods
+    assert 0 < remaining < periods, (remaining, periods, endpoint, stride)
+
+    midpoint = int(_generate_range_overflow_safe(endpoint, mid_periods, stride, side))
+    return _generate_range_overflow_safe(midpoint, remaining, stride, side)
+
+
+def _generate_range_overflow_safe_signed(
+    endpoint: int, periods: int, stride: int, side: str
+) -> int:
+    """
+    A special case for _generate_range_overflow_safe where `periods * stride`
+    can be calculated without overflowing int64 bounds.
+    """
+    assert side in ["start", "end"]
+    if side == "end":
+        stride *= -1
+
+    with np.errstate(over="raise"):
+        addend = np.int64(periods) * np.int64(stride)
+        try:
+            # easy case with no overflows
+            result = np.int64(endpoint) + addend
+            if result == iNaT:
+                # Putting this into a DatetimeArray/TimedeltaArray
+                #  would incorrectly be interpreted as NaT
+                raise OverflowError
+            return int(result)
+        except (FloatingPointError, OverflowError):
+            # with endpoint negative and addend positive we risk
+            #  FloatingPointError; with reversed signed we risk OverflowError
+            pass
+
+        # if stride and endpoint had opposite signs, then endpoint + addend
+        #  should never overflow.  so they must have the same signs
+        assert (stride > 0 and endpoint >= 0) or (stride < 0 and endpoint <= 0)
+
+        if stride > 0:
+            # watch out for very special case in which we just slightly
+            #  exceed implementation bounds, but when passing the result to
+            #  np.arange will get a result slightly within the bounds
+
+            uresult = np.uint64(endpoint) + np.uint64(addend)
+            i64max = np.uint64(i8max)
+            assert uresult > i64max
+            if uresult <= i64max + np.uint64(stride):
+                return int(uresult)
+
+    raise OutOfBoundsDatetime(
+        f"Cannot generate range with {side}={endpoint} and periods={periods}"
+    )

lib/python3.11/site-packages/pandas/core/arrays/_utils.py

@@ -0,0 +1,63 @@
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas.errors import LossySetitemError
+
+from pandas.core.dtypes.cast import np_can_hold_element
+from pandas.core.dtypes.common import is_numeric_dtype
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        npt,
+    )
+
+
+def to_numpy_dtype_inference(
+    arr: ArrayLike, dtype: npt.DTypeLike | None, na_value, hasna: bool
+) -> tuple[npt.DTypeLike, Any]:
+    if dtype is None and is_numeric_dtype(arr.dtype):
+        dtype_given = False
+        if hasna:
+            if arr.dtype.kind == "b":
+                dtype = np.dtype(np.object_)
+            else:
+                if arr.dtype.kind in "iu":
+                    dtype = np.dtype(np.float64)
+                else:
+                    dtype = arr.dtype.numpy_dtype  # type: ignore[union-attr]
+                if na_value is lib.no_default:
+                    na_value = np.nan
+        else:
+            dtype = arr.dtype.numpy_dtype  # type: ignore[union-attr]
+    elif dtype is not None:
+        dtype = np.dtype(dtype)
+        dtype_given = True
+    else:
+        dtype_given = True
+
+    if na_value is lib.no_default:
+        if dtype is None or not hasna:
+            na_value = arr.dtype.na_value
+        elif dtype.kind == "f":  # type: ignore[union-attr]
+            na_value = np.nan
+        elif dtype.kind == "M":  # type: ignore[union-attr]
+            na_value = np.datetime64("nat")
+        elif dtype.kind == "m":  # type: ignore[union-attr]
+            na_value = np.timedelta64("nat")
+        else:
+            na_value = arr.dtype.na_value
+
+    if not dtype_given and hasna:
+        try:
+            np_can_hold_element(dtype, na_value)  # type: ignore[arg-type]
+        except LossySetitemError:
+            dtype = np.dtype(np.object_)
+    return dtype, na_value

lib/python3.11/site-packages/pandas/core/arrays/arrow/__init__.py

@@ -0,0 +1,7 @@
+from pandas.core.arrays.arrow.accessors import (
+    ListAccessor,
+    StructAccessor,
+)
+from pandas.core.arrays.arrow.array import ArrowExtensionArray
+
+__all__ = ["ArrowExtensionArray", "StructAccessor", "ListAccessor"]

lib/python3.11/site-packages/pandas/core/arrays/arrow/_arrow_utils.py

@@ -0,0 +1,50 @@
+from __future__ import annotations
+
+import numpy as np
+import pyarrow
+
+
+def pyarrow_array_to_numpy_and_mask(
+    arr, dtype: np.dtype
+) -> tuple[np.ndarray, np.ndarray]:
+    """
+    Convert a primitive pyarrow.Array to a numpy array and boolean mask based
+    on the buffers of the Array.
+
+    At the moment pyarrow.BooleanArray is not supported.
+
+    Parameters
+    ----------
+    arr : pyarrow.Array
+    dtype : numpy.dtype
+
+    Returns
+    -------
+    (data, mask)
+        Tuple of two numpy arrays with the raw data (with specified dtype) and
+        a boolean mask (validity mask, so False means missing)
+    """
+    dtype = np.dtype(dtype)
+
+    if pyarrow.types.is_null(arr.type):
+        # No initialization of data is needed since everything is null
+        data = np.empty(len(arr), dtype=dtype)
+        mask = np.zeros(len(arr), dtype=bool)
+        return data, mask
+    buflist = arr.buffers()
+    # Since Arrow buffers might contain padding and the data might be offset,
+    # the buffer gets sliced here before handing it to numpy.
+    # See also https://github.com/pandas-dev/pandas/issues/40896
+    offset = arr.offset * dtype.itemsize
+    length = len(arr) * dtype.itemsize
+    data_buf = buflist[1][offset : offset + length]
+    data = np.frombuffer(data_buf, dtype=dtype)
+    bitmask = buflist[0]
+    if bitmask is not None:
+        mask = pyarrow.BooleanArray.from_buffers(
+            pyarrow.bool_(), len(arr), [None, bitmask], offset=arr.offset
+        )
+        mask = np.asarray(mask)
+    else:
+        mask = np.ones(len(arr), dtype=bool)
+    return data, mask

lib/python3.11/site-packages/pandas/core/arrays/arrow/accessors.py

@@ -0,0 +1,473 @@
+"""Accessors for arrow-backed data."""
+
+from __future__ import annotations
+
+from abc import (
+    ABCMeta,
+    abstractmethod,
+)
+from typing import (
+    TYPE_CHECKING,
+    cast,
+)
+
+from pandas.compat import (
+    pa_version_under10p1,
+    pa_version_under11p0,
+)
+
+from pandas.core.dtypes.common import is_list_like
+
+if not pa_version_under10p1:
+    import pyarrow as pa
+    import pyarrow.compute as pc
+
+    from pandas.core.dtypes.dtypes import ArrowDtype
+
+if TYPE_CHECKING:
+    from collections.abc import Iterator
+
+    from pandas import (
+        DataFrame,
+        Series,
+    )
+
+
+class ArrowAccessor(metaclass=ABCMeta):
+    @abstractmethod
+    def __init__(self, data, validation_msg: str) -> None:
+        self._data = data
+        self._validation_msg = validation_msg
+        self._validate(data)
+
+    @abstractmethod
+    def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
+        pass
+
+    def _validate(self, data):
+        dtype = data.dtype
+        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))
+
+        if not self._is_valid_pyarrow_dtype(dtype.pyarrow_dtype):
+            # Raise AttributeError so that inspect can handle invalid Series.
+            raise AttributeError(self._validation_msg.format(dtype=dtype))
+
+    @property
+    def _pa_array(self):
+        return self._data.array._pa_array
+
+
+class ListAccessor(ArrowAccessor):
+    """
+    Accessor object for list data properties of the Series values.
+
+    Parameters
+    ----------
+    data : Series
+        Series containing Arrow list data.
+    """
+
+    def __init__(self, data=None) -> None:
+        super().__init__(
+            data,
+            validation_msg="Can only use the '.list' accessor with "
+            "'list[pyarrow]' dtype, not {dtype}.",
+        )
+
+    def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
+        return (
+            pa.types.is_list(pyarrow_dtype)
+            or pa.types.is_fixed_size_list(pyarrow_dtype)
+            or pa.types.is_large_list(pyarrow_dtype)
+        )
+
+    def len(self) -> Series:
+        """
+        Return the length of each list in the Series.
+
+        Returns
+        -------
+        pandas.Series
+            The length of each list.
+
+        Examples
+        --------
+        >>> import pyarrow as pa
+        >>> s = pd.Series(
+        ...     [
+        ...         [1, 2, 3],
+        ...         [3],
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.list_(
+        ...         pa.int64()
+        ...     ))
+        ... )
+        >>> s.list.len()
+        0    3
+        1    1
+        dtype: int32[pyarrow]
+        """
+        from pandas import Series
+
+        value_lengths = pc.list_value_length(self._pa_array)
+        return Series(value_lengths, dtype=ArrowDtype(value_lengths.type))
+
+    def __getitem__(self, key: int | slice) -> Series:
+        """
+        Index or slice lists in the Series.
+
+        Parameters
+        ----------
+        key : int | slice
+            Index or slice of indices to access from each list.
+
+        Returns
+        -------
+        pandas.Series
+            The list at requested index.
+
+        Examples
+        --------
+        >>> import pyarrow as pa
+        >>> s = pd.Series(
+        ...     [
+        ...         [1, 2, 3],
+        ...         [3],
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.list_(
+        ...         pa.int64()
+        ...     ))
+        ... )
+        >>> s.list[0]
+        0    1
+        1    3
+        dtype: int64[pyarrow]
+        """
+        from pandas import Series
+
+        if isinstance(key, int):
+            # TODO: Support negative key but pyarrow does not allow
+            # element index to be an array.
+            # if key < 0:
+            #     key = pc.add(key, pc.list_value_length(self._pa_array))
+            element = pc.list_element(self._pa_array, key)
+            return Series(element, dtype=ArrowDtype(element.type))
+        elif isinstance(key, slice):
+            if pa_version_under11p0:
+                raise NotImplementedError(
+                    f"List slice not supported by pyarrow {pa.__version__}."
+                )
+
+            # TODO: Support negative start/stop/step, ideally this would be added
+            # upstream in pyarrow.
+            start, stop, step = key.start, key.stop, key.step
+            if start is None:
+                # TODO: When adding negative step support
+                #  this should be setto last element of array
+                # when step is negative.
+                start = 0
+            if step is None:
+                step = 1
+            sliced = pc.list_slice(self._pa_array, start, stop, step)
+            return Series(sliced, dtype=ArrowDtype(sliced.type))
+        else:
+            raise ValueError(f"key must be an int or slice, got {type(key).__name__}")
+
+    def __iter__(self) -> Iterator:
+        raise TypeError(f"'{type(self).__name__}' object is not iterable")
+
+    def flatten(self) -> Series:
+        """
+        Flatten list values.
+
+        Returns
+        -------
+        pandas.Series
+            The data from all lists in the series flattened.
+
+        Examples
+        --------
+        >>> import pyarrow as pa
+        >>> s = pd.Series(
+        ...     [
+        ...         [1, 2, 3],
+        ...         [3],
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.list_(
+        ...         pa.int64()
+        ...     ))
+        ... )
+        >>> s.list.flatten()
+        0    1
+        1    2
+        2    3
+        3    3
+        dtype: int64[pyarrow]
+        """
+        from pandas import Series
+
+        flattened = pc.list_flatten(self._pa_array)
+        return Series(flattened, dtype=ArrowDtype(flattened.type))
+
+
+class StructAccessor(ArrowAccessor):
+    """
+    Accessor object for structured data properties of the Series values.
+
+    Parameters
+    ----------
+    data : Series
+        Series containing Arrow struct data.
+    """
+
+    def __init__(self, data=None) -> None:
+        super().__init__(
+            data,
+            validation_msg=(
+                "Can only use the '.struct' accessor with 'struct[pyarrow]' "
+                "dtype, not {dtype}."
+            ),
+        )
+
+    def _is_valid_pyarrow_dtype(self, pyarrow_dtype) -> bool:
+        return pa.types.is_struct(pyarrow_dtype)
+
+    @property
+    def dtypes(self) -> Series:
+        """
+        Return the dtype object of each child field of the struct.
+
+        Returns
+        -------
+        pandas.Series
+            The data type of each child field.
+
+        Examples
+        --------
+        >>> import pyarrow as pa
+        >>> s = pd.Series(
+        ...     [
+        ...         {"version": 1, "project": "pandas"},
+        ...         {"version": 2, "project": "pandas"},
+        ...         {"version": 1, "project": "numpy"},
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.struct(
+        ...         [("version", pa.int64()), ("project", pa.string())]
+        ...     ))
+        ... )
+        >>> s.struct.dtypes
+        version     int64[pyarrow]
+        project    string[pyarrow]
+        dtype: object
+        """
+        from pandas import (
+            Index,
+            Series,
+        )
+
+        pa_type = self._data.dtype.pyarrow_dtype
+        types = [ArrowDtype(struct.type) for struct in pa_type]
+        names = [struct.name for struct in pa_type]
+        return Series(types, index=Index(names))
+
+    def field(
+        self,
+        name_or_index: list[str]
+        | list[bytes]
+        | list[int]
+        | pc.Expression
+        | bytes
+        | str
+        | int,
+    ) -> Series:
+        """
+        Extract a child field of a struct as a Series.
+
+        Parameters
+        ----------
+        name_or_index : str | bytes | int | expression | list
+            Name or index of the child field to extract.
+
+            For list-like inputs, this will index into a nested
+            struct.
+
+        Returns
+        -------
+        pandas.Series
+            The data corresponding to the selected child field.
+
+        See Also
+        --------
+        Series.struct.explode : Return all child fields as a DataFrame.
+
+        Notes
+        -----
+        The name of the resulting Series will be set using the following
+        rules:
+
+        - For string, bytes, or integer `name_or_index` (or a list of these, for
+          a nested selection), the Series name is set to the selected
+          field's name.
+        - For a :class:`pyarrow.compute.Expression`, this is set to
+          the string form of the expression.
+        - For list-like `name_or_index`, the name will be set to the
+          name of the final field selected.
+
+        Examples
+        --------
+        >>> import pyarrow as pa
+        >>> s = pd.Series(
+        ...     [
+        ...         {"version": 1, "project": "pandas"},
+        ...         {"version": 2, "project": "pandas"},
+        ...         {"version": 1, "project": "numpy"},
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.struct(
+        ...         [("version", pa.int64()), ("project", pa.string())]
+        ...     ))
+        ... )
+
+        Extract by field name.
+
+        >>> s.struct.field("project")
+        0    pandas
+        1    pandas
+        2     numpy
+        Name: project, dtype: string[pyarrow]
+
+        Extract by field index.
+
+        >>> s.struct.field(0)
+        0    1
+        1    2
+        2    1
+        Name: version, dtype: int64[pyarrow]
+
+        Or an expression
+
+        >>> import pyarrow.compute as pc
+        >>> s.struct.field(pc.field("project"))
+        0    pandas
+        1    pandas
+        2     numpy
+        Name: project, dtype: string[pyarrow]
+
+        For nested struct types, you can pass a list of values to index
+        multiple levels:
+
+        >>> version_type = pa.struct([
+        ...     ("major", pa.int64()),
+        ...     ("minor", pa.int64()),
+        ... ])
+        >>> s = pd.Series(
+        ...     [
+        ...         {"version": {"major": 1, "minor": 5}, "project": "pandas"},
+        ...         {"version": {"major": 2, "minor": 1}, "project": "pandas"},
+        ...         {"version": {"major": 1, "minor": 26}, "project": "numpy"},
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.struct(
+        ...         [("version", version_type), ("project", pa.string())]
+        ...     ))
+        ... )
+        >>> s.struct.field(["version", "minor"])
+        0     5
+        1     1
+        2    26
+        Name: minor, dtype: int64[pyarrow]
+        >>> s.struct.field([0, 0])
+        0    1
+        1    2
+        2    1
+        Name: major, dtype: int64[pyarrow]
+        """
+        from pandas import Series
+
+        def get_name(
+            level_name_or_index: list[str]
+            | list[bytes]
+            | list[int]
+            | pc.Expression
+            | bytes
+            | str
+            | int,
+            data: pa.ChunkedArray,
+        ):
+            if isinstance(level_name_or_index, int):
+                name = data.type.field(level_name_or_index).name
+            elif isinstance(level_name_or_index, (str, bytes)):
+                name = level_name_or_index
+            elif isinstance(level_name_or_index, pc.Expression):
+                name = str(level_name_or_index)
+            elif is_list_like(level_name_or_index):
+                # For nested input like [2, 1, 2]
+                # iteratively get the struct and field name. The last
+                # one is used for the name of the index.
+                level_name_or_index = list(reversed(level_name_or_index))
+                selected = data
+                while level_name_or_index:
+                    # we need the cast, otherwise mypy complains about
+                    # getting ints, bytes, or str here, which isn't possible.
+                    level_name_or_index = cast(list, level_name_or_index)
+                    name_or_index = level_name_or_index.pop()
+                    name = get_name(name_or_index, selected)
+                    selected = selected.type.field(selected.type.get_field_index(name))
+                    name = selected.name
+            else:
+                raise ValueError(
+                    "name_or_index must be an int, str, bytes, "
+                    "pyarrow.compute.Expression, or list of those"
+                )
+            return name
+
+        pa_arr = self._data.array._pa_array
+        name = get_name(name_or_index, pa_arr)
+        field_arr = pc.struct_field(pa_arr, name_or_index)
+
+        return Series(
+            field_arr,
+            dtype=ArrowDtype(field_arr.type),
+            index=self._data.index,
+            name=name,
+        )
+
+    def explode(self) -> DataFrame:
+        """
+        Extract all child fields of a struct as a DataFrame.
+
+        Returns
+        -------
+        pandas.DataFrame
+            The data corresponding to all child fields.
+
+        See Also
+        --------
+        Series.struct.field : Return a single child field as a Series.
+
+        Examples
+        --------
+        >>> import pyarrow as pa
+        >>> s = pd.Series(
+        ...     [
+        ...         {"version": 1, "project": "pandas"},
+        ...         {"version": 2, "project": "pandas"},
+        ...         {"version": 1, "project": "numpy"},
+        ...     ],
+        ...     dtype=pd.ArrowDtype(pa.struct(
+        ...         [("version", pa.int64()), ("project", pa.string())]
+        ...     ))
+        ... )
+
+        >>> s.struct.explode()
+           version project
+        0        1  pandas
+        1        2  pandas
+        2        1   numpy
+        """
+        from pandas import concat
+
+        pa_type = self._pa_array.type
+        return concat(
+            [self.field(i) for i in range(pa_type.num_fields)], axis="columns"
+        )

lib/python3.11/site-packages/pandas/core/arrays/arrow/extension_types.py

@@ -0,0 +1,174 @@
+from __future__ import annotations
+
+import json
+from typing import TYPE_CHECKING
+
+import pyarrow
+
+from pandas.compat import pa_version_under14p1
+
+from pandas.core.dtypes.dtypes import (
+    IntervalDtype,
+    PeriodDtype,
+)
+
+from pandas.core.arrays.interval import VALID_CLOSED
+
+if TYPE_CHECKING:
+    from pandas._typing import IntervalClosedType
+
+
+class ArrowPeriodType(pyarrow.ExtensionType):
+    def __init__(self, freq) -> None:
+        # attributes need to be set first before calling
+        # super init (as that calls serialize)
+        self._freq = freq
+        pyarrow.ExtensionType.__init__(self, pyarrow.int64(), "pandas.period")
+
+    @property
+    def freq(self):
+        return self._freq
+
+    def __arrow_ext_serialize__(self) -> bytes:
+        metadata = {"freq": self.freq}
+        return json.dumps(metadata).encode()
+
+    @classmethod
+    def __arrow_ext_deserialize__(cls, storage_type, serialized) -> ArrowPeriodType:
+        metadata = json.loads(serialized.decode())
+        return ArrowPeriodType(metadata["freq"])
+
+    def __eq__(self, other):
+        if isinstance(other, pyarrow.BaseExtensionType):
+            return type(self) == type(other) and self.freq == other.freq
+        else:
+            return NotImplemented
+
+    def __ne__(self, other) -> bool:
+        return not self == other
+
+    def __hash__(self) -> int:
+        return hash((str(self), self.freq))
+
+    def to_pandas_dtype(self) -> PeriodDtype:
+        return PeriodDtype(freq=self.freq)
+
+
+# register the type with a dummy instance
+_period_type = ArrowPeriodType("D")
+pyarrow.register_extension_type(_period_type)
+
+
+class ArrowIntervalType(pyarrow.ExtensionType):
+    def __init__(self, subtype, closed: IntervalClosedType) -> None:
+        # attributes need to be set first before calling
+        # super init (as that calls serialize)
+        assert closed in VALID_CLOSED
+        self._closed: IntervalClosedType = closed
+        if not isinstance(subtype, pyarrow.DataType):
+            subtype = pyarrow.type_for_alias(str(subtype))
+        self._subtype = subtype
+
+        storage_type = pyarrow.struct([("left", subtype), ("right", subtype)])
+        pyarrow.ExtensionType.__init__(self, storage_type, "pandas.interval")
+
+    @property
+    def subtype(self):
+        return self._subtype
+
+    @property
+    def closed(self) -> IntervalClosedType:
+        return self._closed
+
+    def __arrow_ext_serialize__(self) -> bytes:
+        metadata = {"subtype": str(self.subtype), "closed": self.closed}
+        return json.dumps(metadata).encode()
+
+    @classmethod
+    def __arrow_ext_deserialize__(cls, storage_type, serialized) -> ArrowIntervalType:
+        metadata = json.loads(serialized.decode())
+        subtype = pyarrow.type_for_alias(metadata["subtype"])
+        closed = metadata["closed"]
+        return ArrowIntervalType(subtype, closed)
+
+    def __eq__(self, other):
+        if isinstance(other, pyarrow.BaseExtensionType):
+            return (
+                type(self) == type(other)
+                and self.subtype == other.subtype
+                and self.closed == other.closed
+            )
+        else:
+            return NotImplemented
+
+    def __ne__(self, other) -> bool:
+        return not self == other
+
+    def __hash__(self) -> int:
+        return hash((str(self), str(self.subtype), self.closed))
+
+    def to_pandas_dtype(self) -> IntervalDtype:
+        return IntervalDtype(self.subtype.to_pandas_dtype(), self.closed)
+
+
+# register the type with a dummy instance
+_interval_type = ArrowIntervalType(pyarrow.int64(), "left")
+pyarrow.register_extension_type(_interval_type)
+
+
+_ERROR_MSG = """\
+Disallowed deserialization of 'arrow.py_extension_type':
+storage_type = {storage_type}
+serialized = {serialized}
+pickle disassembly:\n{pickle_disassembly}
+
+Reading of untrusted Parquet or Feather files with a PyExtensionType column
+allows arbitrary code execution.
+If you trust this file, you can enable reading the extension type by one of:
+
+- upgrading to pyarrow >= 14.0.1, and call `pa.PyExtensionType.set_auto_load(True)`
+- install pyarrow-hotfix (`pip install pyarrow-hotfix`) and disable it by running
+  `import pyarrow_hotfix; pyarrow_hotfix.uninstall()`
+
+We strongly recommend updating your Parquet/Feather files to use extension types
+derived from `pyarrow.ExtensionType` instead, and register this type explicitly.
+"""
+
+
+def patch_pyarrow():
+    # starting from pyarrow 14.0.1, it has its own mechanism
+    if not pa_version_under14p1:
+        return
+
+    # if https://github.com/pitrou/pyarrow-hotfix was installed and enabled
+    if getattr(pyarrow, "_hotfix_installed", False):
+        return
+
+    class ForbiddenExtensionType(pyarrow.ExtensionType):
+        def __arrow_ext_serialize__(self):
+            return b""
+
+        @classmethod
+        def __arrow_ext_deserialize__(cls, storage_type, serialized):
+            import io
+            import pickletools
+
+            out = io.StringIO()
+            pickletools.dis(serialized, out)
+            raise RuntimeError(
+                _ERROR_MSG.format(
+                    storage_type=storage_type,
+                    serialized=serialized,
+                    pickle_disassembly=out.getvalue(),
+                )
+            )
+
+    pyarrow.unregister_extension_type("arrow.py_extension_type")
+    pyarrow.register_extension_type(
+        ForbiddenExtensionType(pyarrow.null(), "arrow.py_extension_type")
+    )
+
+    pyarrow._hotfix_installed = True
+
+
+patch_pyarrow()

lib/python3.11/site-packages/pandas/core/arrays/boolean.py

@@ -0,0 +1,407 @@
+from __future__ import annotations
+
+import numbers
+from typing import (
+    TYPE_CHECKING,
+    ClassVar,
+    cast,
+)
+
+import numpy as np
+
+from pandas._libs import (
+    lib,
+    missing as libmissing,
+)
+
+from pandas.core.dtypes.common import is_list_like
+from pandas.core.dtypes.dtypes import register_extension_dtype
+from pandas.core.dtypes.missing import isna
+
+from pandas.core import ops
+from pandas.core.array_algos import masked_accumulations
+from pandas.core.arrays.masked import (
+    BaseMaskedArray,
+    BaseMaskedDtype,
+)
+
+if TYPE_CHECKING:
+    import pyarrow
+
+    from pandas._typing import (
+        Dtype,
+        DtypeObj,
+        Self,
+        npt,
+        type_t,
+    )
+
+
+@register_extension_dtype
+class BooleanDtype(BaseMaskedDtype):
+    """
+    Extension dtype for boolean data.
+
+    .. warning::
+
+       BooleanDtype is considered experimental. The implementation and
+       parts of the API may change without warning.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+
+    Examples
+    --------
+    >>> pd.BooleanDtype()
+    BooleanDtype
+    """
+
+    name: ClassVar[str] = "boolean"
+
+    # https://github.com/python/mypy/issues/4125
+    # error: Signature of "type" incompatible with supertype "BaseMaskedDtype"
+    @property
+    def type(self) -> type:  # type: ignore[override]
+        return np.bool_
+
+    @property
+    def kind(self) -> str:
+        return "b"
+
+    @property
+    def numpy_dtype(self) -> np.dtype:
+        return np.dtype("bool")
+
+    @classmethod
+    def construct_array_type(cls) -> type_t[BooleanArray]:
+        """
+        Return the array type associated with this dtype.
+
+        Returns
+        -------
+        type
+        """
+        return BooleanArray
+
+    def __repr__(self) -> str:
+        return "BooleanDtype"
+
+    @property
+    def _is_boolean(self) -> bool:
+        return True
+
+    @property
+    def _is_numeric(self) -> bool:
+        return True
+
+    def __from_arrow__(
+        self, array: pyarrow.Array | pyarrow.ChunkedArray
+    ) -> BooleanArray:
+        """
+        Construct BooleanArray from pyarrow Array/ChunkedArray.
+        """
+        import pyarrow
+
+        if array.type != pyarrow.bool_() and not pyarrow.types.is_null(array.type):
+            raise TypeError(f"Expected array of boolean type, got {array.type} instead")
+
+        if isinstance(array, pyarrow.Array):
+            chunks = [array]
+            length = len(array)
+        else:
+            # pyarrow.ChunkedArray
+            chunks = array.chunks
+            length = array.length()
+
+        if pyarrow.types.is_null(array.type):
+            mask = np.ones(length, dtype=bool)
+            # No need to init data, since all null
+            data = np.empty(length, dtype=bool)
+            return BooleanArray(data, mask)
+
+        results = []
+        for arr in chunks:
+            buflist = arr.buffers()
+            data = pyarrow.BooleanArray.from_buffers(
+                arr.type, len(arr), [None, buflist[1]], offset=arr.offset
+            ).to_numpy(zero_copy_only=False)
+            if arr.null_count != 0:
+                mask = pyarrow.BooleanArray.from_buffers(
+                    arr.type, len(arr), [None, buflist[0]], offset=arr.offset
+                ).to_numpy(zero_copy_only=False)
+                mask = ~mask
+            else:
+                mask = np.zeros(len(arr), dtype=bool)
+
+            bool_arr = BooleanArray(data, mask)
+            results.append(bool_arr)
+
+        if not results:
+            return BooleanArray(
+                np.array([], dtype=np.bool_), np.array([], dtype=np.bool_)
+            )
+        else:
+            return BooleanArray._concat_same_type(results)
+
+
+def coerce_to_array(
+    values, mask=None, copy: bool = False
+) -> tuple[np.ndarray, np.ndarray]:
+    """
+    Coerce the input values array to numpy arrays with a mask.
+
+    Parameters
+    ----------
+    values : 1D list-like
+    mask : bool 1D array, optional
+    copy : bool, default False
+        if True, copy the input
+
+    Returns
+    -------
+    tuple of (values, mask)
+    """
+    if isinstance(values, BooleanArray):
+        if mask is not None:
+            raise ValueError("cannot pass mask for BooleanArray input")
+        values, mask = values._data, values._mask
+        if copy:
+            values = values.copy()
+            mask = mask.copy()
+        return values, mask
+
+    mask_values = None
+    if isinstance(values, np.ndarray) and values.dtype == np.bool_:
+        if copy:
+            values = values.copy()
+    elif isinstance(values, np.ndarray) and values.dtype.kind in "iufcb":
+        mask_values = isna(values)
+
+        values_bool = np.zeros(len(values), dtype=bool)
+        values_bool[~mask_values] = values[~mask_values].astype(bool)
+
+        if not np.all(
+            values_bool[~mask_values].astype(values.dtype) == values[~mask_values]
+        ):
+            raise TypeError("Need to pass bool-like values")
+
+        values = values_bool
+    else:
+        values_object = np.asarray(values, dtype=object)
+
+        inferred_dtype = lib.infer_dtype(values_object, skipna=True)
+        integer_like = ("floating", "integer", "mixed-integer-float")
+        if inferred_dtype not in ("boolean", "empty") + integer_like:
+            raise TypeError("Need to pass bool-like values")
+
+        # mypy does not narrow the type of mask_values to npt.NDArray[np.bool_]
+        # within this branch, it assumes it can also be None
+        mask_values = cast("npt.NDArray[np.bool_]", isna(values_object))
+        values = np.zeros(len(values), dtype=bool)
+        values[~mask_values] = values_object[~mask_values].astype(bool)
+
+        # if the values were integer-like, validate it were actually 0/1's
+        if (inferred_dtype in integer_like) and not (
+            np.all(
+                values[~mask_values].astype(float)
+                == values_object[~mask_values].astype(float)
+            )
+        ):
+            raise TypeError("Need to pass bool-like values")
+
+    if mask is None and mask_values is None:
+        mask = np.zeros(values.shape, dtype=bool)
+    elif mask is None:
+        mask = mask_values
+    else:
+        if isinstance(mask, np.ndarray) and mask.dtype == np.bool_:
+            if mask_values is not None:
+                mask = mask | mask_values
+            else:
+                if copy:
+                    mask = mask.copy()
+        else:
+            mask = np.array(mask, dtype=bool)
+            if mask_values is not None:
+                mask = mask | mask_values
+
+    if values.shape != mask.shape:
+        raise ValueError("values.shape and mask.shape must match")
+
+    return values, mask
+
+
+class BooleanArray(BaseMaskedArray):
+    """
+    Array of boolean (True/False) data with missing values.
+
+    This is a pandas Extension array for boolean data, under the hood
+    represented by 2 numpy arrays: a boolean array with the data and
+    a boolean array with the mask (True indicating missing).
+
+    BooleanArray implements Kleene logic (sometimes called three-value
+    logic) for logical operations. See :ref:`boolean.kleene` for more.
+
+    To construct an BooleanArray from generic array-like input, use
+    :func:`pandas.array` specifying ``dtype="boolean"`` (see examples
+    below).
+
+    .. warning::
+
+       BooleanArray is considered experimental. The implementation and
+       parts of the API may change without warning.
+
+    Parameters
+    ----------
+    values : numpy.ndarray
+        A 1-d boolean-dtype array with the data.
+    mask : numpy.ndarray
+        A 1-d boolean-dtype array indicating missing values (True
+        indicates missing).
+    copy : bool, default False
+        Whether to copy the `values` and `mask` arrays.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+
+    Returns
+    -------
+    BooleanArray
+
+    Examples
+    --------
+    Create an BooleanArray with :func:`pandas.array`:
+
+    >>> pd.array([True, False, None], dtype="boolean")
+    <BooleanArray>
+    [True, False, <NA>]
+    Length: 3, dtype: boolean
+    """
+
+    # The value used to fill '_data' to avoid upcasting
+    _internal_fill_value = False
+    # Fill values used for any/all
+    # Incompatible types in assignment (expression has type "bool", base class
+    # "BaseMaskedArray" defined the type as "<typing special form>")
+    _truthy_value = True  # type: ignore[assignment]
+    _falsey_value = False  # type: ignore[assignment]
+    _TRUE_VALUES = {"True", "TRUE", "true", "1", "1.0"}
+    _FALSE_VALUES = {"False", "FALSE", "false", "0", "0.0"}
+
+    @classmethod
+    def _simple_new(cls, values: np.ndarray, mask: npt.NDArray[np.bool_]) -> Self:
+        result = super()._simple_new(values, mask)
+        result._dtype = BooleanDtype()
+        return result
+
+    def __init__(
+        self, values: np.ndarray, mask: np.ndarray, copy: bool = False
+    ) -> None:
+        if not (isinstance(values, np.ndarray) and values.dtype == np.bool_):
+            raise TypeError(
+                "values should be boolean numpy array. Use "
+                "the 'pd.array' function instead"
+            )
+        self._dtype = BooleanDtype()
+        super().__init__(values, mask, copy=copy)
+
+    @property
+    def dtype(self) -> BooleanDtype:
+        return self._dtype
+
+    @classmethod
+    def _from_sequence_of_strings(
+        cls,
+        strings: list[str],
+        *,
+        dtype: Dtype | None = None,
+        copy: bool = False,
+        true_values: list[str] | None = None,
+        false_values: list[str] | None = None,
+    ) -> BooleanArray:
+        true_values_union = cls._TRUE_VALUES.union(true_values or [])
+        false_values_union = cls._FALSE_VALUES.union(false_values or [])
+
+        def map_string(s) -> bool:
+            if s in true_values_union:
+                return True
+            elif s in false_values_union:
+                return False
+            else:
+                raise ValueError(f"{s} cannot be cast to bool")
+
+        scalars = np.array(strings, dtype=object)
+        mask = isna(scalars)
+        scalars[~mask] = list(map(map_string, scalars[~mask]))
+        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
+
+    _HANDLED_TYPES = (np.ndarray, numbers.Number, bool, np.bool_)
+
+    @classmethod
+    def _coerce_to_array(
+        cls, value, *, dtype: DtypeObj, copy: bool = False
+    ) -> tuple[np.ndarray, np.ndarray]:
+        if dtype:
+            assert dtype == "boolean"
+        return coerce_to_array(value, copy=copy)
+
+    def _logical_method(self, other, op):
+        assert op.__name__ in {"or_", "ror_", "and_", "rand_", "xor", "rxor"}
+        other_is_scalar = lib.is_scalar(other)
+        mask = None
+
+        if isinstance(other, BooleanArray):
+            other, mask = other._data, other._mask
+        elif is_list_like(other):
+            other = np.asarray(other, dtype="bool")
+            if other.ndim > 1:
+                raise NotImplementedError("can only perform ops with 1-d structures")
+            other, mask = coerce_to_array(other, copy=False)
+        elif isinstance(other, np.bool_):
+            other = other.item()
+
+        if other_is_scalar and other is not libmissing.NA and not lib.is_bool(other):
+            raise TypeError(
+                "'other' should be pandas.NA or a bool. "
+                f"Got {type(other).__name__} instead."
+            )
+
+        if not other_is_scalar and len(self) != len(other):
+            raise ValueError("Lengths must match")
+
+        if op.__name__ in {"or_", "ror_"}:
+            result, mask = ops.kleene_or(self._data, other, self._mask, mask)
+        elif op.__name__ in {"and_", "rand_"}:
+            result, mask = ops.kleene_and(self._data, other, self._mask, mask)
+        else:
+            # i.e. xor, rxor
+            result, mask = ops.kleene_xor(self._data, other, self._mask, mask)
+
+        # i.e. BooleanArray
+        return self._maybe_mask_result(result, mask)
+
+    def _accumulate(
+        self, name: str, *, skipna: bool = True, **kwargs
+    ) -> BaseMaskedArray:
+        data = self._data
+        mask = self._mask
+        if name in ("cummin", "cummax"):
+            op = getattr(masked_accumulations, name)
+            data, mask = op(data, mask, skipna=skipna, **kwargs)
+            return self._simple_new(data, mask)
+        else:
+            from pandas.core.arrays import IntegerArray
+
+            return IntegerArray(data.astype(int), mask)._accumulate(
+                name, skipna=skipna, **kwargs
+            )

lib/python3.11/site-packages/pandas/core/arrays/floating.py

@@ -0,0 +1,173 @@
+from __future__ import annotations
+
+from typing import ClassVar
+
+import numpy as np
+
+from pandas.core.dtypes.base import register_extension_dtype
+from pandas.core.dtypes.common import is_float_dtype
+
+from pandas.core.arrays.numeric import (
+    NumericArray,
+    NumericDtype,
+)
+
+
+class FloatingDtype(NumericDtype):
+    """
+    An ExtensionDtype to hold a single size of floating dtype.
+
+    These specific implementations are subclasses of the non-public
+    FloatingDtype. For example we have Float32Dtype to represent float32.
+
+    The attributes name & type are set when these subclasses are created.
+    """
+
+    _default_np_dtype = np.dtype(np.float64)
+    _checker = is_float_dtype
+
+    @classmethod
+    def construct_array_type(cls) -> type[FloatingArray]:
+        """
+        Return the array type associated with this dtype.
+
+        Returns
+        -------
+        type
+        """
+        return FloatingArray
+
+    @classmethod
+    def _get_dtype_mapping(cls) -> dict[np.dtype, FloatingDtype]:
+        return NUMPY_FLOAT_TO_DTYPE
+
+    @classmethod
+    def _safe_cast(cls, values: np.ndarray, dtype: np.dtype, copy: bool) -> np.ndarray:
+        """
+        Safely cast the values to the given dtype.
+
+        "safe" in this context means the casting is lossless.
+        """
+        # This is really only here for compatibility with IntegerDtype
+        # Here for compat with IntegerDtype
+        return values.astype(dtype, copy=copy)
+
+
+class FloatingArray(NumericArray):
+    """
+    Array of floating (optional missing) values.
+
+    .. warning::
+
+       FloatingArray is currently experimental, and its API or internal
+       implementation may change without warning. Especially the behaviour
+       regarding NaN (distinct from NA missing values) is subject to change.
+
+    We represent a FloatingArray with 2 numpy arrays:
+
+    - data: contains a numpy float array of the appropriate dtype
+    - mask: a boolean array holding a mask on the data, True is missing
+
+    To construct an FloatingArray from generic array-like input, use
+    :func:`pandas.array` with one of the float dtypes (see examples).
+
+    See :ref:`integer_na` for more.
+
+    Parameters
+    ----------
+    values : numpy.ndarray
+        A 1-d float-dtype array.
+    mask : numpy.ndarray
+        A 1-d boolean-dtype array indicating missing values.
+    copy : bool, default False
+        Whether to copy the `values` and `mask`.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+
+    Returns
+    -------
+    FloatingArray
+
+    Examples
+    --------
+    Create an FloatingArray with :func:`pandas.array`:
+
+    >>> pd.array([0.1, None, 0.3], dtype=pd.Float32Dtype())
+    <FloatingArray>
+    [0.1, <NA>, 0.3]
+    Length: 3, dtype: Float32
+
+    String aliases for the dtypes are also available. They are capitalized.
+
+    >>> pd.array([0.1, None, 0.3], dtype="Float32")
+    <FloatingArray>
+    [0.1, <NA>, 0.3]
+    Length: 3, dtype: Float32
+    """
+
+    _dtype_cls = FloatingDtype
+
+    # The value used to fill '_data' to avoid upcasting
+    _internal_fill_value = np.nan
+    # Fill values used for any/all
+    # Incompatible types in assignment (expression has type "float", base class
+    # "BaseMaskedArray" defined the type as "<typing special form>")
+    _truthy_value = 1.0  # type: ignore[assignment]
+    _falsey_value = 0.0  # type: ignore[assignment]
+
+
+_dtype_docstring = """
+An ExtensionDtype for {dtype} data.
+
+This dtype uses ``pd.NA`` as missing value indicator.
+
+Attributes
+----------
+None
+
+Methods
+-------
+None
+
+Examples
+--------
+For Float32Dtype:
+
+>>> ser = pd.Series([2.25, pd.NA], dtype=pd.Float32Dtype())
+>>> ser.dtype
+Float32Dtype()
+
+For Float64Dtype:
+
+>>> ser = pd.Series([2.25, pd.NA], dtype=pd.Float64Dtype())
+>>> ser.dtype
+Float64Dtype()
+"""
+
+# create the Dtype
+
+
+@register_extension_dtype
+class Float32Dtype(FloatingDtype):
+    type = np.float32
+    name: ClassVar[str] = "Float32"
+    __doc__ = _dtype_docstring.format(dtype="float32")
+
+
+@register_extension_dtype
+class Float64Dtype(FloatingDtype):
+    type = np.float64
+    name: ClassVar[str] = "Float64"
+    __doc__ = _dtype_docstring.format(dtype="float64")
+
+
+NUMPY_FLOAT_TO_DTYPE: dict[np.dtype, FloatingDtype] = {
+    np.dtype(np.float32): Float32Dtype(),
+    np.dtype(np.float64): Float64Dtype(),
+}

lib/python3.11/site-packages/pandas/core/arrays/integer.py

@@ -0,0 +1,272 @@
+from __future__ import annotations
+
+from typing import ClassVar
+
+import numpy as np
+
+from pandas.core.dtypes.base import register_extension_dtype
+from pandas.core.dtypes.common import is_integer_dtype
+
+from pandas.core.arrays.numeric import (
+    NumericArray,
+    NumericDtype,
+)
+
+
+class IntegerDtype(NumericDtype):
+    """
+    An ExtensionDtype to hold a single size & kind of integer dtype.
+
+    These specific implementations are subclasses of the non-public
+    IntegerDtype. For example, we have Int8Dtype to represent signed int 8s.
+
+    The attributes name & type are set when these subclasses are created.
+    """
+
+    _default_np_dtype = np.dtype(np.int64)
+    _checker = is_integer_dtype
+
+    @classmethod
+    def construct_array_type(cls) -> type[IntegerArray]:
+        """
+        Return the array type associated with this dtype.
+
+        Returns
+        -------
+        type
+        """
+        return IntegerArray
+
+    @classmethod
+    def _get_dtype_mapping(cls) -> dict[np.dtype, IntegerDtype]:
+        return NUMPY_INT_TO_DTYPE
+
+    @classmethod
+    def _safe_cast(cls, values: np.ndarray, dtype: np.dtype, copy: bool) -> np.ndarray:
+        """
+        Safely cast the values to the given dtype.
+
+        "safe" in this context means the casting is lossless. e.g. if 'values'
+        has a floating dtype, each value must be an integer.
+        """
+        try:
+            return values.astype(dtype, casting="safe", copy=copy)
+        except TypeError as err:
+            casted = values.astype(dtype, copy=copy)
+            if (casted == values).all():
+                return casted
+
+            raise TypeError(
+                f"cannot safely cast non-equivalent {values.dtype} to {np.dtype(dtype)}"
+            ) from err
+
+
+class IntegerArray(NumericArray):
+    """
+    Array of integer (optional missing) values.
+
+    Uses :attr:`pandas.NA` as the missing value.
+
+    .. warning::
+
+       IntegerArray is currently experimental, and its API or internal
+       implementation may change without warning.
+
+    We represent an IntegerArray with 2 numpy arrays:
+
+    - data: contains a numpy integer array of the appropriate dtype
+    - mask: a boolean array holding a mask on the data, True is missing
+
+    To construct an IntegerArray from generic array-like input, use
+    :func:`pandas.array` with one of the integer dtypes (see examples).
+
+    See :ref:`integer_na` for more.
+
+    Parameters
+    ----------
+    values : numpy.ndarray
+        A 1-d integer-dtype array.
+    mask : numpy.ndarray
+        A 1-d boolean-dtype array indicating missing values.
+    copy : bool, default False
+        Whether to copy the `values` and `mask`.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+
+    Returns
+    -------
+    IntegerArray
+
+    Examples
+    --------
+    Create an IntegerArray with :func:`pandas.array`.
+
+    >>> int_array = pd.array([1, None, 3], dtype=pd.Int32Dtype())
+    >>> int_array
+    <IntegerArray>
+    [1, <NA>, 3]
+    Length: 3, dtype: Int32
+
+    String aliases for the dtypes are also available. They are capitalized.
+
+    >>> pd.array([1, None, 3], dtype='Int32')
+    <IntegerArray>
+    [1, <NA>, 3]
+    Length: 3, dtype: Int32
+
+    >>> pd.array([1, None, 3], dtype='UInt16')
+    <IntegerArray>
+    [1, <NA>, 3]
+    Length: 3, dtype: UInt16
+    """
+
+    _dtype_cls = IntegerDtype
+
+    # The value used to fill '_data' to avoid upcasting
+    _internal_fill_value = 1
+    # Fill values used for any/all
+    # Incompatible types in assignment (expression has type "int", base class
+    # "BaseMaskedArray" defined the type as "<typing special form>")
+    _truthy_value = 1  # type: ignore[assignment]
+    _falsey_value = 0  # type: ignore[assignment]
+
+
+_dtype_docstring = """
+An ExtensionDtype for {dtype} integer data.
+
+Uses :attr:`pandas.NA` as its missing value, rather than :attr:`numpy.nan`.
+
+Attributes
+----------
+None
+
+Methods
+-------
+None
+
+Examples
+--------
+For Int8Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.Int8Dtype())
+>>> ser.dtype
+Int8Dtype()
+
+For Int16Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.Int16Dtype())
+>>> ser.dtype
+Int16Dtype()
+
+For Int32Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.Int32Dtype())
+>>> ser.dtype
+Int32Dtype()
+
+For Int64Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.Int64Dtype())
+>>> ser.dtype
+Int64Dtype()
+
+For UInt8Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.UInt8Dtype())
+>>> ser.dtype
+UInt8Dtype()
+
+For UInt16Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.UInt16Dtype())
+>>> ser.dtype
+UInt16Dtype()
+
+For UInt32Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.UInt32Dtype())
+>>> ser.dtype
+UInt32Dtype()
+
+For UInt64Dtype:
+
+>>> ser = pd.Series([2, pd.NA], dtype=pd.UInt64Dtype())
+>>> ser.dtype
+UInt64Dtype()
+"""
+
+# create the Dtype
+
+
+@register_extension_dtype
+class Int8Dtype(IntegerDtype):
+    type = np.int8
+    name: ClassVar[str] = "Int8"
+    __doc__ = _dtype_docstring.format(dtype="int8")
+
+
+@register_extension_dtype
+class Int16Dtype(IntegerDtype):
+    type = np.int16
+    name: ClassVar[str] = "Int16"
+    __doc__ = _dtype_docstring.format(dtype="int16")
+
+
+@register_extension_dtype
+class Int32Dtype(IntegerDtype):
+    type = np.int32
+    name: ClassVar[str] = "Int32"
+    __doc__ = _dtype_docstring.format(dtype="int32")
+
+
+@register_extension_dtype
+class Int64Dtype(IntegerDtype):
+    type = np.int64
+    name: ClassVar[str] = "Int64"
+    __doc__ = _dtype_docstring.format(dtype="int64")
+
+
+@register_extension_dtype
+class UInt8Dtype(IntegerDtype):
+    type = np.uint8
+    name: ClassVar[str] = "UInt8"
+    __doc__ = _dtype_docstring.format(dtype="uint8")
+
+
+@register_extension_dtype
+class UInt16Dtype(IntegerDtype):
+    type = np.uint16
+    name: ClassVar[str] = "UInt16"
+    __doc__ = _dtype_docstring.format(dtype="uint16")
+
+
+@register_extension_dtype
+class UInt32Dtype(IntegerDtype):
+    type = np.uint32
+    name: ClassVar[str] = "UInt32"
+    __doc__ = _dtype_docstring.format(dtype="uint32")
+
+
+@register_extension_dtype
+class UInt64Dtype(IntegerDtype):
+    type = np.uint64
+    name: ClassVar[str] = "UInt64"
+    __doc__ = _dtype_docstring.format(dtype="uint64")
+
+
+NUMPY_INT_TO_DTYPE: dict[np.dtype, IntegerDtype] = {
+    np.dtype(np.int8): Int8Dtype(),
+    np.dtype(np.int16): Int16Dtype(),
+    np.dtype(np.int32): Int32Dtype(),
+    np.dtype(np.int64): Int64Dtype(),
+    np.dtype(np.uint8): UInt8Dtype(),
+    np.dtype(np.uint16): UInt16Dtype(),
+    np.dtype(np.uint32): UInt32Dtype(),
+    np.dtype(np.uint64): UInt64Dtype(),
+}

lib/python3.11/site-packages/pandas/core/arrays/numeric.py

@@ -0,0 +1,286 @@
+from __future__ import annotations
+
+import numbers
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+)
+
+import numpy as np
+
+from pandas._libs import (
+    lib,
+    missing as libmissing,
+)
+from pandas.errors import AbstractMethodError
+from pandas.util._decorators import cache_readonly
+
+from pandas.core.dtypes.common import (
+    is_integer_dtype,
+    is_string_dtype,
+    pandas_dtype,
+)
+
+from pandas.core.arrays.masked import (
+    BaseMaskedArray,
+    BaseMaskedDtype,
+)
+
+if TYPE_CHECKING:
+    from collections.abc import Mapping
+
+    import pyarrow
+
+    from pandas._typing import (
+        Dtype,
+        DtypeObj,
+        Self,
+        npt,
+    )
+
+
+class NumericDtype(BaseMaskedDtype):
+    _default_np_dtype: np.dtype
+    _checker: Callable[[Any], bool]  # is_foo_dtype
+
+    def __repr__(self) -> str:
+        return f"{self.name}Dtype()"
+
+    @cache_readonly
+    def is_signed_integer(self) -> bool:
+        return self.kind == "i"
+
+    @cache_readonly
+    def is_unsigned_integer(self) -> bool:
+        return self.kind == "u"
+
+    @property
+    def _is_numeric(self) -> bool:
+        return True
+
+    def __from_arrow__(
+        self, array: pyarrow.Array | pyarrow.ChunkedArray
+    ) -> BaseMaskedArray:
+        """
+        Construct IntegerArray/FloatingArray from pyarrow Array/ChunkedArray.
+        """
+        import pyarrow
+
+        from pandas.core.arrays.arrow._arrow_utils import (
+            pyarrow_array_to_numpy_and_mask,
+        )
+
+        array_class = self.construct_array_type()
+
+        pyarrow_type = pyarrow.from_numpy_dtype(self.type)
+        if not array.type.equals(pyarrow_type) and not pyarrow.types.is_null(
+            array.type
+        ):
+            # test_from_arrow_type_error raise for string, but allow
+            #  through itemsize conversion GH#31896
+            rt_dtype = pandas_dtype(array.type.to_pandas_dtype())
+            if rt_dtype.kind not in "iuf":
+                # Could allow "c" or potentially disallow float<->int conversion,
+                #  but at the moment we specifically test that uint<->int works
+                raise TypeError(
+                    f"Expected array of {self} type, got {array.type} instead"
+                )
+
+            array = array.cast(pyarrow_type)
+
+        if isinstance(array, pyarrow.ChunkedArray):
+            # TODO this "if" can be removed when requiring pyarrow >= 10.0, which fixed
+            # combine_chunks for empty arrays https://github.com/apache/arrow/pull/13757
+            if array.num_chunks == 0:
+                array = pyarrow.array([], type=array.type)
+            else:
+                array = array.combine_chunks()
+
+        data, mask = pyarrow_array_to_numpy_and_mask(array, dtype=self.numpy_dtype)
+        return array_class(data.copy(), ~mask, copy=False)
+
+    @classmethod
+    def _get_dtype_mapping(cls) -> Mapping[np.dtype, NumericDtype]:
+        raise AbstractMethodError(cls)
+
+    @classmethod
+    def _standardize_dtype(cls, dtype: NumericDtype | str | np.dtype) -> NumericDtype:
+        """
+        Convert a string representation or a numpy dtype to NumericDtype.
+        """
+        if isinstance(dtype, str) and (dtype.startswith(("Int", "UInt", "Float"))):
+            # Avoid DeprecationWarning from NumPy about np.dtype("Int64")
+            # https://github.com/numpy/numpy/pull/7476
+            dtype = dtype.lower()
+
+        if not isinstance(dtype, NumericDtype):
+            mapping = cls._get_dtype_mapping()
+            try:
+                dtype = mapping[np.dtype(dtype)]
+            except KeyError as err:
+                raise ValueError(f"invalid dtype specified {dtype}") from err
+        return dtype
+
+    @classmethod
+    def _safe_cast(cls, values: np.ndarray, dtype: np.dtype, copy: bool) -> np.ndarray:
+        """
+        Safely cast the values to the given dtype.
+
+        "safe" in this context means the casting is lossless.
+        """
+        raise AbstractMethodError(cls)
+
+
+def _coerce_to_data_and_mask(
+    values, dtype, copy: bool, dtype_cls: type[NumericDtype], default_dtype: np.dtype
+):
+    checker = dtype_cls._checker
+
+    mask = None
+    inferred_type = None
+
+    if dtype is None and hasattr(values, "dtype"):
+        if checker(values.dtype):
+            dtype = values.dtype
+
+    if dtype is not None:
+        dtype = dtype_cls._standardize_dtype(dtype)
+
+    cls = dtype_cls.construct_array_type()
+    if isinstance(values, cls):
+        values, mask = values._data, values._mask
+        if dtype is not None:
+            values = values.astype(dtype.numpy_dtype, copy=False)
+
+        if copy:
+            values = values.copy()
+            mask = mask.copy()
+        return values, mask, dtype, inferred_type
+
+    original = values
+    if not copy:
+        values = np.asarray(values)
+    else:
+        values = np.array(values, copy=copy)
+    inferred_type = None
+    if values.dtype == object or is_string_dtype(values.dtype):
+        inferred_type = lib.infer_dtype(values, skipna=True)
+        if inferred_type == "boolean" and dtype is None:
+            name = dtype_cls.__name__.strip("_")
+            raise TypeError(f"{values.dtype} cannot be converted to {name}")
+
+    elif values.dtype.kind == "b" and checker(dtype):
+        if not copy:
+            values = np.asarray(values, dtype=default_dtype)
+        else:
+            values = np.array(values, dtype=default_dtype, copy=copy)
+
+    elif values.dtype.kind not in "iuf":
+        name = dtype_cls.__name__.strip("_")
+        raise TypeError(f"{values.dtype} cannot be converted to {name}")
+
+    if values.ndim != 1:
+        raise TypeError("values must be a 1D list-like")
+
+    if mask is None:
+        if values.dtype.kind in "iu":
+            # fastpath
+            mask = np.zeros(len(values), dtype=np.bool_)
+        else:
+            mask = libmissing.is_numeric_na(values)
+    else:
+        assert len(mask) == len(values)
+
+    if mask.ndim != 1:
+        raise TypeError("mask must be a 1D list-like")
+
+    # infer dtype if needed
+    if dtype is None:
+        dtype = default_dtype
+    else:
+        dtype = dtype.numpy_dtype
+
+    if is_integer_dtype(dtype) and values.dtype.kind == "f" and len(values) > 0:
+        if mask.all():
+            values = np.ones(values.shape, dtype=dtype)
+        else:
+            idx = np.nanargmax(values)
+            if int(values[idx]) != original[idx]:
+                # We have ints that lost precision during the cast.
+                inferred_type = lib.infer_dtype(original, skipna=True)
+                if (
+                    inferred_type not in ["floating", "mixed-integer-float"]
+                    and not mask.any()
+                ):
+                    values = np.asarray(original, dtype=dtype)
+                else:
+                    values = np.asarray(original, dtype="object")
+
+    # we copy as need to coerce here
+    if mask.any():
+        values = values.copy()
+        values[mask] = cls._internal_fill_value
+    if inferred_type in ("string", "unicode"):
+        # casts from str are always safe since they raise
+        # a ValueError if the str cannot be parsed into a float
+        values = values.astype(dtype, copy=copy)
+    else:
+        values = dtype_cls._safe_cast(values, dtype, copy=False)
+
+    return values, mask, dtype, inferred_type
+
+
+class NumericArray(BaseMaskedArray):
+    """
+    Base class for IntegerArray and FloatingArray.
+    """
+
+    _dtype_cls: type[NumericDtype]
+
+    def __init__(
+        self, values: np.ndarray, mask: npt.NDArray[np.bool_], copy: bool = False
+    ) -> None:
+        checker = self._dtype_cls._checker
+        if not (isinstance(values, np.ndarray) and checker(values.dtype)):
+            descr = (
+                "floating"
+                if self._dtype_cls.kind == "f"  # type: ignore[comparison-overlap]
+                else "integer"
+            )
+            raise TypeError(
+                f"values should be {descr} numpy array. Use "
+                "the 'pd.array' function instead"
+            )
+        if values.dtype == np.float16:
+            # If we don't raise here, then accessing self.dtype would raise
+            raise TypeError("FloatingArray does not support np.float16 dtype.")
+
+        super().__init__(values, mask, copy=copy)
+
+    @cache_readonly
+    def dtype(self) -> NumericDtype:
+        mapping = self._dtype_cls._get_dtype_mapping()
+        return mapping[self._data.dtype]
+
+    @classmethod
+    def _coerce_to_array(
+        cls, value, *, dtype: DtypeObj, copy: bool = False
+    ) -> tuple[np.ndarray, np.ndarray]:
+        dtype_cls = cls._dtype_cls
+        default_dtype = dtype_cls._default_np_dtype
+        values, mask, _, _ = _coerce_to_data_and_mask(
+            value, dtype, copy, dtype_cls, default_dtype
+        )
+        return values, mask
+
+    @classmethod
+    def _from_sequence_of_strings(
+        cls, strings, *, dtype: Dtype | None = None, copy: bool = False
+    ) -> Self:
+        from pandas.core.tools.numeric import to_numeric
+
+        scalars = to_numeric(strings, errors="raise", dtype_backend="numpy_nullable")
+        return cls._from_sequence(scalars, dtype=dtype, copy=copy)
+
+    _HANDLED_TYPES = (np.ndarray, numbers.Number)

lib/python3.11/site-packages/pandas/core/arrays/numpy_.py

@@ -0,0 +1,574 @@
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+from pandas._libs.tslibs import is_supported_dtype
+from pandas.compat.numpy import function as nv
+
+from pandas.core.dtypes.astype import astype_array
+from pandas.core.dtypes.cast import construct_1d_object_array_from_listlike
+from pandas.core.dtypes.common import pandas_dtype
+from pandas.core.dtypes.dtypes import NumpyEADtype
+from pandas.core.dtypes.missing import isna
+
+from pandas.core import (
+    arraylike,
+    missing,
+    nanops,
+    ops,
+)
+from pandas.core.arraylike import OpsMixin
+from pandas.core.arrays._mixins import NDArrayBackedExtensionArray
+from pandas.core.construction import ensure_wrapped_if_datetimelike
+from pandas.core.strings.object_array import ObjectStringArrayMixin
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
+    from pandas._typing import (
+        AxisInt,
+        Dtype,
+        FillnaOptions,
+        InterpolateOptions,
+        NpDtype,
+        Scalar,
+        Self,
+        npt,
+    )
+
+    from pandas import Index
+
+
+# error: Definition of "_concat_same_type" in base class "NDArrayBacked" is
+# incompatible with definition in base class "ExtensionArray"
+class NumpyExtensionArray(  # type: ignore[misc]
+    OpsMixin,
+    NDArrayBackedExtensionArray,
+    ObjectStringArrayMixin,
+):
+    """
+    A pandas ExtensionArray for NumPy data.
+
+    This is mostly for internal compatibility, and is not especially
+    useful on its own.
+
+    Parameters
+    ----------
+    values : ndarray
+        The NumPy ndarray to wrap. Must be 1-dimensional.
+    copy : bool, default False
+        Whether to copy `values`.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+
+    Examples
+    --------
+    >>> pd.arrays.NumpyExtensionArray(np.array([0, 1, 2, 3]))
+    <NumpyExtensionArray>
+    [0, 1, 2, 3]
+    Length: 4, dtype: int64
+    """
+
+    # If you're wondering why pd.Series(cls) doesn't put the array in an
+    # ExtensionBlock, search for `ABCNumpyExtensionArray`. We check for
+    # that _typ to ensure that users don't unnecessarily use EAs inside
+    # pandas internals, which turns off things like block consolidation.
+    _typ = "npy_extension"
+    __array_priority__ = 1000
+    _ndarray: np.ndarray
+    _dtype: NumpyEADtype
+    _internal_fill_value = np.nan
+
+    # ------------------------------------------------------------------------
+    # Constructors
+
+    def __init__(
+        self, values: np.ndarray | NumpyExtensionArray, copy: bool = False
+    ) -> None:
+        if isinstance(values, type(self)):
+            values = values._ndarray
+        if not isinstance(values, np.ndarray):
+            raise ValueError(
+                f"'values' must be a NumPy array, not {type(values).__name__}"
+            )
+
+        if values.ndim == 0:
+            # Technically we support 2, but do not advertise that fact.
+            raise ValueError("NumpyExtensionArray must be 1-dimensional.")
+
+        if copy:
+            values = values.copy()
+
+        dtype = NumpyEADtype(values.dtype)
+        super().__init__(values, dtype)
+
+    @classmethod
+    def _from_sequence(
+        cls, scalars, *, dtype: Dtype | None = None, copy: bool = False
+    ) -> NumpyExtensionArray:
+        if isinstance(dtype, NumpyEADtype):
+            dtype = dtype._dtype
+
+        # error: Argument "dtype" to "asarray" has incompatible type
+        # "Union[ExtensionDtype, str, dtype[Any], dtype[floating[_64Bit]], Type[object],
+        # None]"; expected "Union[dtype[Any], None, type, _SupportsDType, str,
+        # Union[Tuple[Any, int], Tuple[Any, Union[int, Sequence[int]]], List[Any],
+        # _DTypeDict, Tuple[Any, Any]]]"
+        result = np.asarray(scalars, dtype=dtype)  # type: ignore[arg-type]
+        if (
+            result.ndim > 1
+            and not hasattr(scalars, "dtype")
+            and (dtype is None or dtype == object)
+        ):
+            # e.g. list-of-tuples
+            result = construct_1d_object_array_from_listlike(scalars)
+
+        if copy and result is scalars:
+            result = result.copy()
+        return cls(result)
+
+    # ------------------------------------------------------------------------
+    # Data
+
+    @property
+    def dtype(self) -> NumpyEADtype:
+        return self._dtype
+
+    # ------------------------------------------------------------------------
+    # NumPy Array Interface
+
+    def __array__(
+        self, dtype: NpDtype | None = None, copy: bool | None = None
+    ) -> np.ndarray:
+        if copy is not None:
+            # Note: branch avoids `copy=None` for NumPy 1.x support
+            return np.array(self._ndarray, dtype=dtype, copy=copy)
+        return np.asarray(self._ndarray, dtype=dtype)
+
+    def __array_ufunc__(self, ufunc: np.ufunc, method: str, *inputs, **kwargs):
+        # Lightly modified version of
+        # https://numpy.org/doc/stable/reference/generated/numpy.lib.mixins.NDArrayOperatorsMixin.html
+        # The primary modification is not boxing scalar return values
+        # in NumpyExtensionArray, since pandas' ExtensionArrays are 1-d.
+        out = kwargs.get("out", ())
+
+        result = arraylike.maybe_dispatch_ufunc_to_dunder_op(
+            self, ufunc, method, *inputs, **kwargs
+        )
+        if result is not NotImplemented:
+            return result
+
+        if "out" in kwargs:
+            # e.g. test_ufunc_unary
+            return arraylike.dispatch_ufunc_with_out(
+                self, ufunc, method, *inputs, **kwargs
+            )
+
+        if method == "reduce":
+            result = arraylike.dispatch_reduction_ufunc(
+                self, ufunc, method, *inputs, **kwargs
+            )
+            if result is not NotImplemented:
+                # e.g. tests.series.test_ufunc.TestNumpyReductions
+                return result
+
+        # Defer to the implementation of the ufunc on unwrapped values.
+        inputs = tuple(
+            x._ndarray if isinstance(x, NumpyExtensionArray) else x for x in inputs
+        )
+        if out:
+            kwargs["out"] = tuple(
+                x._ndarray if isinstance(x, NumpyExtensionArray) else x for x in out
+            )
+        result = getattr(ufunc, method)(*inputs, **kwargs)
+
+        if ufunc.nout > 1:
+            # multiple return values; re-box array-like results
+            return tuple(type(self)(x) for x in result)
+        elif method == "at":
+            # no return value
+            return None
+        elif method == "reduce":
+            if isinstance(result, np.ndarray):
+                # e.g. test_np_reduce_2d
+                return type(self)(result)
+
+            # e.g. test_np_max_nested_tuples
+            return result
+        else:
+            # one return value; re-box array-like results
+            return type(self)(result)
+
+    # ------------------------------------------------------------------------
+    # Pandas ExtensionArray Interface
+
+    def astype(self, dtype, copy: bool = True):
+        dtype = pandas_dtype(dtype)
+
+        if dtype == self.dtype:
+            if copy:
+                return self.copy()
+            return self
+
+        result = astype_array(self._ndarray, dtype=dtype, copy=copy)
+        return result
+
+    def isna(self) -> np.ndarray:
+        return isna(self._ndarray)
+
+    def _validate_scalar(self, fill_value):
+        if fill_value is None:
+            # Primarily for subclasses
+            fill_value = self.dtype.na_value
+        return fill_value
+
+    def _values_for_factorize(self) -> tuple[np.ndarray, float | None]:
+        if self.dtype.kind in "iub":
+            fv = None
+        else:
+            fv = np.nan
+        return self._ndarray, fv
+
+    # Base EA class (and all other EA classes) don't have limit_area keyword
+    # This can be removed here as well when the interpolate ffill/bfill method
+    # deprecation is enforced
+    def _pad_or_backfill(
+        self,
+        *,
+        method: FillnaOptions,
+        limit: int | None = None,
+        limit_area: Literal["inside", "outside"] | None = None,
+        copy: bool = True,
+    ) -> Self:
+        """
+        ffill or bfill along axis=0.
+        """
+        if copy:
+            out_data = self._ndarray.copy()
+        else:
+            out_data = self._ndarray
+
+        meth = missing.clean_fill_method(method)
+        missing.pad_or_backfill_inplace(
+            out_data.T,
+            method=meth,
+            axis=0,
+            limit=limit,
+            limit_area=limit_area,
+        )
+
+        if not copy:
+            return self
+        return type(self)._simple_new(out_data, dtype=self.dtype)
+
+    def interpolate(
+        self,
+        *,
+        method: InterpolateOptions,
+        axis: int,
+        index: Index,
+        limit,
+        limit_direction,
+        limit_area,
+        copy: bool,
+        **kwargs,
+    ) -> Self:
+        """
+        See NDFrame.interpolate.__doc__.
+        """
+        # NB: we return type(self) even if copy=False
+        if not self.dtype._is_numeric:
+            raise TypeError(f"Cannot interpolate with {self.dtype} dtype")
+
+        if not copy:
+            out_data = self._ndarray
+        else:
+            out_data = self._ndarray.copy()
+
+        # TODO: assert we have floating dtype?
+        missing.interpolate_2d_inplace(
+            out_data,
+            method=method,
+            axis=axis,
+            index=index,
+            limit=limit,
+            limit_direction=limit_direction,
+            limit_area=limit_area,
+            **kwargs,
+        )
+        if not copy:
+            return self
+        return type(self)._simple_new(out_data, dtype=self.dtype)
+
+    # ------------------------------------------------------------------------
+    # Reductions
+
+    def any(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_any((), {"out": out, "keepdims": keepdims})
+        result = nanops.nanany(self._ndarray, axis=axis, skipna=skipna)
+        return self._wrap_reduction_result(axis, result)
+
+    def all(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_all((), {"out": out, "keepdims": keepdims})
+        result = nanops.nanall(self._ndarray, axis=axis, skipna=skipna)
+        return self._wrap_reduction_result(axis, result)
+
+    def min(
+        self, *, axis: AxisInt | None = None, skipna: bool = True, **kwargs
+    ) -> Scalar:
+        nv.validate_min((), kwargs)
+        result = nanops.nanmin(
+            values=self._ndarray, axis=axis, mask=self.isna(), skipna=skipna
+        )
+        return self._wrap_reduction_result(axis, result)
+
+    def max(
+        self, *, axis: AxisInt | None = None, skipna: bool = True, **kwargs
+    ) -> Scalar:
+        nv.validate_max((), kwargs)
+        result = nanops.nanmax(
+            values=self._ndarray, axis=axis, mask=self.isna(), skipna=skipna
+        )
+        return self._wrap_reduction_result(axis, result)
+
+    def sum(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        skipna: bool = True,
+        min_count: int = 0,
+        **kwargs,
+    ) -> Scalar:
+        nv.validate_sum((), kwargs)
+        result = nanops.nansum(
+            self._ndarray, axis=axis, skipna=skipna, min_count=min_count
+        )
+        return self._wrap_reduction_result(axis, result)
+
+    def prod(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        skipna: bool = True,
+        min_count: int = 0,
+        **kwargs,
+    ) -> Scalar:
+        nv.validate_prod((), kwargs)
+        result = nanops.nanprod(
+            self._ndarray, axis=axis, skipna=skipna, min_count=min_count
+        )
+        return self._wrap_reduction_result(axis, result)
+
+    def mean(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        dtype: NpDtype | None = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_mean((), {"dtype": dtype, "out": out, "keepdims": keepdims})
+        result = nanops.nanmean(self._ndarray, axis=axis, skipna=skipna)
+        return self._wrap_reduction_result(axis, result)
+
+    def median(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        out=None,
+        overwrite_input: bool = False,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_median(
+            (), {"out": out, "overwrite_input": overwrite_input, "keepdims": keepdims}
+        )
+        result = nanops.nanmedian(self._ndarray, axis=axis, skipna=skipna)
+        return self._wrap_reduction_result(axis, result)
+
+    def std(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        dtype: NpDtype | None = None,
+        out=None,
+        ddof: int = 1,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_stat_ddof_func(
+            (), {"dtype": dtype, "out": out, "keepdims": keepdims}, fname="std"
+        )
+        result = nanops.nanstd(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
+        return self._wrap_reduction_result(axis, result)
+
+    def var(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        dtype: NpDtype | None = None,
+        out=None,
+        ddof: int = 1,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_stat_ddof_func(
+            (), {"dtype": dtype, "out": out, "keepdims": keepdims}, fname="var"
+        )
+        result = nanops.nanvar(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
+        return self._wrap_reduction_result(axis, result)
+
+    def sem(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        dtype: NpDtype | None = None,
+        out=None,
+        ddof: int = 1,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_stat_ddof_func(
+            (), {"dtype": dtype, "out": out, "keepdims": keepdims}, fname="sem"
+        )
+        result = nanops.nansem(self._ndarray, axis=axis, skipna=skipna, ddof=ddof)
+        return self._wrap_reduction_result(axis, result)
+
+    def kurt(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        dtype: NpDtype | None = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_stat_ddof_func(
+            (), {"dtype": dtype, "out": out, "keepdims": keepdims}, fname="kurt"
+        )
+        result = nanops.nankurt(self._ndarray, axis=axis, skipna=skipna)
+        return self._wrap_reduction_result(axis, result)
+
+    def skew(
+        self,
+        *,
+        axis: AxisInt | None = None,
+        dtype: NpDtype | None = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        nv.validate_stat_ddof_func(
+            (), {"dtype": dtype, "out": out, "keepdims": keepdims}, fname="skew"
+        )
+        result = nanops.nanskew(self._ndarray, axis=axis, skipna=skipna)
+        return self._wrap_reduction_result(axis, result)
+
+    # ------------------------------------------------------------------------
+    # Additional Methods
+
+    def to_numpy(
+        self,
+        dtype: npt.DTypeLike | None = None,
+        copy: bool = False,
+        na_value: object = lib.no_default,
+    ) -> np.ndarray:
+        mask = self.isna()
+        if na_value is not lib.no_default and mask.any():
+            result = self._ndarray.copy()
+            result[mask] = na_value
+        else:
+            result = self._ndarray
+
+        result = np.asarray(result, dtype=dtype)
+
+        if copy and result is self._ndarray:
+            result = result.copy()
+
+        return result
+
+    # ------------------------------------------------------------------------
+    # Ops
+
+    def __invert__(self) -> NumpyExtensionArray:
+        return type(self)(~self._ndarray)
+
+    def __neg__(self) -> NumpyExtensionArray:
+        return type(self)(-self._ndarray)
+
+    def __pos__(self) -> NumpyExtensionArray:
+        return type(self)(+self._ndarray)
+
+    def __abs__(self) -> NumpyExtensionArray:
+        return type(self)(abs(self._ndarray))
+
+    def _cmp_method(self, other, op):
+        if isinstance(other, NumpyExtensionArray):
+            other = other._ndarray
+
+        other = ops.maybe_prepare_scalar_for_op(other, (len(self),))
+        pd_op = ops.get_array_op(op)
+        other = ensure_wrapped_if_datetimelike(other)
+        result = pd_op(self._ndarray, other)
+
+        if op is divmod or op is ops.rdivmod:
+            a, b = result
+            if isinstance(a, np.ndarray):
+                # for e.g. op vs TimedeltaArray, we may already
+                #  have an ExtensionArray, in which case we do not wrap
+                return self._wrap_ndarray_result(a), self._wrap_ndarray_result(b)
+            return a, b
+
+        if isinstance(result, np.ndarray):
+            # for e.g. multiplication vs TimedeltaArray, we may already
+            #  have an ExtensionArray, in which case we do not wrap
+            return self._wrap_ndarray_result(result)
+        return result
+
+    _arith_method = _cmp_method
+
+    def _wrap_ndarray_result(self, result: np.ndarray):
+        # If we have timedelta64[ns] result, return a TimedeltaArray instead
+        #  of a NumpyExtensionArray
+        if result.dtype.kind == "m" and is_supported_dtype(result.dtype):
+            from pandas.core.arrays import TimedeltaArray
+
+            return TimedeltaArray._simple_new(result, dtype=result.dtype)
+        return type(self)(result)
+
+    def _formatter(self, boxed: bool = False) -> Callable[[Any], str | None]:
+        # NEP 51: https://github.com/numpy/numpy/pull/22449
+        if self.dtype.kind in "SU":
+            return "'{}'".format
+        elif self.dtype == "object":
+            return repr
+        else:
+            return str

lib/python3.11/site-packages/pandas/core/arrays/sparse/__init__.py

@@ -0,0 +1,19 @@
+from pandas.core.arrays.sparse.accessor import (
+    SparseAccessor,
+    SparseFrameAccessor,
+)
+from pandas.core.arrays.sparse.array import (
+    BlockIndex,
+    IntIndex,
+    SparseArray,
+    make_sparse_index,
+)
+
+__all__ = [
+    "BlockIndex",
+    "IntIndex",
+    "make_sparse_index",
+    "SparseAccessor",
+    "SparseArray",
+    "SparseFrameAccessor",
+]

lib/python3.11/site-packages/pandas/core/arrays/sparse/accessor.py

@@ -0,0 +1,414 @@
+"""Sparse accessor"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from pandas.compat._optional import import_optional_dependency
+
+from pandas.core.dtypes.cast import find_common_type
+from pandas.core.dtypes.dtypes import SparseDtype
+
+from pandas.core.accessor import (
+    PandasDelegate,
+    delegate_names,
+)
+from pandas.core.arrays.sparse.array import SparseArray
+
+if TYPE_CHECKING:
+    from pandas import (
+        DataFrame,
+        Series,
+    )
+
+
+class BaseAccessor:
+    _validation_msg = "Can only use the '.sparse' accessor with Sparse data."
+
+    def __init__(self, data=None) -> None:
+        self._parent = data
+        self._validate(data)
+
+    def _validate(self, data):
+        raise NotImplementedError
+
+
+@delegate_names(
+    SparseArray, ["npoints", "density", "fill_value", "sp_values"], typ="property"
+)
+class SparseAccessor(BaseAccessor, PandasDelegate):
+    """
+    Accessor for SparseSparse from other sparse matrix data types.
+
+    Examples
+    --------
+    >>> ser = pd.Series([0, 0, 2, 2, 2], dtype="Sparse[int]")
+    >>> ser.sparse.density
+    0.6
+    >>> ser.sparse.sp_values
+    array([2, 2, 2])
+    """
+
+    def _validate(self, data):
+        if not isinstance(data.dtype, SparseDtype):
+            raise AttributeError(self._validation_msg)
+
+    def _delegate_property_get(self, name: str, *args, **kwargs):
+        return getattr(self._parent.array, name)
+
+    def _delegate_method(self, name: str, *args, **kwargs):
+        if name == "from_coo":
+            return self.from_coo(*args, **kwargs)
+        elif name == "to_coo":
+            return self.to_coo(*args, **kwargs)
+        else:
+            raise ValueError
+
+    @classmethod
+    def from_coo(cls, A, dense_index: bool = False) -> Series:
+        """
+        Create a Series with sparse values from a scipy.sparse.coo_matrix.
+
+        Parameters
+        ----------
+        A : scipy.sparse.coo_matrix
+        dense_index : bool, default False
+            If False (default), the index consists of only the
+            coords of the non-null entries of the original coo_matrix.
+            If True, the index consists of the full sorted
+            (row, col) coordinates of the coo_matrix.
+
+        Returns
+        -------
+        s : Series
+            A Series with sparse values.
+
+        Examples
+        --------
+        >>> from scipy import sparse
+
+        >>> A = sparse.coo_matrix(
+        ...     ([3.0, 1.0, 2.0], ([1, 0, 0], [0, 2, 3])), shape=(3, 4)
+        ... )
+        >>> A
+        <COOrdinate sparse matrix of dtype 'float64'
+            with 3 stored elements and shape (3, 4)>
+
+        >>> A.todense()
+        matrix([[0., 0., 1., 2.],
+        [3., 0., 0., 0.],
+        [0., 0., 0., 0.]])
+
+        >>> ss = pd.Series.sparse.from_coo(A)
+        >>> ss
+        0  2    1.0
+           3    2.0
+        1  0    3.0
+        dtype: Sparse[float64, nan]
+        """
+        from pandas import Series
+        from pandas.core.arrays.sparse.scipy_sparse import coo_to_sparse_series
+
+        result = coo_to_sparse_series(A, dense_index=dense_index)
+        result = Series(result.array, index=result.index, copy=False)
+
+        return result
+
+    def to_coo(self, row_levels=(0,), column_levels=(1,), sort_labels: bool = False):
+        """
+        Create a scipy.sparse.coo_matrix from a Series with MultiIndex.
+
+        Use row_levels and column_levels to determine the row and column
+        coordinates respectively. row_levels and column_levels are the names
+        (labels) or numbers of the levels. {row_levels, column_levels} must be
+        a partition of the MultiIndex level names (or numbers).
+
+        Parameters
+        ----------
+        row_levels : tuple/list
+        column_levels : tuple/list
+        sort_labels : bool, default False
+            Sort the row and column labels before forming the sparse matrix.
+            When `row_levels` and/or `column_levels` refer to a single level,
+            set to `True` for a faster execution.
+
+        Returns
+        -------
+        y : scipy.sparse.coo_matrix
+        rows : list (row labels)
+        columns : list (column labels)
+
+        Examples
+        --------
+        >>> s = pd.Series([3.0, np.nan, 1.0, 3.0, np.nan, np.nan])
+        >>> s.index = pd.MultiIndex.from_tuples(
+        ...     [
+        ...         (1, 2, "a", 0),
+        ...         (1, 2, "a", 1),
+        ...         (1, 1, "b", 0),
+        ...         (1, 1, "b", 1),
+        ...         (2, 1, "b", 0),
+        ...         (2, 1, "b", 1)
+        ...     ],
+        ...     names=["A", "B", "C", "D"],
+        ... )
+        >>> s
+        A  B  C  D
+        1  2  a  0    3.0
+                 1    NaN
+           1  b  0    1.0
+                 1    3.0
+        2  1  b  0    NaN
+                 1    NaN
+        dtype: float64
+
+        >>> ss = s.astype("Sparse")
+        >>> ss
+        A  B  C  D
+        1  2  a  0    3.0
+                 1    NaN
+           1  b  0    1.0
+                 1    3.0
+        2  1  b  0    NaN
+                 1    NaN
+        dtype: Sparse[float64, nan]
+
+        >>> A, rows, columns = ss.sparse.to_coo(
+        ...     row_levels=["A", "B"], column_levels=["C", "D"], sort_labels=True
+        ... )
+        >>> A
+        <COOrdinate sparse matrix of dtype 'float64'
+            with 3 stored elements and shape (3, 4)>
+        >>> A.todense()
+        matrix([[0., 0., 1., 3.],
+        [3., 0., 0., 0.],
+        [0., 0., 0., 0.]])
+
+        >>> rows
+        [(1, 1), (1, 2), (2, 1)]
+        >>> columns
+        [('a', 0), ('a', 1), ('b', 0), ('b', 1)]
+        """
+        from pandas.core.arrays.sparse.scipy_sparse import sparse_series_to_coo
+
+        A, rows, columns = sparse_series_to_coo(
+            self._parent, row_levels, column_levels, sort_labels=sort_labels
+        )
+        return A, rows, columns
+
+    def to_dense(self) -> Series:
+        """
+        Convert a Series from sparse values to dense.
+
+        Returns
+        -------
+        Series:
+            A Series with the same values, stored as a dense array.
+
+        Examples
+        --------
+        >>> series = pd.Series(pd.arrays.SparseArray([0, 1, 0]))
+        >>> series
+        0    0
+        1    1
+        2    0
+        dtype: Sparse[int64, 0]
+
+        >>> series.sparse.to_dense()
+        0    0
+        1    1
+        2    0
+        dtype: int64
+        """
+        from pandas import Series
+
+        return Series(
+            self._parent.array.to_dense(),
+            index=self._parent.index,
+            name=self._parent.name,
+            copy=False,
+        )
+
+
+class SparseFrameAccessor(BaseAccessor, PandasDelegate):
+    """
+    DataFrame accessor for sparse data.
+
+    Examples
+    --------
+    >>> df = pd.DataFrame({"a": [1, 2, 0, 0],
+    ...                   "b": [3, 0, 0, 4]}, dtype="Sparse[int]")
+    >>> df.sparse.density
+    0.5
+    """
+
+    def _validate(self, data):
+        dtypes = data.dtypes
+        if not all(isinstance(t, SparseDtype) for t in dtypes):
+            raise AttributeError(self._validation_msg)
+
+    @classmethod
+    def from_spmatrix(cls, data, index=None, columns=None) -> DataFrame:
+        """
+        Create a new DataFrame from a scipy sparse matrix.
+
+        Parameters
+        ----------
+        data : scipy.sparse.spmatrix
+            Must be convertible to csc format.
+        index, columns : Index, optional
+            Row and column labels to use for the resulting DataFrame.
+            Defaults to a RangeIndex.
+
+        Returns
+        -------
+        DataFrame
+            Each column of the DataFrame is stored as a
+            :class:`arrays.SparseArray`.
+
+        Examples
+        --------
+        >>> import scipy.sparse
+        >>> mat = scipy.sparse.eye(3, dtype=float)
+        >>> pd.DataFrame.sparse.from_spmatrix(mat)
+             0    1    2
+        0  1.0    0    0
+        1    0  1.0    0
+        2    0    0  1.0
+        """
+        from pandas._libs.sparse import IntIndex
+
+        from pandas import DataFrame
+
+        data = data.tocsc()
+        index, columns = cls._prep_index(data, index, columns)
+        n_rows, n_columns = data.shape
+        # We need to make sure indices are sorted, as we create
+        # IntIndex with no input validation (i.e. check_integrity=False ).
+        # Indices may already be sorted in scipy in which case this adds
+        # a small overhead.
+        data.sort_indices()
+        indices = data.indices
+        indptr = data.indptr
+        array_data = data.data
+        dtype = SparseDtype(array_data.dtype, 0)
+        arrays = []
+        for i in range(n_columns):
+            sl = slice(indptr[i], indptr[i + 1])
+            idx = IntIndex(n_rows, indices[sl], check_integrity=False)
+            arr = SparseArray._simple_new(array_data[sl], idx, dtype)
+            arrays.append(arr)
+        return DataFrame._from_arrays(
+            arrays, columns=columns, index=index, verify_integrity=False
+        )
+
+    def to_dense(self) -> DataFrame:
+        """
+        Convert a DataFrame with sparse values to dense.
+
+        Returns
+        -------
+        DataFrame
+            A DataFrame with the same values stored as dense arrays.
+
+        Examples
+        --------
+        >>> df = pd.DataFrame({"A": pd.arrays.SparseArray([0, 1, 0])})
+        >>> df.sparse.to_dense()
+           A
+        0  0
+        1  1
+        2  0
+        """
+        from pandas import DataFrame
+
+        data = {k: v.array.to_dense() for k, v in self._parent.items()}
+        return DataFrame(data, index=self._parent.index, columns=self._parent.columns)
+
+    def to_coo(self):
+        """
+        Return the contents of the frame as a sparse SciPy COO matrix.
+
+        Returns
+        -------
+        scipy.sparse.spmatrix
+            If the caller is heterogeneous and contains booleans or objects,
+            the result will be of dtype=object. See Notes.
+
+        Notes
+        -----
+        The dtype will be the lowest-common-denominator type (implicit
+        upcasting); that is to say if the dtypes (even of numeric types)
+        are mixed, the one that accommodates all will be chosen.
+
+        e.g. If the dtypes are float16 and float32, dtype will be upcast to
+        float32. By numpy.find_common_type convention, mixing int64 and
+        and uint64 will result in a float64 dtype.
+
+        Examples
+        --------
+        >>> df = pd.DataFrame({"A": pd.arrays.SparseArray([0, 1, 0, 1])})
+        >>> df.sparse.to_coo()
+        <COOrdinate sparse matrix of dtype 'int64'
+            with 2 stored elements and shape (4, 1)>
+        """
+        import_optional_dependency("scipy")
+        from scipy.sparse import coo_matrix
+
+        dtype = find_common_type(self._parent.dtypes.to_list())
+        if isinstance(dtype, SparseDtype):
+            dtype = dtype.subtype
+
+        cols, rows, data = [], [], []
+        for col, (_, ser) in enumerate(self._parent.items()):
+            sp_arr = ser.array
+            if sp_arr.fill_value != 0:
+                raise ValueError("fill value must be 0 when converting to COO matrix")
+
+            row = sp_arr.sp_index.indices
+            cols.append(np.repeat(col, len(row)))
+            rows.append(row)
+            data.append(sp_arr.sp_values.astype(dtype, copy=False))
+
+        cols = np.concatenate(cols)
+        rows = np.concatenate(rows)
+        data = np.concatenate(data)
+        return coo_matrix((data, (rows, cols)), shape=self._parent.shape)
+
+    @property
+    def density(self) -> float:
+        """
+        Ratio of non-sparse points to total (dense) data points.
+
+        Examples
+        --------
+        >>> df = pd.DataFrame({"A": pd.arrays.SparseArray([0, 1, 0, 1])})
+        >>> df.sparse.density
+        0.5
+        """
+        tmp = np.mean([column.array.density for _, column in self._parent.items()])
+        return tmp
+
+    @staticmethod
+    def _prep_index(data, index, columns):
+        from pandas.core.indexes.api import (
+            default_index,
+            ensure_index,
+        )
+
+        N, K = data.shape
+        if index is None:
+            index = default_index(N)
+        else:
+            index = ensure_index(index)
+        if columns is None:
+            columns = default_index(K)
+        else:
+            columns = ensure_index(columns)
+
+        if len(columns) != K:
+            raise ValueError(f"Column length mismatch: {len(columns)} vs. {K}")
+        if len(index) != N:
+            raise ValueError(f"Index length mismatch: {len(index)} vs. {N}")
+        return index, columns

lib/python3.11/site-packages/pandas/core/arrays/sparse/scipy_sparse.py

@@ -0,0 +1,207 @@
+"""
+Interaction with scipy.sparse matrices.
+
+Currently only includes to_coo helpers.
+"""
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+from pandas._libs import lib
+
+from pandas.core.dtypes.missing import notna
+
+from pandas.core.algorithms import factorize
+from pandas.core.indexes.api import MultiIndex
+from pandas.core.series import Series
+
+if TYPE_CHECKING:
+    from collections.abc import Iterable
+
+    import numpy as np
+    import scipy.sparse
+
+    from pandas._typing import (
+        IndexLabel,
+        npt,
+    )
+
+
+def _check_is_partition(parts: Iterable, whole: Iterable):
+    whole = set(whole)
+    parts = [set(x) for x in parts]
+    if set.intersection(*parts) != set():
+        raise ValueError("Is not a partition because intersection is not null.")
+    if set.union(*parts) != whole:
+        raise ValueError("Is not a partition because union is not the whole.")
+
+
+def _levels_to_axis(
+    ss,
+    levels: tuple[int] | list[int],
+    valid_ilocs: npt.NDArray[np.intp],
+    sort_labels: bool = False,
+) -> tuple[npt.NDArray[np.intp], list[IndexLabel]]:
+    """
+    For a MultiIndexed sparse Series `ss`, return `ax_coords` and `ax_labels`,
+    where `ax_coords` are the coordinates along one of the two axes of the
+    destination sparse matrix, and `ax_labels` are the labels from `ss`' Index
+    which correspond to these coordinates.
+
+    Parameters
+    ----------
+    ss : Series
+    levels : tuple/list
+    valid_ilocs : numpy.ndarray
+        Array of integer positions of valid values for the sparse matrix in ss.
+    sort_labels : bool, default False
+        Sort the axis labels before forming the sparse matrix. When `levels`
+        refers to a single level, set to True for a faster execution.
+
+    Returns
+    -------
+    ax_coords : numpy.ndarray (axis coordinates)
+    ax_labels : list (axis labels)
+    """
+    # Since the labels are sorted in `Index.levels`, when we wish to sort and
+    # there is only one level of the MultiIndex for this axis, the desired
+    # output can be obtained in the following simpler, more efficient way.
+    if sort_labels and len(levels) == 1:
+        ax_coords = ss.index.codes[levels[0]][valid_ilocs]
+        ax_labels = ss.index.levels[levels[0]]
+
+    else:
+        levels_values = lib.fast_zip(
+            [ss.index.get_level_values(lvl).to_numpy() for lvl in levels]
+        )
+        codes, ax_labels = factorize(levels_values, sort=sort_labels)
+        ax_coords = codes[valid_ilocs]
+
+    ax_labels = ax_labels.tolist()
+    return ax_coords, ax_labels
+
+
+def _to_ijv(
+    ss,
+    row_levels: tuple[int] | list[int] = (0,),
+    column_levels: tuple[int] | list[int] = (1,),
+    sort_labels: bool = False,
+) -> tuple[
+    np.ndarray,
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+    list[IndexLabel],
+    list[IndexLabel],
+]:
+    """
+    For an arbitrary MultiIndexed sparse Series return (v, i, j, ilabels,
+    jlabels) where (v, (i, j)) is suitable for passing to scipy.sparse.coo
+    constructor, and ilabels and jlabels are the row and column labels
+    respectively.
+
+    Parameters
+    ----------
+    ss : Series
+    row_levels : tuple/list
+    column_levels : tuple/list
+    sort_labels : bool, default False
+        Sort the row and column labels before forming the sparse matrix.
+        When `row_levels` and/or `column_levels` refer to a single level,
+        set to `True` for a faster execution.
+
+    Returns
+    -------
+    values : numpy.ndarray
+        Valid values to populate a sparse matrix, extracted from
+        ss.
+    i_coords : numpy.ndarray (row coordinates of the values)
+    j_coords : numpy.ndarray (column coordinates of the values)
+    i_labels : list (row labels)
+    j_labels : list (column labels)
+    """
+    # index and column levels must be a partition of the index
+    _check_is_partition([row_levels, column_levels], range(ss.index.nlevels))
+    # From the sparse Series, get the integer indices and data for valid sparse
+    # entries.
+    sp_vals = ss.array.sp_values
+    na_mask = notna(sp_vals)
+    values = sp_vals[na_mask]
+    valid_ilocs = ss.array.sp_index.indices[na_mask]
+
+    i_coords, i_labels = _levels_to_axis(
+        ss, row_levels, valid_ilocs, sort_labels=sort_labels
+    )
+
+    j_coords, j_labels = _levels_to_axis(
+        ss, column_levels, valid_ilocs, sort_labels=sort_labels
+    )
+
+    return values, i_coords, j_coords, i_labels, j_labels
+
+
+def sparse_series_to_coo(
+    ss: Series,
+    row_levels: Iterable[int] = (0,),
+    column_levels: Iterable[int] = (1,),
+    sort_labels: bool = False,
+) -> tuple[scipy.sparse.coo_matrix, list[IndexLabel], list[IndexLabel]]:
+    """
+    Convert a sparse Series to a scipy.sparse.coo_matrix using index
+    levels row_levels, column_levels as the row and column
+    labels respectively. Returns the sparse_matrix, row and column labels.
+    """
+    import scipy.sparse
+
+    if ss.index.nlevels < 2:
+        raise ValueError("to_coo requires MultiIndex with nlevels >= 2.")
+    if not ss.index.is_unique:
+        raise ValueError(
+            "Duplicate index entries are not allowed in to_coo transformation."
+        )
+
+    # to keep things simple, only rely on integer indexing (not labels)
+    row_levels = [ss.index._get_level_number(x) for x in row_levels]
+    column_levels = [ss.index._get_level_number(x) for x in column_levels]
+
+    v, i, j, rows, columns = _to_ijv(
+        ss, row_levels=row_levels, column_levels=column_levels, sort_labels=sort_labels
+    )
+    sparse_matrix = scipy.sparse.coo_matrix(
+        (v, (i, j)), shape=(len(rows), len(columns))
+    )
+    return sparse_matrix, rows, columns
+
+
+def coo_to_sparse_series(
+    A: scipy.sparse.coo_matrix, dense_index: bool = False
+) -> Series:
+    """
+    Convert a scipy.sparse.coo_matrix to a Series with type sparse.
+
+    Parameters
+    ----------
+    A : scipy.sparse.coo_matrix
+    dense_index : bool, default False
+
+    Returns
+    -------
+    Series
+
+    Raises
+    ------
+    TypeError if A is not a coo_matrix
+    """
+    from pandas import SparseDtype
+
+    try:
+        ser = Series(A.data, MultiIndex.from_arrays((A.row, A.col)), copy=False)
+    except AttributeError as err:
+        raise TypeError(
+            f"Expected coo_matrix. Got {type(A).__name__} instead."
+        ) from err
+    ser = ser.sort_index()
+    ser = ser.astype(SparseDtype(ser.dtype))
+    if dense_index:
+        ind = MultiIndex.from_product([A.row, A.col])
+        ser = ser.reindex(ind)
+    return ser

lib/python3.11/site-packages/pandas/core/arrays/string_arrow.py

@@ -0,0 +1,495 @@
+from __future__ import annotations
+
+import operator
+import re
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+    Union,
+)
+import warnings
+
+import numpy as np
+
+from pandas._libs import (
+    lib,
+    missing as libmissing,
+)
+from pandas.compat import (
+    pa_version_under10p1,
+    pa_version_under13p0,
+    pa_version_under16p0,
+)
+from pandas.util._exceptions import find_stack_level
+
+from pandas.core.dtypes.common import (
+    is_scalar,
+    pandas_dtype,
+)
+from pandas.core.dtypes.missing import isna
+
+from pandas.core.arrays._arrow_string_mixins import ArrowStringArrayMixin
+from pandas.core.arrays.arrow import ArrowExtensionArray
+from pandas.core.arrays.boolean import BooleanDtype
+from pandas.core.arrays.floating import Float64Dtype
+from pandas.core.arrays.integer import Int64Dtype
+from pandas.core.arrays.numeric import NumericDtype
+from pandas.core.arrays.string_ import (
+    BaseStringArray,
+    StringDtype,
+)
+from pandas.core.strings.object_array import ObjectStringArrayMixin
+
+if not pa_version_under10p1:
+    import pyarrow as pa
+    import pyarrow.compute as pc
+
+
+if TYPE_CHECKING:
+    from collections.abc import Sequence
+
+    from pandas._typing import (
+        ArrayLike,
+        Dtype,
+        Self,
+        npt,
+    )
+
+    from pandas import Series
+
+
+ArrowStringScalarOrNAT = Union[str, libmissing.NAType]
+
+
+def _chk_pyarrow_available() -> None:
+    if pa_version_under10p1:
+        msg = "pyarrow>=10.0.1 is required for PyArrow backed ArrowExtensionArray."
+        raise ImportError(msg)
+
+
+def _is_string_view(typ):
+    return not pa_version_under16p0 and pa.types.is_string_view(typ)
+
+
+# TODO: Inherit directly from BaseStringArrayMethods. Currently we inherit from
+# ObjectStringArrayMixin because we want to have the object-dtype based methods as
+# fallback for the ones that pyarrow doesn't yet support
+
+
+class ArrowStringArray(ObjectStringArrayMixin, ArrowExtensionArray, BaseStringArray):
+    """
+    Extension array for string data in a ``pyarrow.ChunkedArray``.
+
+    .. warning::
+
+       ArrowStringArray is considered experimental. The implementation and
+       parts of the API may change without warning.
+
+    Parameters
+    ----------
+    values : pyarrow.Array or pyarrow.ChunkedArray
+        The array of data.
+
+    Attributes
+    ----------
+    None
+
+    Methods
+    -------
+    None
+
+    See Also
+    --------
+    :func:`pandas.array`
+        The recommended function for creating a ArrowStringArray.
+    Series.str
+        The string methods are available on Series backed by
+        a ArrowStringArray.
+
+    Notes
+    -----
+    ArrowStringArray returns a BooleanArray for comparison methods.
+
+    Examples
+    --------
+    >>> pd.array(['This is', 'some text', None, 'data.'], dtype="string[pyarrow]")
+    <ArrowStringArray>
+    ['This is', 'some text', <NA>, 'data.']
+    Length: 4, dtype: string
+    """
+
+    # error: Incompatible types in assignment (expression has type "StringDtype",
+    # base class "ArrowExtensionArray" defined the type as "ArrowDtype")
+    _dtype: StringDtype  # type: ignore[assignment]
+    _storage = "pyarrow"
+    _na_value: libmissing.NAType | float = libmissing.NA
+
+    def __init__(self, values) -> None:
+        _chk_pyarrow_available()
+        if isinstance(values, (pa.Array, pa.ChunkedArray)) and (
+            pa.types.is_string(values.type)
+            or _is_string_view(values.type)
+            or (
+                pa.types.is_dictionary(values.type)
+                and (
+                    pa.types.is_string(values.type.value_type)
+                    or pa.types.is_large_string(values.type.value_type)
+                    or _is_string_view(values.type.value_type)
+                )
+            )
+        ):
+            values = pc.cast(values, pa.large_string())
+
+        super().__init__(values)
+        self._dtype = StringDtype(storage=self._storage, na_value=self._na_value)
+
+        if not pa.types.is_large_string(self._pa_array.type):
+            raise ValueError(
+                "ArrowStringArray requires a PyArrow (chunked) array of "
+                "large_string type"
+            )
+
+    @classmethod
+    def _box_pa_scalar(cls, value, pa_type: pa.DataType | None = None) -> pa.Scalar:
+        pa_scalar = super()._box_pa_scalar(value, pa_type)
+        if pa.types.is_string(pa_scalar.type) and pa_type is None:
+            pa_scalar = pc.cast(pa_scalar, pa.large_string())
+        return pa_scalar
+
+    @classmethod
+    def _box_pa_array(
+        cls, value, pa_type: pa.DataType | None = None, copy: bool = False
+    ) -> pa.Array | pa.ChunkedArray:
+        pa_array = super()._box_pa_array(value, pa_type)
+        if pa.types.is_string(pa_array.type) and pa_type is None:
+            pa_array = pc.cast(pa_array, pa.large_string())
+        return pa_array
+
+    def __len__(self) -> int:
+        """
+        Length of this array.
+
+        Returns
+        -------
+        length : int
+        """
+        return len(self._pa_array)
+
+    @classmethod
+    def _from_sequence(cls, scalars, *, dtype: Dtype | None = None, copy: bool = False):
+        from pandas.core.arrays.masked import BaseMaskedArray
+
+        _chk_pyarrow_available()
+
+        if dtype and not (isinstance(dtype, str) and dtype == "string"):
+            dtype = pandas_dtype(dtype)
+            assert isinstance(dtype, StringDtype) and dtype.storage == "pyarrow"
+
+        if isinstance(scalars, BaseMaskedArray):
+            # avoid costly conversion to object dtype in ensure_string_array and
+            # numerical issues with Float32Dtype
+            na_values = scalars._mask
+            result = scalars._data
+            result = lib.ensure_string_array(result, copy=copy, convert_na_value=False)
+            return cls(pa.array(result, mask=na_values, type=pa.large_string()))
+        elif isinstance(scalars, (pa.Array, pa.ChunkedArray)):
+            return cls(pc.cast(scalars, pa.large_string()))
+
+        # convert non-na-likes to str
+        result = lib.ensure_string_array(scalars, copy=copy)
+        return cls(pa.array(result, type=pa.large_string(), from_pandas=True))
+
+    @classmethod
+    def _from_sequence_of_strings(
+        cls, strings, dtype: Dtype | None = None, copy: bool = False
+    ):
+        return cls._from_sequence(strings, dtype=dtype, copy=copy)
+
+    @property
+    def dtype(self) -> StringDtype:  # type: ignore[override]
+        """
+        An instance of 'string[pyarrow]'.
+        """
+        return self._dtype
+
+    def insert(self, loc: int, item) -> ArrowStringArray:
+        if self.dtype.na_value is np.nan and item is np.nan:
+            item = libmissing.NA
+        if not isinstance(item, str) and item is not libmissing.NA:
+            raise TypeError(
+                f"Invalid value '{item}' for dtype 'str'. Value should be a "
+                f"string or missing value, got '{type(item).__name__}' instead."
+            )
+        return super().insert(loc, item)
+
+    def _convert_bool_result(self, values, na=lib.no_default, method_name=None):
+        if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
+            # GH#59561
+            warnings.warn(
+                f"Allowing a non-bool 'na' in obj.str.{method_name} is deprecated "
+                "and will raise in a future version.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+            na = bool(na)
+
+        if self.dtype.na_value is np.nan:
+            if na is lib.no_default or isna(na):
+                # NaN propagates as False
+                values = values.fill_null(False)
+            else:
+                values = values.fill_null(na)
+            return values.to_numpy()
+        else:
+            if na is not lib.no_default and not isna(
+                na
+            ):  # pyright: ignore [reportGeneralTypeIssues]
+                values = values.fill_null(na)
+        return BooleanDtype().__from_arrow__(values)
+
+    def _maybe_convert_setitem_value(self, value):
+        """Maybe convert value to be pyarrow compatible."""
+        if is_scalar(value):
+            if isna(value):
+                value = None
+            elif not isinstance(value, str):
+                raise TypeError(
+                    f"Invalid value '{value}' for dtype 'str'. Value should be a "
+                    f"string or missing value, got '{type(value).__name__}' instead."
+                )
+        else:
+            value = np.array(value, dtype=object, copy=True)
+            value[isna(value)] = None
+            for v in value:
+                if not (v is None or isinstance(v, str)):
+                    raise TypeError(
+                        "Invalid value for dtype 'str'. Value should be a "
+                        "string or missing value (or array of those)."
+                    )
+        return super()._maybe_convert_setitem_value(value)
+
+    def isin(self, values: ArrayLike) -> npt.NDArray[np.bool_]:
+        value_set = [
+            pa_scalar.as_py()
+            for pa_scalar in [pa.scalar(value, from_pandas=True) for value in values]
+            if pa_scalar.type in (pa.string(), pa.null(), pa.large_string())
+        ]
+
+        # short-circuit to return all False array.
+        if not len(value_set):
+            return np.zeros(len(self), dtype=bool)
+
+        result = pc.is_in(
+            self._pa_array, value_set=pa.array(value_set, type=self._pa_array.type)
+        )
+        # pyarrow 2.0.0 returned nulls, so we explicily specify dtype to convert nulls
+        # to False
+        return np.array(result, dtype=np.bool_)
+
+    def astype(self, dtype, copy: bool = True):
+        dtype = pandas_dtype(dtype)
+
+        if dtype == self.dtype:
+            if copy:
+                return self.copy()
+            return self
+        elif isinstance(dtype, NumericDtype):
+            data = self._pa_array.cast(pa.from_numpy_dtype(dtype.numpy_dtype))
+            return dtype.__from_arrow__(data)
+        elif isinstance(dtype, np.dtype) and np.issubdtype(dtype, np.floating):
+            return self.to_numpy(dtype=dtype, na_value=np.nan)
+
+        return super().astype(dtype, copy=copy)
+
+    @property
+    def _data(self):
+        # dask accesses ._data directlys
+        warnings.warn(
+            f"{type(self).__name__}._data is a deprecated and will be removed "
+            "in a future version, use ._pa_array instead",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
+        return self._pa_array
+
+    # ------------------------------------------------------------------------
+    # String methods interface
+
+    _str_isalnum = ArrowStringArrayMixin._str_isalnum
+    _str_isalpha = ArrowStringArrayMixin._str_isalpha
+    _str_isdecimal = ArrowStringArrayMixin._str_isdecimal
+    _str_isdigit = ArrowStringArrayMixin._str_isdigit
+    _str_islower = ArrowStringArrayMixin._str_islower
+    _str_isnumeric = ArrowStringArrayMixin._str_isnumeric
+    _str_isspace = ArrowStringArrayMixin._str_isspace
+    _str_istitle = ArrowStringArrayMixin._str_istitle
+    _str_isupper = ArrowStringArrayMixin._str_isupper
+
+    _str_map = BaseStringArray._str_map
+    _str_startswith = ArrowStringArrayMixin._str_startswith
+    _str_endswith = ArrowStringArrayMixin._str_endswith
+    _str_pad = ArrowStringArrayMixin._str_pad
+    _str_match = ArrowStringArrayMixin._str_match
+    _str_fullmatch = ArrowStringArrayMixin._str_fullmatch
+    _str_lower = ArrowStringArrayMixin._str_lower
+    _str_upper = ArrowStringArrayMixin._str_upper
+    _str_strip = ArrowStringArrayMixin._str_strip
+    _str_lstrip = ArrowStringArrayMixin._str_lstrip
+    _str_rstrip = ArrowStringArrayMixin._str_rstrip
+    _str_removesuffix = ArrowStringArrayMixin._str_removesuffix
+    _str_get = ArrowStringArrayMixin._str_get
+    _str_capitalize = ArrowStringArrayMixin._str_capitalize
+    _str_title = ArrowStringArrayMixin._str_title
+    _str_swapcase = ArrowStringArrayMixin._str_swapcase
+    _str_slice_replace = ArrowStringArrayMixin._str_slice_replace
+    _str_len = ArrowStringArrayMixin._str_len
+    _str_slice = ArrowStringArrayMixin._str_slice
+
+    def _str_contains(
+        self,
+        pat,
+        case: bool = True,
+        flags: int = 0,
+        na=lib.no_default,
+        regex: bool = True,
+    ):
+        if flags:
+            return super()._str_contains(pat, case, flags, na, regex)
+        if isinstance(pat, re.Pattern):
+            pat = pat.pattern
+
+        return ArrowStringArrayMixin._str_contains(self, pat, case, flags, na, regex)
+
+    def _str_replace(
+        self,
+        pat: str | re.Pattern,
+        repl: str | Callable,
+        n: int = -1,
+        case: bool = True,
+        flags: int = 0,
+        regex: bool = True,
+    ):
+        if isinstance(pat, re.Pattern) or callable(repl) or not case or flags:
+            return super()._str_replace(pat, repl, n, case, flags, regex)
+
+        return ArrowStringArrayMixin._str_replace(
+            self, pat, repl, n, case, flags, regex
+        )
+
+    def _str_repeat(self, repeats: int | Sequence[int]):
+        if not isinstance(repeats, int):
+            return super()._str_repeat(repeats)
+        else:
+            return ArrowExtensionArray._str_repeat(self, repeats=repeats)
+
+    def _str_removeprefix(self, prefix: str):
+        if not pa_version_under13p0:
+            return ArrowStringArrayMixin._str_removeprefix(self, prefix)
+        return super()._str_removeprefix(prefix)
+
+    def _str_count(self, pat: str, flags: int = 0):
+        if flags:
+            return super()._str_count(pat, flags)
+        result = pc.count_substring_regex(self._pa_array, pat)
+        return self._convert_int_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
+            return super()._str_find(sub, start, end)
+        return ArrowStringArrayMixin._str_find(self, sub, start, end)
+
+    def _str_get_dummies(self, sep: str = "|"):
+        dummies_pa, labels = ArrowExtensionArray(self._pa_array)._str_get_dummies(sep)
+        if len(labels) == 0:
+            return np.empty(shape=(0, 0), dtype=np.int64), labels
+        dummies = np.vstack(dummies_pa.to_numpy())
+        return dummies.astype(np.int64, copy=False), labels
+
+    def _convert_int_result(self, result):
+        if self.dtype.na_value is np.nan:
+            if isinstance(result, pa.Array):
+                result = result.to_numpy(zero_copy_only=False)
+            else:
+                result = result.to_numpy()
+            if result.dtype == np.int32:
+                result = result.astype(np.int64)
+            return result
+
+        return Int64Dtype().__from_arrow__(result)
+
+    def _convert_rank_result(self, result):
+        if self.dtype.na_value is np.nan:
+            if isinstance(result, pa.Array):
+                result = result.to_numpy(zero_copy_only=False)
+            else:
+                result = result.to_numpy()
+            return result.astype("float64", copy=False)
+
+        return Float64Dtype().__from_arrow__(result)
+
+    def _reduce(
+        self, name: str, *, skipna: bool = True, keepdims: bool = False, **kwargs
+    ):
+        if self.dtype.na_value is np.nan and name in ["any", "all"]:
+            if not skipna:
+                nas = pc.is_null(self._pa_array)
+                arr = pc.or_kleene(nas, pc.not_equal(self._pa_array, ""))
+            else:
+                arr = pc.not_equal(self._pa_array, "")
+            result = ArrowExtensionArray(arr)._reduce(
+                name, skipna=skipna, keepdims=keepdims, **kwargs
+            )
+            if keepdims:
+                # ArrowExtensionArray will return a length-1 bool[pyarrow] array
+                return result.astype(np.bool_)
+            return result
+
+        if name in ("min", "max", "sum", "argmin", "argmax"):
+            result = self._reduce_calc(name, skipna=skipna, keepdims=keepdims, **kwargs)
+        else:
+            raise TypeError(f"Cannot perform reduction '{name}' with string dtype")
+
+        if name in ("argmin", "argmax") and isinstance(result, pa.Array):
+            return self._convert_int_result(result)
+        elif isinstance(result, pa.Array):
+            return type(self)(result)
+        else:
+            return result
+
+    def value_counts(self, dropna: bool = True) -> Series:
+        result = super().value_counts(dropna=dropna)
+        if self.dtype.na_value is np.nan:
+            res_values = result._values.to_numpy()
+            return result._constructor(
+                res_values, index=result.index, name=result.name, copy=False
+            )
+        return result
+
+    def _cmp_method(self, other, op):
+        if (
+            isinstance(other, (BaseStringArray, ArrowExtensionArray))
+            and self.dtype.na_value is not libmissing.NA
+            and other.dtype.na_value is libmissing.NA
+        ):
+            # NA has priority of NaN semantics
+            return NotImplemented
+
+        result = super()._cmp_method(other, op)
+        if self.dtype.na_value is np.nan:
+            if op == operator.ne:
+                return result.to_numpy(np.bool_, na_value=True)
+            else:
+                return result.to_numpy(np.bool_, na_value=False)
+        return result
+
+    def __pos__(self) -> Self:
+        raise TypeError(f"bad operand type for unary +: '{self.dtype}'")
+
+
+class ArrowStringArrayNumpySemantics(ArrowStringArray):
+    _na_value = np.nan