Add files using upload-large-folder tool

lib/python3.12/site-packages/pandas/_libs/__init__.py

@@ -0,0 +1,27 @@
+__all__ = [
+    "NaT",
+    "NaTType",
+    "OutOfBoundsDatetime",
+    "Period",
+    "Timedelta",
+    "Timestamp",
+    "iNaT",
+    "Interval",
+]
+
+
+# Below imports needs to happen first to ensure pandas top level
+# module gets monkeypatched with the pandas_datetime_CAPI
+# see pandas_datetime_exec in pd_datetime.c
+import pandas._libs.pandas_parser  # isort: skip # type: ignore[reportUnusedImport]
+import pandas._libs.pandas_datetime  # noqa: F401 # isort: skip # type: ignore[reportUnusedImport]
+from pandas._libs.interval import Interval
+from pandas._libs.tslibs import (
+    NaT,
+    NaTType,
+    OutOfBoundsDatetime,
+    Period,
+    Timedelta,
+    Timestamp,
+    iNaT,
+)

lib/python3.12/site-packages/pandas/_libs/algos.pyi

@@ -0,0 +1,416 @@
+from typing import Any
+
+import numpy as np
+
+from pandas._typing import npt
+
+class Infinity:
+    def __eq__(self, other) -> bool: ...
+    def __ne__(self, other) -> bool: ...
+    def __lt__(self, other) -> bool: ...
+    def __le__(self, other) -> bool: ...
+    def __gt__(self, other) -> bool: ...
+    def __ge__(self, other) -> bool: ...
+
+class NegInfinity:
+    def __eq__(self, other) -> bool: ...
+    def __ne__(self, other) -> bool: ...
+    def __lt__(self, other) -> bool: ...
+    def __le__(self, other) -> bool: ...
+    def __gt__(self, other) -> bool: ...
+    def __ge__(self, other) -> bool: ...
+
+def unique_deltas(
+    arr: np.ndarray,  # const int64_t[:]
+) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=1]
+def is_lexsorted(list_of_arrays: list[npt.NDArray[np.int64]]) -> bool: ...
+def groupsort_indexer(
+    index: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+) -> tuple[
+    np.ndarray,  # ndarray[int64_t, ndim=1]
+    np.ndarray,  # ndarray[int64_t, ndim=1]
+]: ...
+def kth_smallest(
+    arr: np.ndarray,  # numeric[:]
+    k: int,
+) -> Any: ...  # numeric
+
+# ----------------------------------------------------------------------
+# Pairwise correlation/covariance
+
+def nancorr(
+    mat: npt.NDArray[np.float64],  # const float64_t[:, :]
+    cov: bool = ...,
+    minp: int | None = ...,
+) -> npt.NDArray[np.float64]: ...  # ndarray[float64_t, ndim=2]
+def nancorr_spearman(
+    mat: npt.NDArray[np.float64],  # ndarray[float64_t, ndim=2]
+    minp: int = ...,
+) -> npt.NDArray[np.float64]: ...  # ndarray[float64_t, ndim=2]
+
+# ----------------------------------------------------------------------
+
+def validate_limit(nobs: int | None, limit=...) -> int: ...
+def get_fill_indexer(
+    mask: npt.NDArray[np.bool_],
+    limit: int | None = None,
+) -> npt.NDArray[np.intp]: ...
+def pad(
+    old: np.ndarray,  # ndarray[numeric_object_t]
+    new: np.ndarray,  # ndarray[numeric_object_t]
+    limit=...,
+) -> npt.NDArray[np.intp]: ...  # np.ndarray[np.intp, ndim=1]
+def pad_inplace(
+    values: np.ndarray,  # numeric_object_t[:]
+    mask: np.ndarray,  # uint8_t[:]
+    limit=...,
+) -> None: ...
+def pad_2d_inplace(
+    values: np.ndarray,  # numeric_object_t[:, :]
+    mask: np.ndarray,  # const uint8_t[:, :]
+    limit=...,
+) -> None: ...
+def backfill(
+    old: np.ndarray,  # ndarray[numeric_object_t]
+    new: np.ndarray,  # ndarray[numeric_object_t]
+    limit=...,
+) -> npt.NDArray[np.intp]: ...  # np.ndarray[np.intp, ndim=1]
+def backfill_inplace(
+    values: np.ndarray,  # numeric_object_t[:]
+    mask: np.ndarray,  # uint8_t[:]
+    limit=...,
+) -> None: ...
+def backfill_2d_inplace(
+    values: np.ndarray,  # numeric_object_t[:, :]
+    mask: np.ndarray,  # const uint8_t[:, :]
+    limit=...,
+) -> None: ...
+def is_monotonic(
+    arr: np.ndarray,  # ndarray[numeric_object_t, ndim=1]
+    timelike: bool,
+) -> tuple[bool, bool, bool]: ...
+
+# ----------------------------------------------------------------------
+# rank_1d, rank_2d
+# ----------------------------------------------------------------------
+
+def rank_1d(
+    values: np.ndarray,  # ndarray[numeric_object_t, ndim=1]
+    labels: np.ndarray | None = ...,  # const int64_t[:]=None
+    is_datetimelike: bool = ...,
+    ties_method=...,
+    ascending: bool = ...,
+    pct: bool = ...,
+    na_option=...,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> np.ndarray: ...  # np.ndarray[float64_t, ndim=1]
+def rank_2d(
+    in_arr: np.ndarray,  # ndarray[numeric_object_t, ndim=2]
+    axis: int = ...,
+    is_datetimelike: bool = ...,
+    ties_method=...,
+    ascending: bool = ...,
+    na_option=...,
+    pct: bool = ...,
+) -> np.ndarray: ...  # np.ndarray[float64_t, ndim=1]
+def diff_2d(
+    arr: np.ndarray,  # ndarray[diff_t, ndim=2]
+    out: np.ndarray,  # ndarray[out_t, ndim=2]
+    periods: int,
+    axis: int,
+    datetimelike: bool = ...,
+) -> None: ...
+def ensure_platform_int(arr: object) -> npt.NDArray[np.intp]: ...
+def ensure_object(arr: object) -> npt.NDArray[np.object_]: ...
+def ensure_float64(arr: object) -> npt.NDArray[np.float64]: ...
+def ensure_int8(arr: object) -> npt.NDArray[np.int8]: ...
+def ensure_int16(arr: object) -> npt.NDArray[np.int16]: ...
+def ensure_int32(arr: object) -> npt.NDArray[np.int32]: ...
+def ensure_int64(arr: object) -> npt.NDArray[np.int64]: ...
+def ensure_uint64(arr: object) -> npt.NDArray[np.uint64]: ...
+def take_1d_int8_int8(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int8_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int8_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int8_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_int16(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int16_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int32_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int32_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int64_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_int64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_float32_float32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_float32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_float64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_object_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_bool_bool(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_1d_bool_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_int8(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int8_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_int16(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int16_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int32_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int32_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int64_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_int64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_float32_float32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_float32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_float64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_object_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_bool_bool(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis0_bool_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_int8(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int8_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_int16(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int16_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int32_int32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int32_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int64_int64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_int64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_float32_float32(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_float32_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_float64_float64(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_object_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_bool_bool(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_axis1_bool_object(
+    values: np.ndarray, indexer: npt.NDArray[np.intp], out: np.ndarray, fill_value=...
+) -> None: ...
+def take_2d_multi_int8_int8(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int8_int32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int8_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int8_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_int16(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_int32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int16_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int32_int32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int32_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int32_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int64_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_float32_float32(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_float32_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_float64_float64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_object_object(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_bool_bool(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_bool_object(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...
+def take_2d_multi_int64_int64(
+    values: np.ndarray,
+    indexer: tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]],
+    out: np.ndarray,
+    fill_value=...,
+) -> None: ...

lib/python3.12/site-packages/pandas/_libs/arrays.pyi

@@ -0,0 +1,40 @@
+from typing import Sequence
+
+import numpy as np
+
+from pandas._typing import (
+    AxisInt,
+    DtypeObj,
+    Self,
+    Shape,
+)
+
+class NDArrayBacked:
+    _dtype: DtypeObj
+    _ndarray: np.ndarray
+    def __init__(self, values: np.ndarray, dtype: DtypeObj) -> None: ...
+    @classmethod
+    def _simple_new(cls, values: np.ndarray, dtype: DtypeObj): ...
+    def _from_backing_data(self, values: np.ndarray): ...
+    def __setstate__(self, state): ...
+    def __len__(self) -> int: ...
+    @property
+    def shape(self) -> Shape: ...
+    @property
+    def ndim(self) -> int: ...
+    @property
+    def size(self) -> int: ...
+    @property
+    def nbytes(self) -> int: ...
+    def copy(self, order=...): ...
+    def delete(self, loc, axis=...): ...
+    def swapaxes(self, axis1, axis2): ...
+    def repeat(self, repeats: int | Sequence[int], axis: int | None = ...): ...
+    def reshape(self, *args, **kwargs): ...
+    def ravel(self, order=...): ...
+    @property
+    def T(self): ...
+    @classmethod
+    def _concat_same_type(
+        cls, to_concat: Sequence[Self], axis: AxisInt = ...
+    ) -> Self: ...

lib/python3.12/site-packages/pandas/_libs/byteswap.pyi

@@ -0,0 +1,5 @@
+def read_float_with_byteswap(data: bytes, offset: int, byteswap: bool) -> float: ...
+def read_double_with_byteswap(data: bytes, offset: int, byteswap: bool) -> float: ...
+def read_uint16_with_byteswap(data: bytes, offset: int, byteswap: bool) -> int: ...
+def read_uint32_with_byteswap(data: bytes, offset: int, byteswap: bool) -> int: ...
+def read_uint64_with_byteswap(data: bytes, offset: int, byteswap: bool) -> int: ...

lib/python3.12/site-packages/pandas/_libs/groupby.pyi

@@ -0,0 +1,216 @@
+from typing import Literal
+
+import numpy as np
+
+from pandas._typing import npt
+
+def group_median_float64(
+    out: np.ndarray,  # ndarray[float64_t, ndim=2]
+    counts: npt.NDArray[np.int64],
+    values: np.ndarray,  # ndarray[float64_t, ndim=2]
+    labels: npt.NDArray[np.int64],
+    min_count: int = ...,  # Py_ssize_t
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_cumprod(
+    out: np.ndarray,  # float64_t[:, ::1]
+    values: np.ndarray,  # const float64_t[:, :]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    skipna: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_cumsum(
+    out: np.ndarray,  # int64float_t[:, ::1]
+    values: np.ndarray,  # ndarray[int64float_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    skipna: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_shift_indexer(
+    out: np.ndarray,  # int64_t[::1]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    periods: int,
+) -> None: ...
+def group_fillna_indexer(
+    out: np.ndarray,  # ndarray[intp_t]
+    labels: np.ndarray,  # ndarray[int64_t]
+    sorted_labels: npt.NDArray[np.intp],
+    mask: npt.NDArray[np.uint8],
+    limit: int,  # int64_t
+    dropna: bool,
+) -> None: ...
+def group_any_all(
+    out: np.ndarray,  # uint8_t[::1]
+    values: np.ndarray,  # const uint8_t[::1]
+    labels: np.ndarray,  # const int64_t[:]
+    mask: np.ndarray,  # const uint8_t[::1]
+    val_test: Literal["any", "all"],
+    skipna: bool,
+    result_mask: np.ndarray | None,
+) -> None: ...
+def group_sum(
+    out: np.ndarray,  # complexfloatingintuint_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[complexfloatingintuint_t, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    mask: np.ndarray | None,
+    result_mask: np.ndarray | None = ...,
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+) -> None: ...
+def group_prod(
+    out: np.ndarray,  # int64float_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[int64float_t, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    mask: np.ndarray | None,
+    result_mask: np.ndarray | None = ...,
+    min_count: int = ...,
+) -> None: ...
+def group_var(
+    out: np.ndarray,  # floating[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[floating, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    min_count: int = ...,  # Py_ssize_t
+    ddof: int = ...,  # int64_t
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    is_datetimelike: bool = ...,
+    name: str = ...,
+) -> None: ...
+def group_skew(
+    out: np.ndarray,  # float64_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[float64_T, ndim=2]
+    labels: np.ndarray,  # const intp_t[::1]
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
+) -> None: ...
+def group_mean(
+    out: np.ndarray,  # floating[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[floating, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    min_count: int = ...,  # Py_ssize_t
+    is_datetimelike: bool = ...,  # bint
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_ohlc(
+    out: np.ndarray,  # floatingintuint_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[floatingintuint_t, ndim=2]
+    labels: np.ndarray,  # const intp_t[:]
+    min_count: int = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_quantile(
+    out: npt.NDArray[np.float64],
+    values: np.ndarray,  # ndarray[numeric, ndim=1]
+    labels: npt.NDArray[np.intp],
+    mask: npt.NDArray[np.uint8],
+    qs: npt.NDArray[np.float64],  # const
+    starts: npt.NDArray[np.int64],
+    ends: npt.NDArray[np.int64],
+    interpolation: Literal["linear", "lower", "higher", "nearest", "midpoint"],
+    result_mask: np.ndarray | None,
+    is_datetimelike: bool,
+) -> None: ...
+def group_last(
+    out: np.ndarray,  # rank_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[rank_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    mask: npt.NDArray[np.bool_] | None,
+    result_mask: npt.NDArray[np.bool_] | None = ...,
+    min_count: int = ...,  # Py_ssize_t
+    is_datetimelike: bool = ...,
+    skipna: bool = ...,
+) -> None: ...
+def group_nth(
+    out: np.ndarray,  # rank_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[rank_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    mask: npt.NDArray[np.bool_] | None,
+    result_mask: npt.NDArray[np.bool_] | None = ...,
+    min_count: int = ...,  # int64_t
+    rank: int = ...,  # int64_t
+    is_datetimelike: bool = ...,
+    skipna: bool = ...,
+) -> None: ...
+def group_rank(
+    out: np.ndarray,  # float64_t[:, ::1]
+    values: np.ndarray,  # ndarray[rank_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    ties_method: Literal["average", "min", "max", "first", "dense"] = ...,
+    ascending: bool = ...,
+    pct: bool = ...,
+    na_option: Literal["keep", "top", "bottom"] = ...,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> None: ...
+def group_max(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_min(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    counts: np.ndarray,  # int64_t[::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_idxmin_idxmax(
+    out: npt.NDArray[np.intp],
+    counts: npt.NDArray[np.int64],
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: npt.NDArray[np.intp],
+    min_count: int = ...,
+    is_datetimelike: bool = ...,
+    mask: np.ndarray | None = ...,
+    name: str = ...,
+    skipna: bool = ...,
+    result_mask: np.ndarray | None = ...,
+) -> None: ...
+def group_cummin(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
+) -> None: ...
+def group_cummax(
+    out: np.ndarray,  # groupby_t[:, ::1]
+    values: np.ndarray,  # ndarray[groupby_t, ndim=2]
+    labels: np.ndarray,  # const int64_t[:]
+    ngroups: int,
+    is_datetimelike: bool,
+    mask: np.ndarray | None = ...,
+    result_mask: np.ndarray | None = ...,
+    skipna: bool = ...,
+) -> None: ...

lib/python3.12/site-packages/pandas/_libs/hashing.pyi

@@ -0,0 +1,9 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def hash_object_array(
+    arr: npt.NDArray[np.object_],
+    key: str,
+    encoding: str = ...,
+) -> npt.NDArray[np.uint64]: ...

lib/python3.12/site-packages/pandas/_libs/hashtable.pyi

@@ -0,0 +1,252 @@
+from typing import (
+    Any,
+    Hashable,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._typing import npt
+
+def unique_label_indices(
+    labels: np.ndarray,  # const int64_t[:]
+) -> np.ndarray: ...
+
+class Factorizer:
+    count: int
+    uniques: Any
+    def __init__(self, size_hint: int) -> None: ...
+    def get_count(self) -> int: ...
+    def factorize(
+        self,
+        values: np.ndarray,
+        na_sentinel=...,
+        na_value=...,
+        mask=...,
+    ) -> npt.NDArray[np.intp]: ...
+
+class ObjectFactorizer(Factorizer):
+    table: PyObjectHashTable
+    uniques: ObjectVector
+
+class Int64Factorizer(Factorizer):
+    table: Int64HashTable
+    uniques: Int64Vector
+
+class UInt64Factorizer(Factorizer):
+    table: UInt64HashTable
+    uniques: UInt64Vector
+
+class Int32Factorizer(Factorizer):
+    table: Int32HashTable
+    uniques: Int32Vector
+
+class UInt32Factorizer(Factorizer):
+    table: UInt32HashTable
+    uniques: UInt32Vector
+
+class Int16Factorizer(Factorizer):
+    table: Int16HashTable
+    uniques: Int16Vector
+
+class UInt16Factorizer(Factorizer):
+    table: UInt16HashTable
+    uniques: UInt16Vector
+
+class Int8Factorizer(Factorizer):
+    table: Int8HashTable
+    uniques: Int8Vector
+
+class UInt8Factorizer(Factorizer):
+    table: UInt8HashTable
+    uniques: UInt8Vector
+
+class Float64Factorizer(Factorizer):
+    table: Float64HashTable
+    uniques: Float64Vector
+
+class Float32Factorizer(Factorizer):
+    table: Float32HashTable
+    uniques: Float32Vector
+
+class Complex64Factorizer(Factorizer):
+    table: Complex64HashTable
+    uniques: Complex64Vector
+
+class Complex128Factorizer(Factorizer):
+    table: Complex128HashTable
+    uniques: Complex128Vector
+
+class Int64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int64]: ...
+
+class Int32Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int32]: ...
+
+class Int16Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int16]: ...
+
+class Int8Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.int8]: ...
+
+class UInt64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint64]: ...
+
+class UInt32Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint32]: ...
+
+class UInt16Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint16]: ...
+
+class UInt8Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.uint8]: ...
+
+class Float64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.float64]: ...
+
+class Float32Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.float32]: ...
+
+class Complex128Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.complex128]: ...
+
+class Complex64Vector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.complex64]: ...
+
+class StringVector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.object_]: ...
+
+class ObjectVector:
+    def __init__(self, *args) -> None: ...
+    def __len__(self) -> int: ...
+    def to_array(self) -> npt.NDArray[np.object_]: ...
+
+class HashTable:
+    # NB: The base HashTable class does _not_ actually have these methods;
+    #  we are putting them here for the sake of mypy to avoid
+    #  reproducing them in each subclass below.
+    def __init__(self, size_hint: int = ..., uses_mask: bool = ...) -> None: ...
+    def __len__(self) -> int: ...
+    def __contains__(self, key: Hashable) -> bool: ...
+    def sizeof(self, deep: bool = ...) -> int: ...
+    def get_state(self) -> dict[str, int]: ...
+    # TODO: `val/key` type is subclass-specific
+    def get_item(self, val): ...  # TODO: return type?
+    def set_item(self, key, val) -> None: ...
+    def get_na(self): ...  # TODO: return type?
+    def set_na(self, val) -> None: ...
+    def map_locations(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        mask: npt.NDArray[np.bool_] | None = ...,
+    ) -> None: ...
+    def lookup(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        mask: npt.NDArray[np.bool_] | None = ...,
+    ) -> npt.NDArray[np.intp]: ...
+    def get_labels(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        uniques,  # SubclassTypeVector
+        count_prior: int = ...,
+        na_sentinel: int = ...,
+        na_value: object = ...,
+        mask=...,
+    ) -> npt.NDArray[np.intp]: ...
+    def unique(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        return_inverse: bool = ...,
+        mask=...,
+    ) -> (
+        tuple[
+            np.ndarray,  # np.ndarray[subclass-specific]
+            npt.NDArray[np.intp],
+        ]
+        | np.ndarray
+    ): ...  # np.ndarray[subclass-specific]
+    def factorize(
+        self,
+        values: np.ndarray,  # np.ndarray[subclass-specific]
+        na_sentinel: int = ...,
+        na_value: object = ...,
+        mask=...,
+        ignore_na: bool = True,
+    ) -> tuple[np.ndarray, npt.NDArray[np.intp]]: ...  # np.ndarray[subclass-specific]
+
+class Complex128HashTable(HashTable): ...
+class Complex64HashTable(HashTable): ...
+class Float64HashTable(HashTable): ...
+class Float32HashTable(HashTable): ...
+
+class Int64HashTable(HashTable):
+    # Only Int64HashTable has get_labels_groupby, map_keys_to_values
+    def get_labels_groupby(
+        self,
+        values: npt.NDArray[np.int64],  # const int64_t[:]
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.int64]]: ...
+    def map_keys_to_values(
+        self,
+        keys: npt.NDArray[np.int64],
+        values: npt.NDArray[np.int64],  # const int64_t[:]
+    ) -> None: ...
+
+class Int32HashTable(HashTable): ...
+class Int16HashTable(HashTable): ...
+class Int8HashTable(HashTable): ...
+class UInt64HashTable(HashTable): ...
+class UInt32HashTable(HashTable): ...
+class UInt16HashTable(HashTable): ...
+class UInt8HashTable(HashTable): ...
+class StringHashTable(HashTable): ...
+class PyObjectHashTable(HashTable): ...
+class IntpHashTable(HashTable): ...
+
+def duplicated(
+    values: np.ndarray,
+    keep: Literal["last", "first", False] = ...,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> npt.NDArray[np.bool_]: ...
+def mode(
+    values: np.ndarray, dropna: bool, mask: npt.NDArray[np.bool_] | None = ...
+) -> np.ndarray: ...
+def value_count(
+    values: np.ndarray,
+    dropna: bool,
+    mask: npt.NDArray[np.bool_] | None = ...,
+) -> tuple[np.ndarray, npt.NDArray[np.int64], int]: ...  # np.ndarray[same-as-values]
+
+# arr and values should have same dtype
+def ismember(
+    arr: np.ndarray,
+    values: np.ndarray,
+) -> npt.NDArray[np.bool_]: ...
+def object_hash(obj) -> int: ...
+def objects_are_equal(a, b) -> bool: ...

lib/python3.12/site-packages/pandas/_libs/index.pyi

@@ -0,0 +1,100 @@
+import numpy as np
+
+from pandas._typing import npt
+
+from pandas import MultiIndex
+from pandas.core.arrays import ExtensionArray
+
+multiindex_nulls_shift: int
+
+class IndexEngine:
+    over_size_threshold: bool
+    def __init__(self, values: np.ndarray) -> None: ...
+    def __contains__(self, val: object) -> bool: ...
+
+    # -> int | slice | np.ndarray[bool]
+    def get_loc(self, val: object) -> int | slice | np.ndarray: ...
+    def sizeof(self, deep: bool = ...) -> int: ...
+    def __sizeof__(self) -> int: ...
+    @property
+    def is_unique(self) -> bool: ...
+    @property
+    def is_monotonic_increasing(self) -> bool: ...
+    @property
+    def is_monotonic_decreasing(self) -> bool: ...
+    @property
+    def is_mapping_populated(self) -> bool: ...
+    def clear_mapping(self): ...
+    def get_indexer(self, values: np.ndarray) -> npt.NDArray[np.intp]: ...
+    def get_indexer_non_unique(
+        self,
+        targets: np.ndarray,
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+
+class MaskedIndexEngine(IndexEngine):
+    def __init__(self, values: object) -> None: ...
+    def get_indexer_non_unique(
+        self, targets: object
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+
+class Float64Engine(IndexEngine): ...
+class Float32Engine(IndexEngine): ...
+class Complex128Engine(IndexEngine): ...
+class Complex64Engine(IndexEngine): ...
+class Int64Engine(IndexEngine): ...
+class Int32Engine(IndexEngine): ...
+class Int16Engine(IndexEngine): ...
+class Int8Engine(IndexEngine): ...
+class UInt64Engine(IndexEngine): ...
+class UInt32Engine(IndexEngine): ...
+class UInt16Engine(IndexEngine): ...
+class UInt8Engine(IndexEngine): ...
+class ObjectEngine(IndexEngine): ...
+class DatetimeEngine(Int64Engine): ...
+class TimedeltaEngine(DatetimeEngine): ...
+class PeriodEngine(Int64Engine): ...
+class BoolEngine(UInt8Engine): ...
+class MaskedFloat64Engine(MaskedIndexEngine): ...
+class MaskedFloat32Engine(MaskedIndexEngine): ...
+class MaskedComplex128Engine(MaskedIndexEngine): ...
+class MaskedComplex64Engine(MaskedIndexEngine): ...
+class MaskedInt64Engine(MaskedIndexEngine): ...
+class MaskedInt32Engine(MaskedIndexEngine): ...
+class MaskedInt16Engine(MaskedIndexEngine): ...
+class MaskedInt8Engine(MaskedIndexEngine): ...
+class MaskedUInt64Engine(MaskedIndexEngine): ...
+class MaskedUInt32Engine(MaskedIndexEngine): ...
+class MaskedUInt16Engine(MaskedIndexEngine): ...
+class MaskedUInt8Engine(MaskedIndexEngine): ...
+class MaskedBoolEngine(MaskedUInt8Engine): ...
+
+class BaseMultiIndexCodesEngine:
+    levels: list[np.ndarray]
+    offsets: np.ndarray  # ndarray[uint64_t, ndim=1]
+
+    def __init__(
+        self,
+        levels: list[np.ndarray],  # all entries hashable
+        labels: list[np.ndarray],  # all entries integer-dtyped
+        offsets: np.ndarray,  # np.ndarray[np.uint64, ndim=1]
+    ) -> None: ...
+    def get_indexer(self, target: npt.NDArray[np.object_]) -> npt.NDArray[np.intp]: ...
+    def _extract_level_codes(self, target: MultiIndex) -> np.ndarray: ...
+
+class ExtensionEngine:
+    def __init__(self, values: ExtensionArray) -> None: ...
+    def __contains__(self, val: object) -> bool: ...
+    def get_loc(self, val: object) -> int | slice | np.ndarray: ...
+    def get_indexer(self, values: np.ndarray) -> npt.NDArray[np.intp]: ...
+    def get_indexer_non_unique(
+        self,
+        targets: np.ndarray,
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+    @property
+    def is_unique(self) -> bool: ...
+    @property
+    def is_monotonic_increasing(self) -> bool: ...
+    @property
+    def is_monotonic_decreasing(self) -> bool: ...
+    def sizeof(self, deep: bool = ...) -> int: ...
+    def clear_mapping(self): ...

lib/python3.12/site-packages/pandas/_libs/indexing.pyi

@@ -0,0 +1,17 @@
+from typing import (
+    Generic,
+    TypeVar,
+)
+
+from pandas.core.indexing import IndexingMixin
+
+_IndexingMixinT = TypeVar("_IndexingMixinT", bound=IndexingMixin)
+
+class NDFrameIndexerBase(Generic[_IndexingMixinT]):
+    name: str
+    # in practice obj is either a DataFrame or a Series
+    obj: _IndexingMixinT
+
+    def __init__(self, name: str, obj: _IndexingMixinT) -> None: ...
+    @property
+    def ndim(self) -> int: ...

lib/python3.12/site-packages/pandas/_libs/internals.pyi

@@ -0,0 +1,94 @@
+from typing import (
+    Iterator,
+    Sequence,
+    final,
+    overload,
+)
+import weakref
+
+import numpy as np
+
+from pandas._typing import (
+    ArrayLike,
+    Self,
+    npt,
+)
+
+from pandas import Index
+from pandas.core.internals.blocks import Block as B
+
+def slice_len(slc: slice, objlen: int = ...) -> int: ...
+def get_concat_blkno_indexers(
+    blknos_list: list[npt.NDArray[np.intp]],
+) -> list[tuple[npt.NDArray[np.intp], BlockPlacement]]: ...
+def get_blkno_indexers(
+    blknos: np.ndarray,  # int64_t[:]
+    group: bool = ...,
+) -> list[tuple[int, slice | np.ndarray]]: ...
+def get_blkno_placements(
+    blknos: np.ndarray,
+    group: bool = ...,
+) -> Iterator[tuple[int, BlockPlacement]]: ...
+def update_blklocs_and_blknos(
+    blklocs: npt.NDArray[np.intp],
+    blknos: npt.NDArray[np.intp],
+    loc: int,
+    nblocks: int,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+@final
+class BlockPlacement:
+    def __init__(self, val: int | slice | np.ndarray) -> None: ...
+    @property
+    def indexer(self) -> np.ndarray | slice: ...
+    @property
+    def as_array(self) -> np.ndarray: ...
+    @property
+    def as_slice(self) -> slice: ...
+    @property
+    def is_slice_like(self) -> bool: ...
+    @overload
+    def __getitem__(
+        self, loc: slice | Sequence[int] | npt.NDArray[np.intp]
+    ) -> BlockPlacement: ...
+    @overload
+    def __getitem__(self, loc: int) -> int: ...
+    def __iter__(self) -> Iterator[int]: ...
+    def __len__(self) -> int: ...
+    def delete(self, loc) -> BlockPlacement: ...
+    def add(self, other) -> BlockPlacement: ...
+    def append(self, others: list[BlockPlacement]) -> BlockPlacement: ...
+    def tile_for_unstack(self, factor: int) -> npt.NDArray[np.intp]: ...
+
+class Block:
+    _mgr_locs: BlockPlacement
+    ndim: int
+    values: ArrayLike
+    refs: BlockValuesRefs
+    def __init__(
+        self,
+        values: ArrayLike,
+        placement: BlockPlacement,
+        ndim: int,
+        refs: BlockValuesRefs | None = ...,
+    ) -> None: ...
+    def slice_block_rows(self, slicer: slice) -> Self: ...
+
+class BlockManager:
+    blocks: tuple[B, ...]
+    axes: list[Index]
+    _known_consolidated: bool
+    _is_consolidated: bool
+    _blknos: np.ndarray
+    _blklocs: np.ndarray
+    def __init__(
+        self, blocks: tuple[B, ...], axes: list[Index], verify_integrity=...
+    ) -> None: ...
+    def get_slice(self, slobj: slice, axis: int = ...) -> Self: ...
+    def _rebuild_blknos_and_blklocs(self) -> None: ...
+
+class BlockValuesRefs:
+    referenced_blocks: list[weakref.ref]
+    def __init__(self, blk: Block | None = ...) -> None: ...
+    def add_reference(self, blk: Block) -> None: ...
+    def add_index_reference(self, index: Index) -> None: ...
+    def has_reference(self) -> bool: ...

lib/python3.12/site-packages/pandas/_libs/interval.pyi

@@ -0,0 +1,174 @@
+from typing import (
+    Any,
+    Generic,
+    TypeVar,
+    overload,
+)
+
+import numpy as np
+import numpy.typing as npt
+
+from pandas._typing import (
+    IntervalClosedType,
+    Timedelta,
+    Timestamp,
+)
+
+VALID_CLOSED: frozenset[str]
+
+_OrderableScalarT = TypeVar("_OrderableScalarT", int, float)
+_OrderableTimesT = TypeVar("_OrderableTimesT", Timestamp, Timedelta)
+_OrderableT = TypeVar("_OrderableT", int, float, Timestamp, Timedelta)
+
+class _LengthDescriptor:
+    @overload
+    def __get__(
+        self, instance: Interval[_OrderableScalarT], owner: Any
+    ) -> _OrderableScalarT: ...
+    @overload
+    def __get__(
+        self, instance: Interval[_OrderableTimesT], owner: Any
+    ) -> Timedelta: ...
+
+class _MidDescriptor:
+    @overload
+    def __get__(self, instance: Interval[_OrderableScalarT], owner: Any) -> float: ...
+    @overload
+    def __get__(
+        self, instance: Interval[_OrderableTimesT], owner: Any
+    ) -> _OrderableTimesT: ...
+
+class IntervalMixin:
+    @property
+    def closed_left(self) -> bool: ...
+    @property
+    def closed_right(self) -> bool: ...
+    @property
+    def open_left(self) -> bool: ...
+    @property
+    def open_right(self) -> bool: ...
+    @property
+    def is_empty(self) -> bool: ...
+    def _check_closed_matches(self, other: IntervalMixin, name: str = ...) -> None: ...
+
+class Interval(IntervalMixin, Generic[_OrderableT]):
+    @property
+    def left(self: Interval[_OrderableT]) -> _OrderableT: ...
+    @property
+    def right(self: Interval[_OrderableT]) -> _OrderableT: ...
+    @property
+    def closed(self) -> IntervalClosedType: ...
+    mid: _MidDescriptor
+    length: _LengthDescriptor
+    def __init__(
+        self,
+        left: _OrderableT,
+        right: _OrderableT,
+        closed: IntervalClosedType = ...,
+    ) -> None: ...
+    def __hash__(self) -> int: ...
+    @overload
+    def __contains__(
+        self: Interval[Timedelta], key: Timedelta | Interval[Timedelta]
+    ) -> bool: ...
+    @overload
+    def __contains__(
+        self: Interval[Timestamp], key: Timestamp | Interval[Timestamp]
+    ) -> bool: ...
+    @overload
+    def __contains__(
+        self: Interval[_OrderableScalarT],
+        key: _OrderableScalarT | Interval[_OrderableScalarT],
+    ) -> bool: ...
+    @overload
+    def __add__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __add__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __add__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __radd__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __radd__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __radd__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __sub__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __sub__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __sub__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __rsub__(
+        self: Interval[_OrderableTimesT], y: Timedelta
+    ) -> Interval[_OrderableTimesT]: ...
+    @overload
+    def __rsub__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __rsub__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __mul__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __mul__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __rmul__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __rmul__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __truediv__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __truediv__(self: Interval[float], y: float) -> Interval[float]: ...
+    @overload
+    def __floordiv__(
+        self: Interval[int], y: _OrderableScalarT
+    ) -> Interval[_OrderableScalarT]: ...
+    @overload
+    def __floordiv__(self: Interval[float], y: float) -> Interval[float]: ...
+    def overlaps(self: Interval[_OrderableT], other: Interval[_OrderableT]) -> bool: ...
+
+def intervals_to_interval_bounds(
+    intervals: np.ndarray, validate_closed: bool = ...
+) -> tuple[np.ndarray, np.ndarray, IntervalClosedType]: ...
+
+class IntervalTree(IntervalMixin):
+    def __init__(
+        self,
+        left: np.ndarray,
+        right: np.ndarray,
+        closed: IntervalClosedType = ...,
+        leaf_size: int = ...,
+    ) -> None: ...
+    @property
+    def mid(self) -> np.ndarray: ...
+    @property
+    def length(self) -> np.ndarray: ...
+    def get_indexer(self, target) -> npt.NDArray[np.intp]: ...
+    def get_indexer_non_unique(
+        self, target
+    ) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+    _na_count: int
+    @property
+    def is_overlapping(self) -> bool: ...
+    @property
+    def is_monotonic_increasing(self) -> bool: ...
+    def clear_mapping(self) -> None: ...

lib/python3.12/site-packages/pandas/_libs/join.pyi

@@ -0,0 +1,79 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def inner_join(
+    left: np.ndarray,  # const intp_t[:]
+    right: np.ndarray,  # const intp_t[:]
+    max_groups: int,
+    sort: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def left_outer_join(
+    left: np.ndarray,  # const intp_t[:]
+    right: np.ndarray,  # const intp_t[:]
+    max_groups: int,
+    sort: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def full_outer_join(
+    left: np.ndarray,  # const intp_t[:]
+    right: np.ndarray,  # const intp_t[:]
+    max_groups: int,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def ffill_indexer(
+    indexer: np.ndarray,  # const intp_t[:]
+) -> npt.NDArray[np.intp]: ...
+def left_join_indexer_unique(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> npt.NDArray[np.intp]: ...
+def left_join_indexer(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> tuple[
+    np.ndarray,  # np.ndarray[join_t]
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+]: ...
+def inner_join_indexer(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> tuple[
+    np.ndarray,  # np.ndarray[join_t]
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+]: ...
+def outer_join_indexer(
+    left: np.ndarray,  # ndarray[join_t]
+    right: np.ndarray,  # ndarray[join_t]
+) -> tuple[
+    np.ndarray,  # np.ndarray[join_t]
+    npt.NDArray[np.intp],
+    npt.NDArray[np.intp],
+]: ...
+def asof_join_backward_on_X_by_Y(
+    left_values: np.ndarray,  # ndarray[numeric_t]
+    right_values: np.ndarray,  # ndarray[numeric_t]
+    left_by_values: np.ndarray,  # const int64_t[:]
+    right_by_values: np.ndarray,  # const int64_t[:]
+    allow_exact_matches: bool = ...,
+    tolerance: np.number | float | None = ...,
+    use_hashtable: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def asof_join_forward_on_X_by_Y(
+    left_values: np.ndarray,  # ndarray[numeric_t]
+    right_values: np.ndarray,  # ndarray[numeric_t]
+    left_by_values: np.ndarray,  # const int64_t[:]
+    right_by_values: np.ndarray,  # const int64_t[:]
+    allow_exact_matches: bool = ...,
+    tolerance: np.number | float | None = ...,
+    use_hashtable: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...
+def asof_join_nearest_on_X_by_Y(
+    left_values: np.ndarray,  # ndarray[numeric_t]
+    right_values: np.ndarray,  # ndarray[numeric_t]
+    left_by_values: np.ndarray,  # const int64_t[:]
+    right_by_values: np.ndarray,  # const int64_t[:]
+    allow_exact_matches: bool = ...,
+    tolerance: np.number | float | None = ...,
+    use_hashtable: bool = ...,
+) -> tuple[npt.NDArray[np.intp], npt.NDArray[np.intp]]: ...

lib/python3.12/site-packages/pandas/_libs/json.pyi

@@ -0,0 +1,23 @@
+from typing import (
+    Any,
+    Callable,
+)
+
+def ujson_dumps(
+    obj: Any,
+    ensure_ascii: bool = ...,
+    double_precision: int = ...,
+    indent: int = ...,
+    orient: str = ...,
+    date_unit: str = ...,
+    iso_dates: bool = ...,
+    default_handler: None
+    | Callable[[Any], str | float | bool | list | dict | None] = ...,
+) -> str: ...
+def ujson_loads(
+    s: str,
+    precise_float: bool = ...,
+    numpy: bool = ...,
+    dtype: None = ...,
+    labelled: bool = ...,
+) -> Any: ...

lib/python3.12/site-packages/pandas/_libs/lib.pyi

@@ -0,0 +1,213 @@
+# TODO(npdtypes): Many types specified here can be made more specific/accurate;
+#  the more specific versions are specified in comments
+from decimal import Decimal
+from typing import (
+    Any,
+    Callable,
+    Final,
+    Generator,
+    Hashable,
+    Literal,
+    TypeAlias,
+    overload,
+)
+
+import numpy as np
+
+from pandas._libs.interval import Interval
+from pandas._libs.tslibs import Period
+from pandas._typing import (
+    ArrayLike,
+    DtypeObj,
+    TypeGuard,
+    npt,
+)
+
+# placeholder until we can specify np.ndarray[object, ndim=2]
+ndarray_obj_2d = np.ndarray
+
+from enum import Enum
+
+class _NoDefault(Enum):
+    no_default = ...
+
+no_default: Final = _NoDefault.no_default
+NoDefault: TypeAlias = Literal[_NoDefault.no_default]
+
+i8max: int
+u8max: int
+
+def is_np_dtype(dtype: object, kinds: str | None = ...) -> TypeGuard[np.dtype]: ...
+def item_from_zerodim(val: object) -> object: ...
+def infer_dtype(value: object, skipna: bool = ...) -> str: ...
+def is_iterator(obj: object) -> bool: ...
+def is_scalar(val: object) -> bool: ...
+def is_list_like(obj: object, allow_sets: bool = ...) -> bool: ...
+def is_pyarrow_array(obj: object) -> bool: ...
+def is_period(val: object) -> TypeGuard[Period]: ...
+def is_interval(obj: object) -> TypeGuard[Interval]: ...
+def is_decimal(obj: object) -> TypeGuard[Decimal]: ...
+def is_complex(obj: object) -> TypeGuard[complex]: ...
+def is_bool(obj: object) -> TypeGuard[bool | np.bool_]: ...
+def is_integer(obj: object) -> TypeGuard[int | np.integer]: ...
+def is_int_or_none(obj) -> bool: ...
+def is_float(obj: object) -> TypeGuard[float]: ...
+def is_interval_array(values: np.ndarray) -> bool: ...
+def is_datetime64_array(values: np.ndarray, skipna: bool = True) -> bool: ...
+def is_timedelta_or_timedelta64_array(
+    values: np.ndarray, skipna: bool = True
+) -> bool: ...
+def is_datetime_with_singletz_array(values: np.ndarray) -> bool: ...
+def is_time_array(values: np.ndarray, skipna: bool = ...): ...
+def is_date_array(values: np.ndarray, skipna: bool = ...): ...
+def is_datetime_array(values: np.ndarray, skipna: bool = ...): ...
+def is_string_array(values: np.ndarray, skipna: bool = ...): ...
+def is_float_array(values: np.ndarray): ...
+def is_integer_array(values: np.ndarray, skipna: bool = ...): ...
+def is_bool_array(values: np.ndarray, skipna: bool = ...): ...
+def fast_multiget(
+    mapping: dict,
+    keys: np.ndarray,  # object[:]
+    default=...,
+) -> np.ndarray: ...
+def fast_unique_multiple_list_gen(gen: Generator, sort: bool = ...) -> list: ...
+def fast_unique_multiple_list(lists: list, sort: bool | None = ...) -> list: ...
+def map_infer(
+    arr: np.ndarray,
+    f: Callable[[Any], Any],
+    convert: bool = ...,
+    ignore_na: bool = ...,
+) -> np.ndarray: ...
+@overload
+def maybe_convert_objects(
+    objects: npt.NDArray[np.object_],
+    *,
+    try_float: bool = ...,
+    safe: bool = ...,
+    convert_numeric: bool = ...,
+    convert_non_numeric: Literal[False] = ...,
+    convert_to_nullable_dtype: Literal[False] = ...,
+    dtype_if_all_nat: DtypeObj | None = ...,
+) -> npt.NDArray[np.object_ | np.number]: ...
+@overload
+def maybe_convert_objects(
+    objects: npt.NDArray[np.object_],
+    *,
+    try_float: bool = ...,
+    safe: bool = ...,
+    convert_numeric: bool = ...,
+    convert_non_numeric: bool = ...,
+    convert_to_nullable_dtype: Literal[True] = ...,
+    dtype_if_all_nat: DtypeObj | None = ...,
+) -> ArrayLike: ...
+@overload
+def maybe_convert_objects(
+    objects: npt.NDArray[np.object_],
+    *,
+    try_float: bool = ...,
+    safe: bool = ...,
+    convert_numeric: bool = ...,
+    convert_non_numeric: bool = ...,
+    convert_to_nullable_dtype: bool = ...,
+    dtype_if_all_nat: DtypeObj | None = ...,
+) -> ArrayLike: ...
+@overload
+def maybe_convert_numeric(
+    values: npt.NDArray[np.object_],
+    na_values: set,
+    convert_empty: bool = ...,
+    coerce_numeric: bool = ...,
+    convert_to_masked_nullable: Literal[False] = ...,
+) -> tuple[np.ndarray, None]: ...
+@overload
+def maybe_convert_numeric(
+    values: npt.NDArray[np.object_],
+    na_values: set,
+    convert_empty: bool = ...,
+    coerce_numeric: bool = ...,
+    *,
+    convert_to_masked_nullable: Literal[True],
+) -> tuple[np.ndarray, np.ndarray]: ...
+
+# TODO: restrict `arr`?
+def ensure_string_array(
+    arr,
+    na_value: object = ...,
+    convert_na_value: bool = ...,
+    copy: bool = ...,
+    skipna: bool = ...,
+) -> npt.NDArray[np.object_]: ...
+def convert_nans_to_NA(
+    arr: npt.NDArray[np.object_],
+) -> npt.NDArray[np.object_]: ...
+def fast_zip(ndarrays: list) -> npt.NDArray[np.object_]: ...
+
+# TODO: can we be more specific about rows?
+def to_object_array_tuples(rows: object) -> ndarray_obj_2d: ...
+def tuples_to_object_array(
+    tuples: npt.NDArray[np.object_],
+) -> ndarray_obj_2d: ...
+
+# TODO: can we be more specific about rows?
+def to_object_array(rows: object, min_width: int = ...) -> ndarray_obj_2d: ...
+def dicts_to_array(dicts: list, columns: list) -> ndarray_obj_2d: ...
+def maybe_booleans_to_slice(
+    mask: npt.NDArray[np.uint8],
+) -> slice | npt.NDArray[np.uint8]: ...
+def maybe_indices_to_slice(
+    indices: npt.NDArray[np.intp],
+    max_len: int,
+) -> slice | npt.NDArray[np.intp]: ...
+def is_all_arraylike(obj: list) -> bool: ...
+
+# -----------------------------------------------------------------
+# Functions which in reality take memoryviews
+
+def memory_usage_of_objects(arr: np.ndarray) -> int: ...  # object[:]  # np.int64
+def map_infer_mask(
+    arr: np.ndarray,
+    f: Callable[[Any], Any],
+    mask: np.ndarray,  # const uint8_t[:]
+    convert: bool = ...,
+    na_value: Any = ...,
+    dtype: np.dtype = ...,
+) -> np.ndarray: ...
+def indices_fast(
+    index: npt.NDArray[np.intp],
+    labels: np.ndarray,  # const int64_t[:]
+    keys: list,
+    sorted_labels: list[npt.NDArray[np.int64]],
+) -> dict[Hashable, npt.NDArray[np.intp]]: ...
+def generate_slices(
+    labels: np.ndarray, ngroups: int  # const intp_t[:]
+) -> tuple[npt.NDArray[np.int64], npt.NDArray[np.int64]]: ...
+def count_level_2d(
+    mask: np.ndarray,  # ndarray[uint8_t, ndim=2, cast=True],
+    labels: np.ndarray,  # const intp_t[:]
+    max_bin: int,
+) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=2]
+def get_level_sorter(
+    codes: np.ndarray,  # const int64_t[:]
+    starts: np.ndarray,  # const intp_t[:]
+) -> np.ndarray: ...  # np.ndarray[np.intp, ndim=1]
+def generate_bins_dt64(
+    values: npt.NDArray[np.int64],
+    binner: np.ndarray,  # const int64_t[:]
+    closed: object = ...,
+    hasnans: bool = ...,
+) -> np.ndarray: ...  # np.ndarray[np.int64, ndim=1]
+def array_equivalent_object(
+    left: npt.NDArray[np.object_],
+    right: npt.NDArray[np.object_],
+) -> bool: ...
+def has_infs(arr: np.ndarray) -> bool: ...  # const floating[:]
+def has_only_ints_or_nan(arr: np.ndarray) -> bool: ...  # const floating[:]
+def get_reverse_indexer(
+    indexer: np.ndarray,  # const intp_t[:]
+    length: int,
+) -> npt.NDArray[np.intp]: ...
+def is_bool_list(obj: list) -> bool: ...
+def dtypes_all_equal(types: list[DtypeObj]) -> bool: ...
+def is_range_indexer(
+    left: np.ndarray, n: int  # np.ndarray[np.int64, ndim=1]
+) -> bool: ...

lib/python3.12/site-packages/pandas/_libs/missing.pyi

@@ -0,0 +1,16 @@
+import numpy as np
+from numpy import typing as npt
+
+class NAType:
+    def __new__(cls, *args, **kwargs): ...
+
+NA: NAType
+
+def is_matching_na(
+    left: object, right: object, nan_matches_none: bool = ...
+) -> bool: ...
+def isposinf_scalar(val: object) -> bool: ...
+def isneginf_scalar(val: object) -> bool: ...
+def checknull(val: object, inf_as_na: bool = ...) -> bool: ...
+def isnaobj(arr: np.ndarray, inf_as_na: bool = ...) -> npt.NDArray[np.bool_]: ...
+def is_numeric_na(values: np.ndarray) -> npt.NDArray[np.bool_]: ...

lib/python3.12/site-packages/pandas/_libs/ops.pyi

@@ -0,0 +1,51 @@
+from typing import (
+    Any,
+    Callable,
+    Iterable,
+    Literal,
+    TypeAlias,
+    overload,
+)
+
+import numpy as np
+
+from pandas._typing import npt
+
+_BinOp: TypeAlias = Callable[[Any, Any], Any]
+_BoolOp: TypeAlias = Callable[[Any, Any], bool]
+
+def scalar_compare(
+    values: np.ndarray,  # object[:]
+    val: object,
+    op: _BoolOp,  # {operator.eq, operator.ne, ...}
+) -> npt.NDArray[np.bool_]: ...
+def vec_compare(
+    left: npt.NDArray[np.object_],
+    right: npt.NDArray[np.object_],
+    op: _BoolOp,  # {operator.eq, operator.ne, ...}
+) -> npt.NDArray[np.bool_]: ...
+def scalar_binop(
+    values: np.ndarray,  # object[:]
+    val: object,
+    op: _BinOp,  # binary operator
+) -> np.ndarray: ...
+def vec_binop(
+    left: np.ndarray,  # object[:]
+    right: np.ndarray,  # object[:]
+    op: _BinOp,  # binary operator
+) -> np.ndarray: ...
+@overload
+def maybe_convert_bool(
+    arr: npt.NDArray[np.object_],
+    true_values: Iterable | None = None,
+    false_values: Iterable | None = None,
+    convert_to_masked_nullable: Literal[False] = ...,
+) -> tuple[np.ndarray, None]: ...
+@overload
+def maybe_convert_bool(
+    arr: npt.NDArray[np.object_],
+    true_values: Iterable = ...,
+    false_values: Iterable = ...,
+    *,
+    convert_to_masked_nullable: Literal[True],
+) -> tuple[np.ndarray, np.ndarray]: ...

lib/python3.12/site-packages/pandas/_libs/ops_dispatch.pyi

@@ -0,0 +1,5 @@
+import numpy as np
+
+def maybe_dispatch_ufunc_to_dunder_op(
+    self, ufunc: np.ufunc, method: str, *inputs, **kwargs
+): ...

lib/python3.12/site-packages/pandas/_libs/parsers.pyi

@@ -0,0 +1,77 @@
+from typing import (
+    Hashable,
+    Literal,
+)
+
+import numpy as np
+
+from pandas._typing import (
+    ArrayLike,
+    Dtype,
+    npt,
+)
+
+STR_NA_VALUES: set[str]
+DEFAULT_BUFFER_HEURISTIC: int
+
+def sanitize_objects(
+    values: npt.NDArray[np.object_],
+    na_values: set,
+) -> int: ...
+
+class TextReader:
+    unnamed_cols: set[str]
+    table_width: int  # int64_t
+    leading_cols: int  # int64_t
+    header: list[list[int]]  # non-negative integers
+    def __init__(
+        self,
+        source,
+        delimiter: bytes | str = ...,  # single-character only
+        header=...,
+        header_start: int = ...,  # int64_t
+        header_end: int = ...,  # uint64_t
+        index_col=...,
+        names=...,
+        tokenize_chunksize: int = ...,  # int64_t
+        delim_whitespace: bool = ...,
+        converters=...,
+        skipinitialspace: bool = ...,
+        escapechar: bytes | str | None = ...,  # single-character only
+        doublequote: bool = ...,
+        quotechar: str | bytes | None = ...,  # at most 1 character
+        quoting: int = ...,
+        lineterminator: bytes | str | None = ...,  # at most 1 character
+        comment=...,
+        decimal: bytes | str = ...,  # single-character only
+        thousands: bytes | str | None = ...,  # single-character only
+        dtype: Dtype | dict[Hashable, Dtype] = ...,
+        usecols=...,
+        error_bad_lines: bool = ...,
+        warn_bad_lines: bool = ...,
+        na_filter: bool = ...,
+        na_values=...,
+        na_fvalues=...,
+        keep_default_na: bool = ...,
+        true_values=...,
+        false_values=...,
+        allow_leading_cols: bool = ...,
+        skiprows=...,
+        skipfooter: int = ...,  # int64_t
+        verbose: bool = ...,
+        float_precision: Literal["round_trip", "legacy", "high"] | None = ...,
+        skip_blank_lines: bool = ...,
+        encoding_errors: bytes | str = ...,
+    ) -> None: ...
+    def set_noconvert(self, i: int) -> None: ...
+    def remove_noconvert(self, i: int) -> None: ...
+    def close(self) -> None: ...
+    def read(self, rows: int | None = ...) -> dict[int, ArrayLike]: ...
+    def read_low_memory(self, rows: int | None) -> list[dict[int, ArrayLike]]: ...
+
+# _maybe_upcast, na_values are only exposed for testing
+na_values: dict
+
+def _maybe_upcast(
+    arr, use_dtype_backend: bool = ..., dtype_backend: str = ...
+) -> np.ndarray: ...

lib/python3.12/site-packages/pandas/_libs/properties.pyi

@@ -0,0 +1,27 @@
+from typing import (
+    Sequence,
+    overload,
+)
+
+from pandas._typing import (
+    AnyArrayLike,
+    DataFrame,
+    Index,
+    Series,
+)
+
+# note: this is a lie to make type checkers happy (they special
+# case property). cache_readonly uses attribute names similar to
+# property (fget) but it does not provide fset and fdel.
+cache_readonly = property
+
+class AxisProperty:
+    axis: int
+    def __init__(self, axis: int = ..., doc: str = ...) -> None: ...
+    @overload
+    def __get__(self, obj: DataFrame | Series, type) -> Index: ...
+    @overload
+    def __get__(self, obj: None, type) -> AxisProperty: ...
+    def __set__(
+        self, obj: DataFrame | Series, value: AnyArrayLike | Sequence
+    ) -> None: ...

lib/python3.12/site-packages/pandas/_libs/reshape.pyi

@@ -0,0 +1,16 @@
+import numpy as np
+
+from pandas._typing import npt
+
+def unstack(
+    values: np.ndarray,  # reshape_t[:, :]
+    mask: np.ndarray,  # const uint8_t[:]
+    stride: int,
+    length: int,
+    width: int,
+    new_values: np.ndarray,  # reshape_t[:, :]
+    new_mask: np.ndarray,  # uint8_t[:, :]
+) -> None: ...
+def explode(
+    values: npt.NDArray[np.object_],
+) -> tuple[npt.NDArray[np.object_], npt.NDArray[np.int64]]: ...

lib/python3.12/site-packages/pandas/_libs/sas.pyi

@@ -0,0 +1,7 @@
+from pandas.io.sas.sas7bdat import SAS7BDATReader
+
+class Parser:
+    def __init__(self, parser: SAS7BDATReader) -> None: ...
+    def read(self, nrows: int) -> None: ...
+
+def get_subheader_index(signature: bytes) -> int: ...

lib/python3.12/site-packages/pandas/_libs/sparse.pyi

@@ -0,0 +1,51 @@
+from typing import Sequence
+
+import numpy as np
+
+from pandas._typing import (
+    Self,
+    npt,
+)
+
+class SparseIndex:
+    length: int
+    npoints: int
+    def __init__(self) -> None: ...
+    @property
+    def ngaps(self) -> int: ...
+    @property
+    def nbytes(self) -> int: ...
+    @property
+    def indices(self) -> npt.NDArray[np.int32]: ...
+    def equals(self, other) -> bool: ...
+    def lookup(self, index: int) -> np.int32: ...
+    def lookup_array(self, indexer: npt.NDArray[np.int32]) -> npt.NDArray[np.int32]: ...
+    def to_int_index(self) -> IntIndex: ...
+    def to_block_index(self) -> BlockIndex: ...
+    def intersect(self, y_: SparseIndex) -> Self: ...
+    def make_union(self, y_: SparseIndex) -> Self: ...
+
+class IntIndex(SparseIndex):
+    indices: npt.NDArray[np.int32]
+    def __init__(
+        self, length: int, indices: Sequence[int], check_integrity: bool = ...
+    ) -> None: ...
+
+class BlockIndex(SparseIndex):
+    nblocks: int
+    blocs: np.ndarray
+    blengths: np.ndarray
+    def __init__(
+        self, length: int, blocs: np.ndarray, blengths: np.ndarray
+    ) -> None: ...
+
+    # Override to have correct parameters
+    def intersect(self, other: SparseIndex) -> Self: ...
+    def make_union(self, y: SparseIndex) -> Self: ...
+
+def make_mask_object_ndarray(
+    arr: npt.NDArray[np.object_], fill_value
+) -> npt.NDArray[np.bool_]: ...
+def get_blocks(
+    indices: npt.NDArray[np.int32],
+) -> tuple[npt.NDArray[np.int32], npt.NDArray[np.int32]]: ...

lib/python3.12/site-packages/pandas/_libs/testing.pyi

@@ -0,0 +1,12 @@
+def assert_dict_equal(a, b, compare_keys: bool = ...): ...
+def assert_almost_equal(
+    a,
+    b,
+    rtol: float = ...,
+    atol: float = ...,
+    check_dtype: bool = ...,
+    obj=...,
+    lobj=...,
+    robj=...,
+    index_values=...,
+): ...

lib/python3.12/site-packages/pandas/_libs/tslib.pyi

@@ -0,0 +1,37 @@
+from datetime import tzinfo
+
+import numpy as np
+
+from pandas._typing import npt
+
+def format_array_from_datetime(
+    values: npt.NDArray[np.int64],
+    tz: tzinfo | None = ...,
+    format: str | None = ...,
+    na_rep: str | float = ...,
+    reso: int = ...,  # NPY_DATETIMEUNIT
+) -> npt.NDArray[np.object_]: ...
+def array_with_unit_to_datetime(
+    values: npt.NDArray[np.object_],
+    unit: str,
+    errors: str = ...,
+) -> tuple[np.ndarray, tzinfo | None]: ...
+def first_non_null(values: np.ndarray) -> int: ...
+def array_to_datetime(
+    values: npt.NDArray[np.object_],
+    errors: str = ...,
+    dayfirst: bool = ...,
+    yearfirst: bool = ...,
+    utc: bool = ...,
+    creso: int = ...,
+) -> tuple[np.ndarray, tzinfo | None]: ...
+
+# returned ndarray may be object dtype or datetime64[ns]
+
+def array_to_datetime_with_tz(
+    values: npt.NDArray[np.object_],
+    tz: tzinfo,
+    dayfirst: bool,
+    yearfirst: bool,
+    creso: int,
+) -> npt.NDArray[np.int64]: ...

lib/python3.12/site-packages/pandas/_libs/writers.pyi

@@ -0,0 +1,20 @@
+import numpy as np
+
+from pandas._typing import ArrayLike
+
+def write_csv_rows(
+    data: list[ArrayLike],
+    data_index: np.ndarray,
+    nlevels: int,
+    cols: np.ndarray,
+    writer: object,  # _csv.writer
+) -> None: ...
+def convert_json_to_lines(arr: str) -> str: ...
+def max_len_string_array(
+    arr: np.ndarray,  # pandas_string[:]
+) -> int: ...
+def word_len(val: object) -> int: ...
+def string_array_replace_from_nan_rep(
+    arr: np.ndarray,  # np.ndarray[object, ndim=1]
+    nan_rep: object,
+) -> None: ...

lib/python3.12/site-packages/pandas/core/accessor.py

@@ -0,0 +1,340 @@
+"""
+
+accessor.py contains base classes for implementing accessor properties
+that can be mixed into or pinned onto other pandas classes.
+
+"""
+from __future__ import annotations
+
+from typing import (
+    Callable,
+    final,
+)
+import warnings
+
+from pandas.util._decorators import doc
+from pandas.util._exceptions import find_stack_level
+
+
+class DirNamesMixin:
+    _accessors: set[str] = set()
+    _hidden_attrs: frozenset[str] = frozenset()
+
+    @final
+    def _dir_deletions(self) -> set[str]:
+        """
+        Delete unwanted __dir__ for this object.
+        """
+        return self._accessors | self._hidden_attrs
+
+    def _dir_additions(self) -> set[str]:
+        """
+        Add additional __dir__ for this object.
+        """
+        return {accessor for accessor in self._accessors if hasattr(self, accessor)}
+
+    def __dir__(self) -> list[str]:
+        """
+        Provide method name lookup and completion.
+
+        Notes
+        -----
+        Only provide 'public' methods.
+        """
+        rv = set(super().__dir__())
+        rv = (rv - self._dir_deletions()) | self._dir_additions()
+        return sorted(rv)
+
+
+class PandasDelegate:
+    """
+    Abstract base class for delegating methods/properties.
+    """
+
+    def _delegate_property_get(self, name: str, *args, **kwargs):
+        raise TypeError(f"You cannot access the property {name}")
+
+    def _delegate_property_set(self, name: str, value, *args, **kwargs):
+        raise TypeError(f"The property {name} cannot be set")
+
+    def _delegate_method(self, name: str, *args, **kwargs):
+        raise TypeError(f"You cannot call method {name}")
+
+    @classmethod
+    def _add_delegate_accessors(
+        cls,
+        delegate,
+        accessors: list[str],
+        typ: str,
+        overwrite: bool = False,
+        accessor_mapping: Callable[[str], str] = lambda x: x,
+        raise_on_missing: bool = True,
+    ) -> None:
+        """
+        Add accessors to cls from the delegate class.
+
+        Parameters
+        ----------
+        cls
+            Class to add the methods/properties to.
+        delegate
+            Class to get methods/properties and doc-strings.
+        accessors : list of str
+            List of accessors to add.
+        typ : {'property', 'method'}
+        overwrite : bool, default False
+            Overwrite the method/property in the target class if it exists.
+        accessor_mapping: Callable, default lambda x: x
+            Callable to map the delegate's function to the cls' function.
+        raise_on_missing: bool, default True
+            Raise if an accessor does not exist on delegate.
+            False skips the missing accessor.
+        """
+
+        def _create_delegator_property(name: str):
+            def _getter(self):
+                return self._delegate_property_get(name)
+
+            def _setter(self, new_values):
+                return self._delegate_property_set(name, new_values)
+
+            _getter.__name__ = name
+            _setter.__name__ = name
+
+            return property(
+                fget=_getter,
+                fset=_setter,
+                doc=getattr(delegate, accessor_mapping(name)).__doc__,
+            )
+
+        def _create_delegator_method(name: str):
+            def f(self, *args, **kwargs):
+                return self._delegate_method(name, *args, **kwargs)
+
+            f.__name__ = name
+            f.__doc__ = getattr(delegate, accessor_mapping(name)).__doc__
+
+            return f
+
+        for name in accessors:
+            if (
+                not raise_on_missing
+                and getattr(delegate, accessor_mapping(name), None) is None
+            ):
+                continue
+
+            if typ == "property":
+                f = _create_delegator_property(name)
+            else:
+                f = _create_delegator_method(name)
+
+            # don't overwrite existing methods/properties
+            if overwrite or not hasattr(cls, name):
+                setattr(cls, name, f)
+
+
+def delegate_names(
+    delegate,
+    accessors: list[str],
+    typ: str,
+    overwrite: bool = False,
+    accessor_mapping: Callable[[str], str] = lambda x: x,
+    raise_on_missing: bool = True,
+):
+    """
+    Add delegated names to a class using a class decorator.  This provides
+    an alternative usage to directly calling `_add_delegate_accessors`
+    below a class definition.
+
+    Parameters
+    ----------
+    delegate : object
+        The class to get methods/properties & doc-strings.
+    accessors : Sequence[str]
+        List of accessor to add.
+    typ : {'property', 'method'}
+    overwrite : bool, default False
+       Overwrite the method/property in the target class if it exists.
+    accessor_mapping: Callable, default lambda x: x
+        Callable to map the delegate's function to the cls' function.
+    raise_on_missing: bool, default True
+        Raise if an accessor does not exist on delegate.
+        False skips the missing accessor.
+
+    Returns
+    -------
+    callable
+        A class decorator.
+
+    Examples
+    --------
+    @delegate_names(Categorical, ["categories", "ordered"], "property")
+    class CategoricalAccessor(PandasDelegate):
+        [...]
+    """
+
+    def add_delegate_accessors(cls):
+        cls._add_delegate_accessors(
+            delegate,
+            accessors,
+            typ,
+            overwrite=overwrite,
+            accessor_mapping=accessor_mapping,
+            raise_on_missing=raise_on_missing,
+        )
+        return cls
+
+    return add_delegate_accessors
+
+
+# Ported with modifications from xarray; licence at LICENSES/XARRAY_LICENSE
+# https://github.com/pydata/xarray/blob/master/xarray/core/extensions.py
+# 1. We don't need to catch and re-raise AttributeErrors as RuntimeErrors
+# 2. We use a UserWarning instead of a custom Warning
+
+
+class CachedAccessor:
+    """
+    Custom property-like object.
+
+    A descriptor for caching accessors.
+
+    Parameters
+    ----------
+    name : str
+        Namespace that will be accessed under, e.g. ``df.foo``.
+    accessor : cls
+        Class with the extension methods.
+
+    Notes
+    -----
+    For accessor, The class's __init__ method assumes that one of
+    ``Series``, ``DataFrame`` or ``Index`` as the
+    single argument ``data``.
+    """
+
+    def __init__(self, name: str, accessor) -> None:
+        self._name = name
+        self._accessor = accessor
+
+    def __get__(self, obj, cls):
+        if obj is None:
+            # we're accessing the attribute of the class, i.e., Dataset.geo
+            return self._accessor
+        accessor_obj = self._accessor(obj)
+        # Replace the property with the accessor object. Inspired by:
+        # https://www.pydanny.com/cached-property.html
+        # We need to use object.__setattr__ because we overwrite __setattr__ on
+        # NDFrame
+        object.__setattr__(obj, self._name, accessor_obj)
+        return accessor_obj
+
+
+@doc(klass="", others="")
+def _register_accessor(name: str, cls):
+    """
+    Register a custom accessor on {klass} objects.
+
+    Parameters
+    ----------
+    name : str
+        Name under which the accessor should be registered. A warning is issued
+        if this name conflicts with a preexisting attribute.
+
+    Returns
+    -------
+    callable
+        A class decorator.
+
+    See Also
+    --------
+    register_dataframe_accessor : Register a custom accessor on DataFrame objects.
+    register_series_accessor : Register a custom accessor on Series objects.
+    register_index_accessor : Register a custom accessor on Index objects.
+
+    Notes
+    -----
+    When accessed, your accessor will be initialized with the pandas object
+    the user is interacting with. So the signature must be
+
+    .. code-block:: python
+
+        def __init__(self, pandas_object):  # noqa: E999
+            ...
+
+    For consistency with pandas methods, you should raise an ``AttributeError``
+    if the data passed to your accessor has an incorrect dtype.
+
+    >>> pd.Series(['a', 'b']).dt
+    Traceback (most recent call last):
+    ...
+    AttributeError: Can only use .dt accessor with datetimelike values
+
+    Examples
+    --------
+    In your library code::
+
+        import pandas as pd
+
+        @pd.api.extensions.register_dataframe_accessor("geo")
+        class GeoAccessor:
+            def __init__(self, pandas_obj):
+                self._obj = pandas_obj
+
+            @property
+            def center(self):
+                # return the geographic center point of this DataFrame
+                lat = self._obj.latitude
+                lon = self._obj.longitude
+                return (float(lon.mean()), float(lat.mean()))
+
+            def plot(self):
+                # plot this array's data on a map, e.g., using Cartopy
+                pass
+
+    Back in an interactive IPython session:
+
+        .. code-block:: ipython
+
+            In [1]: ds = pd.DataFrame({{"longitude": np.linspace(0, 10),
+               ...:                    "latitude": np.linspace(0, 20)}})
+            In [2]: ds.geo.center
+            Out[2]: (5.0, 10.0)
+            In [3]: ds.geo.plot()  # plots data on a map
+    """
+
+    def decorator(accessor):
+        if hasattr(cls, name):
+            warnings.warn(
+                f"registration of accessor {repr(accessor)} under name "
+                f"{repr(name)} for type {repr(cls)} is overriding a preexisting "
+                f"attribute with the same name.",
+                UserWarning,
+                stacklevel=find_stack_level(),
+            )
+        setattr(cls, name, CachedAccessor(name, accessor))
+        cls._accessors.add(name)
+        return accessor
+
+    return decorator
+
+
+@doc(_register_accessor, klass="DataFrame")
+def register_dataframe_accessor(name: str):
+    from pandas import DataFrame
+
+    return _register_accessor(name, DataFrame)
+
+
+@doc(_register_accessor, klass="Series")
+def register_series_accessor(name: str):
+    from pandas import Series
+
+    return _register_accessor(name, Series)
+
+
+@doc(_register_accessor, klass="Index")
+def register_index_accessor(name: str):
+    from pandas import Index
+
+    return _register_accessor(name, Index)

lib/python3.12/site-packages/pandas/core/algorithms.py

@@ -0,0 +1,1747 @@
+"""
+Generic data algorithms. This module is experimental at the moment and not
+intended for public consumption
+"""
+from __future__ import annotations
+
+import decimal
+import operator
+from textwrap import dedent
+from typing import (
+    TYPE_CHECKING,
+    Literal,
+    cast,
+)
+import warnings
+
+import numpy as np
+
+from pandas._libs import (
+    algos,
+    hashtable as htable,
+    iNaT,
+    lib,
+)
+from pandas._typing import (
+    AnyArrayLike,
+    ArrayLike,
+    AxisInt,
+    DtypeObj,
+    TakeIndexer,
+    npt,
+)
+from pandas.util._decorators import doc
+from pandas.util._exceptions import find_stack_level
+
+from pandas.core.dtypes.cast import (
+    construct_1d_object_array_from_listlike,
+    np_find_common_type,
+)
+from pandas.core.dtypes.common import (
+    ensure_float64,
+    ensure_object,
+    ensure_platform_int,
+    is_array_like,
+    is_bool_dtype,
+    is_complex_dtype,
+    is_dict_like,
+    is_extension_array_dtype,
+    is_float_dtype,
+    is_integer,
+    is_integer_dtype,
+    is_list_like,
+    is_object_dtype,
+    is_signed_integer_dtype,
+    needs_i8_conversion,
+)
+from pandas.core.dtypes.concat import concat_compat
+from pandas.core.dtypes.dtypes import (
+    BaseMaskedDtype,
+    CategoricalDtype,
+    ExtensionDtype,
+    NumpyEADtype,
+)
+from pandas.core.dtypes.generic import (
+    ABCDatetimeArray,
+    ABCExtensionArray,
+    ABCIndex,
+    ABCMultiIndex,
+    ABCSeries,
+    ABCTimedeltaArray,
+)
+from pandas.core.dtypes.missing import (
+    isna,
+    na_value_for_dtype,
+)
+
+from pandas.core.array_algos.take import take_nd
+from pandas.core.construction import (
+    array as pd_array,
+    ensure_wrapped_if_datetimelike,
+    extract_array,
+)
+from pandas.core.indexers import validate_indices
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ListLike,
+        NumpySorter,
+        NumpyValueArrayLike,
+    )
+
+    from pandas import (
+        Categorical,
+        Index,
+        Series,
+    )
+    from pandas.core.arrays import (
+        BaseMaskedArray,
+        ExtensionArray,
+    )
+
+
+# --------------- #
+# dtype access    #
+# --------------- #
+def _ensure_data(values: ArrayLike) -> np.ndarray:
+    """
+    routine to ensure that our data is of the correct
+    input dtype for lower-level routines
+
+    This will coerce:
+    - ints -> int64
+    - uint -> uint64
+    - bool -> uint8
+    - datetimelike -> i8
+    - datetime64tz -> i8 (in local tz)
+    - categorical -> codes
+
+    Parameters
+    ----------
+    values : np.ndarray or ExtensionArray
+
+    Returns
+    -------
+    np.ndarray
+    """
+
+    if not isinstance(values, ABCMultiIndex):
+        # extract_array would raise
+        values = extract_array(values, extract_numpy=True)
+
+    if is_object_dtype(values.dtype):
+        return ensure_object(np.asarray(values))
+
+    elif isinstance(values.dtype, BaseMaskedDtype):
+        # i.e. BooleanArray, FloatingArray, IntegerArray
+        values = cast("BaseMaskedArray", values)
+        if not values._hasna:
+            # No pd.NAs -> We can avoid an object-dtype cast (and copy) GH#41816
+            #  recurse to avoid re-implementing logic for eg bool->uint8
+            return _ensure_data(values._data)
+        return np.asarray(values)
+
+    elif isinstance(values.dtype, CategoricalDtype):
+        # NB: cases that go through here should NOT be using _reconstruct_data
+        #  on the back-end.
+        values = cast("Categorical", values)
+        return values.codes
+
+    elif is_bool_dtype(values.dtype):
+        if isinstance(values, np.ndarray):
+            # i.e. actually dtype == np.dtype("bool")
+            return np.asarray(values).view("uint8")
+        else:
+            # e.g. Sparse[bool, False]  # TODO: no test cases get here
+            return np.asarray(values).astype("uint8", copy=False)
+
+    elif is_integer_dtype(values.dtype):
+        return np.asarray(values)
+
+    elif is_float_dtype(values.dtype):
+        # Note: checking `values.dtype == "float128"` raises on Windows and 32bit
+        # error: Item "ExtensionDtype" of "Union[Any, ExtensionDtype, dtype[Any]]"
+        # has no attribute "itemsize"
+        if values.dtype.itemsize in [2, 12, 16]:  # type: ignore[union-attr]
+            # we dont (yet) have float128 hashtable support
+            return ensure_float64(values)
+        return np.asarray(values)
+
+    elif is_complex_dtype(values.dtype):
+        return cast(np.ndarray, values)
+
+    # datetimelike
+    elif needs_i8_conversion(values.dtype):
+        npvalues = values.view("i8")
+        npvalues = cast(np.ndarray, npvalues)
+        return npvalues
+
+    # we have failed, return object
+    values = np.asarray(values, dtype=object)
+    return ensure_object(values)
+
+
+def _reconstruct_data(
+    values: ArrayLike, dtype: DtypeObj, original: AnyArrayLike
+) -> ArrayLike:
+    """
+    reverse of _ensure_data
+
+    Parameters
+    ----------
+    values : np.ndarray or ExtensionArray
+    dtype : np.dtype or ExtensionDtype
+    original : AnyArrayLike
+
+    Returns
+    -------
+    ExtensionArray or np.ndarray
+    """
+    if isinstance(values, ABCExtensionArray) and values.dtype == dtype:
+        # Catch DatetimeArray/TimedeltaArray
+        return values
+
+    if not isinstance(dtype, np.dtype):
+        # i.e. ExtensionDtype; note we have ruled out above the possibility
+        #  that values.dtype == dtype
+        cls = dtype.construct_array_type()
+
+        values = cls._from_sequence(values, dtype=dtype)
+
+    else:
+        values = values.astype(dtype, copy=False)
+
+    return values
+
+
+def _ensure_arraylike(values, func_name: str) -> ArrayLike:
+    """
+    ensure that we are arraylike if not already
+    """
+    if not isinstance(values, (ABCIndex, ABCSeries, ABCExtensionArray, np.ndarray)):
+        # GH#52986
+        if func_name != "isin-targets":
+            # Make an exception for the comps argument in isin.
+            warnings.warn(
+                f"{func_name} with argument that is not not a Series, Index, "
+                "ExtensionArray, or np.ndarray is deprecated and will raise in a "
+                "future version.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+
+        inferred = lib.infer_dtype(values, skipna=False)
+        if inferred in ["mixed", "string", "mixed-integer"]:
+            # "mixed-integer" to ensure we do not cast ["ss", 42] to str GH#22160
+            if isinstance(values, tuple):
+                values = list(values)
+            values = construct_1d_object_array_from_listlike(values)
+        else:
+            values = np.asarray(values)
+    return values
+
+
+_hashtables = {
+    "complex128": htable.Complex128HashTable,
+    "complex64": htable.Complex64HashTable,
+    "float64": htable.Float64HashTable,
+    "float32": htable.Float32HashTable,
+    "uint64": htable.UInt64HashTable,
+    "uint32": htable.UInt32HashTable,
+    "uint16": htable.UInt16HashTable,
+    "uint8": htable.UInt8HashTable,
+    "int64": htable.Int64HashTable,
+    "int32": htable.Int32HashTable,
+    "int16": htable.Int16HashTable,
+    "int8": htable.Int8HashTable,
+    "string": htable.StringHashTable,
+    "object": htable.PyObjectHashTable,
+}
+
+
+def _get_hashtable_algo(values: np.ndarray):
+    """
+    Parameters
+    ----------
+    values : np.ndarray
+
+    Returns
+    -------
+    htable : HashTable subclass
+    values : ndarray
+    """
+    values = _ensure_data(values)
+
+    ndtype = _check_object_for_strings(values)
+    hashtable = _hashtables[ndtype]
+    return hashtable, values
+
+
+def _check_object_for_strings(values: np.ndarray) -> str:
+    """
+    Check if we can use string hashtable instead of object hashtable.
+
+    Parameters
+    ----------
+    values : ndarray
+
+    Returns
+    -------
+    str
+    """
+    ndtype = values.dtype.name
+    if ndtype == "object":
+        # it's cheaper to use a String Hash Table than Object; we infer
+        # including nulls because that is the only difference between
+        # StringHashTable and ObjectHashtable
+        if lib.is_string_array(values, skipna=False):
+            ndtype = "string"
+    return ndtype
+
+
+# --------------- #
+# top-level algos #
+# --------------- #
+
+
+def unique(values):
+    """
+    Return unique values based on a hash table.
+
+    Uniques are returned in order of appearance. This does NOT sort.
+
+    Significantly faster than numpy.unique for long enough sequences.
+    Includes NA values.
+
+    Parameters
+    ----------
+    values : 1d array-like
+
+    Returns
+    -------
+    numpy.ndarray or ExtensionArray
+
+        The return can be:
+
+        * Index : when the input is an Index
+        * Categorical : when the input is a Categorical dtype
+        * ndarray : when the input is a Series/ndarray
+
+        Return numpy.ndarray or ExtensionArray.
+
+    See Also
+    --------
+    Index.unique : Return unique values from an Index.
+    Series.unique : Return unique values of Series object.
+
+    Examples
+    --------
+    >>> pd.unique(pd.Series([2, 1, 3, 3]))
+    array([2, 1, 3])
+
+    >>> pd.unique(pd.Series([2] + [1] * 5))
+    array([2, 1])
+
+    >>> pd.unique(pd.Series([pd.Timestamp("20160101"), pd.Timestamp("20160101")]))
+    array(['2016-01-01T00:00:00.000000000'], dtype='datetime64[ns]')
+
+    >>> pd.unique(
+    ...     pd.Series(
+    ...         [
+    ...             pd.Timestamp("20160101", tz="US/Eastern"),
+    ...             pd.Timestamp("20160101", tz="US/Eastern"),
+    ...         ]
+    ...     )
+    ... )
+    <DatetimeArray>
+    ['2016-01-01 00:00:00-05:00']
+    Length: 1, dtype: datetime64[ns, US/Eastern]
+
+    >>> pd.unique(
+    ...     pd.Index(
+    ...         [
+    ...             pd.Timestamp("20160101", tz="US/Eastern"),
+    ...             pd.Timestamp("20160101", tz="US/Eastern"),
+    ...         ]
+    ...     )
+    ... )
+    DatetimeIndex(['2016-01-01 00:00:00-05:00'],
+            dtype='datetime64[ns, US/Eastern]',
+            freq=None)
+
+    >>> pd.unique(np.array(list("baabc"), dtype="O"))
+    array(['b', 'a', 'c'], dtype=object)
+
+    An unordered Categorical will return categories in the
+    order of appearance.
+
+    >>> pd.unique(pd.Series(pd.Categorical(list("baabc"))))
+    ['b', 'a', 'c']
+    Categories (3, object): ['a', 'b', 'c']
+
+    >>> pd.unique(pd.Series(pd.Categorical(list("baabc"), categories=list("abc"))))
+    ['b', 'a', 'c']
+    Categories (3, object): ['a', 'b', 'c']
+
+    An ordered Categorical preserves the category ordering.
+
+    >>> pd.unique(
+    ...     pd.Series(
+    ...         pd.Categorical(list("baabc"), categories=list("abc"), ordered=True)
+    ...     )
+    ... )
+    ['b', 'a', 'c']
+    Categories (3, object): ['a' < 'b' < 'c']
+
+    An array of tuples
+
+    >>> pd.unique(pd.Series([("a", "b"), ("b", "a"), ("a", "c"), ("b", "a")]).values)
+    array([('a', 'b'), ('b', 'a'), ('a', 'c')], dtype=object)
+    """
+    return unique_with_mask(values)
+
+
+def nunique_ints(values: ArrayLike) -> int:
+    """
+    Return the number of unique values for integer array-likes.
+
+    Significantly faster than pandas.unique for long enough sequences.
+    No checks are done to ensure input is integral.
+
+    Parameters
+    ----------
+    values : 1d array-like
+
+    Returns
+    -------
+    int : The number of unique values in ``values``
+    """
+    if len(values) == 0:
+        return 0
+    values = _ensure_data(values)
+    # bincount requires intp
+    result = (np.bincount(values.ravel().astype("intp")) != 0).sum()
+    return result
+
+
+def unique_with_mask(values, mask: npt.NDArray[np.bool_] | None = None):
+    """See algorithms.unique for docs. Takes a mask for masked arrays."""
+    values = _ensure_arraylike(values, func_name="unique")
+
+    if isinstance(values.dtype, ExtensionDtype):
+        # Dispatch to extension dtype's unique.
+        return values.unique()
+
+    original = values
+    hashtable, values = _get_hashtable_algo(values)
+
+    table = hashtable(len(values))
+    if mask is None:
+        uniques = table.unique(values)
+        uniques = _reconstruct_data(uniques, original.dtype, original)
+        return uniques
+
+    else:
+        uniques, mask = table.unique(values, mask=mask)
+        uniques = _reconstruct_data(uniques, original.dtype, original)
+        assert mask is not None  # for mypy
+        return uniques, mask.astype("bool")
+
+
+unique1d = unique
+
+
+_MINIMUM_COMP_ARR_LEN = 1_000_000
+
+
+def isin(comps: ListLike, values: ListLike) -> npt.NDArray[np.bool_]:
+    """
+    Compute the isin boolean array.
+
+    Parameters
+    ----------
+    comps : list-like
+    values : list-like
+
+    Returns
+    -------
+    ndarray[bool]
+        Same length as `comps`.
+    """
+    if not is_list_like(comps):
+        raise TypeError(
+            "only list-like objects are allowed to be passed "
+            f"to isin(), you passed a `{type(comps).__name__}`"
+        )
+    if not is_list_like(values):
+        raise TypeError(
+            "only list-like objects are allowed to be passed "
+            f"to isin(), you passed a `{type(values).__name__}`"
+        )
+
+    if not isinstance(values, (ABCIndex, ABCSeries, ABCExtensionArray, np.ndarray)):
+        orig_values = list(values)
+        values = _ensure_arraylike(orig_values, func_name="isin-targets")
+
+        if (
+            len(values) > 0
+            and values.dtype.kind in "iufcb"
+            and not is_signed_integer_dtype(comps)
+        ):
+            # GH#46485 Use object to avoid upcast to float64 later
+            # TODO: Share with _find_common_type_compat
+            values = construct_1d_object_array_from_listlike(orig_values)
+
+    elif isinstance(values, ABCMultiIndex):
+        # Avoid raising in extract_array
+        values = np.array(values)
+    else:
+        values = extract_array(values, extract_numpy=True, extract_range=True)
+
+    comps_array = _ensure_arraylike(comps, func_name="isin")
+    comps_array = extract_array(comps_array, extract_numpy=True)
+    if not isinstance(comps_array, np.ndarray):
+        # i.e. Extension Array
+        return comps_array.isin(values)
+
+    elif needs_i8_conversion(comps_array.dtype):
+        # Dispatch to DatetimeLikeArrayMixin.isin
+        return pd_array(comps_array).isin(values)
+    elif needs_i8_conversion(values.dtype) and not is_object_dtype(comps_array.dtype):
+        # e.g. comps_array are integers and values are datetime64s
+        return np.zeros(comps_array.shape, dtype=bool)
+        # TODO: not quite right ... Sparse/Categorical
+    elif needs_i8_conversion(values.dtype):
+        return isin(comps_array, values.astype(object))
+
+    elif isinstance(values.dtype, ExtensionDtype):
+        return isin(np.asarray(comps_array), np.asarray(values))
+
+    # GH16012
+    # Ensure np.isin doesn't get object types or it *may* throw an exception
+    # Albeit hashmap has O(1) look-up (vs. O(logn) in sorted array),
+    # isin is faster for small sizes
+    if (
+        len(comps_array) > _MINIMUM_COMP_ARR_LEN
+        and len(values) <= 26
+        and comps_array.dtype != object
+    ):
+        # If the values include nan we need to check for nan explicitly
+        # since np.nan it not equal to np.nan
+        if isna(values).any():
+
+            def f(c, v):
+                return np.logical_or(np.isin(c, v).ravel(), np.isnan(c))
+
+        else:
+            f = lambda a, b: np.isin(a, b).ravel()
+
+    else:
+        common = np_find_common_type(values.dtype, comps_array.dtype)
+        values = values.astype(common, copy=False)
+        comps_array = comps_array.astype(common, copy=False)
+        f = htable.ismember
+
+    return f(comps_array, values)
+
+
+def factorize_array(
+    values: np.ndarray,
+    use_na_sentinel: bool = True,
+    size_hint: int | None = None,
+    na_value: object = None,
+    mask: npt.NDArray[np.bool_] | None = None,
+) -> tuple[npt.NDArray[np.intp], np.ndarray]:
+    """
+    Factorize a numpy array to codes and uniques.
+
+    This doesn't do any coercion of types or unboxing before factorization.
+
+    Parameters
+    ----------
+    values : ndarray
+    use_na_sentinel : bool, default True
+        If True, the sentinel -1 will be used for NaN values. If False,
+        NaN values will be encoded as non-negative integers and will not drop the
+        NaN from the uniques of the values.
+    size_hint : int, optional
+        Passed through to the hashtable's 'get_labels' method
+    na_value : object, optional
+        A value in `values` to consider missing. Note: only use this
+        parameter when you know that you don't have any values pandas would
+        consider missing in the array (NaN for float data, iNaT for
+        datetimes, etc.).
+    mask : ndarray[bool], optional
+        If not None, the mask is used as indicator for missing values
+        (True = missing, False = valid) instead of `na_value` or
+        condition "val != val".
+
+    Returns
+    -------
+    codes : ndarray[np.intp]
+    uniques : ndarray
+    """
+    original = values
+    if values.dtype.kind in "mM":
+        # _get_hashtable_algo will cast dt64/td64 to i8 via _ensure_data, so we
+        #  need to do the same to na_value. We are assuming here that the passed
+        #  na_value is an appropriately-typed NaT.
+        # e.g. test_where_datetimelike_categorical
+        na_value = iNaT
+
+    hash_klass, values = _get_hashtable_algo(values)
+
+    table = hash_klass(size_hint or len(values))
+    uniques, codes = table.factorize(
+        values,
+        na_sentinel=-1,
+        na_value=na_value,
+        mask=mask,
+        ignore_na=use_na_sentinel,
+    )
+
+    # re-cast e.g. i8->dt64/td64, uint8->bool
+    uniques = _reconstruct_data(uniques, original.dtype, original)
+
+    codes = ensure_platform_int(codes)
+    return codes, uniques
+
+
+@doc(
+    values=dedent(
+        """\
+    values : sequence
+        A 1-D sequence. Sequences that aren't pandas objects are
+        coerced to ndarrays before factorization.
+    """
+    ),
+    sort=dedent(
+        """\
+    sort : bool, default False
+        Sort `uniques` and shuffle `codes` to maintain the
+        relationship.
+    """
+    ),
+    size_hint=dedent(
+        """\
+    size_hint : int, optional
+        Hint to the hashtable sizer.
+    """
+    ),
+)
+def factorize(
+    values,
+    sort: bool = False,
+    use_na_sentinel: bool = True,
+    size_hint: int | None = None,
+) -> tuple[np.ndarray, np.ndarray | Index]:
+    """
+    Encode the object as an enumerated type or categorical variable.
+
+    This method is useful for obtaining a numeric representation of an
+    array when all that matters is identifying distinct values. `factorize`
+    is available as both a top-level function :func:`pandas.factorize`,
+    and as a method :meth:`Series.factorize` and :meth:`Index.factorize`.
+
+    Parameters
+    ----------
+    {values}{sort}
+    use_na_sentinel : bool, default True
+        If True, the sentinel -1 will be used for NaN values. If False,
+        NaN values will be encoded as non-negative integers and will not drop the
+        NaN from the uniques of the values.
+
+        .. versionadded:: 1.5.0
+    {size_hint}\
+
+    Returns
+    -------
+    codes : ndarray
+        An integer ndarray that's an indexer into `uniques`.
+        ``uniques.take(codes)`` will have the same values as `values`.
+    uniques : ndarray, Index, or Categorical
+        The unique valid values. When `values` is Categorical, `uniques`
+        is a Categorical. When `values` is some other pandas object, an
+        `Index` is returned. Otherwise, a 1-D ndarray is returned.
+
+        .. note::
+
+           Even if there's a missing value in `values`, `uniques` will
+           *not* contain an entry for it.
+
+    See Also
+    --------
+    cut : Discretize continuous-valued array.
+    unique : Find the unique value in an array.
+
+    Notes
+    -----
+    Reference :ref:`the user guide <reshaping.factorize>` for more examples.
+
+    Examples
+    --------
+    These examples all show factorize as a top-level method like
+    ``pd.factorize(values)``. The results are identical for methods like
+    :meth:`Series.factorize`.
+
+    >>> codes, uniques = pd.factorize(np.array(['b', 'b', 'a', 'c', 'b'], dtype="O"))
+    >>> codes
+    array([0, 0, 1, 2, 0])
+    >>> uniques
+    array(['b', 'a', 'c'], dtype=object)
+
+    With ``sort=True``, the `uniques` will be sorted, and `codes` will be
+    shuffled so that the relationship is the maintained.
+
+    >>> codes, uniques = pd.factorize(np.array(['b', 'b', 'a', 'c', 'b'], dtype="O"),
+    ...                               sort=True)
+    >>> codes
+    array([1, 1, 0, 2, 1])
+    >>> uniques
+    array(['a', 'b', 'c'], dtype=object)
+
+    When ``use_na_sentinel=True`` (the default), missing values are indicated in
+    the `codes` with the sentinel value ``-1`` and missing values are not
+    included in `uniques`.
+
+    >>> codes, uniques = pd.factorize(np.array(['b', None, 'a', 'c', 'b'], dtype="O"))
+    >>> codes
+    array([ 0, -1,  1,  2,  0])
+    >>> uniques
+    array(['b', 'a', 'c'], dtype=object)
+
+    Thus far, we've only factorized lists (which are internally coerced to
+    NumPy arrays). When factorizing pandas objects, the type of `uniques`
+    will differ. For Categoricals, a `Categorical` is returned.
+
+    >>> cat = pd.Categorical(['a', 'a', 'c'], categories=['a', 'b', 'c'])
+    >>> codes, uniques = pd.factorize(cat)
+    >>> codes
+    array([0, 0, 1])
+    >>> uniques
+    ['a', 'c']
+    Categories (3, object): ['a', 'b', 'c']
+
+    Notice that ``'b'`` is in ``uniques.categories``, despite not being
+    present in ``cat.values``.
+
+    For all other pandas objects, an Index of the appropriate type is
+    returned.
+
+    >>> cat = pd.Series(['a', 'a', 'c'])
+    >>> codes, uniques = pd.factorize(cat)
+    >>> codes
+    array([0, 0, 1])
+    >>> uniques
+    Index(['a', 'c'], dtype='object')
+
+    If NaN is in the values, and we want to include NaN in the uniques of the
+    values, it can be achieved by setting ``use_na_sentinel=False``.
+
+    >>> values = np.array([1, 2, 1, np.nan])
+    >>> codes, uniques = pd.factorize(values)  # default: use_na_sentinel=True
+    >>> codes
+    array([ 0,  1,  0, -1])
+    >>> uniques
+    array([1., 2.])
+
+    >>> codes, uniques = pd.factorize(values, use_na_sentinel=False)
+    >>> codes
+    array([0, 1, 0, 2])
+    >>> uniques
+    array([ 1.,  2., nan])
+    """
+    # Implementation notes: This method is responsible for 3 things
+    # 1.) coercing data to array-like (ndarray, Index, extension array)
+    # 2.) factorizing codes and uniques
+    # 3.) Maybe boxing the uniques in an Index
+    #
+    # Step 2 is dispatched to extension types (like Categorical). They are
+    # responsible only for factorization. All data coercion, sorting and boxing
+    # should happen here.
+    if isinstance(values, (ABCIndex, ABCSeries)):
+        return values.factorize(sort=sort, use_na_sentinel=use_na_sentinel)
+
+    values = _ensure_arraylike(values, func_name="factorize")
+    original = values
+
+    if (
+        isinstance(values, (ABCDatetimeArray, ABCTimedeltaArray))
+        and values.freq is not None
+    ):
+        # The presence of 'freq' means we can fast-path sorting and know there
+        #  aren't NAs
+        codes, uniques = values.factorize(sort=sort)
+        return codes, uniques
+
+    elif not isinstance(values, np.ndarray):
+        # i.e. ExtensionArray
+        codes, uniques = values.factorize(use_na_sentinel=use_na_sentinel)
+
+    else:
+        values = np.asarray(values)  # convert DTA/TDA/MultiIndex
+
+        if not use_na_sentinel and values.dtype == object:
+            # factorize can now handle differentiating various types of null values.
+            # These can only occur when the array has object dtype.
+            # However, for backwards compatibility we only use the null for the
+            # provided dtype. This may be revisited in the future, see GH#48476.
+            null_mask = isna(values)
+            if null_mask.any():
+                na_value = na_value_for_dtype(values.dtype, compat=False)
+                # Don't modify (potentially user-provided) array
+                values = np.where(null_mask, na_value, values)
+
+        codes, uniques = factorize_array(
+            values,
+            use_na_sentinel=use_na_sentinel,
+            size_hint=size_hint,
+        )
+
+    if sort and len(uniques) > 0:
+        uniques, codes = safe_sort(
+            uniques,
+            codes,
+            use_na_sentinel=use_na_sentinel,
+            assume_unique=True,
+            verify=False,
+        )
+
+    uniques = _reconstruct_data(uniques, original.dtype, original)
+
+    return codes, uniques
+
+
+def value_counts(
+    values,
+    sort: bool = True,
+    ascending: bool = False,
+    normalize: bool = False,
+    bins=None,
+    dropna: bool = True,
+) -> Series:
+    """
+    Compute a histogram of the counts of non-null values.
+
+    Parameters
+    ----------
+    values : ndarray (1-d)
+    sort : bool, default True
+        Sort by values
+    ascending : bool, default False
+        Sort in ascending order
+    normalize: bool, default False
+        If True then compute a relative histogram
+    bins : integer, optional
+        Rather than count values, group them into half-open bins,
+        convenience for pd.cut, only works with numeric data
+    dropna : bool, default True
+        Don't include counts of NaN
+
+    Returns
+    -------
+    Series
+    """
+    warnings.warn(
+        # GH#53493
+        "pandas.value_counts is deprecated and will be removed in a "
+        "future version. Use pd.Series(obj).value_counts() instead.",
+        FutureWarning,
+        stacklevel=find_stack_level(),
+    )
+    return value_counts_internal(
+        values,
+        sort=sort,
+        ascending=ascending,
+        normalize=normalize,
+        bins=bins,
+        dropna=dropna,
+    )
+
+
+def value_counts_internal(
+    values,
+    sort: bool = True,
+    ascending: bool = False,
+    normalize: bool = False,
+    bins=None,
+    dropna: bool = True,
+) -> Series:
+    from pandas import (
+        Index,
+        Series,
+    )
+
+    index_name = getattr(values, "name", None)
+    name = "proportion" if normalize else "count"
+
+    if bins is not None:
+        from pandas.core.reshape.tile import cut
+
+        if isinstance(values, Series):
+            values = values._values
+
+        try:
+            ii = cut(values, bins, include_lowest=True)
+        except TypeError as err:
+            raise TypeError("bins argument only works with numeric data.") from err
+
+        # count, remove nulls (from the index), and but the bins
+        result = ii.value_counts(dropna=dropna)
+        result.name = name
+        result = result[result.index.notna()]
+        result.index = result.index.astype("interval")
+        result = result.sort_index()
+
+        # if we are dropna and we have NO values
+        if dropna and (result._values == 0).all():
+            result = result.iloc[0:0]
+
+        # normalizing is by len of all (regardless of dropna)
+        counts = np.array([len(ii)])
+
+    else:
+        if is_extension_array_dtype(values):
+            # handle Categorical and sparse,
+            result = Series(values, copy=False)._values.value_counts(dropna=dropna)
+            result.name = name
+            result.index.name = index_name
+            counts = result._values
+            if not isinstance(counts, np.ndarray):
+                # e.g. ArrowExtensionArray
+                counts = np.asarray(counts)
+
+        elif isinstance(values, ABCMultiIndex):
+            # GH49558
+            levels = list(range(values.nlevels))
+            result = (
+                Series(index=values, name=name)
+                .groupby(level=levels, dropna=dropna)
+                .size()
+            )
+            result.index.names = values.names
+            counts = result._values
+
+        else:
+            values = _ensure_arraylike(values, func_name="value_counts")
+            keys, counts, _ = value_counts_arraylike(values, dropna)
+            if keys.dtype == np.float16:
+                keys = keys.astype(np.float32)
+
+            # For backwards compatibility, we let Index do its normal type
+            #  inference, _except_ for if if infers from object to bool.
+            idx = Index(keys)
+            if idx.dtype == bool and keys.dtype == object:
+                idx = idx.astype(object)
+            elif (
+                idx.dtype != keys.dtype  # noqa: PLR1714  # # pylint: disable=R1714
+                and idx.dtype != "string[pyarrow_numpy]"
+            ):
+                warnings.warn(
+                    # GH#56161
+                    "The behavior of value_counts with object-dtype is deprecated. "
+                    "In a future version, this will *not* perform dtype inference "
+                    "on the resulting index. To retain the old behavior, use "
+                    "`result.index = result.index.infer_objects()`",
+                    FutureWarning,
+                    stacklevel=find_stack_level(),
+                )
+            idx.name = index_name
+
+            result = Series(counts, index=idx, name=name, copy=False)
+
+    if sort:
+        result = result.sort_values(ascending=ascending)
+
+    if normalize:
+        result = result / counts.sum()
+
+    return result
+
+
+# Called once from SparseArray, otherwise could be private
+def value_counts_arraylike(
+    values: np.ndarray, dropna: bool, mask: npt.NDArray[np.bool_] | None = None
+) -> tuple[ArrayLike, npt.NDArray[np.int64], int]:
+    """
+    Parameters
+    ----------
+    values : np.ndarray
+    dropna : bool
+    mask : np.ndarray[bool] or None, default None
+
+    Returns
+    -------
+    uniques : np.ndarray
+    counts : np.ndarray[np.int64]
+    """
+    original = values
+    values = _ensure_data(values)
+
+    keys, counts, na_counter = htable.value_count(values, dropna, mask=mask)
+
+    if needs_i8_conversion(original.dtype):
+        # datetime, timedelta, or period
+
+        if dropna:
+            mask = keys != iNaT
+            keys, counts = keys[mask], counts[mask]
+
+    res_keys = _reconstruct_data(keys, original.dtype, original)
+    return res_keys, counts, na_counter
+
+
+def duplicated(
+    values: ArrayLike,
+    keep: Literal["first", "last", False] = "first",
+    mask: npt.NDArray[np.bool_] | None = None,
+) -> npt.NDArray[np.bool_]:
+    """
+    Return boolean ndarray denoting duplicate values.
+
+    Parameters
+    ----------
+    values : np.ndarray or ExtensionArray
+        Array over which to check for duplicate values.
+    keep : {'first', 'last', False}, default 'first'
+        - ``first`` : Mark duplicates as ``True`` except for the first
+          occurrence.
+        - ``last`` : Mark duplicates as ``True`` except for the last
+          occurrence.
+        - False : Mark all duplicates as ``True``.
+    mask : ndarray[bool], optional
+        array indicating which elements to exclude from checking
+
+    Returns
+    -------
+    duplicated : ndarray[bool]
+    """
+    values = _ensure_data(values)
+    return htable.duplicated(values, keep=keep, mask=mask)
+
+
+def mode(
+    values: ArrayLike, dropna: bool = True, mask: npt.NDArray[np.bool_] | None = None
+) -> ArrayLike:
+    """
+    Returns the mode(s) of an array.
+
+    Parameters
+    ----------
+    values : array-like
+        Array over which to check for duplicate values.
+    dropna : bool, default True
+        Don't consider counts of NaN/NaT.
+
+    Returns
+    -------
+    np.ndarray or ExtensionArray
+    """
+    values = _ensure_arraylike(values, func_name="mode")
+    original = values
+
+    if needs_i8_conversion(values.dtype):
+        # Got here with ndarray; dispatch to DatetimeArray/TimedeltaArray.
+        values = ensure_wrapped_if_datetimelike(values)
+        values = cast("ExtensionArray", values)
+        return values._mode(dropna=dropna)
+
+    values = _ensure_data(values)
+
+    npresult, res_mask = htable.mode(values, dropna=dropna, mask=mask)
+    if res_mask is not None:
+        return npresult, res_mask  # type: ignore[return-value]
+
+    try:
+        npresult = np.sort(npresult)
+    except TypeError as err:
+        warnings.warn(
+            f"Unable to sort modes: {err}",
+            stacklevel=find_stack_level(),
+        )
+
+    result = _reconstruct_data(npresult, original.dtype, original)
+    return result
+
+
+def rank(
+    values: ArrayLike,
+    axis: AxisInt = 0,
+    method: str = "average",
+    na_option: str = "keep",
+    ascending: bool = True,
+    pct: bool = False,
+) -> npt.NDArray[np.float64]:
+    """
+    Rank the values along a given axis.
+
+    Parameters
+    ----------
+    values : np.ndarray or ExtensionArray
+        Array whose values will be ranked. The number of dimensions in this
+        array must not exceed 2.
+    axis : int, default 0
+        Axis over which to perform rankings.
+    method : {'average', 'min', 'max', 'first', 'dense'}, default 'average'
+        The method by which tiebreaks are broken during the ranking.
+    na_option : {'keep', 'top'}, default 'keep'
+        The method by which NaNs are placed in the ranking.
+        - ``keep``: rank each NaN value with a NaN ranking
+        - ``top``: replace each NaN with either +/- inf so that they
+                   there are ranked at the top
+    ascending : bool, default True
+        Whether or not the elements should be ranked in ascending order.
+    pct : bool, default False
+        Whether or not to the display the returned rankings in integer form
+        (e.g. 1, 2, 3) or in percentile form (e.g. 0.333..., 0.666..., 1).
+    """
+    is_datetimelike = needs_i8_conversion(values.dtype)
+    values = _ensure_data(values)
+
+    if values.ndim == 1:
+        ranks = algos.rank_1d(
+            values,
+            is_datetimelike=is_datetimelike,
+            ties_method=method,
+            ascending=ascending,
+            na_option=na_option,
+            pct=pct,
+        )
+    elif values.ndim == 2:
+        ranks = algos.rank_2d(
+            values,
+            axis=axis,
+            is_datetimelike=is_datetimelike,
+            ties_method=method,
+            ascending=ascending,
+            na_option=na_option,
+            pct=pct,
+        )
+    else:
+        raise TypeError("Array with ndim > 2 are not supported.")
+
+    return ranks
+
+
+# ---- #
+# take #
+# ---- #
+
+
+def take(
+    arr,
+    indices: TakeIndexer,
+    axis: AxisInt = 0,
+    allow_fill: bool = False,
+    fill_value=None,
+):
+    """
+    Take elements from an array.
+
+    Parameters
+    ----------
+    arr : array-like or scalar value
+        Non array-likes (sequences/scalars without a dtype) are coerced
+        to an ndarray.
+
+        .. deprecated:: 2.1.0
+            Passing an argument other than a numpy.ndarray, ExtensionArray,
+            Index, or Series is deprecated.
+
+    indices : sequence of int or one-dimensional np.ndarray of int
+        Indices to be taken.
+    axis : int, default 0
+        The axis over which to select values.
+    allow_fill : bool, default False
+        How to handle negative values in `indices`.
+
+        * False: negative values in `indices` indicate positional indices
+          from the right (the default). This is similar to :func:`numpy.take`.
+
+        * True: negative values in `indices` indicate
+          missing values. These values are set to `fill_value`. Any other
+          negative values raise a ``ValueError``.
+
+    fill_value : any, optional
+        Fill value to use for NA-indices when `allow_fill` is True.
+        This may be ``None``, in which case the default NA value for
+        the type (``self.dtype.na_value``) is used.
+
+        For multi-dimensional `arr`, each *element* is filled with
+        `fill_value`.
+
+    Returns
+    -------
+    ndarray or ExtensionArray
+        Same type as the input.
+
+    Raises
+    ------
+    IndexError
+        When `indices` is out of bounds for the array.
+    ValueError
+        When the indexer contains negative values other than ``-1``
+        and `allow_fill` is True.
+
+    Notes
+    -----
+    When `allow_fill` is False, `indices` may be whatever dimensionality
+    is accepted by NumPy for `arr`.
+
+    When `allow_fill` is True, `indices` should be 1-D.
+
+    See Also
+    --------
+    numpy.take : Take elements from an array along an axis.
+
+    Examples
+    --------
+    >>> import pandas as pd
+
+    With the default ``allow_fill=False``, negative numbers indicate
+    positional indices from the right.
+
+    >>> pd.api.extensions.take(np.array([10, 20, 30]), [0, 0, -1])
+    array([10, 10, 30])
+
+    Setting ``allow_fill=True`` will place `fill_value` in those positions.
+
+    >>> pd.api.extensions.take(np.array([10, 20, 30]), [0, 0, -1], allow_fill=True)
+    array([10., 10., nan])
+
+    >>> pd.api.extensions.take(np.array([10, 20, 30]), [0, 0, -1], allow_fill=True,
+    ...      fill_value=-10)
+    array([ 10,  10, -10])
+    """
+    if not isinstance(arr, (np.ndarray, ABCExtensionArray, ABCIndex, ABCSeries)):
+        # GH#52981
+        warnings.warn(
+            "pd.api.extensions.take accepting non-standard inputs is deprecated "
+            "and will raise in a future version. Pass either a numpy.ndarray, "
+            "ExtensionArray, Index, or Series instead.",
+            FutureWarning,
+            stacklevel=find_stack_level(),
+        )
+
+    if not is_array_like(arr):
+        arr = np.asarray(arr)
+
+    indices = ensure_platform_int(indices)
+
+    if allow_fill:
+        # Pandas style, -1 means NA
+        validate_indices(indices, arr.shape[axis])
+        result = take_nd(
+            arr, indices, axis=axis, allow_fill=True, fill_value=fill_value
+        )
+    else:
+        # NumPy style
+        result = arr.take(indices, axis=axis)
+    return result
+
+
+# ------------ #
+# searchsorted #
+# ------------ #
+
+
+def searchsorted(
+    arr: ArrayLike,
+    value: NumpyValueArrayLike | ExtensionArray,
+    side: Literal["left", "right"] = "left",
+    sorter: NumpySorter | None = None,
+) -> npt.NDArray[np.intp] | np.intp:
+    """
+    Find indices where elements should be inserted to maintain order.
+
+    Find the indices into a sorted array `arr` (a) such that, if the
+    corresponding elements in `value` were inserted before the indices,
+    the order of `arr` would be preserved.
+
+    Assuming that `arr` is sorted:
+
+    ======  ================================
+    `side`  returned index `i` satisfies
+    ======  ================================
+    left    ``arr[i-1] < value <= self[i]``
+    right   ``arr[i-1] <= value < self[i]``
+    ======  ================================
+
+    Parameters
+    ----------
+    arr: np.ndarray, ExtensionArray, Series
+        Input array. If `sorter` is None, then it must be sorted in
+        ascending order, otherwise `sorter` must be an array of indices
+        that sort it.
+    value : array-like or scalar
+        Values to insert into `arr`.
+    side : {'left', 'right'}, optional
+        If 'left', the index of the first suitable location found is given.
+        If 'right', return the last such index.  If there is no suitable
+        index, return either 0 or N (where N is the length of `self`).
+    sorter : 1-D array-like, optional
+        Optional array of integer indices that sort array a into ascending
+        order. They are typically the result of argsort.
+
+    Returns
+    -------
+    array of ints or int
+        If value is array-like, array of insertion points.
+        If value is scalar, a single integer.
+
+    See Also
+    --------
+    numpy.searchsorted : Similar method from NumPy.
+    """
+    if sorter is not None:
+        sorter = ensure_platform_int(sorter)
+
+    if (
+        isinstance(arr, np.ndarray)
+        and arr.dtype.kind in "iu"
+        and (is_integer(value) or is_integer_dtype(value))
+    ):
+        # if `arr` and `value` have different dtypes, `arr` would be
+        # recast by numpy, causing a slow search.
+        # Before searching below, we therefore try to give `value` the
+        # same dtype as `arr`, while guarding against integer overflows.
+        iinfo = np.iinfo(arr.dtype.type)
+        value_arr = np.array([value]) if is_integer(value) else np.array(value)
+        if (value_arr >= iinfo.min).all() and (value_arr <= iinfo.max).all():
+            # value within bounds, so no overflow, so can convert value dtype
+            # to dtype of arr
+            dtype = arr.dtype
+        else:
+            dtype = value_arr.dtype
+
+        if is_integer(value):
+            # We know that value is int
+            value = cast(int, dtype.type(value))
+        else:
+            value = pd_array(cast(ArrayLike, value), dtype=dtype)
+    else:
+        # E.g. if `arr` is an array with dtype='datetime64[ns]'
+        # and `value` is a pd.Timestamp, we may need to convert value
+        arr = ensure_wrapped_if_datetimelike(arr)
+
+    # Argument 1 to "searchsorted" of "ndarray" has incompatible type
+    # "Union[NumpyValueArrayLike, ExtensionArray]"; expected "NumpyValueArrayLike"
+    return arr.searchsorted(value, side=side, sorter=sorter)  # type: ignore[arg-type]
+
+
+# ---- #
+# diff #
+# ---- #
+
+_diff_special = {"float64", "float32", "int64", "int32", "int16", "int8"}
+
+
+def diff(arr, n: int, axis: AxisInt = 0):
+    """
+    difference of n between self,
+    analogous to s-s.shift(n)
+
+    Parameters
+    ----------
+    arr : ndarray or ExtensionArray
+    n : int
+        number of periods
+    axis : {0, 1}
+        axis to shift on
+    stacklevel : int, default 3
+        The stacklevel for the lost dtype warning.
+
+    Returns
+    -------
+    shifted
+    """
+
+    n = int(n)
+    na = np.nan
+    dtype = arr.dtype
+
+    is_bool = is_bool_dtype(dtype)
+    if is_bool:
+        op = operator.xor
+    else:
+        op = operator.sub
+
+    if isinstance(dtype, NumpyEADtype):
+        # NumpyExtensionArray cannot necessarily hold shifted versions of itself.
+        arr = arr.to_numpy()
+        dtype = arr.dtype
+
+    if not isinstance(arr, np.ndarray):
+        # i.e ExtensionArray
+        if hasattr(arr, f"__{op.__name__}__"):
+            if axis != 0:
+                raise ValueError(f"cannot diff {type(arr).__name__} on axis={axis}")
+            return op(arr, arr.shift(n))
+        else:
+            raise TypeError(
+                f"{type(arr).__name__} has no 'diff' method. "
+                "Convert to a suitable dtype prior to calling 'diff'."
+            )
+
+    is_timedelta = False
+    if arr.dtype.kind in "mM":
+        dtype = np.int64
+        arr = arr.view("i8")
+        na = iNaT
+        is_timedelta = True
+
+    elif is_bool:
+        # We have to cast in order to be able to hold np.nan
+        dtype = np.object_
+
+    elif dtype.kind in "iu":
+        # We have to cast in order to be able to hold np.nan
+
+        # int8, int16 are incompatible with float64,
+        # see https://github.com/cython/cython/issues/2646
+        if arr.dtype.name in ["int8", "int16"]:
+            dtype = np.float32
+        else:
+            dtype = np.float64
+
+    orig_ndim = arr.ndim
+    if orig_ndim == 1:
+        # reshape so we can always use algos.diff_2d
+        arr = arr.reshape(-1, 1)
+        # TODO: require axis == 0
+
+    dtype = np.dtype(dtype)
+    out_arr = np.empty(arr.shape, dtype=dtype)
+
+    na_indexer = [slice(None)] * 2
+    na_indexer[axis] = slice(None, n) if n >= 0 else slice(n, None)
+    out_arr[tuple(na_indexer)] = na
+
+    if arr.dtype.name in _diff_special:
+        # TODO: can diff_2d dtype specialization troubles be fixed by defining
+        #  out_arr inside diff_2d?
+        algos.diff_2d(arr, out_arr, n, axis, datetimelike=is_timedelta)
+    else:
+        # To keep mypy happy, _res_indexer is a list while res_indexer is
+        #  a tuple, ditto for lag_indexer.
+        _res_indexer = [slice(None)] * 2
+        _res_indexer[axis] = slice(n, None) if n >= 0 else slice(None, n)
+        res_indexer = tuple(_res_indexer)
+
+        _lag_indexer = [slice(None)] * 2
+        _lag_indexer[axis] = slice(None, -n) if n > 0 else slice(-n, None)
+        lag_indexer = tuple(_lag_indexer)
+
+        out_arr[res_indexer] = op(arr[res_indexer], arr[lag_indexer])
+
+    if is_timedelta:
+        out_arr = out_arr.view("timedelta64[ns]")
+
+    if orig_ndim == 1:
+        out_arr = out_arr[:, 0]
+    return out_arr
+
+
+# --------------------------------------------------------------------
+# Helper functions
+
+
+# Note: safe_sort is in algorithms.py instead of sorting.py because it is
+#  low-dependency, is used in this module, and used private methods from
+#  this module.
+def safe_sort(
+    values: Index | ArrayLike,
+    codes: npt.NDArray[np.intp] | None = None,
+    use_na_sentinel: bool = True,
+    assume_unique: bool = False,
+    verify: bool = True,
+) -> AnyArrayLike | tuple[AnyArrayLike, np.ndarray]:
+    """
+    Sort ``values`` and reorder corresponding ``codes``.
+
+    ``values`` should be unique if ``codes`` is not None.
+    Safe for use with mixed types (int, str), orders ints before strs.
+
+    Parameters
+    ----------
+    values : list-like
+        Sequence; must be unique if ``codes`` is not None.
+    codes : np.ndarray[intp] or None, default None
+        Indices to ``values``. All out of bound indices are treated as
+        "not found" and will be masked with ``-1``.
+    use_na_sentinel : bool, default True
+        If True, the sentinel -1 will be used for NaN values. If False,
+        NaN values will be encoded as non-negative integers and will not drop the
+        NaN from the uniques of the values.
+    assume_unique : bool, default False
+        When True, ``values`` are assumed to be unique, which can speed up
+        the calculation. Ignored when ``codes`` is None.
+    verify : bool, default True
+        Check if codes are out of bound for the values and put out of bound
+        codes equal to ``-1``. If ``verify=False``, it is assumed there
+        are no out of bound codes. Ignored when ``codes`` is None.
+
+    Returns
+    -------
+    ordered : AnyArrayLike
+        Sorted ``values``
+    new_codes : ndarray
+        Reordered ``codes``; returned when ``codes`` is not None.
+
+    Raises
+    ------
+    TypeError
+        * If ``values`` is not list-like or if ``codes`` is neither None
+        nor list-like
+        * If ``values`` cannot be sorted
+    ValueError
+        * If ``codes`` is not None and ``values`` contain duplicates.
+    """
+    if not isinstance(values, (np.ndarray, ABCExtensionArray, ABCIndex)):
+        raise TypeError(
+            "Only np.ndarray, ExtensionArray, and Index objects are allowed to "
+            "be passed to safe_sort as values"
+        )
+
+    sorter = None
+    ordered: AnyArrayLike
+
+    if (
+        not isinstance(values.dtype, ExtensionDtype)
+        and lib.infer_dtype(values, skipna=False) == "mixed-integer"
+    ):
+        ordered = _sort_mixed(values)
+    else:
+        try:
+            sorter = values.argsort()
+            ordered = values.take(sorter)
+        except (TypeError, decimal.InvalidOperation):
+            # Previous sorters failed or were not applicable, try `_sort_mixed`
+            # which would work, but which fails for special case of 1d arrays
+            # with tuples.
+            if values.size and isinstance(values[0], tuple):
+                # error: Argument 1 to "_sort_tuples" has incompatible type
+                # "Union[Index, ExtensionArray, ndarray[Any, Any]]"; expected
+                # "ndarray[Any, Any]"
+                ordered = _sort_tuples(values)  # type: ignore[arg-type]
+            else:
+                ordered = _sort_mixed(values)
+
+    # codes:
+
+    if codes is None:
+        return ordered
+
+    if not is_list_like(codes):
+        raise TypeError(
+            "Only list-like objects or None are allowed to "
+            "be passed to safe_sort as codes"
+        )
+    codes = ensure_platform_int(np.asarray(codes))
+
+    if not assume_unique and not len(unique(values)) == len(values):
+        raise ValueError("values should be unique if codes is not None")
+
+    if sorter is None:
+        # mixed types
+        # error: Argument 1 to "_get_hashtable_algo" has incompatible type
+        # "Union[Index, ExtensionArray, ndarray[Any, Any]]"; expected
+        # "ndarray[Any, Any]"
+        hash_klass, values = _get_hashtable_algo(values)  # type: ignore[arg-type]
+        t = hash_klass(len(values))
+        t.map_locations(values)
+        sorter = ensure_platform_int(t.lookup(ordered))
+
+    if use_na_sentinel:
+        # take_nd is faster, but only works for na_sentinels of -1
+        order2 = sorter.argsort()
+        if verify:
+            mask = (codes < -len(values)) | (codes >= len(values))
+            codes[mask] = 0
+        else:
+            mask = None
+        new_codes = take_nd(order2, codes, fill_value=-1)
+    else:
+        reverse_indexer = np.empty(len(sorter), dtype=int)
+        reverse_indexer.put(sorter, np.arange(len(sorter)))
+        # Out of bound indices will be masked with `-1` next, so we
+        # may deal with them here without performance loss using `mode='wrap'`
+        new_codes = reverse_indexer.take(codes, mode="wrap")
+
+        if use_na_sentinel:
+            mask = codes == -1
+            if verify:
+                mask = mask | (codes < -len(values)) | (codes >= len(values))
+
+    if use_na_sentinel and mask is not None:
+        np.putmask(new_codes, mask, -1)
+
+    return ordered, ensure_platform_int(new_codes)
+
+
+def _sort_mixed(values) -> AnyArrayLike:
+    """order ints before strings before nulls in 1d arrays"""
+    str_pos = np.array([isinstance(x, str) for x in values], dtype=bool)
+    null_pos = np.array([isna(x) for x in values], dtype=bool)
+    num_pos = ~str_pos & ~null_pos
+    str_argsort = np.argsort(values[str_pos])
+    num_argsort = np.argsort(values[num_pos])
+    # convert boolean arrays to positional indices, then order by underlying values
+    str_locs = str_pos.nonzero()[0].take(str_argsort)
+    num_locs = num_pos.nonzero()[0].take(num_argsort)
+    null_locs = null_pos.nonzero()[0]
+    locs = np.concatenate([num_locs, str_locs, null_locs])
+    return values.take(locs)
+
+
+def _sort_tuples(values: np.ndarray) -> np.ndarray:
+    """
+    Convert array of tuples (1d) to array of arrays (2d).
+    We need to keep the columns separately as they contain different types and
+    nans (can't use `np.sort` as it may fail when str and nan are mixed in a
+    column as types cannot be compared).
+    """
+    from pandas.core.internals.construction import to_arrays
+    from pandas.core.sorting import lexsort_indexer
+
+    arrays, _ = to_arrays(values, None)
+    indexer = lexsort_indexer(arrays, orders=True)
+    return values[indexer]
+
+
+def union_with_duplicates(
+    lvals: ArrayLike | Index, rvals: ArrayLike | Index
+) -> ArrayLike | Index:
+    """
+    Extracts the union from lvals and rvals with respect to duplicates and nans in
+    both arrays.
+
+    Parameters
+    ----------
+    lvals: np.ndarray or ExtensionArray
+        left values which is ordered in front.
+    rvals: np.ndarray or ExtensionArray
+        right values ordered after lvals.
+
+    Returns
+    -------
+    np.ndarray or ExtensionArray
+        Containing the unsorted union of both arrays.
+
+    Notes
+    -----
+    Caller is responsible for ensuring lvals.dtype == rvals.dtype.
+    """
+    from pandas import Series
+
+    with warnings.catch_warnings():
+        # filter warning from object dtype inference; we will end up discarding
+        # the index here, so the deprecation does not affect the end result here.
+        warnings.filterwarnings(
+            "ignore",
+            "The behavior of value_counts with object-dtype is deprecated",
+            category=FutureWarning,
+        )
+        l_count = value_counts_internal(lvals, dropna=False)
+        r_count = value_counts_internal(rvals, dropna=False)
+    l_count, r_count = l_count.align(r_count, fill_value=0)
+    final_count = np.maximum(l_count.values, r_count.values)
+    final_count = Series(final_count, index=l_count.index, dtype="int", copy=False)
+    if isinstance(lvals, ABCMultiIndex) and isinstance(rvals, ABCMultiIndex):
+        unique_vals = lvals.append(rvals).unique()
+    else:
+        if isinstance(lvals, ABCIndex):
+            lvals = lvals._values
+        if isinstance(rvals, ABCIndex):
+            rvals = rvals._values
+        # error: List item 0 has incompatible type "Union[ExtensionArray,
+        # ndarray[Any, Any], Index]"; expected "Union[ExtensionArray,
+        # ndarray[Any, Any]]"
+        combined = concat_compat([lvals, rvals])  # type: ignore[list-item]
+        unique_vals = unique(combined)
+        unique_vals = ensure_wrapped_if_datetimelike(unique_vals)
+    repeats = final_count.reindex(unique_vals).values
+    return np.repeat(unique_vals, repeats)
+
+
+def map_array(
+    arr: ArrayLike,
+    mapper,
+    na_action: Literal["ignore"] | None = None,
+    convert: bool = True,
+) -> np.ndarray | ExtensionArray | Index:
+    """
+    Map values using an input mapping or function.
+
+    Parameters
+    ----------
+    mapper : function, dict, or Series
+        Mapping correspondence.
+    na_action : {None, 'ignore'}, default None
+        If 'ignore', propagate NA values, without passing them to the
+        mapping correspondence.
+    convert : bool, default True
+        Try to find better dtype for elementwise function results. If
+        False, leave as dtype=object.
+
+    Returns
+    -------
+    Union[ndarray, Index, ExtensionArray]
+        The output of the mapping function applied to the array.
+        If the function returns a tuple with more than one element
+        a MultiIndex will be returned.
+    """
+    if na_action not in (None, "ignore"):
+        msg = f"na_action must either be 'ignore' or None, {na_action} was passed"
+        raise ValueError(msg)
+
+    # we can fastpath dict/Series to an efficient map
+    # as we know that we are not going to have to yield
+    # python types
+    if is_dict_like(mapper):
+        if isinstance(mapper, dict) and hasattr(mapper, "__missing__"):
+            # If a dictionary subclass defines a default value method,
+            # convert mapper to a lookup function (GH #15999).
+            dict_with_default = mapper
+            mapper = lambda x: dict_with_default[
+                np.nan if isinstance(x, float) and np.isnan(x) else x
+            ]
+        else:
+            # Dictionary does not have a default. Thus it's safe to
+            # convert to an Series for efficiency.
+            # we specify the keys here to handle the
+            # possibility that they are tuples
+
+            # The return value of mapping with an empty mapper is
+            # expected to be pd.Series(np.nan, ...). As np.nan is
+            # of dtype float64 the return value of this method should
+            # be float64 as well
+            from pandas import Series
+
+            if len(mapper) == 0:
+                mapper = Series(mapper, dtype=np.float64)
+            else:
+                mapper = Series(mapper)
+
+    if isinstance(mapper, ABCSeries):
+        if na_action == "ignore":
+            mapper = mapper[mapper.index.notna()]
+
+        # Since values were input this means we came from either
+        # a dict or a series and mapper should be an index
+        indexer = mapper.index.get_indexer(arr)
+        new_values = take_nd(mapper._values, indexer)
+
+        return new_values
+
+    if not len(arr):
+        return arr.copy()
+
+    # we must convert to python types
+    values = arr.astype(object, copy=False)
+    if na_action is None:
+        return lib.map_infer(values, mapper, convert=convert)
+    else:
+        return lib.map_infer_mask(
+            values, mapper, mask=isna(values).view(np.uint8), convert=convert
+        )

lib/python3.12/site-packages/pandas/core/api.py

@@ -0,0 +1,140 @@
+from pandas._libs import (
+    NaT,
+    Period,
+    Timedelta,
+    Timestamp,
+)
+from pandas._libs.missing import NA
+
+from pandas.core.dtypes.dtypes import (
+    ArrowDtype,
+    CategoricalDtype,
+    DatetimeTZDtype,
+    IntervalDtype,
+    PeriodDtype,
+)
+from pandas.core.dtypes.missing import (
+    isna,
+    isnull,
+    notna,
+    notnull,
+)
+
+from pandas.core.algorithms import (
+    factorize,
+    unique,
+    value_counts,
+)
+from pandas.core.arrays import Categorical
+from pandas.core.arrays.boolean import BooleanDtype
+from pandas.core.arrays.floating import (
+    Float32Dtype,
+    Float64Dtype,
+)
+from pandas.core.arrays.integer import (
+    Int8Dtype,
+    Int16Dtype,
+    Int32Dtype,
+    Int64Dtype,
+    UInt8Dtype,
+    UInt16Dtype,
+    UInt32Dtype,
+    UInt64Dtype,
+)
+from pandas.core.arrays.string_ import StringDtype
+from pandas.core.construction import array
+from pandas.core.flags import Flags
+from pandas.core.groupby import (
+    Grouper,
+    NamedAgg,
+)
+from pandas.core.indexes.api import (
+    CategoricalIndex,
+    DatetimeIndex,
+    Index,
+    IntervalIndex,
+    MultiIndex,
+    PeriodIndex,
+    RangeIndex,
+    TimedeltaIndex,
+)
+from pandas.core.indexes.datetimes import (
+    bdate_range,
+    date_range,
+)
+from pandas.core.indexes.interval import (
+    Interval,
+    interval_range,
+)
+from pandas.core.indexes.period import period_range
+from pandas.core.indexes.timedeltas import timedelta_range
+from pandas.core.indexing import IndexSlice
+from pandas.core.series import Series
+from pandas.core.tools.datetimes import to_datetime
+from pandas.core.tools.numeric import to_numeric
+from pandas.core.tools.timedeltas import to_timedelta
+
+from pandas.io.formats.format import set_eng_float_format
+from pandas.tseries.offsets import DateOffset
+
+# DataFrame needs to be imported after NamedAgg to avoid a circular import
+from pandas.core.frame import DataFrame  # isort:skip
+
+__all__ = [
+    "array",
+    "ArrowDtype",
+    "bdate_range",
+    "BooleanDtype",
+    "Categorical",
+    "CategoricalDtype",
+    "CategoricalIndex",
+    "DataFrame",
+    "DateOffset",
+    "date_range",
+    "DatetimeIndex",
+    "DatetimeTZDtype",
+    "factorize",
+    "Flags",
+    "Float32Dtype",
+    "Float64Dtype",
+    "Grouper",
+    "Index",
+    "IndexSlice",
+    "Int16Dtype",
+    "Int32Dtype",
+    "Int64Dtype",
+    "Int8Dtype",
+    "Interval",
+    "IntervalDtype",
+    "IntervalIndex",
+    "interval_range",
+    "isna",
+    "isnull",
+    "MultiIndex",
+    "NA",
+    "NamedAgg",
+    "NaT",
+    "notna",
+    "notnull",
+    "Period",
+    "PeriodDtype",
+    "PeriodIndex",
+    "period_range",
+    "RangeIndex",
+    "Series",
+    "set_eng_float_format",
+    "StringDtype",
+    "Timedelta",
+    "TimedeltaIndex",
+    "timedelta_range",
+    "Timestamp",
+    "to_datetime",
+    "to_numeric",
+    "to_timedelta",
+    "UInt16Dtype",
+    "UInt32Dtype",
+    "UInt64Dtype",
+    "UInt8Dtype",
+    "unique",
+    "value_counts",
+]

lib/python3.12/site-packages/pandas/core/apply.py

@@ -0,0 +1,2062 @@
+from __future__ import annotations
+
+import abc
+from collections import defaultdict
+import functools
+from functools import partial
+import inspect
+from typing import (
+    TYPE_CHECKING,
+    Any,
+    Callable,
+    Literal,
+    cast,
+)
+import warnings
+
+import numpy as np
+
+from pandas._config import option_context
+
+from pandas._libs import lib
+from pandas._libs.internals import BlockValuesRefs
+from pandas._typing import (
+    AggFuncType,
+    AggFuncTypeBase,
+    AggFuncTypeDict,
+    AggObjType,
+    Axis,
+    AxisInt,
+    NDFrameT,
+    npt,
+)
+from pandas.compat._optional import import_optional_dependency
+from pandas.errors import SpecificationError
+from pandas.util._decorators import cache_readonly
+from pandas.util._exceptions import find_stack_level
+
+from pandas.core.dtypes.cast import is_nested_object
+from pandas.core.dtypes.common import (
+    is_dict_like,
+    is_extension_array_dtype,
+    is_list_like,
+    is_numeric_dtype,
+    is_sequence,
+)
+from pandas.core.dtypes.dtypes import (
+    CategoricalDtype,
+    ExtensionDtype,
+)
+from pandas.core.dtypes.generic import (
+    ABCDataFrame,
+    ABCNDFrame,
+    ABCSeries,
+)
+
+from pandas.core._numba.executor import generate_apply_looper
+import pandas.core.common as com
+from pandas.core.construction import ensure_wrapped_if_datetimelike
+
+if TYPE_CHECKING:
+    from collections.abc import (
+        Generator,
+        Hashable,
+        Iterable,
+        MutableMapping,
+        Sequence,
+    )
+
+    from pandas import (
+        DataFrame,
+        Index,
+        Series,
+    )
+    from pandas.core.groupby import GroupBy
+    from pandas.core.resample import Resampler
+    from pandas.core.window.rolling import BaseWindow
+
+
+ResType = dict[int, Any]
+
+
+def frame_apply(
+    obj: DataFrame,
+    func: AggFuncType,
+    axis: Axis = 0,
+    raw: bool = False,
+    result_type: str | None = None,
+    by_row: Literal[False, "compat"] = "compat",
+    engine: str = "python",
+    engine_kwargs: dict[str, bool] | None = None,
+    args=None,
+    kwargs=None,
+) -> FrameApply:
+    """construct and return a row or column based frame apply object"""
+    axis = obj._get_axis_number(axis)
+    klass: type[FrameApply]
+    if axis == 0:
+        klass = FrameRowApply
+    elif axis == 1:
+        klass = FrameColumnApply
+
+    _, func, _, _ = reconstruct_func(func, **kwargs)
+    assert func is not None
+
+    return klass(
+        obj,
+        func,
+        raw=raw,
+        result_type=result_type,
+        by_row=by_row,
+        engine=engine,
+        engine_kwargs=engine_kwargs,
+        args=args,
+        kwargs=kwargs,
+    )
+
+
+class Apply(metaclass=abc.ABCMeta):
+    axis: AxisInt
+
+    def __init__(
+        self,
+        obj: AggObjType,
+        func: AggFuncType,
+        raw: bool,
+        result_type: str | None,
+        *,
+        by_row: Literal[False, "compat", "_compat"] = "compat",
+        engine: str = "python",
+        engine_kwargs: dict[str, bool] | None = None,
+        args,
+        kwargs,
+    ) -> None:
+        self.obj = obj
+        self.raw = raw
+
+        assert by_row is False or by_row in ["compat", "_compat"]
+        self.by_row = by_row
+
+        self.args = args or ()
+        self.kwargs = kwargs or {}
+
+        self.engine = engine
+        self.engine_kwargs = {} if engine_kwargs is None else engine_kwargs
+
+        if result_type not in [None, "reduce", "broadcast", "expand"]:
+            raise ValueError(
+                "invalid value for result_type, must be one "
+                "of {None, 'reduce', 'broadcast', 'expand'}"
+            )
+
+        self.result_type = result_type
+
+        self.func = func
+
+    @abc.abstractmethod
+    def apply(self) -> DataFrame | Series:
+        pass
+
+    @abc.abstractmethod
+    def agg_or_apply_list_like(
+        self, op_name: Literal["agg", "apply"]
+    ) -> DataFrame | Series:
+        pass
+
+    @abc.abstractmethod
+    def agg_or_apply_dict_like(
+        self, op_name: Literal["agg", "apply"]
+    ) -> DataFrame | Series:
+        pass
+
+    def agg(self) -> DataFrame | Series | None:
+        """
+        Provide an implementation for the aggregators.
+
+        Returns
+        -------
+        Result of aggregation, or None if agg cannot be performed by
+        this method.
+        """
+        obj = self.obj
+        func = self.func
+        args = self.args
+        kwargs = self.kwargs
+
+        if isinstance(func, str):
+            return self.apply_str()
+
+        if is_dict_like(func):
+            return self.agg_dict_like()
+        elif is_list_like(func):
+            # we require a list, but not a 'str'
+            return self.agg_list_like()
+
+        if callable(func):
+            f = com.get_cython_func(func)
+            if f and not args and not kwargs:
+                warn_alias_replacement(obj, func, f)
+                return getattr(obj, f)()
+
+        # caller can react
+        return None
+
+    def transform(self) -> DataFrame | Series:
+        """
+        Transform a DataFrame or Series.
+
+        Returns
+        -------
+        DataFrame or Series
+            Result of applying ``func`` along the given axis of the
+            Series or DataFrame.
+
+        Raises
+        ------
+        ValueError
+            If the transform function fails or does not transform.
+        """
+        obj = self.obj
+        func = self.func
+        axis = self.axis
+        args = self.args
+        kwargs = self.kwargs
+
+        is_series = obj.ndim == 1
+
+        if obj._get_axis_number(axis) == 1:
+            assert not is_series
+            return obj.T.transform(func, 0, *args, **kwargs).T
+
+        if is_list_like(func) and not is_dict_like(func):
+            func = cast(list[AggFuncTypeBase], func)
+            # Convert func equivalent dict
+            if is_series:
+                func = {com.get_callable_name(v) or v: v for v in func}
+            else:
+                func = {col: func for col in obj}
+
+        if is_dict_like(func):
+            func = cast(AggFuncTypeDict, func)
+            return self.transform_dict_like(func)
+
+        # func is either str or callable
+        func = cast(AggFuncTypeBase, func)
+        try:
+            result = self.transform_str_or_callable(func)
+        except TypeError:
+            raise
+        except Exception as err:
+            raise ValueError("Transform function failed") from err
+
+        # Functions that transform may return empty Series/DataFrame
+        # when the dtype is not appropriate
+        if (
+            isinstance(result, (ABCSeries, ABCDataFrame))
+            and result.empty
+            and not obj.empty
+        ):
+            raise ValueError("Transform function failed")
+        # error: Argument 1 to "__get__" of "AxisProperty" has incompatible type
+        # "Union[Series, DataFrame, GroupBy[Any], SeriesGroupBy,
+        # DataFrameGroupBy, BaseWindow, Resampler]"; expected "Union[DataFrame,
+        # Series]"
+        if not isinstance(result, (ABCSeries, ABCDataFrame)) or not result.index.equals(
+            obj.index  # type: ignore[arg-type]
+        ):
+            raise ValueError("Function did not transform")
+
+        return result
+
+    def transform_dict_like(self, func) -> DataFrame:
+        """
+        Compute transform in the case of a dict-like func
+        """
+        from pandas.core.reshape.concat import concat
+
+        obj = self.obj
+        args = self.args
+        kwargs = self.kwargs
+
+        # transform is currently only for Series/DataFrame
+        assert isinstance(obj, ABCNDFrame)
+
+        if len(func) == 0:
+            raise ValueError("No transform functions were provided")
+
+        func = self.normalize_dictlike_arg("transform", obj, func)
+
+        results: dict[Hashable, DataFrame | Series] = {}
+        for name, how in func.items():
+            colg = obj._gotitem(name, ndim=1)
+            results[name] = colg.transform(how, 0, *args, **kwargs)
+        return concat(results, axis=1)
+
+    def transform_str_or_callable(self, func) -> DataFrame | Series:
+        """
+        Compute transform in the case of a string or callable func
+        """
+        obj = self.obj
+        args = self.args
+        kwargs = self.kwargs
+
+        if isinstance(func, str):
+            return self._apply_str(obj, func, *args, **kwargs)
+
+        if not args and not kwargs:
+            f = com.get_cython_func(func)
+            if f:
+                warn_alias_replacement(obj, func, f)
+                return getattr(obj, f)()
+
+        # Two possible ways to use a UDF - apply or call directly
+        try:
+            return obj.apply(func, args=args, **kwargs)
+        except Exception:
+            return func(obj, *args, **kwargs)
+
+    def agg_list_like(self) -> DataFrame | Series:
+        """
+        Compute aggregation in the case of a list-like argument.
+
+        Returns
+        -------
+        Result of aggregation.
+        """
+        return self.agg_or_apply_list_like(op_name="agg")
+
+    def compute_list_like(
+        self,
+        op_name: Literal["agg", "apply"],
+        selected_obj: Series | DataFrame,
+        kwargs: dict[str, Any],
+    ) -> tuple[list[Hashable] | Index, list[Any]]:
+        """
+        Compute agg/apply results for like-like input.
+
+        Parameters
+        ----------
+        op_name : {"agg", "apply"}
+            Operation being performed.
+        selected_obj : Series or DataFrame
+            Data to perform operation on.
+        kwargs : dict
+            Keyword arguments to pass to the functions.
+
+        Returns
+        -------
+        keys : list[Hashable] or Index
+            Index labels for result.
+        results : list
+            Data for result. When aggregating with a Series, this can contain any
+            Python objects.
+        """
+        func = cast(list[AggFuncTypeBase], self.func)
+        obj = self.obj
+
+        results = []
+        keys = []
+
+        # degenerate case
+        if selected_obj.ndim == 1:
+            for a in func:
+                colg = obj._gotitem(selected_obj.name, ndim=1, subset=selected_obj)
+                args = (
+                    [self.axis, *self.args]
+                    if include_axis(op_name, colg)
+                    else self.args
+                )
+                new_res = getattr(colg, op_name)(a, *args, **kwargs)
+                results.append(new_res)
+
+                # make sure we find a good name
+                name = com.get_callable_name(a) or a
+                keys.append(name)
+
+        else:
+            indices = []
+            for index, col in enumerate(selected_obj):
+                colg = obj._gotitem(col, ndim=1, subset=selected_obj.iloc[:, index])
+                args = (
+                    [self.axis, *self.args]
+                    if include_axis(op_name, colg)
+                    else self.args
+                )
+                new_res = getattr(colg, op_name)(func, *args, **kwargs)
+                results.append(new_res)
+                indices.append(index)
+            # error: Incompatible types in assignment (expression has type "Any |
+            # Index", variable has type "list[Any | Callable[..., Any] | str]")
+            keys = selected_obj.columns.take(indices)  # type: ignore[assignment]
+
+        return keys, results
+
+    def wrap_results_list_like(
+        self, keys: Iterable[Hashable], results: list[Series | DataFrame]
+    ):
+        from pandas.core.reshape.concat import concat
+
+        obj = self.obj
+
+        try:
+            return concat(results, keys=keys, axis=1, sort=False)
+        except TypeError as err:
+            # we are concatting non-NDFrame objects,
+            # e.g. a list of scalars
+            from pandas import Series
+
+            result = Series(results, index=keys, name=obj.name)
+            if is_nested_object(result):
+                raise ValueError(
+                    "cannot combine transform and aggregation operations"
+                ) from err
+            return result
+
+    def agg_dict_like(self) -> DataFrame | Series:
+        """
+        Compute aggregation in the case of a dict-like argument.
+
+        Returns
+        -------
+        Result of aggregation.
+        """
+        return self.agg_or_apply_dict_like(op_name="agg")
+
+    def compute_dict_like(
+        self,
+        op_name: Literal["agg", "apply"],
+        selected_obj: Series | DataFrame,
+        selection: Hashable | Sequence[Hashable],
+        kwargs: dict[str, Any],
+    ) -> tuple[list[Hashable], list[Any]]:
+        """
+        Compute agg/apply results for dict-like input.
+
+        Parameters
+        ----------
+        op_name : {"agg", "apply"}
+            Operation being performed.
+        selected_obj : Series or DataFrame
+            Data to perform operation on.
+        selection : hashable or sequence of hashables
+            Used by GroupBy, Window, and Resample if selection is applied to the object.
+        kwargs : dict
+            Keyword arguments to pass to the functions.
+
+        Returns
+        -------
+        keys : list[hashable]
+            Index labels for result.
+        results : list
+            Data for result. When aggregating with a Series, this can contain any
+            Python object.
+        """
+        from pandas.core.groupby.generic import (
+            DataFrameGroupBy,
+            SeriesGroupBy,
+        )
+
+        obj = self.obj
+        is_groupby = isinstance(obj, (DataFrameGroupBy, SeriesGroupBy))
+        func = cast(AggFuncTypeDict, self.func)
+        func = self.normalize_dictlike_arg(op_name, selected_obj, func)
+
+        is_non_unique_col = (
+            selected_obj.ndim == 2
+            and selected_obj.columns.nunique() < len(selected_obj.columns)
+        )
+
+        if selected_obj.ndim == 1:
+            # key only used for output
+            colg = obj._gotitem(selection, ndim=1)
+            results = [getattr(colg, op_name)(how, **kwargs) for _, how in func.items()]
+            keys = list(func.keys())
+        elif not is_groupby and is_non_unique_col:
+            # key used for column selection and output
+            # GH#51099
+            results = []
+            keys = []
+            for key, how in func.items():
+                indices = selected_obj.columns.get_indexer_for([key])
+                labels = selected_obj.columns.take(indices)
+                label_to_indices = defaultdict(list)
+                for index, label in zip(indices, labels):
+                    label_to_indices[label].append(index)
+
+                key_data = [
+                    getattr(selected_obj._ixs(indice, axis=1), op_name)(how, **kwargs)
+                    for label, indices in label_to_indices.items()
+                    for indice in indices
+                ]
+
+                keys += [key] * len(key_data)
+                results += key_data
+        else:
+            # key used for column selection and output
+            results = [
+                getattr(obj._gotitem(key, ndim=1), op_name)(how, **kwargs)
+                for key, how in func.items()
+            ]
+            keys = list(func.keys())
+
+        return keys, results
+
+    def wrap_results_dict_like(
+        self,
+        selected_obj: Series | DataFrame,
+        result_index: list[Hashable],
+        result_data: list,
+    ):
+        from pandas import Index
+        from pandas.core.reshape.concat import concat
+
+        obj = self.obj
+
+        # Avoid making two isinstance calls in all and any below
+        is_ndframe = [isinstance(r, ABCNDFrame) for r in result_data]
+
+        if all(is_ndframe):
+            results = dict(zip(result_index, result_data))
+            keys_to_use: Iterable[Hashable]
+            keys_to_use = [k for k in result_index if not results[k].empty]
+            # Have to check, if at least one DataFrame is not empty.
+            keys_to_use = keys_to_use if keys_to_use != [] else result_index
+            if selected_obj.ndim == 2:
+                # keys are columns, so we can preserve names
+                ktu = Index(keys_to_use)
+                ktu._set_names(selected_obj.columns.names)
+                keys_to_use = ktu
+
+            axis: AxisInt = 0 if isinstance(obj, ABCSeries) else 1
+            result = concat(
+                {k: results[k] for k in keys_to_use},
+                axis=axis,
+                keys=keys_to_use,
+            )
+        elif any(is_ndframe):
+            # There is a mix of NDFrames and scalars
+            raise ValueError(
+                "cannot perform both aggregation "
+                "and transformation operations "
+                "simultaneously"
+            )
+        else:
+            from pandas import Series
+
+            # we have a list of scalars
+            # GH 36212 use name only if obj is a series
+            if obj.ndim == 1:
+                obj = cast("Series", obj)
+                name = obj.name
+            else:
+                name = None
+
+            result = Series(result_data, index=result_index, name=name)
+
+        return result
+
+    def apply_str(self) -> DataFrame | Series:
+        """
+        Compute apply in case of a string.
+
+        Returns
+        -------
+        result: Series or DataFrame
+        """
+        # Caller is responsible for checking isinstance(self.f, str)
+        func = cast(str, self.func)
+
+        obj = self.obj
+
+        from pandas.core.groupby.generic import (
+            DataFrameGroupBy,
+            SeriesGroupBy,
+        )
+
+        # Support for `frame.transform('method')`
+        # Some methods (shift, etc.) require the axis argument, others
+        # don't, so inspect and insert if necessary.
+        method = getattr(obj, func, None)
+        if callable(method):
+            sig = inspect.getfullargspec(method)
+            arg_names = (*sig.args, *sig.kwonlyargs)
+            if self.axis != 0 and (
+                "axis" not in arg_names or func in ("corrwith", "skew")
+            ):
+                raise ValueError(f"Operation {func} does not support axis=1")
+            if "axis" in arg_names:
+                if isinstance(obj, (SeriesGroupBy, DataFrameGroupBy)):
+                    # Try to avoid FutureWarning for deprecated axis keyword;
+                    # If self.axis matches the axis we would get by not passing
+                    #  axis, we safely exclude the keyword.
+
+                    default_axis = 0
+                    if func in ["idxmax", "idxmin"]:
+                        # DataFrameGroupBy.idxmax, idxmin axis defaults to self.axis,
+                        # whereas other axis keywords default to 0
+                        default_axis = self.obj.axis
+
+                    if default_axis != self.axis:
+                        self.kwargs["axis"] = self.axis
+                else:
+                    self.kwargs["axis"] = self.axis
+        return self._apply_str(obj, func, *self.args, **self.kwargs)
+
+    def apply_list_or_dict_like(self) -> DataFrame | Series:
+        """
+        Compute apply in case of a list-like or dict-like.
+
+        Returns
+        -------
+        result: Series, DataFrame, or None
+            Result when self.func is a list-like or dict-like, None otherwise.
+        """
+
+        if self.engine == "numba":
+            raise NotImplementedError(
+                "The 'numba' engine doesn't support list-like/"
+                "dict likes of callables yet."
+            )
+
+        if self.axis == 1 and isinstance(self.obj, ABCDataFrame):
+            return self.obj.T.apply(self.func, 0, args=self.args, **self.kwargs).T
+
+        func = self.func
+        kwargs = self.kwargs
+
+        if is_dict_like(func):
+            result = self.agg_or_apply_dict_like(op_name="apply")
+        else:
+            result = self.agg_or_apply_list_like(op_name="apply")
+
+        result = reconstruct_and_relabel_result(result, func, **kwargs)
+
+        return result
+
+    def normalize_dictlike_arg(
+        self, how: str, obj: DataFrame | Series, func: AggFuncTypeDict
+    ) -> AggFuncTypeDict:
+        """
+        Handler for dict-like argument.
+
+        Ensures that necessary columns exist if obj is a DataFrame, and
+        that a nested renamer is not passed. Also normalizes to all lists
+        when values consists of a mix of list and non-lists.
+        """
+        assert how in ("apply", "agg", "transform")
+
+        # Can't use func.values(); wouldn't work for a Series
+        if (
+            how == "agg"
+            and isinstance(obj, ABCSeries)
+            and any(is_list_like(v) for _, v in func.items())
+        ) or (any(is_dict_like(v) for _, v in func.items())):
+            # GH 15931 - deprecation of renaming keys
+            raise SpecificationError("nested renamer is not supported")
+
+        if obj.ndim != 1:
+            # Check for missing columns on a frame
+            from pandas import Index
+
+            cols = Index(list(func.keys())).difference(obj.columns, sort=True)
+            if len(cols) > 0:
+                raise KeyError(f"Column(s) {list(cols)} do not exist")
+
+        aggregator_types = (list, tuple, dict)
+
+        # if we have a dict of any non-scalars
+        # eg. {'A' : ['mean']}, normalize all to
+        # be list-likes
+        # Cannot use func.values() because arg may be a Series
+        if any(isinstance(x, aggregator_types) for _, x in func.items()):
+            new_func: AggFuncTypeDict = {}
+            for k, v in func.items():
+                if not isinstance(v, aggregator_types):
+                    new_func[k] = [v]
+                else:
+                    new_func[k] = v
+            func = new_func
+        return func
+
+    def _apply_str(self, obj, func: str, *args, **kwargs):
+        """
+        if arg is a string, then try to operate on it:
+        - try to find a function (or attribute) on obj
+        - try to find a numpy function
+        - raise
+        """
+        assert isinstance(func, str)
+
+        if hasattr(obj, func):
+            f = getattr(obj, func)
+            if callable(f):
+                return f(*args, **kwargs)
+
+            # people may aggregate on a non-callable attribute
+            # but don't let them think they can pass args to it
+            assert len(args) == 0
+            assert len([kwarg for kwarg in kwargs if kwarg not in ["axis"]]) == 0
+            return f
+        elif hasattr(np, func) and hasattr(obj, "__array__"):
+            # in particular exclude Window
+            f = getattr(np, func)
+            return f(obj, *args, **kwargs)
+        else:
+            msg = f"'{func}' is not a valid function for '{type(obj).__name__}' object"
+            raise AttributeError(msg)
+
+
+class NDFrameApply(Apply):
+    """
+    Methods shared by FrameApply and SeriesApply but
+    not GroupByApply or ResamplerWindowApply
+    """
+
+    obj: DataFrame | Series
+
+    @property
+    def index(self) -> Index:
+        return self.obj.index
+
+    @property
+    def agg_axis(self) -> Index:
+        return self.obj._get_agg_axis(self.axis)
+
+    def agg_or_apply_list_like(
+        self, op_name: Literal["agg", "apply"]
+    ) -> DataFrame | Series:
+        obj = self.obj
+        kwargs = self.kwargs
+
+        if op_name == "apply":
+            if isinstance(self, FrameApply):
+                by_row = self.by_row
+
+            elif isinstance(self, SeriesApply):
+                by_row = "_compat" if self.by_row else False
+            else:
+                by_row = False
+            kwargs = {**kwargs, "by_row": by_row}
+
+        if getattr(obj, "axis", 0) == 1:
+            raise NotImplementedError("axis other than 0 is not supported")
+
+        keys, results = self.compute_list_like(op_name, obj, kwargs)
+        result = self.wrap_results_list_like(keys, results)
+        return result
+
+    def agg_or_apply_dict_like(
+        self, op_name: Literal["agg", "apply"]
+    ) -> DataFrame | Series:
+        assert op_name in ["agg", "apply"]
+        obj = self.obj
+
+        kwargs = {}
+        if op_name == "apply":
+            by_row = "_compat" if self.by_row else False
+            kwargs.update({"by_row": by_row})
+
+        if getattr(obj, "axis", 0) == 1:
+            raise NotImplementedError("axis other than 0 is not supported")
+
+        selection = None
+        result_index, result_data = self.compute_dict_like(
+            op_name, obj, selection, kwargs
+        )
+        result = self.wrap_results_dict_like(obj, result_index, result_data)
+        return result
+
+
+class FrameApply(NDFrameApply):
+    obj: DataFrame
+
+    def __init__(
+        self,
+        obj: AggObjType,
+        func: AggFuncType,
+        raw: bool,
+        result_type: str | None,
+        *,
+        by_row: Literal[False, "compat"] = False,
+        engine: str = "python",
+        engine_kwargs: dict[str, bool] | None = None,
+        args,
+        kwargs,
+    ) -> None:
+        if by_row is not False and by_row != "compat":
+            raise ValueError(f"by_row={by_row} not allowed")
+        super().__init__(
+            obj,
+            func,
+            raw,
+            result_type,
+            by_row=by_row,
+            engine=engine,
+            engine_kwargs=engine_kwargs,
+            args=args,
+            kwargs=kwargs,
+        )
+
+    # ---------------------------------------------------------------
+    # Abstract Methods
+
+    @property
+    @abc.abstractmethod
+    def result_index(self) -> Index:
+        pass
+
+    @property
+    @abc.abstractmethod
+    def result_columns(self) -> Index:
+        pass
+
+    @property
+    @abc.abstractmethod
+    def series_generator(self) -> Generator[Series, None, None]:
+        pass
+
+    @staticmethod
+    @functools.cache
+    @abc.abstractmethod
+    def generate_numba_apply_func(
+        func, nogil=True, nopython=True, parallel=False
+    ) -> Callable[[npt.NDArray, Index, Index], dict[int, Any]]:
+        pass
+
+    @abc.abstractmethod
+    def apply_with_numba(self):
+        pass
+
+    def validate_values_for_numba(self):
+        # Validate column dtyps all OK
+        for colname, dtype in self.obj.dtypes.items():
+            if not is_numeric_dtype(dtype):
+                raise ValueError(
+                    f"Column {colname} must have a numeric dtype. "
+                    f"Found '{dtype}' instead"
+                )
+            if is_extension_array_dtype(dtype):
+                raise ValueError(
+                    f"Column {colname} is backed by an extension array, "
+                    f"which is not supported by the numba engine."
+                )
+
+    @abc.abstractmethod
+    def wrap_results_for_axis(
+        self, results: ResType, res_index: Index
+    ) -> DataFrame | Series:
+        pass
+
+    # ---------------------------------------------------------------
+
+    @property
+    def res_columns(self) -> Index:
+        return self.result_columns
+
+    @property
+    def columns(self) -> Index:
+        return self.obj.columns
+
+    @cache_readonly
+    def values(self):
+        return self.obj.values
+
+    def apply(self) -> DataFrame | Series:
+        """compute the results"""
+
+        # dispatch to handle list-like or dict-like
+        if is_list_like(self.func):
+            if self.engine == "numba":
+                raise NotImplementedError(
+                    "the 'numba' engine doesn't support lists of callables yet"
+                )
+            return self.apply_list_or_dict_like()
+
+        # all empty
+        if len(self.columns) == 0 and len(self.index) == 0:
+            return self.apply_empty_result()
+
+        # string dispatch
+        if isinstance(self.func, str):
+            if self.engine == "numba":
+                raise NotImplementedError(
+                    "the 'numba' engine doesn't support using "
+                    "a string as the callable function"
+                )
+            return self.apply_str()
+
+        # ufunc
+        elif isinstance(self.func, np.ufunc):
+            if self.engine == "numba":
+                raise NotImplementedError(
+                    "the 'numba' engine doesn't support "
+                    "using a numpy ufunc as the callable function"
+                )
+            with np.errstate(all="ignore"):
+                results = self.obj._mgr.apply("apply", func=self.func)
+            # _constructor will retain self.index and self.columns
+            return self.obj._constructor_from_mgr(results, axes=results.axes)
+
+        # broadcasting
+        if self.result_type == "broadcast":
+            if self.engine == "numba":
+                raise NotImplementedError(
+                    "the 'numba' engine doesn't support result_type='broadcast'"
+                )
+            return self.apply_broadcast(self.obj)
+
+        # one axis empty
+        elif not all(self.obj.shape):
+            return self.apply_empty_result()
+
+        # raw
+        elif self.raw:
+            return self.apply_raw(engine=self.engine, engine_kwargs=self.engine_kwargs)
+
+        return self.apply_standard()
+
+    def agg(self):
+        obj = self.obj
+        axis = self.axis
+
+        # TODO: Avoid having to change state
+        self.obj = self.obj if self.axis == 0 else self.obj.T
+        self.axis = 0
+
+        result = None
+        try:
+            result = super().agg()
+        finally:
+            self.obj = obj
+            self.axis = axis
+
+        if axis == 1:
+            result = result.T if result is not None else result
+
+        if result is None:
+            result = self.obj.apply(self.func, axis, args=self.args, **self.kwargs)
+
+        return result
+
+    def apply_empty_result(self):
+        """
+        we have an empty result; at least 1 axis is 0
+
+        we will try to apply the function to an empty
+        series in order to see if this is a reduction function
+        """
+        assert callable(self.func)
+
+        # we are not asked to reduce or infer reduction
+        # so just return a copy of the existing object
+        if self.result_type not in ["reduce", None]:
+            return self.obj.copy()
+
+        # we may need to infer
+        should_reduce = self.result_type == "reduce"
+
+        from pandas import Series
+
+        if not should_reduce:
+            try:
+                if self.axis == 0:
+                    r = self.func(
+                        Series([], dtype=np.float64), *self.args, **self.kwargs
+                    )
+                else:
+                    r = self.func(
+                        Series(index=self.columns, dtype=np.float64),
+                        *self.args,
+                        **self.kwargs,
+                    )
+            except Exception:
+                pass
+            else:
+                should_reduce = not isinstance(r, Series)
+
+        if should_reduce:
+            if len(self.agg_axis):
+                r = self.func(Series([], dtype=np.float64), *self.args, **self.kwargs)
+            else:
+                r = np.nan
+
+            return self.obj._constructor_sliced(r, index=self.agg_axis)
+        else:
+            return self.obj.copy()
+
+    def apply_raw(self, engine="python", engine_kwargs=None):
+        """apply to the values as a numpy array"""
+
+        def wrap_function(func):
+            """
+            Wrap user supplied function to work around numpy issue.
+
+            see https://github.com/numpy/numpy/issues/8352
+            """
+
+            def wrapper(*args, **kwargs):
+                result = func(*args, **kwargs)
+                if isinstance(result, str):
+                    result = np.array(result, dtype=object)
+                return result
+
+            return wrapper
+
+        if engine == "numba":
+            engine_kwargs = {} if engine_kwargs is None else engine_kwargs
+
+            # error: Argument 1 to "__call__" of "_lru_cache_wrapper" has
+            # incompatible type "Callable[..., Any] | str | list[Callable
+            # [..., Any] | str] | dict[Hashable,Callable[..., Any] | str |
+            # list[Callable[..., Any] | str]]"; expected "Hashable"
+            nb_looper = generate_apply_looper(
+                self.func, **engine_kwargs  # type: ignore[arg-type]
+            )
+            result = nb_looper(self.values, self.axis)
+            # If we made the result 2-D, squeeze it back to 1-D
+            result = np.squeeze(result)
+        else:
+            result = np.apply_along_axis(
+                wrap_function(self.func),
+                self.axis,
+                self.values,
+                *self.args,
+                **self.kwargs,
+            )
+
+        # TODO: mixed type case
+        if result.ndim == 2:
+            return self.obj._constructor(result, index=self.index, columns=self.columns)
+        else:
+            return self.obj._constructor_sliced(result, index=self.agg_axis)
+
+    def apply_broadcast(self, target: DataFrame) -> DataFrame:
+        assert callable(self.func)
+
+        result_values = np.empty_like(target.values)
+
+        # axis which we want to compare compliance
+        result_compare = target.shape[0]
+
+        for i, col in enumerate(target.columns):
+            res = self.func(target[col], *self.args, **self.kwargs)
+            ares = np.asarray(res).ndim
+
+            # must be a scalar or 1d
+            if ares > 1:
+                raise ValueError("too many dims to broadcast")
+            if ares == 1:
+                # must match return dim
+                if result_compare != len(res):
+                    raise ValueError("cannot broadcast result")
+
+            result_values[:, i] = res
+
+        # we *always* preserve the original index / columns
+        result = self.obj._constructor(
+            result_values, index=target.index, columns=target.columns
+        )
+        return result
+
+    def apply_standard(self):
+        if self.engine == "python":
+            results, res_index = self.apply_series_generator()
+        else:
+            results, res_index = self.apply_series_numba()
+
+        # wrap results
+        return self.wrap_results(results, res_index)
+
+    def apply_series_generator(self) -> tuple[ResType, Index]:
+        assert callable(self.func)
+
+        series_gen = self.series_generator
+        res_index = self.result_index
+
+        results = {}
+
+        with option_context("mode.chained_assignment", None):
+            for i, v in enumerate(series_gen):
+                # ignore SettingWithCopy here in case the user mutates
+                results[i] = self.func(v, *self.args, **self.kwargs)
+                if isinstance(results[i], ABCSeries):
+                    # If we have a view on v, we need to make a copy because
+                    #  series_generator will swap out the underlying data
+                    results[i] = results[i].copy(deep=False)
+
+        return results, res_index
+
+    def apply_series_numba(self):
+        if self.engine_kwargs.get("parallel", False):
+            raise NotImplementedError(
+                "Parallel apply is not supported when raw=False and engine='numba'"
+            )
+        if not self.obj.index.is_unique or not self.columns.is_unique:
+            raise NotImplementedError(
+                "The index/columns must be unique when raw=False and engine='numba'"
+            )
+        self.validate_values_for_numba()
+        results = self.apply_with_numba()
+        return results, self.result_index
+
+    def wrap_results(self, results: ResType, res_index: Index) -> DataFrame | Series:
+        from pandas import Series
+
+        # see if we can infer the results
+        if len(results) > 0 and 0 in results and is_sequence(results[0]):
+            return self.wrap_results_for_axis(results, res_index)
+
+        # dict of scalars
+
+        # the default dtype of an empty Series is `object`, but this
+        # code can be hit by df.mean() where the result should have dtype
+        # float64 even if it's an empty Series.
+        constructor_sliced = self.obj._constructor_sliced
+        if len(results) == 0 and constructor_sliced is Series:
+            result = constructor_sliced(results, dtype=np.float64)
+        else:
+            result = constructor_sliced(results)
+        result.index = res_index
+
+        return result
+
+    def apply_str(self) -> DataFrame | Series:
+        # Caller is responsible for checking isinstance(self.func, str)
+        # TODO: GH#39993 - Avoid special-casing by replacing with lambda
+        if self.func == "size":
+            # Special-cased because DataFrame.size returns a single scalar
+            obj = self.obj
+            value = obj.shape[self.axis]
+            return obj._constructor_sliced(value, index=self.agg_axis)
+        return super().apply_str()
+
+
+class FrameRowApply(FrameApply):
+    axis: AxisInt = 0
+
+    @property
+    def series_generator(self) -> Generator[Series, None, None]:
+        return (self.obj._ixs(i, axis=1) for i in range(len(self.columns)))
+
+    @staticmethod
+    @functools.cache
+    def generate_numba_apply_func(
+        func, nogil=True, nopython=True, parallel=False
+    ) -> Callable[[npt.NDArray, Index, Index], dict[int, Any]]:
+        numba = import_optional_dependency("numba")
+        from pandas import Series
+
+        # Import helper from extensions to cast string object -> np strings
+        # Note: This also has the side effect of loading our numba extensions
+        from pandas.core._numba.extensions import maybe_cast_str
+
+        jitted_udf = numba.extending.register_jitable(func)
+
+        # Currently the parallel argument doesn't get passed through here
+        # (it's disabled) since the dicts in numba aren't thread-safe.
+        @numba.jit(nogil=nogil, nopython=nopython, parallel=parallel)
+        def numba_func(values, col_names, df_index):
+            results = {}
+            for j in range(values.shape[1]):
+                # Create the series
+                ser = Series(
+                    values[:, j], index=df_index, name=maybe_cast_str(col_names[j])
+                )
+                results[j] = jitted_udf(ser)
+            return results
+
+        return numba_func
+
+    def apply_with_numba(self) -> dict[int, Any]:
+        nb_func = self.generate_numba_apply_func(
+            cast(Callable, self.func), **self.engine_kwargs
+        )
+        from pandas.core._numba.extensions import set_numba_data
+
+        index = self.obj.index
+        if index.dtype == "string":
+            index = index.astype(object)
+
+        columns = self.obj.columns
+        if columns.dtype == "string":
+            columns = columns.astype(object)
+
+        # Convert from numba dict to regular dict
+        # Our isinstance checks in the df constructor don't pass for numbas typed dict
+        with set_numba_data(index) as index, set_numba_data(columns) as columns:
+            res = dict(nb_func(self.values, columns, index))
+        return res
+
+    @property
+    def result_index(self) -> Index:
+        return self.columns
+
+    @property
+    def result_columns(self) -> Index:
+        return self.index
+
+    def wrap_results_for_axis(
+        self, results: ResType, res_index: Index
+    ) -> DataFrame | Series:
+        """return the results for the rows"""
+
+        if self.result_type == "reduce":
+            # e.g. test_apply_dict GH#8735
+            res = self.obj._constructor_sliced(results)
+            res.index = res_index
+            return res
+
+        elif self.result_type is None and all(
+            isinstance(x, dict) for x in results.values()
+        ):
+            # Our operation was a to_dict op e.g.
+            #  test_apply_dict GH#8735, test_apply_reduce_to_dict GH#25196 #37544
+            res = self.obj._constructor_sliced(results)
+            res.index = res_index
+            return res
+
+        try:
+            result = self.obj._constructor(data=results)
+        except ValueError as err:
+            if "All arrays must be of the same length" in str(err):
+                # e.g. result = [[2, 3], [1.5], ['foo', 'bar']]
+                #  see test_agg_listlike_result GH#29587
+                res = self.obj._constructor_sliced(results)
+                res.index = res_index
+                return res
+            else:
+                raise
+
+        if not isinstance(results[0], ABCSeries):
+            if len(result.index) == len(self.res_columns):
+                result.index = self.res_columns
+
+        if len(result.columns) == len(res_index):
+            result.columns = res_index
+
+        return result
+
+
+class FrameColumnApply(FrameApply):
+    axis: AxisInt = 1
+
+    def apply_broadcast(self, target: DataFrame) -> DataFrame:
+        result = super().apply_broadcast(target.T)
+        return result.T
+
+    @property
+    def series_generator(self) -> Generator[Series, None, None]:
+        values = self.values
+        values = ensure_wrapped_if_datetimelike(values)
+        assert len(values) > 0
+
+        # We create one Series object, and will swap out the data inside
+        #  of it.  Kids: don't do this at home.
+        ser = self.obj._ixs(0, axis=0)
+        mgr = ser._mgr
+
+        is_view = mgr.blocks[0].refs.has_reference()  # type: ignore[union-attr]
+
+        if isinstance(ser.dtype, ExtensionDtype):
+            # values will be incorrect for this block
+            # TODO(EA2D): special case would be unnecessary with 2D EAs
+            obj = self.obj
+            for i in range(len(obj)):
+                yield obj._ixs(i, axis=0)
+
+        else:
+            for arr, name in zip(values, self.index):
+                # GH#35462 re-pin mgr in case setitem changed it
+                ser._mgr = mgr
+                mgr.set_values(arr)
+                object.__setattr__(ser, "_name", name)
+                if not is_view:
+                    # In apply_series_generator we store the a shallow copy of the
+                    # result, which potentially increases the ref count of this reused
+                    # `ser` object (depending on the result of the applied function)
+                    # -> if that happened and `ser` is already a copy, then we reset
+                    # the refs here to avoid triggering a unnecessary CoW inside the
+                    # applied function (https://github.com/pandas-dev/pandas/pull/56212)
+                    mgr.blocks[0].refs = BlockValuesRefs(mgr.blocks[0])  # type: ignore[union-attr]
+                yield ser
+
+    @staticmethod
+    @functools.cache
+    def generate_numba_apply_func(
+        func, nogil=True, nopython=True, parallel=False
+    ) -> Callable[[npt.NDArray, Index, Index], dict[int, Any]]:
+        numba = import_optional_dependency("numba")
+        from pandas import Series
+        from pandas.core._numba.extensions import maybe_cast_str
+
+        jitted_udf = numba.extending.register_jitable(func)
+
+        @numba.jit(nogil=nogil, nopython=nopython, parallel=parallel)
+        def numba_func(values, col_names_index, index):
+            results = {}
+            # Currently the parallel argument doesn't get passed through here
+            # (it's disabled) since the dicts in numba aren't thread-safe.
+            for i in range(values.shape[0]):
+                # Create the series
+                # TODO: values corrupted without the copy
+                ser = Series(
+                    values[i].copy(),
+                    index=col_names_index,
+                    name=maybe_cast_str(index[i]),
+                )
+                results[i] = jitted_udf(ser)
+
+            return results
+
+        return numba_func
+
+    def apply_with_numba(self) -> dict[int, Any]:
+        nb_func = self.generate_numba_apply_func(
+            cast(Callable, self.func), **self.engine_kwargs
+        )
+
+        from pandas.core._numba.extensions import set_numba_data
+
+        # Convert from numba dict to regular dict
+        # Our isinstance checks in the df constructor don't pass for numbas typed dict
+        with set_numba_data(self.obj.index) as index, set_numba_data(
+            self.columns
+        ) as columns:
+            res = dict(nb_func(self.values, columns, index))
+
+        return res
+
+    @property
+    def result_index(self) -> Index:
+        return self.index
+
+    @property
+    def result_columns(self) -> Index:
+        return self.columns
+
+    def wrap_results_for_axis(
+        self, results: ResType, res_index: Index
+    ) -> DataFrame | Series:
+        """return the results for the columns"""
+        result: DataFrame | Series
+
+        # we have requested to expand
+        if self.result_type == "expand":
+            result = self.infer_to_same_shape(results, res_index)
+
+        # we have a non-series and don't want inference
+        elif not isinstance(results[0], ABCSeries):
+            result = self.obj._constructor_sliced(results)
+            result.index = res_index
+
+        # we may want to infer results
+        else:
+            result = self.infer_to_same_shape(results, res_index)
+
+        return result
+
+    def infer_to_same_shape(self, results: ResType, res_index: Index) -> DataFrame:
+        """infer the results to the same shape as the input object"""
+        result = self.obj._constructor(data=results)
+        result = result.T
+
+        # set the index
+        result.index = res_index
+
+        # infer dtypes
+        result = result.infer_objects(copy=False)
+
+        return result
+
+
+class SeriesApply(NDFrameApply):
+    obj: Series
+    axis: AxisInt = 0
+    by_row: Literal[False, "compat", "_compat"]  # only relevant for apply()
+
+    def __init__(
+        self,
+        obj: Series,
+        func: AggFuncType,
+        *,
+        convert_dtype: bool | lib.NoDefault = lib.no_default,
+        by_row: Literal[False, "compat", "_compat"] = "compat",
+        args,
+        kwargs,
+    ) -> None:
+        if convert_dtype is lib.no_default:
+            convert_dtype = True
+        else:
+            warnings.warn(
+                "the convert_dtype parameter is deprecated and will be removed in a "
+                "future version.  Do ``ser.astype(object).apply()`` "
+                "instead if you want ``convert_dtype=False``.",
+                FutureWarning,
+                stacklevel=find_stack_level(),
+            )
+        self.convert_dtype = convert_dtype
+
+        super().__init__(
+            obj,
+            func,
+            raw=False,
+            result_type=None,
+            by_row=by_row,
+            args=args,
+            kwargs=kwargs,
+        )
+
+    def apply(self) -> DataFrame | Series:
+        obj = self.obj
+
+        if len(obj) == 0:
+            return self.apply_empty_result()
+
+        # dispatch to handle list-like or dict-like
+        if is_list_like(self.func):
+            return self.apply_list_or_dict_like()
+
+        if isinstance(self.func, str):
+            # if we are a string, try to dispatch
+            return self.apply_str()
+
+        if self.by_row == "_compat":
+            return self.apply_compat()
+
+        # self.func is Callable
+        return self.apply_standard()
+
+    def agg(self):
+        result = super().agg()
+        if result is None:
+            obj = self.obj
+            func = self.func
+            # string, list-like, and dict-like are entirely handled in super
+            assert callable(func)
+
+            # GH53325: The setup below is just to keep current behavior while emitting a
+            # deprecation message. In the future this will all be replaced with a simple
+            # `result = f(self.obj, *self.args, **self.kwargs)`.
+            try:
+                result = obj.apply(func, args=self.args, **self.kwargs)
+            except (ValueError, AttributeError, TypeError):
+                result = func(obj, *self.args, **self.kwargs)
+            else:
+                msg = (
+                    f"using {func} in {type(obj).__name__}.agg cannot aggregate and "
+                    f"has been deprecated. Use {type(obj).__name__}.transform to "
+                    f"keep behavior unchanged."
+                )
+                warnings.warn(msg, FutureWarning, stacklevel=find_stack_level())
+
+        return result
+
+    def apply_empty_result(self) -> Series:
+        obj = self.obj
+        return obj._constructor(dtype=obj.dtype, index=obj.index).__finalize__(
+            obj, method="apply"
+        )
+
+    def apply_compat(self):
+        """compat apply method for funcs in listlikes and dictlikes.
+
+         Used for each callable when giving listlikes and dictlikes of callables to
+         apply. Needed for compatibility with Pandas < v2.1.
+
+        .. versionadded:: 2.1.0
+        """
+        obj = self.obj
+        func = self.func
+
+        if callable(func):
+            f = com.get_cython_func(func)
+            if f and not self.args and not self.kwargs:
+                return obj.apply(func, by_row=False)
+
+        try:
+            result = obj.apply(func, by_row="compat")
+        except (ValueError, AttributeError, TypeError):
+            result = obj.apply(func, by_row=False)
+        return result
+
+    def apply_standard(self) -> DataFrame | Series:
+        # caller is responsible for ensuring that f is Callable
+        func = cast(Callable, self.func)
+        obj = self.obj
+
+        if isinstance(func, np.ufunc):
+            with np.errstate(all="ignore"):
+                return func(obj, *self.args, **self.kwargs)
+        elif not self.by_row:
+            return func(obj, *self.args, **self.kwargs)
+
+        if self.args or self.kwargs:
+            # _map_values does not support args/kwargs
+            def curried(x):
+                return func(x, *self.args, **self.kwargs)
+
+        else:
+            curried = func
+
+        # row-wise access
+        # apply doesn't have a `na_action` keyword and for backward compat reasons
+        # we need to give `na_action="ignore"` for categorical data.
+        # TODO: remove the `na_action="ignore"` when that default has been changed in
+        #  Categorical (GH51645).
+        action = "ignore" if isinstance(obj.dtype, CategoricalDtype) else None
+        mapped = obj._map_values(
+            mapper=curried, na_action=action, convert=self.convert_dtype
+        )
+
+        if len(mapped) and isinstance(mapped[0], ABCSeries):
+            # GH#43986 Need to do list(mapped) in order to get treated as nested
+            #  See also GH#25959 regarding EA support
+            return obj._constructor_expanddim(list(mapped), index=obj.index)
+        else:
+            return obj._constructor(mapped, index=obj.index).__finalize__(
+                obj, method="apply"
+            )
+
+
+class GroupByApply(Apply):
+    obj: GroupBy | Resampler | BaseWindow
+
+    def __init__(
+        self,
+        obj: GroupBy[NDFrameT],
+        func: AggFuncType,
+        *,
+        args,
+        kwargs,
+    ) -> None:
+        kwargs = kwargs.copy()
+        self.axis = obj.obj._get_axis_number(kwargs.get("axis", 0))
+        super().__init__(
+            obj,
+            func,
+            raw=False,
+            result_type=None,
+            args=args,
+            kwargs=kwargs,
+        )
+
+    def apply(self):
+        raise NotImplementedError
+
+    def transform(self):
+        raise NotImplementedError
+
+    def agg_or_apply_list_like(
+        self, op_name: Literal["agg", "apply"]
+    ) -> DataFrame | Series:
+        obj = self.obj
+        kwargs = self.kwargs
+        if op_name == "apply":
+            kwargs = {**kwargs, "by_row": False}
+
+        if getattr(obj, "axis", 0) == 1:
+            raise NotImplementedError("axis other than 0 is not supported")
+
+        if obj._selected_obj.ndim == 1:
+            # For SeriesGroupBy this matches _obj_with_exclusions
+            selected_obj = obj._selected_obj
+        else:
+            selected_obj = obj._obj_with_exclusions
+
+        # Only set as_index=True on groupby objects, not Window or Resample
+        # that inherit from this class.
+        with com.temp_setattr(
+            obj, "as_index", True, condition=hasattr(obj, "as_index")
+        ):
+            keys, results = self.compute_list_like(op_name, selected_obj, kwargs)
+        result = self.wrap_results_list_like(keys, results)
+        return result
+
+    def agg_or_apply_dict_like(
+        self, op_name: Literal["agg", "apply"]
+    ) -> DataFrame | Series:
+        from pandas.core.groupby.generic import (
+            DataFrameGroupBy,
+            SeriesGroupBy,
+        )
+
+        assert op_name in ["agg", "apply"]
+
+        obj = self.obj
+        kwargs = {}
+        if op_name == "apply":
+            by_row = "_compat" if self.by_row else False
+            kwargs.update({"by_row": by_row})
+
+        if getattr(obj, "axis", 0) == 1:
+            raise NotImplementedError("axis other than 0 is not supported")
+
+        selected_obj = obj._selected_obj
+        selection = obj._selection
+
+        is_groupby = isinstance(obj, (DataFrameGroupBy, SeriesGroupBy))
+
+        # Numba Groupby engine/engine-kwargs passthrough
+        if is_groupby:
+            engine = self.kwargs.get("engine", None)
+            engine_kwargs = self.kwargs.get("engine_kwargs", None)
+            kwargs.update({"engine": engine, "engine_kwargs": engine_kwargs})
+
+        with com.temp_setattr(
+            obj, "as_index", True, condition=hasattr(obj, "as_index")
+        ):
+            result_index, result_data = self.compute_dict_like(
+                op_name, selected_obj, selection, kwargs
+            )
+        result = self.wrap_results_dict_like(selected_obj, result_index, result_data)
+        return result
+
+
+class ResamplerWindowApply(GroupByApply):
+    axis: AxisInt = 0
+    obj: Resampler | BaseWindow
+
+    def __init__(
+        self,
+        obj: Resampler | BaseWindow,
+        func: AggFuncType,
+        *,
+        args,
+        kwargs,
+    ) -> None:
+        super(GroupByApply, self).__init__(
+            obj,
+            func,
+            raw=False,
+            result_type=None,
+            args=args,
+            kwargs=kwargs,
+        )
+
+    def apply(self):
+        raise NotImplementedError
+
+    def transform(self):
+        raise NotImplementedError
+
+
+def reconstruct_func(
+    func: AggFuncType | None, **kwargs
+) -> tuple[bool, AggFuncType, tuple[str, ...] | None, npt.NDArray[np.intp] | None]:
+    """
+    This is the internal function to reconstruct func given if there is relabeling
+    or not and also normalize the keyword to get new order of columns.
+
+    If named aggregation is applied, `func` will be None, and kwargs contains the
+    column and aggregation function information to be parsed;
+    If named aggregation is not applied, `func` is either string (e.g. 'min') or
+    Callable, or list of them (e.g. ['min', np.max]), or the dictionary of column name
+    and str/Callable/list of them (e.g. {'A': 'min'}, or {'A': [np.min, lambda x: x]})
+
+    If relabeling is True, will return relabeling, reconstructed func, column
+    names, and the reconstructed order of columns.
+    If relabeling is False, the columns and order will be None.
+
+    Parameters
+    ----------
+    func: agg function (e.g. 'min' or Callable) or list of agg functions
+        (e.g. ['min', np.max]) or dictionary (e.g. {'A': ['min', np.max]}).
+    **kwargs: dict, kwargs used in is_multi_agg_with_relabel and
+        normalize_keyword_aggregation function for relabelling
+
+    Returns
+    -------
+    relabelling: bool, if there is relabelling or not
+    func: normalized and mangled func
+    columns: tuple of column names
+    order: array of columns indices
+
+    Examples
+    --------
+    >>> reconstruct_func(None, **{"foo": ("col", "min")})
+    (True, defaultdict(<class 'list'>, {'col': ['min']}), ('foo',), array([0]))
+
+    >>> reconstruct_func("min")
+    (False, 'min', None, None)
+    """
+    relabeling = func is None and is_multi_agg_with_relabel(**kwargs)
+    columns: tuple[str, ...] | None = None
+    order: npt.NDArray[np.intp] | None = None
+
+    if not relabeling:
+        if isinstance(func, list) and len(func) > len(set(func)):
+            # GH 28426 will raise error if duplicated function names are used and
+            # there is no reassigned name
+            raise SpecificationError(
+                "Function names must be unique if there is no new column names "
+                "assigned"
+            )
+        if func is None:
+            # nicer error message
+            raise TypeError("Must provide 'func' or tuples of '(column, aggfunc).")
+
+    if relabeling:
+        # error: Incompatible types in assignment (expression has type
+        # "MutableMapping[Hashable, list[Callable[..., Any] | str]]", variable has type
+        # "Callable[..., Any] | str | list[Callable[..., Any] | str] |
+        # MutableMapping[Hashable, Callable[..., Any] | str | list[Callable[..., Any] |
+        # str]] | None")
+        func, columns, order = normalize_keyword_aggregation(  # type: ignore[assignment]
+            kwargs
+        )
+    assert func is not None
+
+    return relabeling, func, columns, order
+
+
+def is_multi_agg_with_relabel(**kwargs) -> bool:
+    """
+    Check whether kwargs passed to .agg look like multi-agg with relabeling.
+
+    Parameters
+    ----------
+    **kwargs : dict
+
+    Returns
+    -------
+    bool
+
+    Examples
+    --------
+    >>> is_multi_agg_with_relabel(a="max")
+    False
+    >>> is_multi_agg_with_relabel(a_max=("a", "max"), a_min=("a", "min"))
+    True
+    >>> is_multi_agg_with_relabel()
+    False
+    """
+    return all(isinstance(v, tuple) and len(v) == 2 for v in kwargs.values()) and (
+        len(kwargs) > 0
+    )
+
+
+def normalize_keyword_aggregation(
+    kwargs: dict,
+) -> tuple[
+    MutableMapping[Hashable, list[AggFuncTypeBase]],
+    tuple[str, ...],
+    npt.NDArray[np.intp],
+]:
+    """
+    Normalize user-provided "named aggregation" kwargs.
+    Transforms from the new ``Mapping[str, NamedAgg]`` style kwargs
+    to the old Dict[str, List[scalar]]].
+
+    Parameters
+    ----------
+    kwargs : dict
+
+    Returns
+    -------
+    aggspec : dict
+        The transformed kwargs.
+    columns : tuple[str, ...]
+        The user-provided keys.
+    col_idx_order : List[int]
+        List of columns indices.
+
+    Examples
+    --------
+    >>> normalize_keyword_aggregation({"output": ("input", "sum")})
+    (defaultdict(<class 'list'>, {'input': ['sum']}), ('output',), array([0]))
+    """
+    from pandas.core.indexes.base import Index
+
+    # Normalize the aggregation functions as Mapping[column, List[func]],
+    # process normally, then fixup the names.
+    # TODO: aggspec type: typing.Dict[str, List[AggScalar]]
+    aggspec = defaultdict(list)
+    order = []
+    columns, pairs = list(zip(*kwargs.items()))
+
+    for column, aggfunc in pairs:
+        aggspec[column].append(aggfunc)
+        order.append((column, com.get_callable_name(aggfunc) or aggfunc))
+
+    # uniquify aggfunc name if duplicated in order list
+    uniquified_order = _make_unique_kwarg_list(order)
+
+    # GH 25719, due to aggspec will change the order of assigned columns in aggregation
+    # uniquified_aggspec will store uniquified order list and will compare it with order
+    # based on index
+    aggspec_order = [
+        (column, com.get_callable_name(aggfunc) or aggfunc)
+        for column, aggfuncs in aggspec.items()
+        for aggfunc in aggfuncs
+    ]
+    uniquified_aggspec = _make_unique_kwarg_list(aggspec_order)
+
+    # get the new index of columns by comparison
+    col_idx_order = Index(uniquified_aggspec).get_indexer(uniquified_order)
+    return aggspec, columns, col_idx_order
+
+
+def _make_unique_kwarg_list(
+    seq: Sequence[tuple[Any, Any]]
+) -> Sequence[tuple[Any, Any]]:
+    """
+    Uniquify aggfunc name of the pairs in the order list
+
+    Examples:
+    --------
+    >>> kwarg_list = [('a', '<lambda>'), ('a', '<lambda>'), ('b', '<lambda>')]
+    >>> _make_unique_kwarg_list(kwarg_list)
+    [('a', '<lambda>_0'), ('a', '<lambda>_1'), ('b', '<lambda>')]
+    """
+    return [
+        (pair[0], f"{pair[1]}_{seq[:i].count(pair)}") if seq.count(pair) > 1 else pair
+        for i, pair in enumerate(seq)
+    ]
+
+
+def relabel_result(
+    result: DataFrame | Series,
+    func: dict[str, list[Callable | str]],
+    columns: Iterable[Hashable],
+    order: Iterable[int],
+) -> dict[Hashable, Series]:
+    """
+    Internal function to reorder result if relabelling is True for
+    dataframe.agg, and return the reordered result in dict.
+
+    Parameters:
+    ----------
+    result: Result from aggregation
+    func: Dict of (column name, funcs)
+    columns: New columns name for relabelling
+    order: New order for relabelling
+
+    Examples
+    --------
+    >>> from pandas.core.apply import relabel_result
+    >>> result = pd.DataFrame(
+    ...     {"A": [np.nan, 2, np.nan], "C": [6, np.nan, np.nan], "B": [np.nan, 4, 2.5]},
+    ...     index=["max", "mean", "min"]
+    ... )
+    >>> funcs = {"A": ["max"], "C": ["max"], "B": ["mean", "min"]}
+    >>> columns = ("foo", "aab", "bar", "dat")
+    >>> order = [0, 1, 2, 3]
+    >>> result_in_dict = relabel_result(result, funcs, columns, order)
+    >>> pd.DataFrame(result_in_dict, index=columns)
+           A    C    B
+    foo  2.0  NaN  NaN
+    aab  NaN  6.0  NaN
+    bar  NaN  NaN  4.0
+    dat  NaN  NaN  2.5
+    """
+    from pandas.core.indexes.base import Index
+
+    reordered_indexes = [
+        pair[0] for pair in sorted(zip(columns, order), key=lambda t: t[1])
+    ]
+    reordered_result_in_dict: dict[Hashable, Series] = {}
+    idx = 0
+
+    reorder_mask = not isinstance(result, ABCSeries) and len(result.columns) > 1
+    for col, fun in func.items():
+        s = result[col].dropna()
+
+        # In the `_aggregate`, the callable names are obtained and used in `result`, and
+        # these names are ordered alphabetically. e.g.
+        #           C2   C1
+        # <lambda>   1  NaN
+        # amax     NaN  4.0
+        # max      NaN  4.0
+        # sum     18.0  6.0
+        # Therefore, the order of functions for each column could be shuffled
+        # accordingly so need to get the callable name if it is not parsed names, and
+        # reorder the aggregated result for each column.
+        # e.g. if df.agg(c1=("C2", sum), c2=("C2", lambda x: min(x))), correct order is
+        # [sum, <lambda>], but in `result`, it will be [<lambda>, sum], and we need to
+        # reorder so that aggregated values map to their functions regarding the order.
+
+        # However there is only one column being used for aggregation, not need to
+        # reorder since the index is not sorted, and keep as is in `funcs`, e.g.
+        #         A
+        # min   1.0
+        # mean  1.5
+        # mean  1.5
+        if reorder_mask:
+            fun = [
+                com.get_callable_name(f) if not isinstance(f, str) else f for f in fun
+            ]
+            col_idx_order = Index(s.index).get_indexer(fun)
+            s = s.iloc[col_idx_order]
+
+        # assign the new user-provided "named aggregation" as index names, and reindex
+        # it based on the whole user-provided names.
+        s.index = reordered_indexes[idx : idx + len(fun)]
+        reordered_result_in_dict[col] = s.reindex(columns, copy=False)
+        idx = idx + len(fun)
+    return reordered_result_in_dict
+
+
+def reconstruct_and_relabel_result(result, func, **kwargs) -> DataFrame | Series:
+    from pandas import DataFrame
+
+    relabeling, func, columns, order = reconstruct_func(func, **kwargs)
+
+    if relabeling:
+        # This is to keep the order to columns occurrence unchanged, and also
+        # keep the order of new columns occurrence unchanged
+
+        # For the return values of reconstruct_func, if relabeling is
+        # False, columns and order will be None.
+        assert columns is not None
+        assert order is not None
+
+        result_in_dict = relabel_result(result, func, columns, order)
+        result = DataFrame(result_in_dict, index=columns)
+
+    return result
+
+
+# TODO: Can't use, because mypy doesn't like us setting __name__
+#   error: "partial[Any]" has no attribute "__name__"
+# the type is:
+#   typing.Sequence[Callable[..., ScalarResult]]
+#     -> typing.Sequence[Callable[..., ScalarResult]]:
+
+
+def _managle_lambda_list(aggfuncs: Sequence[Any]) -> Sequence[Any]:
+    """
+    Possibly mangle a list of aggfuncs.
+
+    Parameters
+    ----------
+    aggfuncs : Sequence
+
+    Returns
+    -------
+    mangled: list-like
+        A new AggSpec sequence, where lambdas have been converted
+        to have unique names.
+
+    Notes
+    -----
+    If just one aggfunc is passed, the name will not be mangled.
+    """
+    if len(aggfuncs) <= 1:
+        # don't mangle for .agg([lambda x: .])
+        return aggfuncs
+    i = 0
+    mangled_aggfuncs = []
+    for aggfunc in aggfuncs:
+        if com.get_callable_name(aggfunc) == "<lambda>":
+            aggfunc = partial(aggfunc)
+            aggfunc.__name__ = f"<lambda_{i}>"
+            i += 1
+        mangled_aggfuncs.append(aggfunc)
+
+    return mangled_aggfuncs
+
+
+def maybe_mangle_lambdas(agg_spec: Any) -> Any:
+    """
+    Make new lambdas with unique names.
+
+    Parameters
+    ----------
+    agg_spec : Any
+        An argument to GroupBy.agg.
+        Non-dict-like `agg_spec` are pass through as is.
+        For dict-like `agg_spec` a new spec is returned
+        with name-mangled lambdas.
+
+    Returns
+    -------
+    mangled : Any
+        Same type as the input.
+
+    Examples
+    --------
+    >>> maybe_mangle_lambdas('sum')
+    'sum'
+    >>> maybe_mangle_lambdas([lambda: 1, lambda: 2])  # doctest: +SKIP
+    [<function __main__.<lambda_0>,
+     <function pandas...._make_lambda.<locals>.f(*args, **kwargs)>]
+    """
+    is_dict = is_dict_like(agg_spec)
+    if not (is_dict or is_list_like(agg_spec)):
+        return agg_spec
+    mangled_aggspec = type(agg_spec)()  # dict or OrderedDict
+
+    if is_dict:
+        for key, aggfuncs in agg_spec.items():
+            if is_list_like(aggfuncs) and not is_dict_like(aggfuncs):
+                mangled_aggfuncs = _managle_lambda_list(aggfuncs)
+            else:
+                mangled_aggfuncs = aggfuncs
+
+            mangled_aggspec[key] = mangled_aggfuncs
+    else:
+        mangled_aggspec = _managle_lambda_list(agg_spec)
+
+    return mangled_aggspec
+
+
+def validate_func_kwargs(
+    kwargs: dict,
+) -> tuple[list[str], list[str | Callable[..., Any]]]:
+    """
+    Validates types of user-provided "named aggregation" kwargs.
+    `TypeError` is raised if aggfunc is not `str` or callable.
+
+    Parameters
+    ----------
+    kwargs : dict
+
+    Returns
+    -------
+    columns : List[str]
+        List of user-provided keys.
+    func : List[Union[str, callable[...,Any]]]
+        List of user-provided aggfuncs
+
+    Examples
+    --------
+    >>> validate_func_kwargs({'one': 'min', 'two': 'max'})
+    (['one', 'two'], ['min', 'max'])
+    """
+    tuple_given_message = "func is expected but received {} in **kwargs."
+    columns = list(kwargs)
+    func = []
+    for col_func in kwargs.values():
+        if not (isinstance(col_func, str) or callable(col_func)):
+            raise TypeError(tuple_given_message.format(type(col_func).__name__))
+        func.append(col_func)
+    if not columns:
+        no_arg_message = "Must provide 'func' or named aggregation **kwargs."
+        raise TypeError(no_arg_message)
+    return columns, func
+
+
+def include_axis(op_name: Literal["agg", "apply"], colg: Series | DataFrame) -> bool:
+    return isinstance(colg, ABCDataFrame) or (
+        isinstance(colg, ABCSeries) and op_name == "agg"
+    )
+
+
+def warn_alias_replacement(
+    obj: AggObjType,
+    func: Callable,
+    alias: str,
+) -> None:
+    if alias.startswith("np."):
+        full_alias = alias
+    else:
+        full_alias = f"{type(obj).__name__}.{alias}"
+        alias = f'"{alias}"'
+    warnings.warn(
+        f"The provided callable {func} is currently using "
+        f"{full_alias}. In a future version of pandas, "
+        f"the provided callable will be used directly. To keep current "
+        f"behavior pass the string {alias} instead.",
+        category=FutureWarning,
+        stacklevel=find_stack_level(),
+    )

lib/python3.12/site-packages/pandas/core/array_algos/__init__.py

@@ -0,0 +1,9 @@
+"""
+core.array_algos is for algorithms that operate on ndarray and ExtensionArray.
+These should:
+
+- Assume that any Index, Series, or DataFrame objects have already been unwrapped.
+- Assume that any list arguments have already been cast to ndarray/EA.
+- Not depend on Index, Series, or DataFrame, nor import any of these.
+- May dispatch to ExtensionArray methods, but should not import from core.arrays.
+"""

lib/python3.12/site-packages/pandas/core/array_algos/datetimelike_accumulations.py

@@ -0,0 +1,67 @@
+"""
+datetimelke_accumulations.py is for accumulations of datetimelike extension arrays
+"""
+
+from __future__ import annotations
+
+from typing import Callable
+
+import numpy as np
+
+from pandas._libs import iNaT
+
+from pandas.core.dtypes.missing import isna
+
+
+def _cum_func(
+    func: Callable,
+    values: np.ndarray,
+    *,
+    skipna: bool = True,
+):
+    """
+    Accumulations for 1D datetimelike arrays.
+
+    Parameters
+    ----------
+    func : np.cumsum, np.maximum.accumulate, np.minimum.accumulate
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation). Values is changed is modified inplace.
+    skipna : bool, default True
+        Whether to skip NA.
+    """
+    try:
+        fill_value = {
+            np.maximum.accumulate: np.iinfo(np.int64).min,
+            np.cumsum: 0,
+            np.minimum.accumulate: np.iinfo(np.int64).max,
+        }[func]
+    except KeyError:
+        raise ValueError(f"No accumulation for {func} implemented on BaseMaskedArray")
+
+    mask = isna(values)
+    y = values.view("i8")
+    y[mask] = fill_value
+
+    if not skipna:
+        mask = np.maximum.accumulate(mask)
+
+    result = func(y)
+    result[mask] = iNaT
+
+    if values.dtype.kind in "mM":
+        return result.view(values.dtype.base)
+    return result
+
+
+def cumsum(values: np.ndarray, *, skipna: bool = True) -> np.ndarray:
+    return _cum_func(np.cumsum, values, skipna=skipna)
+
+
+def cummin(values: np.ndarray, *, skipna: bool = True):
+    return _cum_func(np.minimum.accumulate, values, skipna=skipna)
+
+
+def cummax(values: np.ndarray, *, skipna: bool = True):
+    return _cum_func(np.maximum.accumulate, values, skipna=skipna)

lib/python3.12/site-packages/pandas/core/array_algos/masked_accumulations.py

@@ -0,0 +1,90 @@
+"""
+masked_accumulations.py is for accumulation algorithms using a mask-based approach
+for missing values.
+"""
+
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+)
+
+import numpy as np
+
+if TYPE_CHECKING:
+    from pandas._typing import npt
+
+
+def _cum_func(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+):
+    """
+    Accumulations for 1D masked array.
+
+    We will modify values in place to replace NAs with the appropriate fill value.
+
+    Parameters
+    ----------
+    func : np.cumsum, np.cumprod, np.maximum.accumulate, np.minimum.accumulate
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation).
+    mask : np.ndarray
+        Boolean numpy array (True values indicate missing values).
+    skipna : bool, default True
+        Whether to skip NA.
+    """
+    dtype_info: np.iinfo | np.finfo
+    if values.dtype.kind == "f":
+        dtype_info = np.finfo(values.dtype.type)
+    elif values.dtype.kind in "iu":
+        dtype_info = np.iinfo(values.dtype.type)
+    elif values.dtype.kind == "b":
+        # Max value of bool is 1, but since we are setting into a boolean
+        # array, 255 is fine as well. Min value has to be 0 when setting
+        # into the boolean array.
+        dtype_info = np.iinfo(np.uint8)
+    else:
+        raise NotImplementedError(
+            f"No masked accumulation defined for dtype {values.dtype.type}"
+        )
+    try:
+        fill_value = {
+            np.cumprod: 1,
+            np.maximum.accumulate: dtype_info.min,
+            np.cumsum: 0,
+            np.minimum.accumulate: dtype_info.max,
+        }[func]
+    except KeyError:
+        raise NotImplementedError(
+            f"No accumulation for {func} implemented on BaseMaskedArray"
+        )
+
+    values[mask] = fill_value
+
+    if not skipna:
+        mask = np.maximum.accumulate(mask)
+
+    values = func(values)
+    return values, mask
+
+
+def cumsum(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.cumsum, values, mask, skipna=skipna)
+
+
+def cumprod(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.cumprod, values, mask, skipna=skipna)
+
+
+def cummin(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.minimum.accumulate, values, mask, skipna=skipna)
+
+
+def cummax(values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True):
+    return _cum_func(np.maximum.accumulate, values, mask, skipna=skipna)

lib/python3.12/site-packages/pandas/core/array_algos/masked_reductions.py

@@ -0,0 +1,197 @@
+"""
+masked_reductions.py is for reduction algorithms using a mask-based approach
+for missing values.
+"""
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Callable,
+)
+import warnings
+
+import numpy as np
+
+from pandas._libs import missing as libmissing
+
+from pandas.core.nanops import check_below_min_count
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        AxisInt,
+        npt,
+    )
+
+
+def _reductions(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+    **kwargs,
+):
+    """
+    Sum, mean or product for 1D masked array.
+
+    Parameters
+    ----------
+    func : np.sum or np.prod
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation).
+    mask : np.ndarray[bool]
+        Boolean numpy array (True values indicate missing values).
+    skipna : bool, default True
+        Whether to skip NA.
+    min_count : int, default 0
+        The required number of valid values to perform the operation. If fewer than
+        ``min_count`` non-NA values are present the result will be NA.
+    axis : int, optional, default None
+    """
+    if not skipna:
+        if mask.any() or check_below_min_count(values.shape, None, min_count):
+            return libmissing.NA
+        else:
+            return func(values, axis=axis, **kwargs)
+    else:
+        if check_below_min_count(values.shape, mask, min_count) and (
+            axis is None or values.ndim == 1
+        ):
+            return libmissing.NA
+
+        return func(values, where=~mask, axis=axis, **kwargs)
+
+
+def sum(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+):
+    return _reductions(
+        np.sum, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
+    )
+
+
+def prod(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+):
+    return _reductions(
+        np.prod, values=values, mask=mask, skipna=skipna, min_count=min_count, axis=axis
+    )
+
+
+def _minmax(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    """
+    Reduction for 1D masked array.
+
+    Parameters
+    ----------
+    func : np.min or np.max
+    values : np.ndarray
+        Numpy array with the values (can be of any dtype that support the
+        operation).
+    mask : np.ndarray[bool]
+        Boolean numpy array (True values indicate missing values).
+    skipna : bool, default True
+        Whether to skip NA.
+    axis : int, optional, default None
+    """
+    if not skipna:
+        if mask.any() or not values.size:
+            # min/max with empty array raise in numpy, pandas returns NA
+            return libmissing.NA
+        else:
+            return func(values, axis=axis)
+    else:
+        subset = values[~mask]
+        if subset.size:
+            return func(subset, axis=axis)
+        else:
+            # min/max with empty array raise in numpy, pandas returns NA
+            return libmissing.NA
+
+
+def min(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    return _minmax(np.min, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def max(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    return _minmax(np.max, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def mean(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+    return _reductions(np.mean, values=values, mask=mask, skipna=skipna, axis=axis)
+
+
+def var(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+    ddof: int = 1,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", RuntimeWarning)
+        return _reductions(
+            np.var, values=values, mask=mask, skipna=skipna, axis=axis, ddof=ddof
+        )
+
+
+def std(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    axis: AxisInt | None = None,
+    ddof: int = 1,
+):
+    if not values.size or mask.all():
+        return libmissing.NA
+
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", RuntimeWarning)
+        return _reductions(
+            np.std, values=values, mask=mask, skipna=skipna, axis=axis, ddof=ddof
+        )