ashlr-plugin 1.36.4

package/bench/refs/python-lib/pandas/core/array_algos/masked_accumulations.py

@@ -0,0 +1,97 @@
+"""
+masked_accumulations.py is for accumulation algorithms using a mask-based approach
+for missing values.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
+    from pandas._typing import npt
+
+
+def _cum_func(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
+    """
+    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 as err:
+        raise NotImplementedError(
+            f"No accumulation for {func} implemented on BaseMaskedArray"
+        ) from err
+
+    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
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
+    return _cum_func(np.cumsum, values, mask, skipna=skipna)
+
+
+def cumprod(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
+    return _cum_func(np.cumprod, values, mask, skipna=skipna)
+
+
+def cummin(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
+    return _cum_func(np.minimum.accumulate, values, mask, skipna=skipna)
+
+
+def cummax(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], *, skipna: bool = True
+) -> tuple[np.ndarray, npt.NDArray[np.bool_]]:
+    return _cum_func(np.maximum.accumulate, values, mask, skipna=skipna)

package/bench/refs/python-lib/pandas/core/array_algos/masked_reductions.py

@@ -0,0 +1,252 @@
+"""
+masked_reductions.py is for reduction algorithms using a mask-based approach
+for missing values.
+"""
+
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+import warnings
+
+import numpy as np
+
+from pandas._libs import (
+    lib,
+    missing as libmissing,
+)
+
+from pandas.core.nanops import check_below_min_count
+
+if TYPE_CHECKING:
+    from collections.abc import Callable
+
+    from pandas._typing import (
+        AxisInt,
+        npt,
+    )
+
+
+def _get_min_value(dtype: np.dtype) -> int | float:
+    """Get the minimum value for a given numpy dtype."""
+    if dtype.kind == "f":
+        return -np.inf
+    elif dtype.kind == "u":
+        return 0
+    else:
+        return np.iinfo(dtype).min
+
+
+def _get_max_value(dtype: np.dtype) -> int | float:
+    """Get the maximum value for a given numpy dtype."""
+    if dtype.kind == "f":
+        return np.inf
+    else:
+        return np.iinfo(dtype).max
+
+
+def _reductions(
+    func: Callable,
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    *,
+    skipna: bool = True,
+    min_count: int = 0,
+    axis: AxisInt | None = None,
+    initial: object | lib.NoDefault = lib.no_default,
+    **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
+    initial : scalar, optional
+        Starting value for the reduction. NumPy has a default value for most
+        data types, but for object-dtype arrays we need to specify it explicitly
+    """
+    if initial is not lib.no_default:
+        kwargs["initial"] = initial
+
+    if not skipna:
+        if axis is not None and values.ndim > 1:
+            # For 2D with axis, compute the reduction and let the caller
+            # handle per-row/column masking via _wrap_reduction_result.
+            return func(values, axis=axis, **kwargs)
+        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,
+    initial: object | lib.NoDefault = lib.no_default,
+):
+    return _reductions(
+        np.sum,
+        values=values,
+        mask=mask,
+        skipna=skipna,
+        min_count=min_count,
+        axis=axis,
+        initial=initial,
+    )
+
+
+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 axis is not None and values.ndim > 1:
+            # For 2D with axis, compute the reduction and let the caller
+            # handle per-row/column masking via _wrap_reduction_result.
+            return func(values, axis=axis)
+        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:
+        if axis is not None and values.ndim > 1:
+            # Can't use values[~mask] which would flatten the array.
+            # Instead, replace masked values with the identity element
+            # and then reduce.
+            if func is np.min:
+                fill_value = _get_max_value(values.dtype)
+            else:
+                fill_value = _get_min_value(values.dtype)
+            filled = np.where(mask, fill_value, values)
+            return func(filled, axis=axis)
+        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() and (axis is None or values.ndim == 1)):
+        return libmissing.NA
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore", RuntimeWarning)
+        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() and (axis is None or values.ndim == 1)):
+        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() and (axis is None or values.ndim == 1)):
+        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
+        )

package/bench/refs/python-lib/pandas/core/array_algos/putmask.py

@@ -0,0 +1,150 @@
+"""
+EA-compatible analogue to np.putmask
+"""
+
+from __future__ import annotations
+
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+import numpy as np
+
+from pandas._libs import lib
+
+from pandas.core.dtypes.cast import infer_dtype_from
+from pandas.core.dtypes.common import is_list_like
+
+from pandas.core.arrays import ExtensionArray
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        npt,
+    )
+
+    from pandas import MultiIndex
+
+
+def putmask_inplace(values: ArrayLike, mask: npt.NDArray[np.bool_], value: Any) -> None:
+    """
+    ExtensionArray-compatible implementation of np.putmask.  The main
+    difference is we do not handle repeating or truncating like numpy.
+
+    Parameters
+    ----------
+    values: np.ndarray or ExtensionArray
+    mask : np.ndarray[bool]
+        We assume extract_bool_array has already been called.
+    value : Any
+    """
+
+    if (
+        not isinstance(values, np.ndarray)
+        or (values.dtype == object and not lib.is_scalar(value))
+        # GH#43424: np.putmask raises TypeError if we cannot cast between types with
+        # rule = "safe", a stricter guarantee we may not have here
+        or (
+            isinstance(value, np.ndarray) and not np.can_cast(value.dtype, values.dtype)
+        )
+    ):
+        # GH#19266 using np.putmask gives unexpected results with listlike value
+        #  along with object dtype
+        if is_list_like(value) and len(value) == len(values):
+            values[mask] = value[mask]
+        else:
+            values[mask] = value
+    else:
+        # GH#37833 np.putmask is more performant than __setitem__
+        np.putmask(values, mask, value)
+
+
+def putmask_without_repeat(
+    values: np.ndarray, mask: npt.NDArray[np.bool_], new: Any
+) -> None:
+    """
+    np.putmask will truncate or repeat if `new` is a listlike with
+    len(new) != len(values).  We require an exact match.
+
+    Parameters
+    ----------
+    values : np.ndarray
+    mask : np.ndarray[bool]
+    new : Any
+    """
+    if getattr(new, "ndim", 0) >= 1:
+        new = new.astype(values.dtype, copy=False)
+
+    # TODO: this prob needs some better checking for 2D cases
+    nlocs = mask.sum()
+    if nlocs > 0 and is_list_like(new) and getattr(new, "ndim", 1) == 1:
+        shape = np.shape(new)
+        # np.shape compat for if setitem_datetimelike_compat
+        #  changed arraylike to list e.g. test_where_dt64_2d
+        if nlocs == shape[-1]:
+            # GH#30567
+            # If length of ``new`` is less than the length of ``values``,
+            # `np.putmask` would first repeat the ``new`` array and then
+            # assign the masked values hence produces incorrect result.
+            # `np.place` on the other hand uses the ``new`` values at it is
+            # to place in the masked locations of ``values``
+            np.place(values, mask, new)
+            # i.e. values[mask] = new
+        elif mask.shape[-1] == shape[-1] or shape[-1] == 1:
+            np.putmask(values, mask, new)
+        else:
+            raise ValueError("cannot assign mismatch length to masked array")
+    else:
+        np.putmask(values, mask, new)
+
+
+def validate_putmask(
+    values: ArrayLike | MultiIndex, mask: np.ndarray
+) -> tuple[npt.NDArray[np.bool_], bool]:
+    """
+    Validate mask and check if this putmask operation is a no-op.
+    """
+    mask = extract_bool_array(mask)
+    if mask.shape != values.shape:
+        raise ValueError("putmask: mask and data must be the same size")
+
+    noop = not mask.any()
+    return mask, noop
+
+
+def extract_bool_array(mask: ArrayLike) -> npt.NDArray[np.bool_]:
+    """
+    If we have a SparseArray or BooleanArray, convert it to ndarray[bool].
+    """
+    if isinstance(mask, ExtensionArray):
+        # We could have BooleanArray, Sparse[bool], ...
+        #  Except for BooleanArray, this is equivalent to just
+        #  np.asarray(mask, dtype=bool)
+        mask = mask.to_numpy(dtype=bool, na_value=False)
+
+    mask = np.asarray(mask, dtype=bool)
+    return mask
+
+
+def setitem_datetimelike_compat(values: np.ndarray, num_set: int, other: Any) -> Any:
+    """
+    Parameters
+    ----------
+    values : np.ndarray
+    num_set : int
+        For putmask, this is mask.sum()
+    other : Any
+    """
+    if values.dtype == object:
+        dtype, _ = infer_dtype_from(other)
+
+        if lib.is_np_dtype(dtype, "mM"):
+            # https://github.com/numpy/numpy/issues/12550
+            #  timedelta64 will incorrectly cast to int
+            if not is_list_like(other):
+                other = [other] * num_set
+            else:
+                other = list(other)
+
+    return other