ashlr-plugin 1.36.4

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

@@ -0,0 +1,232 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+import numpy as np
+
+from pandas.core.dtypes.missing import (
+    isna,
+    na_value_for_dtype,
+)
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        Scalar,
+        npt,
+    )
+
+
+def quantile_compat(
+    values: ArrayLike, qs: npt.NDArray[np.float64], interpolation: str
+) -> ArrayLike:
+    """
+    Compute the quantiles of the given values for each quantile in `qs`.
+
+    Parameters
+    ----------
+    values : np.ndarray or ExtensionArray
+    qs : np.ndarray[float64]
+    interpolation : str
+
+    Returns
+    -------
+    np.ndarray or ExtensionArray
+    """
+    if isinstance(values, np.ndarray):
+        fill_value = na_value_for_dtype(values.dtype, compat=False)
+        mask = isna(values)
+        return quantile_with_mask(
+            values,
+            mask,
+            fill_value,  # pyright: ignore[reportArgumentType]
+            qs,
+            interpolation,
+        )
+    else:
+        return values._quantile(qs, interpolation)
+
+
+def quantile_with_mask(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    fill_value: Scalar,
+    qs: npt.NDArray[np.float64],
+    interpolation: str,
+) -> np.ndarray:
+    """
+    Compute the quantiles of the given values for each quantile in `qs`.
+
+    Parameters
+    ----------
+    values : np.ndarray
+        For ExtensionArray, this is _values_for_factorize()[0]
+    mask : np.ndarray[bool]
+        mask = isna(values)
+        For ExtensionArray, this is computed before calling _value_for_factorize
+    fill_value : Scalar
+        The value to interpret fill NA entries with
+        For ExtensionArray, this is _values_for_factorize()[1]
+    qs : np.ndarray[float64]
+    interpolation : str
+        Type of interpolation
+
+    Returns
+    -------
+    np.ndarray
+
+    Notes
+    -----
+    Assumes values is already 2D.  For ExtensionArray this means np.atleast_2d
+    has been called on _values_for_factorize()[0]
+
+    Quantile is computed along axis=1.
+    """
+    assert values.shape == mask.shape
+    if values.ndim == 1:
+        # unsqueeze, operate, re-squeeze
+        values = np.atleast_2d(values)
+        mask = np.atleast_2d(mask)
+        res_values = quantile_with_mask(values, mask, fill_value, qs, interpolation)
+        return res_values[0]
+
+    assert values.ndim == 2
+
+    is_empty = values.shape[1] == 0
+
+    if is_empty:
+        # create the array of na_values
+        # 2d len(values) * len(qs)
+        flat = np.full(len(qs), fill_value)
+        result = np.repeat(flat, len(values)).reshape(len(values), len(qs))
+    else:
+        result = _nanquantile(
+            values,
+            qs,
+            na_value=fill_value,
+            mask=mask,
+            interpolation=interpolation,
+        )
+
+        result = np.asarray(result)
+        result = result.T
+
+    return result
+
+
+def _nanquantile_1d(
+    values: np.ndarray,
+    mask: npt.NDArray[np.bool_],
+    qs: npt.NDArray[np.float64],
+    na_value: Scalar,
+    interpolation: str,
+) -> Scalar | np.ndarray:
+    """
+    Wrapper for np.quantile that skips missing values, specialized to
+    1-dimensional case.
+
+    Parameters
+    ----------
+    values : array over which to find quantiles
+    mask : ndarray[bool]
+        locations in values that should be considered missing
+    qs : np.ndarray[float64] of quantile indices to find
+    na_value : scalar
+        value to return for empty or all-null values
+    interpolation : str
+
+    Returns
+    -------
+    quantiles : scalar or array
+    """
+    # mask is Union[ExtensionArray, ndarray]
+    values = values[~mask]
+
+    if len(values) == 0:
+        # Can't pass dtype=values.dtype here bc we might have na_value=np.nan
+        #  with values.dtype=int64 see test_quantile_empty
+        # equiv: 'np.array([na_value] * len(qs))' but much faster
+        return np.full(len(qs), na_value)
+
+    return np.quantile(
+        values,
+        qs,
+        # error: No overload variant of "percentile" matches argument
+        # types "ndarray[Any, Any]", "ndarray[Any, dtype[floating[_64Bit]]]"
+        # , "Dict[str, str]"  [call-overload]
+        method=interpolation,  # type: ignore[call-overload]
+    )
+
+
+def _nanquantile(
+    values: np.ndarray,
+    qs: npt.NDArray[np.float64],
+    *,
+    na_value: Scalar,
+    mask: npt.NDArray[np.bool_],
+    interpolation: str,
+) -> np.ndarray:
+    """
+    Wrapper for np.quantile that skips missing values.
+
+    Parameters
+    ----------
+    values : np.ndarray[ndim=2]  over which to find quantiles
+    qs : np.ndarray[float64] of quantile indices to find
+    na_value : scalar
+        value to return for empty or all-null values
+    mask : np.ndarray[bool]
+        locations in values that should be considered missing
+    interpolation : str
+
+    Returns
+    -------
+    quantiles : scalar or array
+    """
+
+    if values.dtype.kind in "mM":
+        # need to cast to integer to avoid rounding errors in numpy
+        result = _nanquantile(
+            values.view("i8"),
+            qs=qs,
+            na_value=na_value.view("i8"),  # type: ignore[union-attr, arg-type]
+            mask=mask,
+            interpolation=interpolation,
+        )
+
+        # Note: we have to do `astype` and not view because in general we
+        #  have float result at this point, not i8
+        return result.astype(values.dtype)
+
+    if mask.any():
+        # Caller is responsible for ensuring mask shape match
+        assert mask.shape == values.shape
+        result_list = [
+            _nanquantile_1d(val, m, qs, na_value, interpolation=interpolation)
+            for (val, m) in zip(list(values), list(mask), strict=True)
+        ]
+        if values.dtype.kind == "f":
+            # preserve itemsize
+            result = np.asarray(result_list, dtype=values.dtype).T
+        else:
+            result = np.asarray(result_list).T
+            if (
+                result.dtype != values.dtype
+                and not mask.all()
+                and (result == result.astype(values.dtype, copy=False)).all()
+            ):
+                # mask.all() will never get cast back to int
+                # e.g. values id integer dtype and result is floating dtype,
+                #  only cast back to integer dtype if result values are all-integer.
+                result = result.astype(values.dtype, copy=False)
+        return result
+    else:
+        return np.quantile(
+            values,
+            qs,
+            axis=1,
+            # error: No overload variant of "percentile" matches argument types
+            # "ndarray[Any, Any]", "ndarray[Any, dtype[floating[_64Bit]]]",
+            # "int", "Dict[str, str]"  [call-overload]
+            method=interpolation,  # type: ignore[call-overload]
+        )

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

@@ -0,0 +1,159 @@
+"""
+Methods used by Block.replace and related methods.
+"""
+
+from __future__ import annotations
+
+import operator
+import re
+from re import Pattern
+from typing import (
+    TYPE_CHECKING,
+    Any,
+)
+
+import numpy as np
+
+from pandas.core.dtypes.common import (
+    is_bool,
+    is_re,
+    is_re_compilable,
+)
+from pandas.core.dtypes.missing import isna
+
+if TYPE_CHECKING:
+    from pandas._typing import (
+        ArrayLike,
+        Scalar,
+        npt,
+    )
+
+
+def should_use_regex(regex: bool, to_replace: Any) -> bool:
+    """
+    Decide whether to treat `to_replace` as a regular expression.
+    """
+    if is_re(to_replace):
+        regex = True
+
+    regex = regex and is_re_compilable(to_replace)
+
+    # Don't use regex if the pattern is empty.
+    regex = regex and re.compile(to_replace).pattern != ""
+    return regex
+
+
+def compare_or_regex_search(
+    a: ArrayLike, b: Scalar | Pattern, regex: bool, mask: npt.NDArray[np.bool_]
+) -> ArrayLike:
+    """
+    Compare two array-like inputs of the same shape or two scalar values
+
+    Calls operator.eq or re.search, depending on regex argument. If regex is
+    True, perform an element-wise regex matching.
+
+    Parameters
+    ----------
+    a : array-like
+    b : scalar or regex pattern
+    regex : bool
+    mask : np.ndarray[bool]
+
+    Returns
+    -------
+    mask : array-like of bool
+    """
+    if isna(b):
+        return ~mask
+
+    def _check_comparison_types(
+        result: ArrayLike | bool, a: ArrayLike, b: Scalar | Pattern
+    ) -> None:
+        """
+        Raises an error if the two arrays (a,b) cannot be compared.
+        Otherwise, returns the comparison result as expected.
+        """
+        if is_bool(result) and isinstance(a, np.ndarray):
+            type_names = [type(a).__name__, type(b).__name__]
+
+            type_names[0] = f"ndarray(dtype={a.dtype})"
+
+            raise TypeError(
+                f"Cannot compare types {type_names[0]!r} and {type_names[1]!r}"
+            )
+
+    if not regex or not should_use_regex(regex, b):
+        # TODO: should use missing.mask_missing?
+        op = lambda x: operator.eq(x, b)
+    else:
+        op = np.vectorize(
+            lambda x: (
+                bool(re.search(b, x))
+                if isinstance(x, str) and isinstance(b, (str, Pattern))
+                else False
+            ),
+            otypes=[bool],
+        )
+
+    # GH#32621 use mask to avoid comparing to NAs
+    if isinstance(a, np.ndarray) and mask is not None:
+        a = a[mask]
+        result = op(a)
+
+        if isinstance(result, np.ndarray):
+            # The shape of the mask can differ to that of the result
+            # since we may compare only a subset of a's or b's elements
+            tmp = np.zeros(mask.shape, dtype=np.bool_)
+            np.place(tmp, mask, result)
+            result = tmp
+    else:
+        result = op(a)
+
+    _check_comparison_types(result, a, b)
+    return result
+
+
+def replace_regex(
+    values: ArrayLike, rx: re.Pattern, value, mask: npt.NDArray[np.bool_] | None
+) -> None:
+    """
+    Parameters
+    ----------
+    values : ArrayLike
+        Object dtype.
+    rx : re.Pattern
+    value : Any
+    mask : np.ndarray[bool], optional
+
+    Notes
+    -----
+    Alters values in-place.
+    """
+
+    # deal with replacing values with objects (strings) that match but
+    # whose replacement is not a string (numeric, nan, object)
+    if isna(value) or not isinstance(value, str):
+
+        def re_replacer(s):
+            if is_re(rx) and isinstance(s, str):
+                return value if rx.search(s) is not None else s
+            else:
+                return s
+
+    else:
+        # value is guaranteed to be a string here, s can be either a string
+        # or null if it's null it gets returned
+        def re_replacer(s):
+            if is_re(rx) and isinstance(s, str):
+                return rx.sub(value, s)
+            else:
+                return s
+
+    f = np.vectorize(re_replacer, otypes=[np.object_])
+
+    if mask is None:
+        values[:] = f(values)
+    else:
+        if values.ndim != mask.ndim:
+            mask = np.broadcast_to(mask, values.shape)
+        values[mask] = f(values[mask])