def _isna_array(values: ArrayLike, inf_as_na: bool = False):
"""
Return an array indicating which values of the input array are NaN / NA.
Parameters
----------
obj: ndarray or ExtensionArray
The input array whose elements are to be checked.
inf_as_na: bool
Whether or not to treat infinite values as NA.
Returns
-------
array-like
Array of boolean values denoting the NA status of each element.
"""
dtype = values.dtype
if is_extension_array_dtype(dtype):
if inf_as_na and is_categorical_dtype(dtype):
result = libmissing.isnaobj_old(values.to_numpy())
else:
result = values.isna()
elif is_string_dtype(dtype):
result = _isna_string_dtype(values, dtype, inf_as_na=inf_as_na)
elif needs_i8_conversion(dtype):
# this is the NaT pattern
result = values.view("i8") == iNaT
else:
if inf_as_na:
result = ~np.isfinite(values)
else:
result = np.isnan(values)
return result
def _isna_array(values: ArrayLike, inf_as_na: bool = False):
"""
Return an array indicating which values of the input array are NaN / NA.
Parameters
----------
obj: ndarray or ExtensionArray
The input array whose elements are to be checked.
inf_as_na: bool
Whether or not to treat infinite values as NA.
Returns
-------
array-like
Array of boolean values denoting the NA status of each element.
"""
dtype = values.dtype
if is_extension_array_dtype(dtype):
if inf_as_na and is_categorical_dtype(dtype):
# error: Item "ndarray" of "Union[ExtensionArray, ndarray]" has no attribute
# "to_numpy"
result = libmissing.isnaobj_old(
values.to_numpy() # type: ignore[union-attr]
)
else:
# error: Item "ndarray" of "Union[ExtensionArray, ndarray]" has no attribute
# "isna"
result = values.isna() # type: ignore[union-attr]
elif is_string_dtype(dtype):
# error: Argument 1 to "_isna_string_dtype" has incompatible type
# "ExtensionArray"; expected "ndarray"
# error: Argument 2 to "_isna_string_dtype" has incompatible type
# "ExtensionDtype"; expected "dtype[Any]"
result = _isna_string_dtype(
values,
dtype,
inf_as_na=inf_as_na # type: ignore[arg-type]
)
elif needs_i8_conversion(dtype):
# this is the NaT pattern
result = values.view("i8") == iNaT
else:
if inf_as_na:
# error: Argument 1 to "__call__" of "ufunc" has incompatible type
# "ExtensionArray"; expected "Union[Union[int, float, complex, str, bytes,
# generic], Sequence[Union[int, float, complex, str, bytes, generic]],
# Sequence[Sequence[Any]], _SupportsArray]"
result = ~np.isfinite(values) # type: ignore[arg-type]
else:
# error: Argument 1 to "__call__" of "ufunc" has incompatible type
# "ExtensionArray"; expected "Union[Union[int, float, complex, str, bytes,
# generic], Sequence[Union[int, float, complex, str, bytes, generic]],
# Sequence[Sequence[Any]], _SupportsArray]"
result = np.isnan(values) # type: ignore[arg-type]
return result
def _isna_array(values: ArrayLike, inf_as_na: bool = False):
"""
Return an array indicating which values of the input array are NaN / NA.
Parameters
----------
obj: ndarray or ExtensionArray
The input array whose elements are to be checked.
inf_as_na: bool
Whether or not to treat infinite values as NA.
Returns
-------
array-like
Array of boolean values denoting the NA status of each element.
"""
dtype = values.dtype
if not isinstance(values, np.ndarray):
# i.e. ExtensionArray
if inf_as_na and is_categorical_dtype(dtype):
result = libmissing.isnaobj(values.to_numpy(), inf_as_na=inf_as_na)
else:
# error: Incompatible types in assignment (expression has type
# "Union[ndarray[Any, Any], ExtensionArraySupportsAnyAll]", variable has
# type "ndarray[Any, dtype[bool_]]")
result = values.isna() # type: ignore[assignment]
elif is_string_or_object_np_dtype(values.dtype):
result = _isna_string_dtype(values, inf_as_na=inf_as_na)
elif needs_i8_conversion(dtype):
# this is the NaT pattern
result = values.view("i8") == iNaT
else:
if inf_as_na:
result = ~np.isfinite(values)
else:
result = np.isnan(values)
return result
def na_accum_func(values: ArrayLike, accum_func, skipna: bool) -> ArrayLike:
"""
Cumulative function with skipna support.
Parameters
----------
values : np.ndarray or ExtensionArray
accum_func : {np.cumprod, np.maximum.accumulate, np.cumsum, np.minimum.accumulate}
skipna : bool
Returns
-------
np.ndarray or ExtensionArray
"""
mask_a, mask_b = {
np.cumprod: (1.0, np.nan),
np.maximum.accumulate: (-np.inf, np.nan),
np.cumsum: (0.0, np.nan),
np.minimum.accumulate: (np.inf, np.nan),
}[accum_func]
# We will be applying this function to block values
if values.dtype.kind in ["m", "M"]:
# GH#30460, GH#29058
# numpy 1.18 started sorting NaTs at the end instead of beginning,
# so we need to work around to maintain backwards-consistency.
orig_dtype = values.dtype
# We need to define mask before masking NaTs
mask = isna(values)
if accum_func == np.minimum.accumulate:
# Note: the accum_func comparison fails as an "is" comparison
y = values.view("i8")
y[mask] = np.iinfo(np.int64).max
changed = True
else:
y = values
changed = False
result = accum_func(y.view("i8"), axis=0)
if skipna:
result[mask] = iNaT
elif accum_func == np.minimum.accumulate:
# Restore NaTs that we masked previously
nz = (~np.asarray(mask)).nonzero()[0]
if len(nz):
# everything up to the first non-na entry stays NaT
result[: nz[0]] = iNaT
if changed:
# restore NaT elements
y[mask] = iNaT # TODO: could try/finally for this?
if isinstance(values, np.ndarray):
result = result.view(orig_dtype)
else:
# DatetimeArray
result = type(values)._from_sequence(result, dtype=orig_dtype)
elif skipna and not issubclass(values.dtype.type, (np.integer, np.bool_)):
vals = values.copy()
mask = isna(vals)
vals[mask] = mask_a
result = accum_func(vals, axis=0)
result[mask] = mask_b
else:
result = accum_func(values, axis=0)
return result
