def _check_behavior(self, arr, expected):
result = libmissing.isnaobj(arr)
tm.assert_numpy_array_equal(result, expected)
result = libmissing.isnaobj(arr, inf_as_na=True)
tm.assert_numpy_array_equal(result, expected)
arr = np.atleast_2d(arr)
expected = np.atleast_2d(expected)
result = libmissing.isnaobj2d(arr)
tm.assert_numpy_array_equal(result, expected)
result = libmissing.isnaobj2d(arr, inf_as_na=True)
tm.assert_numpy_array_equal(result, expected)
def _isna_ndarraylike(obj):
values = getattr(obj, 'values', obj)
dtype = values.dtype
if is_extension_array_dtype(obj):
if isinstance(obj, (ABCIndexClass, ABCSeries)):
values = obj._values
else:
values = obj
result = values.isna()
elif is_string_dtype(dtype):
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
# object array of strings
result = np.zeros(values.shape, dtype=bool)
else:
# object array of non-strings
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(obj):
# this is the NaT pattern
result = values.view('i8') == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
from pandas import Series
result = Series(result, index=obj.index, name=obj.name, copy=False)
return result
def _isna_ndarraylike(obj):
values = getattr(obj, 'values', obj)
dtype = values.dtype
if is_extension_array_dtype(obj):
if isinstance(obj, (ABCIndexClass, ABCSeries)):
values = obj._values
else:
values = obj
result = values.isna()
elif is_string_dtype(dtype):
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
# object array of strings
result = np.zeros(values.shape, dtype=bool)
else:
# object array of non-strings
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(obj):
# this is the NaT pattern
result = values.view('i8') == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
from pandas import Series
result = Series(result, index=obj.index, name=obj.name, copy=False)
return result
def _isna_string_dtype(values: np.ndarray, inf_as_na: bool) -> npt.NDArray[np.bool_]:
# Working around NumPy ticket 1542
dtype = values.dtype
if dtype.kind in ("S", "U"):
result = np.zeros(values.shape, dtype=bool)
else:
if values.ndim == 1:
result = libmissing.isnaobj(values, inf_as_na=inf_as_na)
elif values.ndim == 2:
result = libmissing.isnaobj2d(values, inf_as_na=inf_as_na)
else:
# 0-D, reached via e.g. mask_missing
result = libmissing.isnaobj(values.ravel(), inf_as_na=inf_as_na)
result = result.reshape(values.shape)
return result
def _isna_string_dtype(values: np.ndarray, inf_as_na: bool) -> np.ndarray:
# Working around NumPy ticket 1542
dtype = values.dtype
shape = values.shape
if dtype.kind in ("S", "U"):
result = np.zeros(values.shape, dtype=bool)
else:
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel(), inf_as_na=inf_as_na)
result[...] = vec.reshape(shape)
return result
def _isna_string_dtype(values: np.ndarray, dtype: np.dtype, old: bool) -> np.ndarray:
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
result = np.zeros(values.shape, dtype=bool)
else:
result = np.empty(shape, dtype=bool)
if old:
vec = libmissing.isnaobj_old(values.ravel())
else:
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
return result
def _isna_ndarraylike(obj):
is_extension = is_extension_array_dtype(obj)
if not is_extension:
# Avoid accessing `.values` on things like
# PeriodIndex, which may be expensive.
values = getattr(obj, "values", obj)
else:
values = obj
dtype = values.dtype
if is_extension:
if isinstance(obj, (ABCIndexClass, ABCSeries)):
values = obj._values
else:
values = obj
result = values.isna()
elif isinstance(obj, ABCDatetimeArray):
return obj.isna()
elif is_string_dtype(dtype):
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
# object array of strings
result = np.zeros(values.shape, dtype=bool)
else:
# object array of non-strings
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(dtype):
# this is the NaT pattern
result = values.view("i8") == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
result = obj._constructor(result,
index=obj.index,
name=obj.name,
copy=False)
return result
def _isna_ndarraylike(obj):
is_extension = is_extension_array_dtype(obj)
if not is_extension:
# Avoid accessing `.values` on things like
# PeriodIndex, which may be expensive.
values = getattr(obj, 'values', obj)
else:
values = obj
dtype = values.dtype
if is_extension:
if isinstance(obj, (ABCIndexClass, ABCSeries)):
values = obj._values
else:
values = obj
result = values.isna()
elif isinstance(obj, ABCDatetimeArray):
return obj.isna()
elif is_string_dtype(dtype):
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
# object array of strings
result = np.zeros(values.shape, dtype=bool)
else:
# object array of non-strings
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(dtype):
# this is the NaT pattern
result = values.view('i8') == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
result = obj._constructor(
result, index=obj.index, name=obj.name, copy=False)
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 _isna_ndarraylike(obj):
values = getattr(obj, 'values', obj)
dtype = values.dtype
if is_string_dtype(dtype):
if is_categorical_dtype(values):
from pandas import Categorical
if not isinstance(values, Categorical):
values = values.values
result = values.isna()
elif is_interval_dtype(values):
from pandas import IntervalIndex
result = IntervalIndex(obj).isna()
else:
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
result = np.zeros(values.shape, dtype=bool)
else:
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(obj):
# this is the NaT pattern
result = values.view('i8') == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
from pandas import Series
result = Series(result, index=obj.index, name=obj.name, copy=False)
return result
def _isna_ndarraylike(obj):
values = getattr(obj, 'values', obj)
dtype = values.dtype
if is_string_dtype(dtype):
if is_categorical_dtype(values):
from pandas import Categorical
if not isinstance(values, Categorical):
values = values.values
result = values.isna()
elif is_interval_dtype(values):
from pandas import IntervalIndex
result = IntervalIndex(obj).isna()
else:
# Working around NumPy ticket 1542
shape = values.shape
if is_string_like_dtype(dtype):
result = np.zeros(values.shape, dtype=bool)
else:
result = np.empty(shape, dtype=bool)
vec = libmissing.isnaobj(values.ravel())
result[...] = vec.reshape(shape)
elif needs_i8_conversion(obj):
# this is the NaT pattern
result = values.view('i8') == iNaT
else:
result = np.isnan(values)
# box
if isinstance(obj, ABCSeries):
from pandas import Series
result = Series(result, index=obj.index, name=obj.name, copy=False)
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:
result = values.isna()
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
