def _sumprod(
func: Callable,
values: np.ndarray,
mask: np.ndarray,
*,
skipna: bool = True,
min_count: int = 0,
):
"""
Sum 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
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.
"""
if not skipna:
if mask.any() or check_below_min_count(values.shape, None, min_count):
return libmissing.NA
else:
return func(values)
else:
if check_below_min_count(values.shape, mask, min_count):
return libmissing.NA
return func(values, where=~mask)
def sum(self, axis: int = 0, min_count: int = 0, *args, **kwargs) -> Scalar:
"""
Sum of non-NA/null values
Parameters
----------
axis : int, default 0
Not Used. NumPy compatibility.
min_count : int, default 0
The required number of valid values to perform the summation. If fewer
than ``min_count`` valid values are present, the result will be the missing
value indicator for subarray type.
*args, **kwargs
Not Used. NumPy compatibility.
Returns
-------
scalar
"""
nv.validate_sum(args, kwargs)
valid_vals = self._valid_sp_values
sp_sum = valid_vals.sum()
if self._null_fill_value:
if check_below_min_count(valid_vals.shape, None, min_count):
return na_value_for_dtype(self.dtype.subtype, compat=False)
return sp_sum
else:
nsparse = self.sp_index.ngaps
if check_below_min_count(valid_vals.shape, None, min_count - nsparse):
return na_value_for_dtype(self.dtype.subtype, compat=False)
return sp_sum + self.fill_value * nsparse
def sum(
values: np.ndarray, mask: np.ndarray, skipna: bool = True, min_count: int = 0,
):
"""
Sum for 1D masked array.
Parameters
----------
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.
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.
"""
if not skipna:
if mask.any():
return libmissing.NA
else:
if check_below_min_count(values.shape, None, min_count):
return libmissing.NA
return np.sum(values)
else:
if check_below_min_count(values.shape, mask, min_count):
return libmissing.NA
if _np_version_under1p17:
return np.sum(values[~mask])
else:
return np.sum(values, where=~mask)
def test_check_below_min_count__large_shape(min_count, expected_result):
# GH35227 large shape used to show that the issue is fixed
shape = (2244367, 1253)
result = nanops.check_below_min_count(shape,
mask=None,
min_count=min_count)
assert result == expected_result
def test_check_below_min_count__positive_min_count(mask, min_count, expected_result):
# GH35227
shape = (10, 10)
result = nanops.check_below_min_count(shape, mask, min_count)
assert result == expected_result
def test_check_below_min_count__negative_or_zero_min_count(min_count):
# GH35227
result = nanops.check_below_min_count((21, 37), None, min_count)
expected_result = False
assert result == expected_result
