def _maybe_mask_result(self, result, mask, other, op_name: str):
"""
Parameters
----------
result : array-like
mask : array-like bool
other : scalar or array-like
op_name : str
"""
# if we have a float operand we are by-definition
# a float result
# or our op is a divide
if (is_float_dtype(other)
or is_float(other)) or (op_name in ["rtruediv", "truediv"]):
from pandas.core.arrays import FloatingArray
return FloatingArray(result, mask, copy=False)
elif is_bool_dtype(result):
return BooleanArray(result, mask, copy=False)
elif is_integer_dtype(result):
from pandas.core.arrays import IntegerArray
return IntegerArray(result, mask, copy=False)
else:
result[mask] = np.nan
return result
def value_counts(self, dropna: bool = True) -> Series:
"""
Returns a Series containing counts of each unique value.
Parameters
----------
dropna : bool, default True
Don't include counts of missing values.
Returns
-------
counts : Series
See Also
--------
Series.value_counts
"""
from pandas import (
Index,
Series,
)
from pandas.arrays import IntegerArray
# compute counts on the data with no nans
data = self._data[~self._mask]
value_counts = Index(data).value_counts()
# TODO(extension)
# if we have allow Index to hold an ExtensionArray
# this is easier
index = value_counts.index._values.astype(object)
# if we want nans, count the mask
if dropna:
counts = value_counts._values
else:
counts = np.empty(len(value_counts) + 1, dtype="int64")
counts[:-1] = value_counts
counts[-1] = self._mask.sum()
index = Index(
np.concatenate(
[index,
np.array([self.dtype.na_value], dtype=object)]),
dtype=object,
)
mask = np.zeros(len(counts), dtype="bool")
counts = IntegerArray(counts, mask)
return Series(counts, index=index)
FloatingArray,
IntegerArray,
IntervalArray,
SparseArray,
StringArray,
TimedeltaArray,
)
from pandas.core.arrays import PandasArray, integer_array, period_array
from pandas.tests.extension.decimal import DecimalArray, DecimalDtype, to_decimal
@pytest.mark.parametrize(
"data, dtype, expected",
[
# Basic NumPy defaults.
([1, 2], None, IntegerArray._from_sequence([1, 2])),
([1, 2], object, PandasArray(np.array([1, 2], dtype=object))),
(
[1, 2],
np.dtype("float32"),
PandasArray(np.array([1.0, 2.0], dtype=np.dtype("float32"))),
),
(np.array([1, 2], dtype="int64"), None, IntegerArray._from_sequence([1, 2])),
(
np.array([1.0, 2.0], dtype="float64"),
None,
FloatingArray._from_sequence([1.0, 2.0]),
),
# String alias passes through to NumPy
([1, 2], "float32", PandasArray(np.array([1, 2], dtype="float32"))),
# Period alias
DatetimeArray,
IntegerArray,
IntervalArray,
SparseArray,
StringArray,
TimedeltaArray,
)
from pandas.core.arrays import PandasArray, integer_array, period_array
from pandas.tests.extension.decimal import DecimalArray, DecimalDtype, to_decimal
@pytest.mark.parametrize(
"data, dtype, expected",
[
# Basic NumPy defaults.
([1, 2], None, IntegerArray._from_sequence([1, 2])),
([1, 2], object, PandasArray(np.array([1, 2], dtype=object))),
(
[1, 2],
np.dtype("float32"),
PandasArray(np.array([1.0, 2.0], dtype=np.dtype("float32"))),
),
(
np.array([1, 2], dtype="int64"),
None,
IntegerArray._from_sequence([1, 2]),
),
# String alias passes through to NumPy
([1, 2], "float32", PandasArray(np.array([1, 2], dtype="float32"))),
# Period alias
(
DatetimeArray,
IntegerArray,
IntervalArray,
SparseArray,
StringArray,
TimedeltaArray,
)
from pandas.core.arrays import PandasArray, integer_array, period_array
from pandas.tests.extension.decimal import DecimalArray, DecimalDtype, to_decimal
@pytest.mark.parametrize(
"data, dtype, expected",
[
# Basic NumPy defaults.
([1, 2], None, IntegerArray._from_sequence([1, 2])),
([1, 2], object, PandasArray(np.array([1, 2], dtype=object))),
(
[1, 2],
np.dtype("float32"),
PandasArray(np.array([1.0, 2.0], dtype=np.dtype("float32"))),
),
(
np.array([1, 2], dtype="int64"),
None,
IntegerArray._from_sequence([1, 2]),
),
# String alias passes through to NumPy
([1, 2], "float32", PandasArray(np.array([1, 2], dtype="float32"))),
# Period alias
(
