def _get_result_dtype(self, dtype: DtypeObj) -> DtypeObj:
"""
Get the desired dtype of a result based on the
input dtype and how it was computed.
Parameters
----------
dtype : np.dtype or ExtensionDtype
Input dtype.
Returns
-------
np.dtype or ExtensionDtype
The desired dtype of the result.
"""
how = self.how
if how in ["add", "cumsum", "sum", "prod"]:
if dtype == np.dtype(bool):
return np.dtype(np.int64)
elif isinstance(dtype, (BooleanDtype, IntegerDtype)):
return Int64Dtype()
elif how in ["mean", "median", "var"]:
if isinstance(dtype, (BooleanDtype, IntegerDtype)):
return Float64Dtype()
elif is_float_dtype(dtype) or is_complex_dtype(dtype):
return dtype
elif is_numeric_dtype(dtype):
return np.dtype(np.float64)
return dtype
def test_to_array_dtype_keyword():
result = pd.array([1, 2], dtype="Float32")
assert result.dtype == Float32Dtype()
# if values has dtype -> override it
result = pd.array(np.array([1, 2], dtype="float32"), dtype="Float64")
assert result.dtype == Float64Dtype()
def get_result_dtype(self, dtype: DtypeObj) -> DtypeObj:
"""
Get the desired dtype of a result based on the
input dtype and how it was computed.
Parameters
----------
dtype : np.dtype or ExtensionDtype
Input dtype.
Returns
-------
np.dtype or ExtensionDtype
The desired dtype of the result.
"""
from pandas.core.arrays.boolean import BooleanDtype
from pandas.core.arrays.floating import Float64Dtype
from pandas.core.arrays.integer import (
Int64Dtype,
_IntegerDtype,
)
how = self.how
if how in ["add", "cumsum", "sum", "prod"]:
if dtype == np.dtype(bool):
return np.dtype(np.int64)
elif isinstance(dtype, (BooleanDtype, _IntegerDtype)):
return Int64Dtype()
elif how in ["mean", "median", "var"] and isinstance(
dtype, (BooleanDtype, _IntegerDtype)):
return Float64Dtype()
return dtype
def test_to_array_inferred_dtype():
# if values has dtype -> respect it
result = pd.array(np.array([1, 2], dtype="float32"))
assert result.dtype == Float32Dtype()
# if values have no dtype -> always float64
result = pd.array([1.0, 2.0])
assert result.dtype == Float64Dtype()
def test_to_array_integer():
result = pd.array([1, 2], dtype="Float64")
expected = pd.array([1.0, 2.0], dtype="Float64")
tm.assert_extension_array_equal(result, expected)
# for integer dtypes, the itemsize is not preserved
# TODO can we specify "floating" in general?
result = pd.array(np.array([1, 2], dtype="int32"), dtype="Float64")
assert result.dtype == Float64Dtype()
def test_uses_pandas_na():
a = pd.array([1, None], dtype=Float64Dtype())
assert a[1] is pd.NA
def test_to_array_integer():
result = pd.array([1, 2], dtype="Float64")
expected = pd.array([1.0, 2.0], dtype="Float64")
tm.assert_extension_array_equal(result, expected)
# for integer dtypes, the itemsize is not preserved
# TODO can we specify "floating" in general?
result = pd.array(np.array([1, 2], dtype="int32"), dtype="Float64")
assert result.dtype == Float64Dtype()
@pytest.mark.parametrize(
"bool_values, values, target_dtype, expected_dtype",
[
([False, True], [0, 1], Float64Dtype(), Float64Dtype()),
([False, True], [0, 1], "Float64", Float64Dtype()),
([False, True, np.nan], [0, 1, np.nan
], Float64Dtype(), Float64Dtype()),
],
)
def test_to_array_bool(bool_values, values, target_dtype, expected_dtype):
result = pd.array(bool_values, dtype=target_dtype)
assert result.dtype == expected_dtype
expected = pd.array(values, dtype=target_dtype)
tm.assert_extension_array_equal(result, expected)
def test_series_from_float(data):
# construct from our dtype & string dtype
dtype = data.dtype
import pytest
import pandas as pd
from pandas.core.arrays.floating import Float32Dtype, Float64Dtype
def test_dtypes(dtype):
# smoke tests on auto dtype construction
np.dtype(dtype.type).kind == "f"
assert dtype.name is not None
@pytest.mark.parametrize(
"dtype, expected",
[(Float32Dtype(), "Float32Dtype()"), (Float64Dtype(), "Float64Dtype()")],
)
def test_repr_dtype(dtype, expected):
assert repr(dtype) == expected
def test_repr_array():
result = repr(pd.array([1.0, None, 3.0]))
expected = "<FloatingArray>\n[1.0, <NA>, 3.0]\nLength: 3, dtype: Float64"
assert result == expected
def test_repr_array_long():
data = pd.array([1.0, 2.0, None] * 1000)
expected = """<FloatingArray>
[ 1.0, 2.0, <NA>, 1.0, 2.0, <NA>, 1.0, 2.0, <NA>, 1.0,
