def data_missing(allow_in_pandas, dtype):
# For NumPy <1.16, np.array([np.nan, (1,)]) raises
# ValueError: setting an array element with a sequence.
if dtype.numpy_dtype == 'object':
if _np_version_under1p16:
raise pytest.skip("Skipping for NumPy <1.16")
return PandasArray(np.array([np.nan, (1, )]))
return PandasArray(np.array([np.nan, 1.0]))
def data_missing_for_sorting(allow_in_pandas, dtype):
"""Length-3 array with a known sort order.
This should be three items [B, NA, A] with
A < B and NA missing.
"""
if dtype.numpy_dtype == 'object':
return PandasArray(np.array([(1, ), np.nan, (0, )]))
return PandasArray(np.array([1, np.nan, 0]))
def data_for_sorting(allow_in_pandas, dtype):
"""Length-3 array with a known sort order.
This should be three items [B, C, A] with
A < B < C
"""
if dtype.numpy_dtype == 'object':
# Use an empty tuple for first element, then remove,
# to disable np.array's shape inference.
return PandasArray(np.array([(), (2, ), (3, ), (1, )])[1:])
return PandasArray(np.array([1, 2, 0]))
def data_missing_for_sorting(allow_in_pandas):
"""Length-3 array with a known sort order.
This should be three items [B, NA, A] with
A < B and NA missing.
"""
return PandasArray(np.array([1, np.nan, 0]))
def data_for_sorting(allow_in_pandas):
"""Length-3 array with a known sort order.
This should be three items [B, C, A] with
A < B < C
"""
return PandasArray(np.array([1, 2, 0]))
def data_for_grouping(allow_in_pandas):
"""Data for factorization, grouping, and unique tests.
Expected to be like [B, B, NA, NA, A, A, B, C]
Where A < B < C and NA is missing
"""
a, b, c = np.arange(3)
return PandasArray(np.array([b, b, np.nan, np.nan, a, a, b, c]))
def data_for_grouping(allow_in_pandas, dtype):
"""Data for factorization, grouping, and unique tests.
Expected to be like [B, B, NA, NA, A, A, B, C]
Where A < B < C and NA is missing
"""
if dtype.numpy_dtype == 'object':
a, b, c = (1, ), (2, ), (3, )
else:
a, b, c = np.arange(3)
return PandasArray(np.array([b, b, np.nan, np.nan, a, a, b, c]))
def array(self) -> ExtensionArray:
"""
The ExtensionArray of the data backing this Series or Index.
.. versionadded:: 0.24.0
Returns
-------
ExtensionArray
An ExtensionArray of the values stored within. For extension
types, this is the actual array. For NumPy native types, this
is a thin (no copy) wrapper around :class:`numpy.ndarray`.
``.array`` differs ``.values`` which may require converting the
data to a different form.
See Also
--------
Index.to_numpy : Similar method that always returns a NumPy array.
Series.to_numpy : Similar method that always returns a NumPy array.
Notes
-----
This table lays out the different array types for each extension
dtype within pandas.
================== =============================
dtype array type
================== =============================
category Categorical
period PeriodArray
interval IntervalArray
IntegerNA IntegerArray
datetime64[ns, tz] DatetimeArray
================== =============================
For any 3rd-party extension types, the array type will be an
ExtensionArray.
For all remaining dtypes ``.array`` will be a
:class:`arrays.NumpyExtensionArray` wrapping the actual ndarray
stored within. If you absolutely need a NumPy array (possibly with
copying / coercing data), then use :meth:`Series.to_numpy` instead.
Examples
--------
For regular NumPy types like int, and float, a PandasArray
is returned.
>>> pd.Series([1, 2, 3]).array
<PandasArray>
[1, 2, 3]
Length: 3, dtype: int64
For extension types, like Categorical, the actual ExtensionArray
is returned
>>> ser = pd.Series(pd.Categorical(['a', 'b', 'a']))
>>> ser.array
[a, b, a]
Categories (2, object): [a, b]
"""
# As a mixin, we depend on the mixing class having _values.
# Special mixin syntax may be developed in the future:
# https://github.com/python/typing/issues/246
result = self._values # type: ignore
if is_datetime64_ns_dtype(result.dtype):
from pandas.arrays import DatetimeArray
result = DatetimeArray(result)
elif is_timedelta64_ns_dtype(result.dtype):
from pandas.arrays import TimedeltaArray
result = TimedeltaArray(result)
elif not is_extension_array_dtype(result.dtype):
from pandas.core.arrays.numpy_ import PandasArray
result = PandasArray(result)
return result
def data(allow_in_pandas, dtype):
if dtype.numpy_dtype == 'object':
return pd.Series([(i, ) for i in range(100)]).array
return PandasArray(np.arange(1, 101, dtype=dtype._dtype))
def data_missing(allow_in_pandas):
return PandasArray(np.array([np.nan, 1.0]))
def data(allow_in_pandas, dtype):
return PandasArray(np.arange(1, 101, dtype=dtype._dtype))
def data_missing(allow_in_pandas, dtype):
if dtype.numpy_dtype == "object":
return PandasArray(np.array([np.nan, (1, )], dtype=object))
return PandasArray(np.array([np.nan, 1.0]))
def array(self):
# type: () -> ExtensionArray
"""
The ExtensionArray of the data backing this Series or Index.
.. versionadded:: 0.24.0
Returns
-------
array : ExtensionArray
An ExtensionArray of the values stored within. For extension
types, this is the actual array. For NumPy native types, this
is a thin (no copy) wrapper around :class:`numpy.ndarray`.
``.array`` differs ``.values`` which may require converting the
data to a different form.
See Also
--------
Index.to_numpy : Similar method that always returns a NumPy array.
Series.to_numpy : Similar method that always returns a NumPy array.
Notes
-----
This table lays out the different array types for each extension
dtype within pandas.
================== =============================
dtype array type
================== =============================
category Categorical
period PeriodArray
interval IntervalArray
IntegerNA IntegerArray
datetime64[ns, tz] DatetimeArray
================== =============================
For any 3rd-party extension types, the array type will be an
ExtensionArray.
For all remaining dtypes ``.array`` will be a
:class:`arrays.NumpyExtensionArray` wrapping the actual ndarray
stored within. If you absolutely need a NumPy array (possibly with
copying / coercing data), then use :meth:`Series.to_numpy` instead.
Examples
--------
For regular NumPy types like int, and float, a PandasArray
is returned.
>>> pd.Series([1, 2, 3]).array
<PandasArray>
[1, 2, 3]
Length: 3, dtype: int64
For extension types, like Categorical, the actual ExtensionArray
is returned
>>> ser = pd.Series(pd.Categorical(['a', 'b', 'a']))
>>> ser.array
[a, b, a]
Categories (2, object): [a, b]
"""
result = self._values
# TODO(DatetimeArray): remvoe the second clause.
if (not is_extension_array_dtype(result.dtype)
and not is_datetime64tz_dtype(result.dtype)):
from pandas.core.arrays.numpy_ import PandasArray
result = PandasArray(result)
return result
