BUG: Series construction with EA dtype and index but no data fails · Issue #26469 · pandas-dev/pandas (original) (raw)
In [8]: pd.Series(None, index=[1, 2, 3], dtype='Int64')
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
~/scipy/pandas/pandas/core/internals/construction.py in _try_cast(arr, take_fast_path, dtype, copy, raise_cast_failure)
691 if is_integer_dtype(dtype):
--> 692 subarr = maybe_cast_to_integer_array(arr, dtype)
693
~/scipy/pandas/pandas/core/dtypes/cast.py in maybe_cast_to_integer_array(arr, dtype, copy)
1311 if not hasattr(arr, "astype"):
-> 1312 casted = np.array(arr, dtype=dtype, copy=copy)
1313 else:
TypeError: data type not understood
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-8-9447295feee6> in <module>
----> 1 pd.Series(None, index=[1, 2, 3], dtype='Int64')
~/scipy/pandas/pandas/core/series.py in __init__(self, data, index, dtype, name, copy, fastpath)
202 data = data._data
203 elif isinstance(data, dict):
--> 204 data, index = self._init_dict(data, index, dtype)
205 dtype = None
206 copy = False
~/scipy/pandas/pandas/core/series.py in _init_dict(self, data, index, dtype)
295
296 # Input is now list-like, so rely on "standard" construction:
--> 297 s = Series(values, index=keys, dtype=dtype)
298
299 # Now we just make sure the order is respected, if any
~/scipy/pandas/pandas/core/series.py in __init__(self, data, index, dtype, name, copy, fastpath)
253 else:
254 data = sanitize_array(data, index, dtype, copy,
--> 255 raise_cast_failure=True)
256
257 data = SingleBlockManager(data, index, fastpath=True)
~/scipy/pandas/pandas/core/internals/construction.py in sanitize_array(data, index, dtype, copy, raise_cast_failure)
620 subarr = _try_cast(arr, False, dtype, copy, raise_cast_failure)
621 else:
--> 622 subarr = _try_cast(data, False, dtype, copy, raise_cast_failure)
623
624 # scalar like, GH
~/scipy/pandas/pandas/core/internals/construction.py in _try_cast(arr, take_fast_path, dtype, copy, raise_cast_failure)
711 # create an extension array from its dtype
712 array_type = dtype.construct_array_type()._from_sequence
--> 713 subarr = array_type(arr, dtype=dtype, copy=copy)
714 elif dtype is not None and raise_cast_failure:
715 raise
~/scipy/pandas/pandas/core/arrays/integer.py in _from_sequence(cls, scalars, dtype, copy)
305 @classmethod
306 def _from_sequence(cls, scalars, dtype=None, copy=False):
--> 307 return integer_array(scalars, dtype=dtype, copy=copy)
308
309 @classmethod
~/scipy/pandas/pandas/core/arrays/integer.py in integer_array(values, dtype, copy)
110 TypeError if incompatible types
111 """
--> 112 values, mask = coerce_to_array(values, dtype=dtype, copy=copy)
113 return IntegerArray(values, mask)
114
~/scipy/pandas/pandas/core/arrays/integer.py in coerce_to_array(values, dtype, mask, copy)
202
203 if not values.ndim == 1:
--> 204 raise TypeError("values must be a 1D list-like")
205 if not mask.ndim == 1:
206 raise TypeError("mask must be a 1D list-like")
TypeError: values must be a 1D list-like
while this works fine for non-EA dtypes.
The problem is that the None / np.nan is eventually passed to the _from_sequence method, which expects a list-like. I don't think we should let people fix their _from_sequence, but we should rather make sure we never pass that to it.