ExtensionArray series.align(frame) not working #20576
Description
Aligning a Series containing extension array data with a dataframe does not work if there is actually something to be aligned:
In [27]: from pandas.tests.extension.decimal.array import DecimalArray, make_data
In [28]: dec_arr = DecimalArray(make_data()[:3])
In [29]: s = pd.Series(dec_arr)
In [30]: s
Out[30]:
0 0.29242561210243966929311909552779980003833770...
1 0.34798224977276304148432473084540106356143951...
2 0.04963128775050906771326708621927537024021148...
dtype: decimal
In [31]: frame = pd.DataFrame({'col': np.arange(3)})
In [32]: s.align(frame)
Out[32]:
(0 0.29242561210243966929311909552779980003833770...
1 0.34798224977276304148432473084540106356143951...
2 0.04963128775050906771326708621927537024021148...
dtype: decimal, col
0 0
1 1
2 2)
In [33]: frame = pd.DataFrame({'col': np.arange(4)})
In [34]: s.align(frame)
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-34-94a43a65d337> in <module>()
----> 1 s.align(frame)
/home/joris/scipy/pandas/pandas/core/series.py in align(self, other, join, axis, level, copy, fill_value, method, limit, fill_axis, broadcast_axis)
3231 fill_value=fill_value, method=method,
3232 limit=limit, fill_axis=fill_axis,
-> 3233 broadcast_axis=broadcast_axis)
3234
3235 def rename(self, index=None, **kwargs):
/home/joris/scipy/pandas/pandas/core/generic.py in align(self, other, join, axis, level, copy, fill_value, method, limit, fill_axis, broadcast_axis)
7174 copy=copy, fill_value=fill_value,
7175 method=method, limit=limit,
-> 7176 fill_axis=fill_axis)
7177 elif isinstance(other, Series):
7178 return self._align_series(other, join=join, axis=axis, level=level,
/home/joris/scipy/pandas/pandas/core/generic.py in _align_frame(self, other, join, axis, level, copy, fill_value, method, limit, fill_axis)
7210 left = self._reindex_with_indexers(reindexers, copy=copy,
7211 fill_value=fill_value,
-> 7212 allow_dups=True)
7213 # other must be always DataFrame
7214 right = other._reindex_with_indexers({0: [join_index, iridx],
/home/joris/scipy/pandas/pandas/core/generic.py in _reindex_with_indexers(self, reindexers, fill_value, copy, allow_dups)
3812 fill_value=fill_value,
3813 allow_dups=allow_dups,
-> 3814 copy=copy)
3815
3816 if copy and new_data is self._data:
/home/joris/scipy/pandas/pandas/core/internals.py in reindex_indexer(self, new_axis, indexer, axis, fill_value, allow_dups, copy)
4377 if axis == 0:
4378 new_blocks = self._slice_take_blocks_ax0(indexer,
-> 4379 fill_tuple=(fill_value,))
4380 else:
4381 new_blocks = [blk.take_nd(indexer, axis=axis, fill_tuple=(
/home/joris/scipy/pandas/pandas/core/internals.py in _slice_take_blocks_ax0(self, slice_or_indexer, fill_tuple)
4411 elif not allow_fill or self.ndim == 1:
4412 if allow_fill and fill_tuple[0] is None:
-> 4413 _, fill_value = maybe_promote(blk.dtype)
4414 fill_tuple = (fill_value, )
4415
/home/joris/scipy/pandas/pandas/core/dtypes/cast.py in maybe_promote(dtype, fill_value)
334 elif is_datetimetz(dtype):
335 pass
--> 336 elif issubclass(np.dtype(dtype).type, string_types):
337 dtype = np.object_
338
TypeError: data type not understood
Other combinations of aligning (frame with series, series with series) do work correctly:
In [36]: frame.align(s, axis=0)
Out[36]:
( col
0 0
1 1
2 2
3 3, 0 0.29242561210243966929311909552779980003833770...
1 0.34798224977276304148432473084540106356143951...
2 0.04963128775050906771326708621927537024021148...
3 NaN
dtype: decimal)
In [37]: s.align(frame['col'])
Out[37]:
(0 0.29242561210243966929311909552779980003833770...
1 0.34798224977276304148432473084540106356143951...
2 0.04963128775050906771326708621927537024021148...
3 NaN
dtype: decimal, 0 0
1 1
2 2
3 3
Name: col, dtype: int64)