BUG: IndexError when slicing a series, if a level of MultiIndex contains only NaN values (original) (raw)

Code Sample, a copy-pastable example

import pandas as pd

s = pd.Series([0, 1], index=[[pd.NA, pd.NA], ["bar", "baz"]]) s.loc[pd.IndexSlice[:, "bar"]]

Traceback

IndexError Traceback (most recent call last) in 2 3 s = pd.Series([0, 1], index=[[pd.NA, pd.NA], ["bar", "baz"]]) ----> 4 s.loc[pd.IndexSlice[:, "bar"]]

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexing.py in getitem(self, key) 887 # AttributeError for IntervalTree get_value 888 return self.obj._get_value(*key, takeable=self._takeable) --> 889 return self._getitem_tuple(key) 890 else: 891 # we by definition only have the 0th axis

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexing.py in _getitem_tuple(self, tup) 1058 def _getitem_tuple(self, tup: Tuple): 1059 with suppress(IndexingError): -> 1060 return self._getitem_lowerdim(tup) 1061 1062 # no multi-index, so validate all of the indexers

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexing.py in _getitem_lowerdim(self, tup) 789 # we may have a nested tuples indexer here 790 if self._is_nested_tuple_indexer(tup): --> 791 return self._getitem_nested_tuple(tup) 792 793 # we maybe be using a tuple to represent multiple dimensions here

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexing.py in _getitem_nested_tuple(self, tup) 845 raise ValueError("Too many indices") 846 with suppress(IndexingError): --> 847 return self._handle_lowerdim_multi_index_axis0(tup) 848 849 # this is a series with a multi-index specified a tuple of

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexing.py in _handle_lowerdim_multi_index_axis0(self, tup) 1078 try: 1079 # fast path for series or for tup devoid of slices -> 1080 return self._get_label(tup, axis=axis) 1081 except (TypeError, InvalidIndexError): 1082 # slices are unhashable

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexing.py in _get_label(self, label, axis) 1071 def _get_label(self, label, axis: int): 1072 # GH#5667 this will fail if the label is not present in the axis. -> 1073 return self.obj.xs(label, axis=axis) 1074 1075 def _handle_lowerdim_multi_index_axis0(self, tup: Tuple):

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/generic.py in xs(self, key, axis, level, drop_level) 3731 if isinstance(index, MultiIndex): 3732 try: -> 3733 loc, new_index = index._get_loc_level( 3734 key, level=0, drop_level=drop_level 3735 )

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexes/multi.py in _get_loc_level(self, key, level, drop_level) 3064 indexer = slice(None, None) 3065 ilevels = [i for i in range(len(key)) if key[i] != slice(None, None)] -> 3066 return indexer, maybe_mi_droplevels(indexer, ilevels, drop_level) 3067 else: 3068 indexer = self._get_level_indexer(key, level=level)

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexes/multi.py in maybe_mi_droplevels(indexer, levels, drop_level) 2981 for i in sorted(levels, reverse=True): 2982 try: -> 2983 new_index = new_index._drop_level_numbers([i]) 2984 except ValueError: 2985

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexes/base.py in _drop_level_numbers(self, levnums) 1639 # set nan if needed 1640 mask = new_codes[0] == -1 -> 1641 result = new_levels[0].take(new_codes[0]) 1642 if mask.any(): 1643 result = result.putmask(mask, np.nan)

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/indexes/base.py in take(self, indices, axis, allow_fill, fill_value, **kwargs) 749 # Note: we discard fill_value and use self._na_value, only relevant 750 # in the case where allow_fill is True and fill_value is not None --> 751 taken = algos.take( 752 self._values, indices, allow_fill=allow_fill, fill_value=self._na_value 753 )

~/.cache/pypoetry/virtualenvs/env-d6X_GUCN-py3.9/lib/python3.9/site-packages/pandas/core/algorithms.py in take(arr, indices, axis, allow_fill, fill_value) 1655 else: 1656 # NumPy style -> 1657 result = arr.take(indices, axis=axis) 1658 return result 1659

IndexError: cannot do a non-empty take from an empty axes.

Problem description

The example runs as expected, when the index contains a non-NaN value such as "foo"

import pandas as pd

s3 = pd.Series([0, 1], index=[[pd.NA, "foo"], ["bar", "baz"]]) s3[pd.IndexSlice[:, "bar"]]

Expected Output

Output identical to
pd.Series(0, index=[pd.NA])

Output of pd.show_versions()

Details

INSTALLED VERSIONS

commit : 2cb9652
python : 3.9.5.final.0
python-bits : 64
OS : Linux
OS-release : 5.10.41-1-MANJARO
Version : #1 SMP PREEMPT Fri May 28 19:10:32 UTC 2021
machine : x86_64
processor :
byteorder : little
LC_ALL : None
LANG : en_US.utf8
LOCALE : en_US.UTF-8

pandas : 1.2.4
numpy : 1.20.3
pytz : 2021.1
dateutil : 2.8.1
pip : 21.0.1
setuptools : 54.1.2
Cython : None
pytest : 6.2.4
hypothesis : 6.14.0
sphinx : 3.5.4
blosc : None
feather : None
xlsxwriter : None
lxml.etree : None
html5lib : 1.1
pymysql : None
psycopg2 : None
jinja2 : 3.0.1
IPython : 7.24.1
pandas_datareader: None
bs4 : None
bottleneck : None
fsspec : None
fastparquet : None
gcsfs : None
matplotlib : 3.4.2
numexpr : None
odfpy : None
openpyxl : None
pandas_gbq : None
pyarrow : None
pyxlsb : None
s3fs : None
scipy : 1.6.3
sqlalchemy : None
tables : None
tabulate : 0.8.9
xarray : None
xlrd : None
xlwt : None
numba : None