MultiIndex.get_loc misbehaves on NaNs · Issue #18485 · pandas-dev/pandas (original) (raw)

Code Sample, a copy-pastable example if possible

In [2]: mi = pd.MultiIndex(levels=[[1, 2, 3, 5], [4, 6]], labels=[[3, 1, 2, 0], [1, -1, 0, -1]])

In [3]: mi.get_loc((2, np.nan))

KeyError Traceback (most recent call last) in () ----> 1 mi.get_loc((2, np.nan))

/home/pietro/nobackup/repo/pandas/pandas/core/indexes/multi.py in get_loc(self, key, method) 2119 key = _values_from_object(key) 2120 key = tuple(map(_maybe_str_to_time_stamp, key, self.levels)) -> 2121 return self._engine.get_loc(key) 2122 2123 # -- partial selection or non-unique index

/home/pietro/nobackup/repo/pandas/pandas/_libs/index.pyx in pandas._libs.index.MultiIndexObjectEngine.get_loc (pandas/_libs/index.c:14965)() 616 return super(MultiIndexObjectEngine, self).get_indexer(values) 617 --> 618 cpdef get_loc(self, object val): 619 620 # convert a MI to an ndarray

/home/pietro/nobackup/repo/pandas/pandas/_libs/index.pyx in pandas._libs.index.MultiIndexObjectEngine.get_loc (pandas/_libs/index.c:14886)() 621 if hasattr(val, 'values'): 622 val = val.values --> 623 return super(MultiIndexObjectEngine, self).get_loc(val) 624 625

/home/pietro/nobackup/repo/pandas/pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5832)() 137 util.set_value_at(arr, loc, value) 138 --> 139 cpdef get_loc(self, object val): 140 if is_definitely_invalid_key(val): 141 raise TypeError("'{val}' is an invalid key".format(val=val))

/home/pietro/nobackup/repo/pandas/pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc (pandas/_libs/index.c:5678)() 159 160 try: --> 161 return self.mapping.get_item(val) 162 except (TypeError, ValueError): 163 raise KeyError(val)

/home/pietro/nobackup/repo/pandas/pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:21018)() 1263 sizeof(uint32_t)) # flags 1264 -> 1265 cpdef get_item(self, object val): 1266 cdef khiter_t k 1267 if val != val or val is None:

/home/pietro/nobackup/repo/pandas/pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.PyObjectHashTable.get_item (pandas/_libs/hashtable.c:20972)() 1271 return self.table.vals[k] 1272 else: -> 1273 raise KeyError(val) 1274 1275 cpdef set_item(self, object key, Py_ssize_t val):

KeyError: (2, nan)

In [4]: mi.get_indexer(mi.copy()) Out[4]: array([ 0, -1, 2, -1])

In [5]: mi == mi.copy() Out[5]: array([ True, False, True, False], dtype=bool)

Problem description

I think this is actually the cause for this example, which is different from the one reported at the top of #18455 .

Expected Output

array([ 0, 1, 2, 3])

Output of pd.show_versions()

INSTALLED VERSIONS

commit: b45325e
python: 3.5.3.final.0
python-bits: 64
OS: Linux
OS-release: 4.9.0-4-amd64
machine: x86_64
processor:
byteorder: little
LC_ALL: None
LANG: en_GB.UTF-8
LOCALE: en_GB.UTF-8

pandas: 0.22.0.dev0+201.gb45325e28
pytest: 3.0.6
pip: 9.0.1
setuptools: 33.1.1
Cython: 0.25.2
numpy: 1.12.1
scipy: 0.18.1
pyarrow: None
xarray: None
IPython: 5.2.2
sphinx: None
patsy: 0.4.1+dev
dateutil: 2.6.0
pytz: 2016.10
blosc: None
bottleneck: 1.2.0
tables: 3.3.0
numexpr: 2.6.1
feather: 0.3.1
matplotlib: 2.0.0
openpyxl: 2.3.0
xlrd: 1.0.0
xlwt: 1.2.0
xlsxwriter: None
lxml: 3.7.1
bs4: 4.5.3
html5lib: 0.999999999
sqlalchemy: 1.0.15
pymysql: None
psycopg2: None
jinja2: 2.8
s3fs: None
fastparquet: None
pandas_gbq: None
pandas_datareader: None