MultiIndexHashEngine can't manage mixed type tuples · Issue #18520 · pandas-dev/pandas (original) (raw)

Code Sample, a copy-pastable example if possible

In [2]: mi = pd.MultiIndex.from_product([[True, False], range(1, 10)])

In [3]: mi.get_loc((False, 1)) Out[3]: 9

In [4]: mi = pd.MultiIndex.from_product([[True, False], range(1, 10000)])

In [5]: mi.get_loc((False, 1))

ValueError Traceback (most recent call last) in () ----> 1 mi.get_loc((False, 1))

/home/pietro/nobackup/repo/pandas/pandas/core/indexes/multi.py in get_loc(self, key, method) 2134 key = _values_from_object(key) 2135 key = tuple(map(_maybe_str_to_time_stamp, key, self.levels)) -> 2136 return self._engine.get_loc(key) 2137 2138 # -- partial selection or non-unique index

/home/pietro/nobackup/repo/pandas/pandas/_libs/index.pyx in pandas._libs.index.MultiIndexHashEngine.get_loc (pandas/_libs/index.c:15854)()

/home/pietro/nobackup/repo/pandas/pandas/_libs/index.pyx in pandas._libs.index.MultiIndexHashEngine.get_loc (pandas/_libs/index.c:15701)()

/home/pietro/nobackup/repo/pandas/pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.MultiIndexHashTable.get_item (pandas/_libs/hashtable.c:24621)()

/home/pietro/nobackup/repo/pandas/pandas/_libs/hashtable_class_helper.pxi in pandas._libs.hashtable.MultiIndexHashTable.get_item (pandas/_libs/hashtable.c:24468)()

/home/pietro/nobackup/repo/pandas/pandas/core/indexes/multi.py in _hashed_indexing_key(self, key) 819 key = tuple([f(k, stringify) 820 for k, stringify in zip(key, self._have_mixed_levels)]) --> 821 return hash_tuple(key) 822 823 @Appender(base._shared_docs['duplicated'] % _index_doc_kwargs)

/home/pietro/nobackup/repo/pandas/pandas/core/util/hashing.py in hash_tuple(val, encoding, hash_key) 186 for v in val) 187 --> 188 h = _combine_hash_arrays(hashes, len(val))[0] 189 190 return h

/home/pietro/nobackup/repo/pandas/pandas/core/util/hashing.py in _combine_hash_arrays(arrays, num_items) 31 """ 32 try: ---> 33 first = next(arrays) 34 except StopIteration: 35 return np.array([], dtype=np.uint64)

/home/pietro/nobackup/repo/pandas/pandas/core/util/hashing.py in (.0) 184 """ 185 hashes = (_hash_scalar(v, encoding=encoding, hash_key=hash_key) --> 186 for v in val) 187 188 h = _combine_hash_arrays(hashes, len(val))[0]

/home/pietro/nobackup/repo/pandas/pandas/core/util/hashing.py in _hash_scalar(val, encoding, hash_key) 330 331 return hash_array(vals, hash_key=hash_key, encoding=encoding, --> 332 categorize=False)

/home/pietro/nobackup/repo/pandas/pandas/core/util/hashing.py in hash_array(vals, encoding, hash_key, categorize) 290 291 try: --> 292 vals = hashing.hash_object_array(vals, hash_key, encoding) 293 except TypeError: 294 # we have mixed types

/home/pietro/nobackup/repo/pandas/pandas/_libs/hashing.pyx in pandas._libs.hashing.hash_object_array (pandas/_libs/hashing.c:1764)()

ValueError: Does not understand character buffer dtype format string ('?')

In [6]: mi = pd.MultiIndex.from_product([[1, 0], range(1, 10000)])

In [7]: mi.get_loc((1, 1)) Out[7]: 0

Problem description

The two engines should give the same result.

Expected Output

Out[3]:

Output of pd.show_versions()

INSTALLED VERSIONS

commit: f745e52
python: 3.5.3.final.0
python-bits: 64
OS: Linux
OS-release: 4.9.0-3-amd64
machine: x86_64
processor:
byteorder: little
LC_ALL: None
LANG: it_IT.UTF-8
LOCALE: it_IT.UTF-8

pandas: 0.22.0.dev0+241.gf745e52e1.dirty
pytest: 3.2.3
pip: 9.0.1
setuptools: 36.7.0
Cython: 0.25.2
numpy: 1.12.1
scipy: 0.19.0
pyarrow: None
xarray: None
IPython: 6.2.1
sphinx: 1.5.6
patsy: 0.4.1
dateutil: 2.6.1
pytz: 2017.2
blosc: None
bottleneck: 1.2.0dev
tables: 3.3.0
numexpr: 2.6.1
feather: 0.3.1
matplotlib: 2.0.0
openpyxl: None
xlrd: 1.0.0
xlwt: 1.1.2
xlsxwriter: 0.9.6
lxml: None
bs4: 4.5.3
html5lib: 0.999999999
sqlalchemy: 1.0.15
pymysql: None
psycopg2: None
jinja2: 2.10
s3fs: None
fastparquet: None
pandas_gbq: None
pandas_datareader: 0.2.1