BUG: read_pickle and categorical data

[fkaufer]

I can pickle dataframes with categoricals but not import them again. Since HDF is officially not supported yet: is there any working alternative for persistence of categoricals?

df = pd.DataFrame({'a':['x','y','x']})

df.to_pickle('/tmp/df.pkl')
pd.read_pickle('/tmp/df.pkl')

df['a'] = df['a'].astype('category')

df.to_pickle('/tmp/dfcat.pkl')
pd.read_pickle('/tmp/dfcat.pkl')

TypeError                                 Traceback (most recent call last)
<ipython-input-21-57b10ac045a6> in <module>()
      7 
      8 df.to_pickle('/tmp/dfcat.pkl')
----> 9 pd.read_pickle('/tmp/dfcat.pkl')

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/io/pickle.pyc in read_pickle(path)
     58 
     59     try:
---> 60         return try_read(path)
     61     except:
     62         if PY3:

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/io/pickle.pyc in try_read(path, encoding)
     55             except:
     56                 with open(path, 'rb') as fh:
---> 57                     return pc.load(fh, encoding=encoding, compat=True)
     58 
     59     try:

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/compat/pickle_compat.pyc in load(fh, encoding, compat, is_verbose)
    114         up.is_verbose = is_verbose
    115 
--> 116         return up.load()
    117     except:
    118         raise

//anaconda/envs/pd15/lib/python2.7/pickle.pyc in load(self)
    856             while 1:
    857                 key = read(1)
--> 858                 dispatch[key](self)
    859         except _Stop, stopinst:
    860             return stopinst.value

//anaconda/envs/pd15/lib/python2.7/pickle.pyc in load_build(self)
   1215         setstate = getattr(inst, "__setstate__", None)
   1216         if setstate:
-> 1217             setstate(state)
   1218             return
   1219         slotstate = None

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/core/internals.pyc in __setstate__(self, state)
   2311             self.blocks = tuple(
   2312                 unpickle_block(b['values'], b['mgr_locs'])
-> 2313                 for b in state['blocks'])
   2314         else:
   2315             # discard anything after 3rd, support beta pickling format for a

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/core/internals.pyc in <genexpr>((b,))
   2311             self.blocks = tuple(
   2312                 unpickle_block(b['values'], b['mgr_locs'])
-> 2313                 for b in state['blocks'])
   2314         else:
   2315             # discard anything after 3rd, support beta pickling format for a

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/core/internals.pyc in unpickle_block(values, mgr_locs)
   2303             if values.dtype == 'M8[us]':
   2304                 values = values.astype('M8[ns]')
-> 2305             return make_block(values, placement=mgr_locs)
   2306 
   2307         if (isinstance(state, tuple) and len(state) >= 4

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/core/internals.pyc in make_block(values, placement, klass, ndim, dtype, fastpath)
   2075 
   2076     return klass(values, ndim=ndim, fastpath=fastpath,
-> 2077                  placement=placement)
   2078 
   2079 

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/core/internals.pyc in __init__(self, values, placement, fastpath, **kwargs)
   1583         super(CategoricalBlock, self).__init__(_maybe_to_categorical(values),
   1584                                                fastpath=True, placement=placement,
-> 1585                                                **kwargs)
   1586 
   1587     @property

//anaconda/envs/pd15/lib/python2.7/site-packages/pandas-0.15.0rc1_10_g215569a-py2.7-macosx-10.5-x86_64.egg/pandas/core/internals.pyc in __init__(self, values, placement, ndim, fastpath)
   1073         # kludgetastic
   1074         if ndim is None:
-> 1075             if len(placement) != 1:
   1076                 ndim = 1
   1077             else:

TypeError: object of type 'slice' has no len()

INSTALLED VERSIONS

commit: None
python: 2.7.8.final.0
python-bits: 64
OS: Darwin
OS-release: 13.4.0
machine: x86_64
processor: i386
byteorder: little
pandas: 0.15.0rc1-10-g215569a

[immerrr]

Looking into this.