regevs/factorial_hmm

FactorialHMM, a Python package for fast exact inference in Factorial Hidden Markov Models

factorial_hmm's Issues

EM on multiple sequences of observed states

I would be nice to have the EM method of FullDiscreteFactorialHMM also support multiple sequences of observed states.
For instance, the fit method of hmmlearn allows parameters estimation from multiple sequences for basic (i.e., non-factorial) HMMs (see https://github.com/hmmlearn/hmmlearn/blob/master/lib/hmmlearn/base.py#L440-L488).

This probably requires to split MStep in two parts: the former (equivalent of hmmlearn's _accumulate_sufficient_statistics) will collect statistics about the parameters and will need to be called on every sequence of observed states; the latter (equivalent of hmmlearn's _do_mstep) will be required to normalize the parameters and will need to be called only once per iteration.

MultiplyTransitionMatrixVector doesn't work for me

I'm having trouble following the logic of the MultiplyTransitionMatrixVector function and I have thusfar been unable to get this function to work as demonstrated by the simple example below... Any guidance would be greatly appreciated -- thanks!

Python 3.7.1 (default, Dec 14 2018, 13:28:58) 
Type 'copyright', 'credits' or 'license' for more information
IPython 7.2.0 -- An enhanced Interactive Python. Type '?' for help.

In [1]: from factorial_hmm_test import *                                                                                        

In [2]: from factorial_hmm import *                                                                                             

In [3]: model = ExampleFullDiscreteFactorialHMM(11)                                                                             

In [4]: model.GetTransitionMatrix(0) @ np.random.randn(16)                                                                      
Out[4]: 
array([-0.0381503 ,  0.08041185, -0.07615602,  0.4513467 , -0.06822525,
        0.02532833, -0.37132319,  0.41988943, -0.06897605, -0.00527082,
       -0.16544137,  0.1655481 , -0.0785179 , -0.04276934, -0.54833598,
        0.15224777])

In [5]: model.MultiplyTransitionMatrixVector(0, np.random.randn(16))                                                            
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-5-1777e0d59086> in <module>
----> 1 model.MultiplyTransitionMatrixVector(0, np.random.randn(16))

~/code/factorial_hmm/factorial_hmm.py in MultiplyTransitionMatrixVector(self, n_step, vector, transpose)
     74                 vector,
     75                 self.idx_in,
---> 76                 self.idx_out[i],
     77                 )
     78 

<__array_function__ internals> in einsum(*args, **kwargs)

~/anaconda3/lib/python3.7/site-packages/numpy/core/einsumfunc.py in einsum(*operands, **kwargs)
   1354     # If no optimization, run pure einsum
   1355     if optimize_arg is False:
-> 1356         return c_einsum(*operands, **kwargs)
   1357 
   1358     valid_einsum_kwargs = ['out', 'dtype', 'order', 'casting']

ValueError: einstein sum subscripts string contains too many subscripts for operand 1