Hi scikit community,
I am playing around with the Hidden Markov Mode module (multinomialHMM) and
one thing I don't understand is why scikit accepts emission probabilities
that add up to more or less than 1.
Here is an example with two states and three emission signals:
>>> import numpy
>>> from sklearn import hmm
>>> startprob = numpy.array([0.5, 0.5])
>>> transition_matrix = numpy.array([[0.5, 0.5], [0.5, 0.5]])
>>> model = hmm.MultinomialHMM(2, startprob, transition_matrix)
>>> model.emissionprob_ = numpy.array([[0, 0, 0.2], [0.6, 0.35, 0.05]])
As you can see, I am specifying the emission proabilities for state 0 as
[0, 0, 0.2]. Scikit accepts this and generates predications with no
complaints. Is this desired behavior? Do these probabilities get normalized?
Thanks,
Anas
------------------------------------------------------------------------------
Is your legacy SCM system holding you back? Join Perforce May 7 to find out:
• 3 signs your SCM is hindering your productivity
• Requirements for releasing software faster
• Expert tips and advice for migrating your SCM now
http://p.sf.net/sfu/perforce
_______________________________________________
Scikit-learn-general mailing list
Scikit-learn-general@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
