# (C) May 2009, Mathieu Blondel

import sys
sys.path.append('/home/mathieu/Desktop/sources/jahmm-0.6.1.jar')

from be.ac.ulg.montefiore.run.jahmm import ObservationInteger
from be.ac.ulg.montefiore.run.jahmm import OpdfInteger
from be.ac.ulg.montefiore.run.jahmm import Hmm
from be.ac.ulg.montefiore.run.jahmm.toolbox import MarkovGenerator
from be.ac.ulg.montefiore.run.jahmm.learn import BaumWelchLearner

from java.util import ArrayList

STATES = ["rainy", "sunny"]
OBSERVATIONS = ["walk", "shop", "clean"]

def state_indices_to_names(indices):
    return [STATES[i] for i in indices]

def observations_to_names(obs):
    return [OBSERVATIONS[o.value] for o in obs]

def names_to_observations(names):
    arr = [ObservationInteger(OBSERVATIONS.index(n)) for n in names]
    return ArrayList(arr)

rainyopdf = OpdfInteger([0.1, 0.4, 0.5])
sunnyopdf = OpdfInteger([0.6, 0.3, 0.1])

pi = [0.6, 0.4]
a = [[0.7, 0.3], [0.4, 0.6]]
b = ArrayList([rainyopdf, sunnyopdf])

hmm = Hmm(pi, a, b)

# We generate fake data with the Markov generator.
# In the real world, we would use real training data.
# Don't forget that HMM are *generative* models ;)
obs_set = ArrayList()
generator = MarkovGenerator(hmm)

from random import randint

for i in range(100):
    # we generate 100 sequences of 20 + k observations where k is variable
    # to show that sequences can be of variable length
    obs_set.add(generator.observationSequence(20 + randint(0, 10)))

# We train our HMM with our fake data
print "HMM, before training"
print str(hmm) + "\n"

learner = BaumWelchLearner()
hmm = learner.learn(hmm, obs_set)

# Note that it shouldn't change that much since we trained the HMM
# with observations generated from itself
print "HMM, after training"
print str(hmm) + "\n"

# Now let's find the log likelihood of a sample sequence
obs = ["walk", "walk", "shop", "clean", "clean"]
print "Log likelihood for", obs
print hmm.lnProbability(names_to_observations(obs))
 
print "Viterbi sequence"
seq = hmm.mostLikelyStateSequence(names_to_observations(obs))
print ", ".join(state_indices_to_names(seq))