# (C) May 2009, Mathieu Blondel

require 'java'
require '/home/mathieu/Desktop/sources/jahmm-0.6.1.jar'

include_class 'be.ac.ulg.montefiore.run.jahmm.ObservationInteger'
include_class 'be.ac.ulg.montefiore.run.jahmm.OpdfInteger'
include_class 'be.ac.ulg.montefiore.run.jahmm.Hmm'
include_class 'be.ac.ulg.montefiore.run.jahmm.toolbox.MarkovGenerator'
include_class 'be.ac.ulg.montefiore.run.jahmm.learn.BaumWelchLearner'

import java.util.ArrayList

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

class Array
    # Converts a Ruby array of floats to a Java double array.
    # Supports one-dimension and two-dimension arrays.
    def to_double
        if JRUBY_VERSION =~ /^1.0/
            # This works for both one and two-dimensonal arrays.
            self.to_java(:double)
        else
            if self.length > 0 and self[0].is_a? Array
                self.to_java(Java::double[])
            else
                self.to_java(:double)
            end
        end
    end
end

def state_indices_to_names(indices)
    indices.to_a.map { |i| STATES[i] }
end

def observations_to_names(obs)
    obs.to_a.map { |o| OBSERVATIONS[o.value] }
end

def names_to_observations(names)
    arr = names.map { |n| ObservationInteger.new(OBSERVATIONS.index(n)) }
    ArrayList.new(arr)
end

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

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

hmm = Hmm.new(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.new
generator = MarkovGenerator.new(hmm)

100.times do
    # we generate 100 sequences of 20 + k observations where k is variable
    # to show that sequences can be of variable length
    obs_set << generator.observation_sequence(20 + rand(10))
end

# We train our HMM with our fake data
puts "HMM, before training"
puts hmm.to_s + "\n"

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

# Note that it shouldn't change that much since we trained the HMM
# with observations generated from itself
puts "HMM, after training"
puts hmm.to_s + "\n"

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