def calculate_viterbi_matrix(N, states, sents, ngram_counts, l, vectors, sentiment_counts, word_lists, popular_words, tags):
M = [[0 for x in range(len(sents))] for x in range(len(states))]
# Populate the first column for the first sentence
for i in range(len(states)):
state = states[i]
ngram = ()
for j in range(0, N-1):
ngram += ("<p>", )
ngram += (state, )
cell_prob = prior_prob.calc_prob(ngram_counts, l, ngram)
cell_prob += likelihood.calc_sentiment_prob(vectors, sentiment_counts, sents[0], state, word_lists, popular_words, tags[0])
M[i][0] = dict()
M[i][0]['prob'] = cell_prob
M[i][0]['ngram'] = ngram
M[i][0]['prev'] = "<p>"
# Populate the rest of the columns
for cur_sent in range(1, len(sents)):
max_prev_prob = float('-infinity')
max_prev_prob_sent = None
for cur_state in range(0, len(states)):
state = states[cur_state]
max_prob = float('-infinity')
max_ngram = ()
prev = None
for test_state in range(0, len(states)):
test_ngram = M[test_state][cur_sent-1]['ngram']
test_ngram = test_ngram[1:] + (state, )
test_prev_prob = M[test_state][cur_sent-1]['prob']
test_prob = test_prev_prob + prior_prob.calc_prob(ngram_counts, l, test_ngram)
if test_prev_prob > max_prev_prob:
max_prev_prob = test_prev_prob
max_prev_prob_sent = states[test_state]
if test_prob > max_prob:
max_prob = test_prob
max_ngram = test_ngram
cell_prob = max_prob + likelihood.calc_sentiment_prob(vectors, sentiment_counts, sents[cur_sent], state, word_lists, popular_words, tags[cur_sent], max_prev_prob_sent)
M[cur_state][cur_sent] = dict()
M[cur_state][cur_sent]['prob'] = cell_prob
M[cur_state][cur_sent]['ngram'] = max_ngram
M[cur_state][cur_sent]['prev'] = max_ngram[N-2]
return M
def backtrace_viterbi(M, states, ngram_counts, l):
num_states = len(M)
num_sents = len(M[0])
max_prob = float('-infinity')
max_prev = None
result = []
for j in range(num_states):
prob = M[j][num_sents-1]['prob']
prev = M[j][num_sents-1]['prev']
test_ngram = M[j][num_sents-1]['ngram']
test_ngram = test_ngram[1:] + ("</p>", )
test_prob = prob + prior_prob.calc_prob(ngram_counts, l, test_ngram)
if test_prob > max_prob:
state = states[j]
max_prob = test_prob
max_prev = prev
result.append(state)
next_prev = max_prev
for i in range(num_sents-2, -1, -1):
max_prev = next_prev
for j in range(num_states):
if states[j] == max_prev:
result.append(max_prev)
next_prev = M[j][i]['prev']
result.reverse()
return result
