class IceCreamHMM(TestCase):
def setUp(self):
"""Initialize Eisner ice cream HMM (J & M, Figure 6.3)"""
self.hmm = HMM()
# These variables have many aliases. J & M call them π, A, B, Q, and V.
# You don't need to use these names, but you do need to provide a way
# of initializing them.
self.hmm.train(
[],
initial_probabilities=[.8, .2], # P(Hot, Cold)
transition_probabilities=[
[.7, .3], # P(Hot, Cold|Hot)
[.4, .6]
], # P(Hot, Cold|Cold)
emission_probabilities=[
[.2, .4, .4], # P(1, 2, 3|Hot)
[.5, .4, .1]
], # P(1, 2, 3|Cold)
states=("Hot", "Cold"),
vocabulary=(1, 2, 3))
def test_likelihood(self):
"""Test likelihood for Eisner ice cream HMM (J & M, Figure 6.7)"""
# Figure 6.7 of J & M (slide 15 of Lecture6_Handout.pdf, 2014-10-15)
# has a known erratum in the computation of alpha_2(2): .7*.2 = .14,
# not .014.
self.assertAlmostEqual(self.hmm.likelihood(IceCreamCones(
[3, 1])), (.32 * .14 + .02 * .08) + (.32 * .15 + .02 * .30))
def test_decoding(self):
"""Test decoding of Eisner ice cream HMM (J & M, Section 6.4)"""
# The same error occurs in Figure 6.10, but the value given for the
# Viterbi variable v_2(2) is .0448, which is correct (as you should
# verify manually and perhaps add a test for here).
self.assertAlmostEqual(
self.hmm.classify(IceCreamCones([3, 1, 3]), Test=True, T=1)[0],
max(.32 * .14, .02 * .08))
self.assertAlmostEqual(
self.hmm.classify(IceCreamCones([3, 1, 3]), Test=True, T=1)[1],
max(.32 * .15, .02 * .30))
#Test the value at time step 2
self.assertEqual(self.hmm.classify(IceCreamCones([3, 1, 3])),
["Hot", "Hot", "Hot"])
class TagHMM(TestCase):
"""Train and test an HMM POS tagger."""
def setUp(self):
self.train, self.test = self.split_sents()
self.hmm = HMM()
self.hmm.train(self.train)
def split_sents(self,
train=0.95,
total=3500,
document_class=TaggedSentence):
sents = tagged_corpus.tagged_sents()[:total]
total = len(sents) if total is None else total
i = int(round(train * total))
j = i + int(round(total - train * total))
return (map(document_class, sents[0:i]), map(document_class,
sents[i:j]))
def accuracy(self, test_sents, verbose=sys.stderr):
"""Compute accuracy of the HMM tagger on the given sentences."""
total = correct = 0
for sent in test_sents:
tags = self.hmm.classify(sent)
total += len(tags)
for guess, tag in zip(tags, sent.label):
correct += (guess == tag)
if verbose:
print >> verbose, "%.2d%% " % (100 * correct / total),
return correct / total
@skip("too slow")
def test_tag_train(self):
"""Tag the training data"""
self.assertGreater(self.accuracy(self.train), 0.85)
def test_tag(self):
"""Tag the test data"""
self.assertGreater(self.accuracy(self.test), 0.85)
class TagHMM(TestCase):
"""Train and test an HMM POS tagger."""
def setUp(self):
self.train, self.test = self.split_sents()
self.hmm = HMM()
self.hmm.train(self.train)
def split_sents(self, train=0.95, total=3500,
document_class=TaggedSentence):
sents = tagged_corpus.tagged_sents()[:total]
total = len(sents) if total is None else total
i = int(round(train * total))
j = i + int(round(total - train * total))
return (map(document_class, sents[0:i]),
map(document_class, sents[i:j]))
def accuracy(self, test_sents, verbose=sys.stderr):
"""Compute accuracy of the HMM tagger on the given sentences."""
total = correct = 0
for sent in test_sents:
tags = self.hmm.classify(sent)
total += len(tags)
for guess, tag in zip(tags, sent.label):
correct += (guess == tag)
if verbose:
print >> verbose, "%.2d%% " % (100 * correct / total),
return correct / total
@skip("too slow")
def test_tag_train(self):
"""Tag the training data"""
self.assertGreater(self.accuracy(self.train), 0.85)
def test_tag(self):
"""Tag the test data"""
self.assertGreater(self.accuracy(self.test), 0.85)
if __name__ == "__main__":
hmm = HMM()
hmm.train(
[],
initial_probabilities=[.5, .5], # P(non-coding, Coding)
transition_probabilities=[
[.95, .05], # P(Hot, Cold|Hot)
[.15, .85]
], # P(Hot, Cold|Cold)
emission_probabilities=[
[.4, .1, .1, .4], # P(1, 2, 3|Hot)
[.2, .3, .3, .2]
], # P(1, 2, 3|Cold)
states=("1", "2"), #noncoding,coding
vocabulary=('A', 'C', 'G', 'T'))
print hmm.likelihood(Gene(['T', 'G', 'C', 'A']))
print hmm.classify(
Gene([
'G', 'C', 'G', 'C', 'A', 'T', 'T', 'A', 'A', 'T', 'C', 'G', 'T',
'C', 'G', 'T', 'C', 'G', 'T', 'A', 'G', 'T', 'T', 'C', 'C', 'T',
'T'
]))
print hmm.classify(
Gene([
'G', 'C', 'G', 'C', 'A', 'T', 'T', 'A', 'A', 'T', 'C', 'G', 'T',
'C', 'G', 'G', 'T', 'C', 'G', 'T', 'A', 'G', 'T', 'T', 'C', 'C',
'T', 'T'
]))
