def train_hmm(train_set, observations, index_features):
'''Training the hmms...'''
# symbols is a vector of inputs, each input is a vector of features (requires to be tuples by nltk)
# we don't need to specify the states so we choose 1 and 2
trainer = HiddenMarkovModelTrainer(states=[1, 2], symbols=observations)
hmms = {}
for cat in train_set.keys():
print "Training HMM of cat:", cat
tuple_sentences = []
for sentence in train_set[cat]:
'''tuple_sentence = [(tuple(word),'') for word in sentence]
tuple_sentences.append(tuple_sentence)
'''
'''feature subset selection'''
new_sentence = []
for word in sentence:
new_word = []
for feature in index_features:
new_word.append(word[feature])
new_sentence.append(new_word)
tuple_sentence = [(tuple(word), '') for word in new_sentence]
tuple_sentences.append(tuple_sentence)
# sentence is a list of list! so w is a list of feature not only a word!
hmms[cat] = trainer.train_unsupervised(tuple_sentences,
max_iterations=10)
return hmms
def train_hmm(train_set, observations, index_features):
"""Training the hmms..."""
# symbols is a vector of inputs, each input is a vector of features (requires to be tuples by nltk)
# we don't need to specify the states so we choose 1 and 2
trainer = HiddenMarkovModelTrainer(states=[1, 2], symbols=observations)
hmms = {}
for cat in train_set.keys():
print "Training HMM of cat:", cat
tuple_sentences = []
for sentence in train_set[cat]:
"""tuple_sentence = [(tuple(word),'') for word in sentence]
tuple_sentences.append(tuple_sentence)
"""
"""feature subset selection"""
new_sentence = []
for word in sentence:
new_word = []
for feature in index_features:
new_word.append(word[feature])
new_sentence.append(new_word)
tuple_sentence = [(tuple(word), "") for word in new_sentence]
tuple_sentences.append(tuple_sentence)
# sentence is a list of list! so w is a list of feature not only a word!
hmms[cat] = trainer.train_unsupervised(tuple_sentences, max_iterations=10)
return hmms
