def train_iteration(self, filepath):
viterbi = Viterbi("EMPTY")
viterbi.v = self.v
with open(filepath) as train_file:
corpus = gen_sentence_train(train_file)
count = 0
for doc in corpus:
count += 1
if count % 1000 == 0:
_logger.debug("%d sentence processed" % count)
sent = [s[0] for s in doc]
tags = [s[1] for s in doc]
tags_pred = viterbi.decode_one(list(sent))
assert len(sent) == len(tags) == len(tags_pred)
feat_gold = feat_vect(sent, tags)
feat_pred = feat_vect(sent, tags_pred)
for feat in feat_pred:
self.v[feat] -= feat_pred[feat]
for feat in feat_gold:
self.v[feat] += feat_gold[feat]
