def main():
with open('model.pickle') as f:
vectorizer, model = pickle.load(f)
for hyp1, hyp2, ref in sentences():
f1 = features.extract(ref, hyp1)
f2 = features.extract(ref, hyp2)
f = features.diff(f2, f1)
if f['min_match'] == f['min_match2'] == f['min_match3'] == 0:
print 0
continue
score = model.predict(vectorizer.transform((f,))) # w . (f_2 - f_1)
if score > 0:
print 1
else:
print -1
def training_data(sentence_fn, score_fn):
for (hyp1, hyp2, ref), score in izip(sentences(sentence_fn), scores(score_fn)):
f1 = features.extract(ref, hyp1)
f2 = features.extract(ref, hyp2)
yield features.diff(f2, f1), score # score = f2 > f1
