if __name__ == '__main__':
# traindata = dataset.get_swedish_train_corpus().parsed_sents()
traindata = dataset.get_english_train_corpus().parsed_sents()
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(traindata)
# tp.save('swedish.model')
# labeleddata = dataset.get_swedish_dev_corpus().parsed_sents()
# blinddata = dataset.get_swedish_dev_blind_corpus().parsed_sents()
tp.save('english.model')
labeleddata = dataset.get_english_dev_corpus().parsed_sents()
blinddata = dataset.get_english_dev_blind_corpus().parsed_sents()
#tp = TransitionParser.load('badfeatures.model')
# parsed = tp.parse(labeleddata)
parsed = tp.parse(blinddata)
with open('test.conll', 'w') as f:
for p in parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
ev = DependencyEvaluator(labeleddata, parsed)
print "UAS: {} \nLAS: {}".format(*ev.eval())
if __name__ == '__main__':
#traindata = dataset.get_swedish_train_corpus().parsed_sents()
traindata = dataset.get_english_train_corpus().parsed_sents()
#traindata = dataset.get_danish_train_corpus().parsed_sents()
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(traindata)
#tp.save('swedish.model')
#tp.save('english.model')
### tp.save('danish.model')
#labeleddata = dataset.get_swedish_dev_corpus().parsed_sents()
labeleddata = dataset.get_english_dev_corpus().parsed_sents()
#labeleddata = dataset.get_danish_dev_corpus().parsed_sents()
#blinddata = dataset.get_swedish_dev_blind_corpus().parsed_sents()
blinddata = dataset.get_english_dev_blind_corpus().parsed_sents()
#blinddata = dataset.get_danish_dev_blind_corpus().parsed_sents()
#tp = TransitionParser.load('badfeatures.model')
parsed = tp.parse(blinddata)
with open('test.conll', 'w') as f:
for p in parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
ev = DependencyEvaluator(labeleddata, parsed)
f.write('\n')
ev = DependencyEvaluator(testdata, parsed)
print 'Swedish results'
print "UAS: {} \nLAS: {}".format(*ev.eval())
# english
print '\n----------------------\n'
print 'Training english'
tpe = TransitionParser(Transition, FeatureExtractor)
tpe.train(english_subdata)
tpe.save('english.model')
print 'testing english'
testdataE = dataset.get_english_dev_corpus().parsed_sents()
tpe = TransitionParser.load('english.model')
parsede = tpe.parse(testdataE)
eve = DependencyEvaluator(testdataE, parsede)
print 'English results'
print "UAS: {} \nLAS: {}".format(*eve.eval())
# danish
print '\n----------------------\n'
print 'Training Danish'
tpD = TransitionParser(Transition, FeatureExtractor)
tpD.train(danish_subdata)
tpD.save('danish.model')
