def get_train_data_from_lang(lang):
if lang == 'swedish':
return dataset.get_swedish_train_corpus().parsed_sents()
elif lang == 'danish':
return dataset.get_danish_train_corpus().parsed_sents()
elif lang == 'english':
return dataset.get_english_train_corpus().parsed_sents()
else:
raise ValueError(
"Please don't use {}, only use english, swedish or danish".format(
lang))
from providedcode import dataset
from providedcode.transitionparser import TransitionParser
from providedcode.evaluate import DependencyEvaluator
from featureextractor import FeatureExtractor
from transition import Transition
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)
from providedcode import dataset
from providedcode.transitionparser import TransitionParser
from providedcode.evaluate import DependencyEvaluator
from featureextractor import FeatureExtractor
from transition import Transition
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'))