def train_model(lang,training_set='train'):
# load and sample data
data = get_data(lang,dataset=training_set).parsed_sents()
if len(data) >200:
random.seed(1234)
subdata = random.sample(data, 200)
else:
subdata = data
# train model and save
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(subdata)
tp.save('{0}.model'.format(lang))
# test performance on new data
if lang != 'english':
testdata = get_data(lang,dataset='test').parsed_sents()
# english test data not available
# so find a subset of training data
# that is disjoint from data used for training
else:
not_in_training = [sent for sent in data if sent not in subdata]
testdata = random.sample(not_in_training,200)
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
# store and print results
with open('results.txt','a') as results_file:
results_file.write('{0} model:\n'.format(lang))
results_file.write("UAS: {} \nLAS: {}\n".format(*ev.eval()))
print '{0} model:\n'.format(lang)
print "UAS: {} \nLAS: {}\n".format(*ev.eval())
return ev.eval()[1]
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)
print "UAS: {} \nLAS: {}".format(*ev.eval())
# parsing arbitrary sentences (english):
# sentence = DependencyGraph.from_sentence('Hi, this is a test')
# tp = TransitionParser.load('english.model')
# parsed = tp.parse([sentence])
# print parsed[0].to_conll(10).encode('utf-8')
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())
# parsing arbitrary sentences (english):
# sentence = DependencyGraph.from_sentence('Hi, this is a test')
# tp = TransitionParser.load('english.model')
# parsed = tp.parse([sentence])
# print parsed[0].to_conll(10).encode('utf-8')
# tp.train(SE_subdata)
# tp.save('swedish.model')
# SE_testdata = dataset.get_swedish_test_corpus().parsed_sents()
# SE_tp = TransitionParser.load('swedish.model')
# SE_parsed = SE_tp.parse(SE_testdata)
#
# DK
tp = TransitionParser(Transition, FeatureExtractor)
print('Training...')
tp.train(DK_subdata)
print('Ok. Saving the model...')
tp.save('danish.model')
print('Ok. Parsing the test corpus...')
DK_testdata = dataset.get_danish_test_corpus().parsed_sents()
#DK_tp = TransitionParser.load('danish.model')
DK_parsed = tp.parse(DK_testdata)
print('Ok.')
# with open('english.conll', 'w') as f:
# for p in EN_parsed:
# f.write(p.to_conll(10).encode('utf-8'))
# f.write('\n')
#
# ev = DependencyEvaluator(EN_testdata, EN_parsed)
# print('Evaluating EN model...')
# print "LAS: {} \nUAS: {}".format(*ev.eval())
with open('danish.conll', 'w') as f:
for p in DK_parsed:
f.write(p.to_conll(10).encode('utf-8'))
if __name__ == '__main__':
data = dataset.get_swedish_train_corpus().parsed_sents()
random.seed(1234)
subdata = random.sample(data, 200)
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(subdata)
tp.save('swedish.model')
testdata = dataset.get_swedish_test_corpus().parsed_sents()
tp = TransitionParser.load('swedish.model')
parsed = tp.parse(testdata)
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(testdata, parsed)
print "UAS: {} \nLAS: {}".format(*ev.eval())
# parsing arbitrary sentences (swedish):
# sentence = DependencyGraph.from_sentence('Hi, this is a test')
# tp = TransitionParser.load('swedish.model')
# parsed = tp.parse([sentence])
# print parsed[0].to_conll(10).encode('utf-8')
from transition import Transition
if __name__ == '__main__':
data = dataset.get_english_train_corpus().parsed_sents()
random.seed(1234)
subdata = random.sample(data, 200)
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(subdata)
tp.save('english.model')
testdata = dataset.get_english_dev_corpus().parsed_sents()
#tp = TransitionParser.load('badfeatures.model')
parsed = tp.parse(testdata)
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(testdata, parsed)
print "UAS: {} \nLAS: {}".format(*ev.eval())
# parsing arbitrary sentences (english):
# sentence = DependencyGraph.from_sentence('Hi, this is a test')
# tp = TransitionParser.load('english.model')
# parsed = tp.parse([sentence])
# print parsed[0].to_conll(10).encode('utf-8')
subdata = random.sample(data, 200)
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(subdata)
# tp.save('swedish.model')
# tp.save('english.model')
tp.save('danish.model')
# testdata = dataset.get_swedish_test_corpus().parsed_sents()
testdata = dataset.get_danish_test_corpus().parsed_sents()
# tp = TransitionParser.load('badfeatures.model')
# testdata = dataset.get_english_test_corpus().parsed_sents()
# tp = TransitionParser.load('english.model')
parsed = tp.parse(testdata)
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(testdata, parsed)
print "LAS: {} \nUAS: {}".format(*ev.eval())
# parsing arbitrary sentences (english):
sentence = DependencyGraph.from_sentence('Hi, this is a test')
tp = TransitionParser.load('english.model')
parsed = tp.parse([sentence])
print parsed[0].to_conll(10).encode('utf-8')
ev = DependencyEvaluator(testdata, parsed)
print "Bad Features Results"
print "UAS: {} \nLAS: {}".format(*ev.eval())
t1 = time.time()
print "Time: " + str(t1 - t0) + '\n'
# SWEDISH FEATURE MODELS
print 'Starting Swedish'
tp_s = TransitionParser(Transition, FeatureExtractor)
tp_s.train(subdata)
tp_s.save('swedish.model')
testdata = dataset.get_swedish_test_corpus().parsed_sents()
tp_s = TransitionParser.load('swedish.model')
parsed = tp_s.parse(testdata)
with open('swedish.conll', 'w') as f:
for p in parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
ev = DependencyEvaluator(testdata, parsed)
print "Swedish Results"
print "UAS: {} \nLAS: {}".format(*ev.eval())
t2 = time.time()
print "Time: " + str(t2 - t1) + "\n"
# NEED TO ALSO DO DANISH AND ENGLISH, BUT IT'S PRACTICALLY THE SAME
# ENGLISH FEATURE MODELS
# tp.train(SE_subdata)
# tp.save('swedish.model')
# SE_testdata = dataset.get_swedish_test_corpus().parsed_sents()
# SE_tp = TransitionParser.load('swedish.model')
# SE_parsed = SE_tp.parse(SE_testdata)
#
# DK
tp = TransitionParser(Transition, FeatureExtractor)
print('Training...')
tp.train(DK_subdata)
print('Ok. Saving the model...')
tp.save('danish.model')
print('Ok. Parsing the test corpus...')
DK_testdata = dataset.get_danish_test_corpus().parsed_sents()
#DK_tp = TransitionParser.load('danish.model')
DK_parsed = tp.parse(DK_testdata)
print('Ok.')
# with open('english.conll', 'w') as f:
# for p in EN_parsed:
# f.write(p.to_conll(10).encode('utf-8'))
# f.write('\n')
#
# ev = DependencyEvaluator(EN_testdata, EN_parsed)
# print('Evaluating EN model...')
# print "LAS: {} \nUAS: {}".format(*ev.eval())
with open('danish.conll', 'w') as f:
for p in DK_parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
danishsubdata = random.sample(danishdata, 235)
try:
#SWEDISH TESTING
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(swedishsubdata)
tp.save('swedish.model')
#badfeatures.model...don't use for real testing
#tp = TransitionParser.load('badfeatures.model')
testdata = dataset.get_swedish_test_corpus().parsed_sents()
parsed = tp.parse(testdata)
#to write output...for badfeatures.model
'''
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(testdata, parsed)
print "SWEDISH UAS: {} \nLAS: {}".format(*ev.eval())
#DANISH TESTING
tp.train(danishsubdata)
try:
model_path = sys.argv[1]
# print 'ModelPath', model_path
except IndexError as ie:
print 'Model Path Not Specified! Exiting...', ie
sys.exit(-1)
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp = TransitionParser.load(model_path) # load the trained model for parsing.
for line in sys.stdin:
# print 'Processing:', line
sentence = DependencyGraph.from_sentence(line)
parsed = tp.parse([sentence]) # parse the input line
print parsed[0].to_conll(10).encode('utf-8')
# with open('test.conll', 'w') as f:
# for p in parsed:
# f.write(p.to_conll(10).encode('utf-8'))
# f.write('\n')
# parsing arbitrary sentences (english):
# sentence = DependencyGraph.from_sentence('Hi, this is a test')
# tp = TransitionParser.load('english.model')
# parsed = tp.parse([sentence])
# print parsed[0].to_conll(10).encode('utf-8')
except Exception as e:
random.seed()
danish_subdata = random.sample(danish_data, 200)
try:
print 'training swedish'
# swedish
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(swedish_subdata)
tp.save('swedish.model')
testdata = dataset.get_swedish_test_corpus().parsed_sents()
tp = TransitionParser.load('swedish.model')
print 'testing swedish'
parsed = tp.parse(testdata)
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(testdata, parsed)
print 'Swedish results'
print "UAS: {} \nLAS: {}".format(*ev.eval())
# english
print '\n----------------------\n'
print 'Training english'
tpe = TransitionParser(Transition, FeatureExtractor)
ev = DependencyEvaluator(testdata, parsed)
print "Bad Features Results"
print "UAS: {} \nLAS: {}".format(*ev.eval())
t1 = time.time()
print "Time: "+str(t1 - t0) + '\n'
# SWEDISH FEATURE MODELS
print 'Starting Swedish'
tp_s = TransitionParser(Transition, FeatureExtractor)
tp_s.train(subdata)
tp_s.save('swedish.model')
testdata = dataset.get_swedish_test_corpus().parsed_sents()
tp_s = TransitionParser.load('swedish.model')
parsed = tp_s.parse(testdata)
with open('swedish.conll', 'w') as f:
for p in parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
ev = DependencyEvaluator(testdata, parsed)
print "Swedish Results"
print "UAS: {} \nLAS: {}".format(*ev.eval())
t2 = time.time()
print "Time: " + str(t2 - t1) + "\n"
# NEED TO ALSO DO DANISH AND ENGLISH, BUT IT'S PRACTICALLY THE SAME
# ENGLISH FEATURE MODELS
'swedish' : ('swedish.model', dataset.get_swedish_train_corpus, dataset.get_swedish_test_corpus)
}
for model_type, model_tuple in model_dict.iteritems():
model, data, testdata = model_tuple[0], model_tuple[1]().parsed_sents(), model_tuple[2]().parsed_sents()
random.seed(1234)
subdata = random.sample(data, 200) # 200 randomly selected DependencyGraphs(sentences) for model training.
try:
tp = TransitionParser(Transition, FeatureExtractor)
tp.train(subdata) # train with 200 randomly selected dependency graphs(sentences).
tp.save(model) # save the trained model.
tp = TransitionParser.load(model) # load the trained model for parsing.
parsed = tp.parse(testdata) # parse the test data
with open('test.conll', 'w') as f:
for p in parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
# evaluate the test parse result here...
ev = DependencyEvaluator(testdata, parsed)
print 'Model: {}'.format(model_type)
# LAS: labeled attachment score - percentage of scoring tokens for which the parsing system has predicted the
# correct head and dependency label.
# UAS:
print "LAS: {} \nUAS: {}".format(*ev.eval())
# parsing arbitrary sentences (english):
