def verify_lang_data(model, conll_output):
try:
lang = extract_lang_from_model_name(model)
testdata = get_data_from_lang(lang)
tp = TransitionParser.load(model)
parsed = tp.parse(testdata)
with open(conll_output, 'w') as f:
for p in parsed:
f.write(p.to_conll(10).encode('utf-8'))
f.write('\n')
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print "\n=====Prediction of {}.model===== \nUAS: {} \nLAS: {}".format(lang, uas, las)
return las
pass
except ValueError as e:
print(e)
def evaluate_parse(partIdx):
if partIdx == 3:
print 'Evaluating your swedish model ... '
testdata = dataset.get_swedish_test_corpus().parsed_sents()
if not os.path.exists('./swedish.model'):
print 'No model. Please save your model as swedish.model at current directory before submission.'
sys.exit(0)
tp = TransitionParser.load('swedish.model')
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print 'UAS:', uas
print 'LAS:', las
swed_score = (min(las, 0.7) / 0.7)**2
return swed_score
if partIdx == 1:
print 'Evaluating your english model ... '
testdata = dataset.get_english_test_corpus().parsed_sents()
if not os.path.exists('./english.model'):
print 'No model. Please save your model as english.model at current directory before submission.'
sys.exit(0)
tp = TransitionParser.load('english.model')
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print 'UAS:', uas
print 'LAS:', las
eng_score = (min(las, 0.7) / 0.7)**2
return eng_score
if partIdx == 2:
print 'Evaluating your danish model ... '
testdata = dataset.get_danish_test_corpus().parsed_sents()
if not os.path.exists('./danish.model'):
print 'No model. Please save your model danish.model at current directory before submission.'
sys.exit(0)
tp = TransitionParser.load('danish.model')
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print 'UAS:', uas
print 'LAS:', las
dan_score = (min(las, 0.7) / 0.7)**2
return dan_score
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]
def evaluate_parse(partIdx):
if partIdx == 3:
print 'Evaluating your swedish model ... '
testdata = dataset.get_swedish_test_corpus().parsed_sents()
if not os.path.exists('./swedish.model'):
print 'No model. Please save your model as swedish.model at current directory before submission.'
sys.exit(0)
tp = TransitionParser.load('swedish.model')
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print 'UAS:',uas
print 'LAS:',las
swed_score = (min(las, 0.7) / 0.7) ** 2
return swed_score
if partIdx == 1:
print 'Evaluating your english model ... '
testdata = dataset.get_english_test_corpus().parsed_sents()
if not os.path.exists('./english.model'):
print 'No model. Please save your model as english.model at current directory before submission.'
sys.exit(0)
tp = TransitionParser.load('english.model')
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print 'UAS:',uas
print 'LAS:',las
eng_score = (min(las, 0.7) / 0.7) ** 2
return eng_score
if partIdx == 2:
print 'Evaluating your danish model ... '
testdata = dataset.get_danish_test_corpus().parsed_sents()
if not os.path.exists('./danish.model'):
print 'No model. Please save your model danish.model at current directory before submission.'
sys.exit(0)
tp = TransitionParser.load('danish.model')
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
uas, las = ev.eval()
print 'UAS:',uas
print 'LAS:',las
dan_score = (min(las, 0.7) / 0.7) ** 2
return dan_score
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')
except NotImplementedError:
print """
This file is currently broken! We removed the implementation of Transition
(in transition.py), which tells the transitionparser how to go from one
Configuration to another Configuration. This is an essential part of the
arc-eager dependency parsing algorithm, so you should probably fix that :)
try:
# tp = TransitionParser(Transition, FeatureExtractor)
# tp.train(subdata)
# tp.save('swedish.model')
testdata = dataset.get_swedish_test_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 "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')
except NotImplementedError:
print """
This file is currently broken! We removed the implementation of Transition
(in transition.py), which tells the transitionparser how to go from one
Configuration to another Configuration. This is an essential part of the
arc-eager dependency parsing algorithm, so you should probably fix that :)
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')
except NotImplementedError:
print """
This file is currently broken! We removed the implementation of Transition
(in transition.py), which tells the transitionparser how to go from one
Configuration to another Configuration. This is an essential part of the
arc-eager dependency parsing algorithm, so you should probably fix that :)
# testdata = dataset.get_swedish_test_corpus().parsed_sents()
testdata = dataset.get_english_test_corpus().parsed_sents()
# testdata = dataset.get_danish_test_corpus().parsed_sents()
# tp = TransitionParser.load('swedish.model')
tp = TransitionParser.load('english.model')
# tp = TransitionParser.load('danish.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')
except NotImplementedError:
print """
This file is currently broken! We removed the implementation of Transition
(in transition.py), which tells the transitionparser how to go from one
Configuration to another Configuration. This is an essential part of the
arc-eager dependency parsing algorithm, so you should probably fix that :)
subdata_d = random.sample(data_d, 200)
try:
# BAD FEATURES MODEL (SWEDISH DATA)
print "Starting Bad Features"
testdata = dataset.get_swedish_test_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 "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)
#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)
tp.save('danish.model')
testdata = dataset.get_danish_test_corpus().parsed_sents()
parsed = tp.parse(testdata)
ev = DependencyEvaluator(testdata, parsed)
print "DANISH UAS: {} \nLAS: {}".format(*ev.eval())
#KOREAN TESTING
tp.train(koreansubdata)
try:
print "Training {0} model...".format(testName)
tp = TransitionParser(Transition, MyFeatureExtractor)
tp.train(traindata)
tp.save(testName + ".model")
print "Testing {0} model...".format(testName)
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 "Test Results For: {0}".format(testName)
(uas, las) = ev.eval()
points = scoreWeight[testName] * (min(0.7, las)/0.7)**2
totalPoints += points
print "UAS: {0} \nLAS: {1}".format(uas, las)
print "Points Scored: {0}".format(points)
# 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 NotImplementedError:
print """