def main():
"""Trains all of the language models and tests them on the dev data. Change devPath if you
wish to do things like test on the training data.
"""
trainPath = '../data/micro/en_US/'
trainingCorpus = CapstoneCorpus(trainPath)
#print str(trainingCorpus)
sent = "When you breathe, I want to be the air for you. I'll be there for you, I'd live and I'd"
tokens = Tokenize(sent)
print 'Uniform Language Model: '
uniformLM = UniformLanguageModel(trainingCorpus)
print "VocSize= " + str(len(uniformLM.words))
print sent
print tokens
print "uniform score=" + str(uniformLM.score(tokens))
print 'Unigram Language Model: '
unigramLM = UnigramLanguageModel(trainingCorpus)
print "VocSize= " + str(len(unigramLM.unigramCounts))
print "unigram score=" + str(unigramLM.score(tokens))
print 'Laplace Unigram Language Model: '
laplaceUnigramLM = LaplaceUnigramLanguageModel(trainingCorpus)
laplaceUnigramLM.save("smallUnigram.LM")
print "VocSize= " + str(len(laplaceUnigramLM.f1))
print "unigram score=" + str(laplaceUnigramLM.score(tokens))
print 'Laplace Bigram Language Model: '
laplaceBigramLM = LaplaceBigramLanguageModel(trainingCorpus)
laplaceBigramLM.save("smallBigram.LM")
print "bigram score=" + str(laplaceBigramLM.score(tokens))
print 'Laplace Ngram Language Model: N=2'
laplaceN2gramLM = LaplaceNgramLanguageModel(trainingCorpus,2)
laplaceN2gramLM.save("smallN2gram.LM")
print "N=2gram score=" + str(laplaceN2gramLM.score(tokens))
print 'Laplace Ngram Language Model: N=3'
laplaceN3gramLM = LaplaceNgramLanguageModel(trainingCorpus,3)
laplaceN3gramLM.save("smallN3gram.LM")
print "N=3gram score=" + str(laplaceN2gramLM.score(tokens))
print 'Custom Language Model: '
customLM = CustomLanguageModel(trainingCorpus,N=2)
print "Custom LM score=" + str(customLM.score(tokens))
def main():
"""Trains all of the language models and tests them on the dev data. Change devPath if you
wish to do things like test on the training data.
"""
trainPath = '../data/micro/en_US/'
trainingCorpus = CapstoneCorpus(trainPath)
#print str(trainingCorpus)
sent = "When you breathe, I want to be the air for you. I'll be there for you, I'd live and I'd"
tokens = Tokenize(sent)
print 'Uniform Language Model: '
uniformLM = UniformLanguageModel(trainingCorpus)
print "VocSize= " + str(len(uniformLM.words))
print sent
print tokens
print "uniform score=" + str(uniformLM.score(tokens))
print 'Unigram Language Model: '
unigramLM = UnigramLanguageModel(trainingCorpus)
print "VocSize= " + str(len(unigramLM.unigramCounts))
print "unigram score=" + str(unigramLM.score(tokens))
print 'Laplace Unigram Language Model: '
laplaceUnigramLM = LaplaceUnigramLanguageModel(trainingCorpus)
laplaceUnigramLM.save("smallUnigram.LM")
print "VocSize= " + str(len(laplaceUnigramLM.f1))
print "unigram score=" + str(laplaceUnigramLM.score(tokens))
print 'Laplace Bigram Language Model: '
laplaceBigramLM = LaplaceBigramLanguageModel(trainingCorpus)
laplaceBigramLM.save("smallBigram.LM")
print "bigram score=" + str(laplaceBigramLM.score(tokens))
print 'Laplace Ngram Language Model: N=2'
laplaceN2gramLM = LaplaceNgramLanguageModel(trainingCorpus, 2)
laplaceN2gramLM.save("smallN2gram.LM")
print "N=2gram score=" + str(laplaceN2gramLM.score(tokens))
print 'Laplace Ngram Language Model: N=3'
laplaceN3gramLM = LaplaceNgramLanguageModel(trainingCorpus, 3)
laplaceN3gramLM.save("smallN3gram.LM")
print "N=3gram score=" + str(laplaceN2gramLM.score(tokens))
print 'Custom Language Model: '
customLM = CustomLanguageModel(trainingCorpus, N=2)
print "Custom LM score=" + str(customLM.score(tokens))
def output(self, partId, ch_aux):
"""Uses the student code to compute the output for test cases."""
trainCorpus = HolbrookCorpus('../data/holbrook-tagged-train.dat')
if partId in [1, 2]:
editModel = EditModel('../data/count_1edit.txt', trainCorpus)
return json.dumps([[(e.editedWord, e.rule())
for e in editModel.edits(line.strip())]
for line in ch_aux.split("\n")])
else:
testCorpus = HolbrookCorpus()
testCorpus.slurpString(ch_aux)
lm = None
if partId in [3, 4]:
lm = LaplaceUnigramLanguageModel(trainCorpus)
elif partId in [5, 6]:
lm = LaplaceBigramLanguageModel(trainCorpus)
elif partId in [7, 8]:
lm = StupidBackoffLanguageModel(trainCorpus)
elif partId in [9, 10]:
lm = CustomLanguageModel(trainCorpus)
else:
print 'Unknown partId: " + partId'
return None
speller = SpellCorrect(lm, trainCorpus)
output = speller.correctCorpus(testCorpus)
# put in the part ID as well
output = '[["%d"],%s' % (partId, output[1:])
return output
def main():
"""Trains all of the language models and tests them on the dev data. Change devPath if you
wish to do things like test on the training data."""
trainPath = '../data/holbrook-tagged-train.dat'
trainingCorpus = HolbrookCorpus(trainPath)
devPath = '../data/holbrook-tagged-dev.dat'
devCorpus = HolbrookCorpus(devPath)
print 'Unigram Language Model: '
unigramLM = UnigramLanguageModel(trainingCorpus)
unigramSpell = SpellCorrect(unigramLM, trainingCorpus)
unigramOutcome = unigramSpell.evaluate(devCorpus)
print str(unigramOutcome)
print 'Uniform Language Model: '
uniformLM = UniformLanguageModel(trainingCorpus)
uniformSpell = SpellCorrect(uniformLM, trainingCorpus)
uniformOutcome = uniformSpell.evaluate(devCorpus)
print str(uniformOutcome)
print 'Laplace Unigram Language Model: '
laplaceUnigramLM = LaplaceUnigramLanguageModel(trainingCorpus)
laplaceUnigramSpell = SpellCorrect(laplaceUnigramLM, trainingCorpus)
laplaceUnigramOutcome = laplaceUnigramSpell.evaluate(devCorpus)
print str(laplaceUnigramOutcome)
print 'Laplace Bigram Language Model: '
laplaceBigramLM = LaplaceBigramLanguageModel(trainingCorpus)
laplaceBigramSpell = SpellCorrect(laplaceBigramLM, trainingCorpus)
laplaceBigramOutcome = laplaceBigramSpell.evaluate(devCorpus)
print str(laplaceBigramOutcome)
print 'Stupid Backoff Language Model: '
sbLM = StupidBackoffLanguageModel(trainingCorpus)
sbSpell = SpellCorrect(sbLM, trainingCorpus)
sbOutcome = sbSpell.evaluate(devCorpus)
print str(sbOutcome)
print 'Custom Language Model (based on LaplaceBigramLanguageModel): '
customLM = CustomLanguageModel(trainingCorpus)
customSpell = SpellCorrect(customLM, trainingCorpus)
customOutcome = customSpell.evaluate(devCorpus)
print str(customOutcome)
print 'Custom Language Model2 (based on StupidBackoffLanguageModel): '
customLM2 = CustomLanguageModel2(trainingCorpus)
customSpell2 = SpellCorrect(customLM2, trainingCorpus)
customOutcome2 = customSpell2.evaluate(devCorpus)
print str(customOutcome2)
def main():
"""Trains all of the language models and tests them on the dev data. Change devPath if you
wish to do things like test on the training data."""
trainPath = '../data/holbrook-tagged-train.dat'
trainingCorpus = HolbrookCorpus(trainPath)
devPath = '../data/holbrook-tagged-dev.dat'
devCorpus = HolbrookCorpus(devPath)
print 'Uniform Language Model: '
uniformLM = UniformLanguageModel(trainingCorpus)
uniformSpell = SpellCorrect(uniformLM, trainingCorpus)
uniformOutcome = uniformSpell.evaluate(devCorpus)
print str(uniformOutcome), '\n'
print 'Laplace Unigram Language Model: '
laplaceUnigramLM = LaplaceUnigramLanguageModel(trainingCorpus)
laplaceUnigramSpell = SpellCorrect(laplaceUnigramLM, trainingCorpus)
laplaceUnigramOutcome = laplaceUnigramSpell.evaluate(devCorpus)
print str(laplaceUnigramOutcome), '\n'
#It has (accuracy: 0.012739) because of the small corpus (I think ^_^)
print 'Good-Turing Unigram Language Model: '
GoodTuringLM = GoodTuringUnigramLanguageModel(trainingCorpus)
GoodTuringSpell = SpellCorrect(GoodTuringLM, trainingCorpus)
GoodTuringOutcome = GoodTuringSpell.evaluate(devCorpus)
print str(GoodTuringOutcome), '\n'
#This model takes some time, about (70) seconds
print 'Laplace Bigram Language Model: '
laplaceBigramLM = LaplaceBigramLanguageModel(trainingCorpus)
laplaceBigramSpell = SpellCorrect(laplaceBigramLM, trainingCorpus)
laplaceBigramOutcome = laplaceBigramSpell.evaluate(devCorpus)
print str(laplaceBigramOutcome), '\n'
#This model takes some time, about (70) seconds
print 'Stupid Backoff Language Model: '
sbLM = StupidBackoffLanguageModel(trainingCorpus)
sbSpell = SpellCorrect(sbLM, trainingCorpus)
sbOutcome = sbSpell.evaluate(devCorpus)
print str(sbOutcome), '\n'
#This model takes some time, about (70) seconds
print 'Custom Language Model: '
customLM = CustomLanguageModel(trainingCorpus)
customSpell = SpellCorrect(customLM, trainingCorpus)
customOutcome = customSpell.evaluate(devCorpus)
print str(customOutcome), '\n'
def main():
"""Trains all of the language models and tests them on the dev data. Change devPath if you
wish to do things like test on the training data."""
trainPath = '../data/holbrook-tagged-train.dat'
trainingCorpus = HolbrookCorpus(trainPath)
devPath = '../data/holbrook-tagged-dev.dat'
devCorpus = HolbrookCorpus(devPath)
# print('Uniform Language Model: ')
# uniformLM = UniformLanguageModel(trainingCorpus)
# uniformSpell = SpellCorrect(uniformLM, trainingCorpus)
# uniformOutcome = uniformSpell.evaluate(devCorpus)
# print(str(uniformOutcome))
print('\nLaplace Unigram Language Model: ')
laplaceUnigramLM = LaplaceUnigramLanguageModel(trainingCorpus)
laplaceUnigramSpell = SpellCorrect(laplaceUnigramLM, trainingCorpus)
laplaceUnigramOutcome = laplaceUnigramSpell.evaluate(devCorpus)
print(str(laplaceUnigramOutcome))
print('\nLaplace Bigram Language Model: ')
laplaceBigramLM = LaplaceBigramLanguageModel(trainingCorpus)
laplaceBigramSpell = SpellCorrect(laplaceBigramLM, trainingCorpus)
laplaceBigramOutcome = laplaceBigramSpell.evaluate(devCorpus)
print(str(laplaceBigramOutcome))
# print('\nStupid Backoff Language Model: ')
# sbLM = StupidBackoffLanguageModel(trainingCorpus)
# sbSpell = SpellCorrect(sbLM, trainingCorpus)
# sbOutcome = sbSpell.evaluate(devCorpus)
# print(str(sbOutcome))
#
print('\nCustom Language Model: ')
customLM = CustomLanguageModel(trainingCorpus)
customSpell = SpellCorrect(customLM, trainingCorpus)
customOutcome = customSpell.evaluate(devCorpus)
print(str(customOutcome))
def output(partId, ch_aux):
"""Uses the student code to compute the output for test cases."""
trainCorpus = HolbrookCorpus('../data/holbrook-tagged-train.dat')
testCorpus = HolbrookCorpus()
testCorpus.slurpString(ch_aux)
lm = None
if partId == 1 or partId == 2:
lm = LaplaceUnigramLanguageModel(trainCorpus)
elif partId == 3 or partId == 4:
lm = LaplaceBigramLanguageModel(trainCorpus)
elif partId == 5 or partId == 6:
lm = StupidBackoffLanguageModel(trainCorpus)
elif partId == 7 or partId == 8:
lm = CustomLanguageModel(trainCorpus)
else:
print('Unknown partId: " + partId')
return None
speller = SpellCorrect(lm, trainCorpus)
output = speller.correctCorpus(testCorpus)
# put in the part ID as well
output = '[["%d"],%s' % (partId, output[1:])
return output
# bad_model = CustomLanguageModel(bad_train, n=n, coef=1)
#
# print('Evaluation of the models...')
# true = 0
# for i in range(len(good_test)):
# print(str(i) + '/' + str(len(good_test)))
# if good_model.score(good_test[i]) > bad_model.score(good_test[i]):
# true += 1
# if good_model.score(bad_test[i]) < bad_model.score(bad_test[i]):
# true += 1
#
# print('accuracy ' + str(n) + '-gram, coef=1: ' + str(true / (len(good_test) * 2)))
#
#################################################
# coef = 0.4
print('Creation of the models...')
good_model = CustomLanguageModel(good_train, n=n, coef=0.4)
bad_model = CustomLanguageModel(bad_train, n=n, coef=0.4)
print('Evaluation of the models...')
true = 0
t = tqdm.tqdm(total=len(good_test))
for i in range(len(good_test)):
t.update()
if good_model.score(good_test[i]) > bad_model.score(good_test[i]):
true += 1
if good_model.score(bad_test[i]) < bad_model.score(bad_test[i]):
true += 1
t.close()
print('accuracy ' + str(n) + '-gram, coef=0.4: ' + str(true / (len(good_test) * 2)))