def main():
parser = optparse.OptionParser()
parser.add_option('-s', '--smoothing', choices=(NO_SMOOTHING,
ADD_ONE_SMOOTHING), default=NO_SMOOTHING)
parser.add_option('-o', '--order', default=1, type=int)
parser.add_option('-u', '--unknown',
choices=(PREDICT_ZERO, PREDICT_MOST_COMMON_PART_OF_SPEECH,),
default=PREDICT_ZERO)
options, args = parser.parse_args()
train_filename, test_filename = args
training_data = nlp_common.read_part_of_speech_file(train_filename)
if options.order == 0:
model = BaselineModel(training_data)
else:
model = HiddenMarkovModel.train(
training_data, options.smoothing, options.unknown, options.order)
predictions = nlp_common.get_predictions(
test_filename, model.predict_sentence)
for word, prediction, true_pos in predictions:
print word, prediction, true_pos
def main():
if len(sys.argv) != 3:
print 'Usage: %s training_filename test_filename' % sys.argv[0]
return 1
train_filename, test_filename = sys.argv[1:]
training_data = nlp_common.read_part_of_speech_file(train_filename)
known_words = set(word for pos, word in training_data)
main_start_time = time.time()
print >> sys.stderr, 'Training baseline model'
start_time = time.time()
baseline_model = nlp.BaselineModel(training_data)
print "Baseline trained in " + str(time.time() - start_time) + " seconds."
print >> sys.stderr, 'Evaluating baseline model'
baseline_unknown_accuracy, baseline_accuracy = compute_score(
nlp_common.get_predictions(
test_filename, baseline_model.predict_sentence), known_words)
start_time = time.time()
print >> sys.stderr, 'Training hmm model'
hmm_model = nlp.HiddenMarkovModel.train(training_data)
print "HMM trained in " + str(time.time() - start_time) + " seconds."
print >> sys.stderr, 'Evaluating hmm model'
hmm_unknown_accuracy, hmm_accuracy = compute_score(
nlp_common.get_predictions(
test_filename, hmm_model.predict_sentence), known_words)
print '%s Baseline accuracy' % baseline_accuracy
print '%s Baseline accuracy on unknown words' % baseline_unknown_accuracy
print '%s HMM accuracy' % hmm_accuracy
print '%s HMM accuracy on unknown words' % hmm_unknown_accuracy
print 'Score for Part III: %d/50' % (
math.ceil(max(baseline_accuracy.value(), hmm_accuracy.value()) * 50))
print 'Score for Part IV-unknown words: %d/20' % (
max(0, math.ceil((hmm_unknown_accuracy.value() - 0.6) * 50)))
print 'Finished in ' + str(time.time() - main_start_time)
