def test_predict(self):
lines = sys.stdin.readlines()
reader = IOBReader(lines)
extractors = [
FieldExtractor(reader.getPosition('FORM')),
FieldExtractor(reader.getPosition('POS')),
CapitalExtractor(reader.getPosition('FORM')),
]
params = {'epochs':25, 'learning_rate':0.01, 'window_size':3, 'name_model':'model.ckpt'}
classifier = Classifier(reader, extractors, LinearEstimator, **params)
predicted = classifier.predict()
#self.assertEqual(len(dataset), len(predicted))
labels_idx_rev = {v:k for k,v in reader.vocabulary[reader.getPosition('LABEL')].items()}
i = 0
for line in lines:
line = line.strip()
if line:
print '%s\t%s\t%s' % (line.split()[0], line.split()[1], labels_idx_rev[predicted[i]])
i += 1
else:
print
def test_train(self):
f = {
'fields': [
{'position': 0, 'name': 'FORM', 'type': str},
{'position': 1, 'name': 'POS', 'type': str},
{'position': 2, 'name': 'LABEL', 'type': str}
]
}
reader = IOBReader(sys.stdin, separator='\t', format=f)
extractors = [
FieldExtractor(reader.getPosition('FORM')),
FieldExtractor(reader.getPosition('POS')),
CapitalExtractor(reader.getPosition('FORM')),
]
params = {'epochs':25, 'learning_rate':0.01, 'window_size':3, 'name_model':'model.ckpt'}
classifier = Classifier(reader, extractors, LinearEstimator, **params)
classifier.train()