def classify(self,_string):
#Expects one sentence as a string
_string = unicode(_string)
_string_processed = self.nlp(_string)
tags = []
for index in range(len(_string_processed)):
featureset = features.feature_compiler(index,_string_processed)
tags.append(self.classifier.classify(featureset))
return tags
def train(self):
for sentence,tags in self.datasource:
sentence_processed = self.nlp(u' '.join(sentence))
for token in range(len(sentence)):
self.featuresets.append((features.feature_compiler(token,sentence_processed),tags[token]))
train_set, test_set = self.featuresets[0:-1000], self.featuresets[-1000:]
pprint(train_set[:10])
self.classifier = MaxentClassifier.train(train_set)
#Saving the classifier
self.save()
import features from spacy.en import English nlp = English(entity=False) a = u'We wish you a merry christmas' ap = nlp(a) x = features.feature_compiler(3,ap)