def classify_comment(self, comment, classifier_type='SVM', no_classes=5): sentiment = None preprocessor = Preprocessing() vectorizer = VectorQuantization() if classifier_type == 'SVM': preprocessed_comment = preprocessor.preprocessing(comment) comment_vector = vectorizer.morphosyntactic_vector(preprocessed_comment) sentiment = classifier_svm.classify(comment_vector) if no_classes == 5: return sentiment elif no_classes == 3: if sentiment == u'positivo' or sentiment == u'muy_positivo': return u'positivo' elif sentiment == u'negativo' or sentiment == u'muy_negativo': return u'negativo' else: return sentiment elif classifier_type == 'MNB': preprocessed_comment = preprocessor.preprocessing(comment) comment_vector = vectorizer.bigram_vector(preprocessed_comment) sentiment = classifier_mnb.classify(comment_vector) if no_classes == 5: return sentiment elif no_classes == 3: if sentiment == u'positivo' or sentiment == u'muy_positivo': return u'positivo' elif sentiment == u'negativo' or sentiment == u'muy_negativo': return u'negativo' else: return sentiment
def create(self, corpus_path, model_type="morphosyntactic"):
preprocessor = Preprocessing()
vectorizer = VectorQuantization()
document_list = []
with codecs.open(corpus_path, 'r', 'utf-8') as corpus:
line = corpus.readline()
while line:
comment = preprocessor.preprocessing(line.split('/|/')[1])
category = line.split('/|/')[2].split('\n')[0]
if model_type == "morphosyntactic":
comment_vector = vectorizer.morphosyntactic_vector(comment)
elif model_type == "bigram":
comment_vector = vectorizer.bigram_vector(comment)
else:
print "No model defined using default: morphosyntactic"
comment_vector = vectorizer.morphosyntactic_vector(comment)
if comment_vector:
document_list.append(pattern_Document(comment_vector,
type=category))
line = corpus.readline()
model = pattern_Model(documents=document_list, weight=None)
return model