def trainClassifiers(self, xml_file, type):
self.prepareModels(xml_file, type)
comentarios = self.procesar(xml_file, type)
if type == 1:
data = load_data_from_disk(tfidfModel)
data_expanded = []
for i in data:
vec = expand(i)
data_expanded.append(vec)
labels = []
for i in comentarios:
labels.append(i[1])
fileClassifiers = [SVM, NB, ME, DT]
for i in range(4):
classifier = SC(data_expanded, labels, i + 1)
fClass = classifier.train()
write_data_to_disk(fileClassifiers[i], fClass)
else:
data = load_data_from_disk(tfidfModelp)
data_expanded = []
for i in data:
vec = expand(i)
data_expanded.append(vec)
labels = []
for i in comentarios:
labels.append(i[1])
fileClassifiers = [SVMp, NBp, MEp, DTp]
for i in range(4):
classifier = SC(data_expanded, labels, i + 1)
fClass = classifier.train()
write_data_to_disk(fileClassifiers[i], fClass)
def test(self, comment, type, corpus):
vectorizer = []
transformer = []
if corpus == 1:
vectorizer = load_data_from_disk(simpleVectorizer)
transformer = load_data_from_disk(tfidfVectorizer)
else:
vectorizer = load_data_from_disk(simpleVectorizerp)
transformer = load_data_from_disk(tfidfVectorizerp)
model = VM()
model.set_models(vectorizer, transformer)
comentario = comment[0]
# seg = Segmentation(comentario)
seg = Segmentation2()
# segmentos = seg.find_sentences()
segmentos = seg.segment_text(comentario)
entities = comment[1].items()
classSVM = ""
classNB = ""
classME = ""
classDT = ""
if corpus == 1:
classSVM = SVM
classNB = NB
classME = ME
classDT = DT
else:
classSVM = SVMp
classNB = NBp
classME = MEp
classDT = DTp
if type == 1:
return self.__testClassifier(segmentos, entities, model, classSVM)
elif type == 2:
return self.__testClassifier(segmentos, entities, model, classNB)
elif type == 3:
return self.__testClassifier(segmentos, entities, model, classME)
elif type == 4:
return self.__testClassifier(segmentos, entities, model, classDT)
elif type == 5:
return self.__testUnsup(segmentos, entities)
def __testClassifier(self, segmentos, entities, model, fileClass):
results = []
for j in segmentos:
proc = TextCleaner(j)
procesado = proc.get_processed_comment()
vector = model.get_comment_tf_idf_vector([procesado])
supClass = load_data_from_disk(fileClass)
classifier = SC()
classifier.set_classifier(supClass)
result = classifier.classify(vector)
polaridadSup = result[0][0]
for i in entities:
if j.find(i[0]) != -1:
value = (i[0], polaridadSup)
results.append(value)
return results
