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 prepareModels(self, xml_file, type):
comentarios = self.procesar(xml_file, type)
train = []
for i in comentarios:
train.append(i[0])
model = VM(train)
vectorModelData = model.prepare_models()
modelVectorizer = vectorModelData[0]
modelVectorizerTFIDF = vectorModelData[1]
modelTFIDF = vectorModelData[2]
if type == 1:
write_data_to_disk(simpleVectorizer, modelVectorizer)
write_data_to_disk(tfidfVectorizer, modelVectorizerTFIDF)
write_data_to_disk(tfidfModel, modelTFIDF)
else:
write_data_to_disk(simpleVectorizerp, modelVectorizer)
write_data_to_disk(tfidfVectorizerp, modelVectorizerTFIDF)
write_data_to_disk(tfidfModelp, modelTFIDF)
