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 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)
