def prepare_all_data(self):
x_train, x_test, y_train, y_test = train_test_split(
self.dataset.review, self.dataset.sentiment, random_state=0,
test_size=0.1)
x_train = doc2VecModel.label_sentences(x_train, 'Train')
x_test = doc2VecModel.label_sentences(x_test, 'Test')
all_data = x_train + x_test
return x_train, x_test, y_train, y_test, all_data
def prepare_all_data(self):
#x_train, x_test, y_train, y_test = train_test_split(
# self.dataset.review, self.dataset.sentiment, random_state=0,
# test_size=0.1)
x_train, x_test, y_train, y_test = train_test_split(
self.dataset.description, self.dataset.organism_code, random_state=0,
test_size=0.1)
x_train = doc2VecModel.label_sentences(x_train, 'Train')
x_test = doc2VecModel.label_sentences(x_test, 'Test')
#x_train2 = doc2VecModel.label_sentences2(x_train, 'Train')
all_data = x_train + x_test
return x_train, x_test, y_train, y_test, all_data
#x_train, x_test, y_train, y_test = train_test_split(tc.dataset.review, tc.dataset.sentiment, random_state=0,test_size=0.1)
#x_train, x_test, y_train, y_test = train_test_split(tc.dataset.description, tc.dataset.category_code, random_state=0,test_size=0.1)
#x_train = doc2VecModel.label_sentences(x_train, 'Train')
x_train2 = doc2VecModel.label_sentences2(x_train, 'Train')
x_train2 = label_sentences2(x_train, 'Train')
def prepare_test_data(self, sentence):
x_test = doc2VecModel.label_sentences(sentence, 'Test')
return x_test