def sentiment_kaggle_dataset(): train_x_1, test_x_1 = senti_lexicon_vectorizor(data=SST_KAGGLE, tfidf=True) train_x_2, test_x_2 = senti_wordnet_vectorizer(data=SST_KAGGLE, tfidf=True) train_x = sparse.hstack((train_x_1, train_x_2)) test_x = sparse.hstack((test_x_1, test_x_2)) _, train_y, _ = read_sst_kaggle_pickle() return train_x, train_y, test_x
def doc2vec_kaggle_dataset(): train_x, test_x = read_doc2vec_pickle(dm=True, concat=False) _, train_y, _ = read_sst_kaggle_pickle() return train_x, train_y, test_x