def pre_process(self, df): featureExtractor = FeatureExtractor(df) # featureExtractor.combine_all_data() featureExtractor.add_features() featureExtractor.stem_gadya() featureExtractor.cnt_remove_sw() featureExtractor.get_hard_word_cnt() # featureExtractor.remove_outliers() # featureExtractor.get_local_word_cnt() featureExtractor.build_word_vec_map() featureExtractor.get_word2vec() featureExtractor.get_word_dist() featureExtractor.build_pos_cols() return featureExtractor.get_df()