def __generate_training_and_test_series(self): Logger.info("Generating training and test datasets ...") self.__preprocess_bios() concatenated = PandasUtils.concat_series( [self.appropriate_bios, self.inappropriate_bios]) shuffled = PandasUtils.shuffle_series(concatenated) self.training_series = shuffled.head(self.number_of_training_records) self.test_series = shuffled.tail(self.number_of_test_records) FileUtils.write_series2file(self.bio_train_path, self.training_series) FileUtils.write_series2file(self.bio_test_path, self.test_series) self.test_list = self.test_series.to_list() self.cleaned_test_list = self.__remove_labels( self.test_series, ['__label__{}'.format(l.value) for l in self.Label]).tolist()