def create_training_data(train_folder): train = [] question_files = fo.list_all_files(os.path.join(train_folder, 'question')) for file in question_files: train += read_training_data(os.path.join(train_folder, 'question', file), True) answer_files = fo.list_all_files(os.path.join(train_folder, 'answer')) for file in answer_files: train += read_training_data(os.path.join(train_folder, 'answer', file), False) return train
def create_testing_data(test_folder): files = fo.list_all_files(test_folder) print files test = [] test_label = [] class_label = ["C2", "C2", "IKEA_IT", "IKEA_IT", "IKEA_EN", "IKEA_EN"] for index, file in enumerate(files): temp = read_testing_data(os.path.join(test_folder, file), class_label[index]) test += temp test_label += [class_label[index] for i in range(len(temp))] return test, test_label