def mock_text_class_data(train_file, dev_file, test_file, text_vocab_file): logging.info("Generate mock data: {}".format(train_file)) mock_a_text_file(samples, 500, train_file) logging.info("Generate mock data: {}".format(dev_file)) mock_a_text_file(samples, 100, dev_file) logging.info("Generate mock data: {}".format(test_file)) mock_a_text_file(samples, 100, test_file) logging.info("Generate text vocab file: {}".format(text_vocab_file)) save_a_vocab_file(text_vocab_file, text_vocab_list)
def mock_text_class_data(train_file, dev_file, test_file, text_vocab_file, data_type): samples = samples_dict[data_type] logging.info("Generate mock data: {}".format(train_file)) mock_a_text_file(samples, 300, train_file) logging.info("Generate mock data: {}".format(dev_file)) mock_a_text_file(samples, 100, dev_file) logging.info("Generate mock data: {}".format(test_file)) mock_a_text_file(samples, 100, test_file) text_vocab_list = text_vocab_dict[data_type] logging.info("Generate text vocab file: {}".format(text_vocab_file)) save_a_vocab_file(text_vocab_file, text_vocab_list)