data_juicer.format.parquet_formatter module# class data_juicer.format.parquet_formatter.ParquetFormatter(dataset_path, suffixes=None, **kwargs)[源代码]# 基类:LocalFormatter The class is used to load and format parquet-type files. Default suffixes is ['.parquet'] SUFFIXES = ['.parquet']# __init__(dataset_path, suffixes=None, **kwargs)[源代码]# Initialization method. 参数: dataset_path -- a dataset file or a dataset directory suffixes -- files with specified suffixes to be processed kwargs -- extra args