karld 0.3.1

分割数据

使用分割文件分割数据文件或使用分割csv文件分割 可能有多行字段以确保它们不被拆分的csv文件。：

import os

import karld

big_file_names = [
    "bigfile1.csv",
    "bigfile2.csv",
    "bigfile3.csv"
]

data_path = os.path.join('path','to','data', 'root')


def main():
    for filename in big_file_names:
        # Name the directory to write the split files into based
        # on the name of the file.
        out_dir = os.path.join(data_path, 'split_data', filename.replace('.csv', ''))

        # Split the file, with a default max_lines=200000 per shard of the file.
        karld.io.split_csv_file(os.path.join(data_path, filename), out_dir)


if __name__ == "__main__":
    main()

当您生成数据并希望根据数量将其分片到文件时，请使用 拆分输出函数之一，如split_file_output_csv、split_file_output或 split_file_output_json：

import os
import pathlib

import karld


def main():
    """
    Python 2 version
    """

    items = (str(x) + os.linesep for x in range(2000))

    out_dir = pathlib.Path('shgen')
    karld.io.ensure_dir(str(out_dir))

    karld.io.split_file_output('big_data', items, str(out_dir))


if __name__ == "__main__":
    main()

CSV可序列化数据：

import pathlib

import karld


def main():
    """
    From a source of data, shard it to csv files.
    """
    if karld.is_py3():
        third = chr
    else:
        third = unichr

    # Your data source
    items = ((x, x + 1, third(x + 10)) for x in range(2000))

    out_dir = pathlib.Path('shard_out_csv')

    karld.io.ensure_dir(str(out_dir))

    karld.io.split_file_output_csv('big_data.csv', items, str(out_dir))


if __name__ == "__main__":
    main()

JSON可序列化数据行：

import pathlib

import karld


def main():
    """
    From a source of data, shard it to csv files.
    """
    if karld.is_py3():
        third = chr
    else:
        third = unichr

    # Your data source
    items = ((x, x + 1, third(x + 10)) for x in range(2000))

    out_dir = pathlib.Path('shard_out_json')

    karld.io.ensure_dir(str(out_dir))

    karld.io.split_file_output_json('big_data.json', items, str(out_dir))


if __name__ == "__main__":
    main()