#!/usr/bin/env python3
# -*- coding:utf-8 -*-
# @FileName :Test.py
# @Software PyCharm

import os
import pandas as pd

# filename為文件路徑，file_num為拆分后的文件行數(shù)
# 根據(jù)是否有表頭執(zhí)行不同程序，默認(rèn)有表頭的
def Data_split(filename,file_num,header=True):
  if header:
    # 設(shè)置每個文件需要有的行數(shù),初始化為1000W
    chunksize=10000
    data1=pd.read_table(filename,chunksize=chunksize,sep=',',encoding='gbk')
    # print(data1)
    # num表示總行數(shù)
    num=0
    for chunk in data1:
      num+=len(chunk)
    # print(num)
    # chunksize表示每個文件需要分配到的行數(shù)
    chunksize=round(num/file_num+1)
    # print(chunksize)
    # 分離文件名與擴(kuò)展名os.path.split(filename)
    head,tail=os.path.split(filename)
    data2=pd.read_table(filename,chunksize=chunksize,sep=',',encoding='gbk')
    i=0
    for chunk in data2:
      chunk.to_csv('{0}_{1}{2}'.format(head,i,tail),header=None,index=False)
      print('保存第{0}個數(shù)據(jù)'.format(i))
      i+=1
  else:
    # 獲得每個文件需要的行數(shù)
    chunksize=10000
    data1=pd.read_table(filename,chunksize=chunksize,header=None,sep=',')
    num=0
    for chunk in data1:
      num+=len(chunk)
      chunksize=round(num/file_num+1)

      head,tail=os.path.split(filename)
      data2=pd.read_table(filename,chunksize=chunksize,header=None,sep=',')
      i=0
      for chunk in data2:
        chunk.to_csv('{0}_{1}{2}'.foemat(head,i,tail),header=None,index=False)
        print('保存第{0}個數(shù)據(jù)'.format(i))
        i+=1

filename='文件路徑'
#num為拆分為的文件個數(shù)
Data_split(filename,num,header=True)