1. 使用python脚本可以轻松生成满足条件的数据,具体如下
#coding: utf-8
import os, sys, time, datetime
from itertools import izip
N = 100000000
def gen_meid():
return
def gen_seq():
return
def generate_message(meid,seq):
ts = time.time();
time_st = datetime.datetime.fromtimestamp(ts).strftime('%Y-%m-%d %H:%M:%S')
print '\t'.join(( meid, seq, '\N', '\N', '\N', '\N', '0', '0', '0', '0', time_st, '\N', '\N', '0', '\N', '\N', '\N', '\N', time_st ))
def main(args):
print '\t'.join(( 'deviceID', 'battery', ... , 'accumulatedTime', 'createDate' )) // for mongodb, mysql delete
for meid,seq in izip(gen_meid(),gen_seq()):
generate_message(meid,seq)
pass
return 0
#==============================
if __name__ == "__main__":
import sys
main(sys.argv)
pass
#==============================
$ python a.py > device.tsv
2. 切分数据(可选)
tail -n +1 device.csv | head -n 5000000 > part1.txt
tail -n +100001 device.csv | head -n 100000 > part2.txt
tail -n +200001 device.csv | head -n 100000 > part3.txt
tail -n +300001 device.csv | head -n 100000 > part4.txt
3. 生成txt 文件
python a.py > device.txt