pandas里map、lambda、merge的使用

# -*- coding:utf-8 -*-

from datetime import datetime
import pandas as pd

def Main():

    print("开始。。。。。")
    print("加载规则数据")
    print(datetime.now().strftime('%Y-%m-%d %H:%M:%S'))

    uname = ['ad', 'host', 'domain', 'url', 'ref', 'time', 'os', 'os_type']
    df_list = pd.read_csv('/data/u_lx_data/zhangqm/sh/yanjie/fudan/muying/muying_11yue_all.txt', header=None,names=uname, sep='\t')
    print("11yue源数据读完。。。。。")

    df_url_ts = pd.read_csv('/data/u_lx_data/zhangqm/sh/yanjie/fudan/muying/babytree.txt', sep=',', header=None,names=['ts', 'url'],dtype={'ts' : str})
    print("url+ts 读完。。。。。")

    target_dir = '/data/u_lx_data/zhangqm/sh/yanjie/fudan/muying/python/url_ts_result.txt'

    #把time转换成string并替换空格
    df_list['ts'] = df_list['time'].map(lambda x: str(x).replace(' ', '')[0:10])
    print("ts 取完。。。。。")

    df_result = pd.merge(df_list, df_url_ts, how='inner', on=['ts', 'url'])[['ts', 'url']].drop_duplicates()
    print("merge完。。。。。")

    df_result.to_csv(target_dir,header=None,sep='\t',index=False)
    print("文件写入完。。。。。")
    # pd.to_csv(target_dir,header=None,sep='\t')

if __name__ == "__main__":
    Main()

版权声明：本文为博主原创文章，未经博主允许不得转载。