Created
July 23, 2014 08:27
-
-
Save chengjun/7181b9722e88c13f768a to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # -*- coding: utf-8 -*- | |
| """ | |
| Spyder Editor | |
| This temporary script file is located here: | |
| D:\chengjun\WinPython-64bit-2.7.6.4\settings\.spyder2\.temp.py | |
| """ | |
| ''' | |
| # Step2: split the duplicated data into about 2000+ files by user ids | |
| # to prepare for deleting the duplicated ties | |
| ''' | |
| path = "D:/renren/" | |
| f = open(path + "friends_all.txt") | |
| n = 0 | |
| for line in f: | |
| From, To, time = line.strip().split('\t') | |
| n += 1 | |
| if n%10000 == 0: | |
| print n, From, To, time | |
| From = int(From) | |
| To = int(To) | |
| From, To = sorted([From, To]) | |
| record = str(From) + '\t' + str(To) + '\t' + time | |
| file_save = path + "friends_sorted/" + str(From/10000) | |
| with open(file_save,'a') as p: | |
| p.write(record+"\n") | |
| ''' | |
| # Step1 detect wheter the data is duplicated | |
| ''' | |
| # the 14 G data is duplicated: | |
| # 1, 2 | |
| # 2, 1 | |
| #path = "D:/renren/" | |
| #f = open(path + "friends_all.txt") | |
| #n = 0 | |
| #for line in f: | |
| # From, To, time = line.strip().split('\t') | |
| # n += 1 | |
| # if n%6000 == 0: | |
| # print n, From, To, time | |
| # if From == "3" and To == "1": | |
| # print "double" | |
| # break |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment