from math import sqrt
import random
import os
from sklearn import cross_validation
os.chdir("/*")
c=[]
filename=r'rating.txt'
out_train=open(r'train.txt','w')
out_test=open(r'test.txt','w')
for line in open(filename):
items=line.strip().split('|')
c.append(items)
c_train,c_test=cross_validation.train_test_split(c,test_size=0.2)
for i in c_train:
out_train.write('|'.join(i)+'
')
for i in c_test:
out_test.write('|'.join(i)+'
')
原文件格式:
1|122|5|838985046
1|185|5|838983525
1|231|5|838983392
1|292|5|838983421
1|316|5|838983392
1|329|5|838983392
1|355|5|838984474