參考了Yehuda Koren 08年的論文Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model

程式碼如下：

# -*- coding: UTF-8 -*-
import random
import math
import cPickle as pickle

class SVD():
    def __init__(self,allfile,trainfile,testfile,factorNum=10):
        #all data file
self.allfile=allfile
        #training set file
 
self.trainfile=trainfile
        #testing set file
self.testfile=testfile
        #get factor number
self.factorNum=factorNum
        #get user number
self.userNum=self.getUserNum()
        #get item number
self.itemNum=self.getItemNum()
        #learning rate
self.learningRate=0.01
#the regularization lamba
 
self.regularization=0.05
#initialize the model and parameters
self.initModel()
        #get user number function
def getUserNum(self):
            file=self.allfile
            cnt=0
userSet=set()
            for line in open(file):
                  user=line.split('\t')[0].strip()
                  if 
 
user not in userSet:
                      userSet.add(user)
                      cnt+=1
return cnt
        #get item number function
def getItemNum(self):
            file=self.allfile
            cnt=0
itemSet=set()
            for line in open(file):
                item=line.split('\t')[1].strip()
                if item not in itemSet:
                    itemSet.add(item)
                    cnt+=1
return cnt
        #initialize all parameters
def initModel(self):
            self.av=self.average(self.trainfile)
            self.bu=[0.0 for i in range(self.userNum)]
            self.bi=[0.0 for i in range(self.itemNum)]
            temp=math.sqrt(self.factorNum)
            self.pu=[[(0.1*random.random()/temp) for i in range(self.factorNum)] for j in range(self.userNum)]
            self.qi=[[0.1*random.random()/temp for i in range(self.factorNum)] for j in range(self.itemNum)]
            print "Initialize end.The user number is:%d,item number is:%d,the average score is:%f" %(self.userNum,self.itemNum,self.av)
            #train model
def train(self,iterTimes=100):
                print "Beginning to train the model......"
trainfile=self.trainfile
                preRmse=10000.0
for iter in range(iterTimes):
                 fi=open(trainfile,'r')
                 #read the training file
for line in fi:
                     content=line.split('\t')
                     user=int(content[0].strip())-1
item=int(content[1].strip())-1
rating=float(content[2].strip())
                     #calculate the predict score
pscore=self.predictScore(self.av,self.bu[user],self.bi[item],self.pu[user],self.qi[item])
                     #the delta between the real score and the predict score
eui=rating-pscore

                     #update parameter bu and bi(user rating bias and item rating bias)
self.bu[user]+=self.learningRate*(eui-self.regularization*self.bu[user])
                     self.bi[item]+=self.learningRate*(eui-self.regularization*self.bi[item])
                     for k in range(self.factorNum):
                         temp=self.pu[user][k]
                         #update pu,qi
self.pu[user][k]+=self.learningRate*(eui*self.qi[item][k]-self.regularization*self.pu[user][k])
                         self.qi[item][k]+=self.learningRate*(eui*temp-self.regularization*self.qi[item][k])
                    #print pscore,eui
                #close the file
fi.close()
                #calculate the current rmse
curRmse=self.test(self.av,self.bu,self.bi,self.pu,self.qi)[0]
                 curMae=self.test(self.av,self.bu,self.bi,self.pu,self.qi)[1]
                 print "Iteration %d times,RMSE is : %f,MAE is : %f" %(iter+1,curRmse,curMae)
                 if curRmse>preRmse:
                    break
                 else:
                    preRmse=curRmse
                print "Iteration finished!"
#test on the test set and calculate the RMSE
def test(self,av,bu,bi,pu,qi):
              testfile=self.testfile
              rmse=0.0
mae=0.0
cnt=0
fi=open(testfile)
              for line in fi:
                cnt+=1
content=line.split('\t')
                user=int(content[0].strip())-1
item=int(content[1].strip())-1
score=float(content[2].strip())
                pscore=self.predictScore(av,bu[user],bi[item],pu[user],qi[item])
                rmse+=math.pow(score-pscore,2)
                mae+=abs(score-pscore)
              fi.close()
              return math.sqrt(rmse/cnt),mae/cnt
        #calculate the average rating in the training set
def average(self,filename):
            result=0.0
cnt=0
for line in open(filename):
                cnt+=1
score=float(line.split('\t')[2].strip())
                result+=score
            return result/cnt
        #calculate the inner product of two vectors
def innerProduct(self,v1,v2):
            result=0.0
for i in range(len(v1)):
                result+=v1[i]*v2[i]
            return result
    def predictScore(self,av,bu,bi,pu,qi):
            pscore=av+bu+bi+self.innerProduct(pu,qi)
            if pscore<1:
                pscore=1
if pscore>5:
                pscore=5
return pscore
if __name__=='__main__':
    s=SVD("data\\u.data","data\\ua.base","data\\ua.test")
    #print s.userNum,s.itemNum
    #print s.average("data\\ua.base")
s.train()

實驗結果如下：

Initialize end.The user number is:943,item number is:1682,the average score is:3.523827
Beginning to train the model......
Iteration 1 times,RMSE is : 1.002799,MAE is : 0.807791
Iteration 2 times,RMSE is : 0.982096,MAE is : 0.783726
Iteration 3 times,RMSE is : 0.972882,MAE is : 0.774163
Iteration 4 times,RMSE is : 0.967721,MAE is : 0.769057
Iteration 5 times,RMSE is : 0.964556,MAE is : 0.765856
Iteration 6 times,RMSE is : 0.962501,MAE is : 0.763699
Iteration 7 times,RMSE is : 0.961121,MAE is : 0.762131
Iteration 8 times,RMSE is : 0.960174,MAE is : 0.760974
Iteration 9 times,RMSE is : 0.959496,MAE is : 0.760075
Iteration 10 times,RMSE is : 0.958957,MAE is : 0.759327
Iteration 11 times,RMSE is : 0.958456,MAE is : 0.758648
Iteration 12 times,RMSE is : 0.957879,MAE is : 0.757935
Iteration 13 times,RMSE is : 0.957088,MAE is : 0.757073
Iteration 14 times,RMSE is : 0.955944,MAE is : 0.755947
Iteration 15 times,RMSE is : 0.954353,MAE is : 0.754484
Iteration 16 times,RMSE is : 0.952345,MAE is : 0.752735
Iteration 17 times,RMSE is : 0.950108,MAE is : 0.750828
Iteration 18 times,RMSE is : 0.947883,MAE is : 0.748934
Iteration 19 times,RMSE is : 0.945824,MAE is : 0.747158
Iteration 20 times,RMSE is : 0.943971,MAE is : 0.745539
Iteration 21 times,RMSE is : 0.942294,MAE is : 0.744083
Iteration 22 times,RMSE is : 0.940736,MAE is : 0.742716
Iteration 23 times,RMSE is : 0.939252,MAE is : 0.741392
Iteration 24 times,RMSE is : 0.937806,MAE is : 0.740099
Iteration 25 times,RMSE is : 0.936384,MAE is : 0.738842
Iteration 26 times,RMSE is : 0.934983,MAE is : 0.737613
Iteration 27 times,RMSE is : 0.933612,MAE is : 0.736412
Iteration 28 times,RMSE is : 0.932294,MAE is : 0.735245
Iteration 29 times,RMSE is : 0.931057,MAE is : 0.734105
Iteration 30 times,RMSE is : 0.929926,MAE is : 0.733049
Iteration 31 times,RMSE is : 0.928929,MAE is : 0.732111
Iteration 32 times,RMSE is : 0.928082,MAE is : 0.731301
Iteration 33 times,RMSE is : 0.927391,MAE is : 0.730614
Iteration 34 times,RMSE is : 0.926858,MAE is : 0.730037
Iteration 35 times,RMSE is : 0.926480,MAE is : 0.729576
Iteration 36 times,RMSE is : 0.926256,MAE is : 0.729231
Iteration 37 times,RMSE is : 0.926174,MAE is : 0.728978
Iteration 38 times,RMSE is : 0.926232,MAE is : 0.728840
Iteration finished!

最後的RMSE是0.926左右，MAE是0.728左右，可見效果一般，後面會嘗試改進。