在MovieLens数据集上用SVD进行评分预测

参考了Yehuda Koren 08年的论文Factorization Meets the Neighborhood: a Multifaceted Collaborative Filtering Model

代码如下：

'''
Version:1.0
Created on 2014-02-25
@Author:Dior
'''

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 lambda
        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 itemSe