基于用户相似性的协同过滤——Python实现

代码基本来自项亮的<推荐系统实践>，把书上的伪代码具体实现，还参考了https://www.douban.com/note/336280497/

还可以加入对用户相似性的归一化操作，效果会更好。

数据集为MovieLens的10万条数据.
链接：MoiveLens

#coding:utf-8
import random,math
from operator import itemgetter

class UserBasedCF:
    def __init__(self,trainDataFile=None,testDataFile=None,splitor='\t'):
        if trainDataFile!=None:
            self.train=self.loadData(trainDataFile, splitor)
        if testDataFile!=None:
            self.test=self.loadData(testDataFile, splitor)
        self.simiMatrix={}
        
    def setData(self,train,test):
        self.train=train
        self.test=test
                 
    def loadData(self,dataFile,splitor='\t'):
        data={}
        for line in open(dataFile):
            user,item,record,_ = line.split()
            data.setdefault(user,{})
            data[user][item]=record
        return data
    
    def recallAndPrecision(self,peersCount,topN=10):
        hit=0
        recall=0
        precision=0
        for user in self.train.keys():
            itemOfuser=self.test.get(user,{})
            recItems=self.recommend(user,peersCount,topN)
            for item,pui in recItems.items():
                if item in itemOfuser:
                    hit+=1
            recall+=len(itemOfuser)
            precision+=topN
        #print 'Recall:%s    hit:%s    allRatings:%s'%(hit/(recall*1.0),hit,precision)
        return (hit / (recall * 1.0),hit / (precision * 1.0))    

    def coverage(self,peersCount,topN=10):
        recommend_items=set()
        all_items=set()
        for user in self.train.keys():
            for item in self.train[user].keys():
                all_items.add(item)
            rank=self.recommend(user,peersCount,topN)
            for item,pui in rank.items():
                recommend_items.add(item)
        return len(recommend_items)/(len(all_items)*1.0)  

    def popularity(self,peersCount,topN=10):
        item_popularity=dict()
        for user,items in self.train.items():
            for item in items.keys():
                if item not in item_popularity:
                    item_popularity[item]=1
                item_popularity[item]+=1
        ret=0
        n=0
        for user in self.train.keys():
            rank=self.recommend(user,peersCount,topN)
            for item,pui in rank.items():
                ret+=math.log(1+item_popularity[item])
                n+=1
        return ret/(n*1.0)
    
    def calUserSimilarity(self):
        item_users=dict()
        for u,ratings in self.train.items():
            for i in ratings.keys():
                item_users.setdefault(i,set())
                item_users[i].add(u)
                
        #calculate co-rated items between users
        coRatedCount=dict()
        itemCountOfUser=dict()
        for item,users in item_users.items():
            for u in users:
                itemCountOfUser.setdefault(u,0)
                itemCountOfUser[u]+=1
                for v in users:
                    if u==v:
                        continue
                    coRatedCount.setdefault(u,{})
                    coRatedCount[u].setdefault(v,0)
                    coRatedCount[u][v]+=1/math.log(1+len(users))
        userSimiMatrix=dict()
        for u,related_users in coRatedCount.items():
            userSimiMatrix.setdefault(u,{})
            for v,cuv in related_users.items():
                userSimiMatrix[u][v]=cuv/math.sqrt(itemCountOfUser[u]*itemCountOfUser[v])
        self.simiMatrix=userSimiMatrix
              
    def recommend(self,userU,peersCount,topN=10):
        recItems=dict()
        interacted_items=self.train[userU]
        '''prepare the user similarity matrix first'''
        if not self.simiMatrix:
            self.calUserSimilarity()
        for userV,simiUV in sorted(self.simiMatrix[userU].items(),key=itemgetter(1),reverse=True)[0:peersCount]:
            for item,ratingV4I in self.train[userV].items():
                if item in interacted_items:
                    continue
                if item not in recItems:
                    recItems[item]=0
                recItems[item]+=simiUV*float(ratingV4I)#transform 4 stars into score 0.8
                
                '''if len(recItems)==topN:
                    return recItems'''
        return dict(sorted(recItems.items(),key = lambda x :x[1],reverse = True)[0:topN])

def testUserBasedCF():
    cf=UserBasedCF(trainDataFile=r'E:\ResearchAndPapers\DataSet\ml-100k\u3.base',testDataFile=r'E:\ResearchAndPapers\DataSet\ml-100k\u3.test')
    #cf.calUserSimilarity()
    print("%3s%15s%15s%15s%15s" % ('K',"precision",'recall','coverage','popularity'))
    for k in [5,10,20,40,80,160]:
        recall,precision = cf.recallAndPrecision(peersCount = k)
        coverage = cf.coverage(peersCount = k)
        popularity = cf.popularity(peersCount = k)
        print("%3d%14.2f%%%14.2f%%%14.2f%%%15.2f" % (k,precision * 100,recall * 100,coverage * 100,popularity))

def SplitData(wholeData,M,k,seed,splitor='\t'):
        test={}
        train={}
        random.seed(seed)
    
        for line in wholeData:
            user,item,score,time=line.strip().split(splitor)
            if random.randint(0,M)==k:
                test.setdefault(user,{})
                test[user][item]=score
            else:
                train.setdefault(user,{})
                train[user][item]=score
        return train,test
    
def testUserBasedCF2():
    wholeData=open(r'E:\ResearchAndPapers\DataSet\ml-1m\ratings.dat')
    train,test=SplitData(wholeData, 8, 5, 10, splitor='::')
    cf=UserBasedCF()
    cf.setData(train, test)
    #cf=UserBasedCF(trainDataFile=r'E:\ResearchAndPapers\DataSet\ml-100k\u5.base',testDataFile=r'E:\ResearchAndPapers\DataSet\ml-100k\u5.test')
    #cf.calUserSimilarity()
    print("%3s%15s%15s%15s%15s" % ('K',"precision",'recall','coverage','popularity'))
    for k in [5,10,20,40,80,160]:
        recall,precision = cf.recallAndPrecision(peersCount = k)
        coverage = cf.coverage(peersCount = k)
        popularity = cf.popularity(peersCount = k)
        print("%3d%14.2f%%%14.2f%%%14.2f%%%15.2f" % (k,precision * 100,recall * 100,coverage * 100,popularity))
        
if __name__=="__main__":
    testUserBasedCF()
    #testUserBasedCF2()