#encoding: utf-8from Similarity import Personfrom Sort import select_sortfile=open(‘user_bookmark‘,‘r‘)filew=open(‘user_bookRecommend‘,‘w‘)#加载训练集trainSet={}while True:    line=file.readline().strip()    if not line: break    userId,itemId=line.split("::")    trainSet.setdefault(userId,[])    trainSet[userId].append(itemId)# 计算每个用户和其他所有用户的相似度,排序,获得相似度最高的前N个用户, # 在计算每个用户的相似度*物品的偏好值(这里没有评分就把偏好值设置为1)for v in trainSet.keys():    v2u={}    K={}    for u in trainSet.keys():       if u!=v:          sim=Person(trainSet[v],trainSet[u])          v2u.setdefault(u,sim)    keys,values=select_sort(v2u)    s=v    for i in range(len(values)-3,len(values)):       s=s+"::"+keys[i]+" "+str(values[i])       K.setdefault(keys[i],values[i])    rank={}    rki=1    interacted_items=trainSet[v]    for k,simk in K.items():        for i in trainSet[k]:            if i in interacted_items:                continue            rvi=rki*simk            rank.setdefault(i,rvi)    s1=v    _keys,_values=select_sort(rank)    for i in range(len(rank)-6,len(rank)):         #s1=s1+_keys[i]+" "+str(_values[i])+"::"         s1=s1+"::"+_keys[i]    print s1    filew.write(s1+‘\n‘)from math import sqrtdef Person(item_a,item_b):    if len(item_a)==0 or len(item_b)==0:        return 0;    else:        sum=0        for i in range(len(item_a)):            for j in range(len(item_b)):                if item_a[i]==item_b[j]:                    sum=sum+1        if sum==0:            return 0        else:            sim=sum/sqrt(len(item_a)*len(item_b))            return sim