协同滤波推荐系统

最近在看推荐系统实践这本书

整体来看，书比较偏向与工程吧

但是我发现了代码有很多错误。

这里提供给大家一个可以运行的python语言。

UserCF程序中user相似度计算程序：

def usersimilarity(train):
    #build inverse table for item_users
    item_users = dict()
    for u, items in train.items():
        for i in items:
            if i not in item_users:
                item_users[i] = set()
            item_users[i].add(u)
    #calculate co-rated items between users
#     c = [[0 for i in range(0,number)] for i in range(0,number)]
#     n = [0 for i in range(0,number)]
    c = dict()
    n = dict()
    for i, users in item_users.items():
        for u in users:
            if n.has_key(u):
                n[u]+=1
            else:
                n[u] =1
            for v in users:
                if u==v:
                    continue
                if c.has_key((u,v)):
                    c[u,v] += 1
                else:
                    c[u,v] = 1           
#     print c
    #calculated finial similarity matrix w
    w = dict()
    for u, value in c.items():
        a = u[0]
        b = u[1]
        temp = {}
        temp[b] = value/math.sqrt(n[a]*n[b])
#         for v, cuv in enumerate(related_users):
        if w.has_key(a):
            w[a] = dict(w[a].items()+temp.items())
        else:
            w[a] = temp
    return w

ItemCF的相似度计算：

def itemsimilarity(train):
    #the num