协作型过滤应用——提供推荐

一、准备数据

critics={'Lisa Rose': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.5,
 'Just My Luck': 3.0, 'Superman Returns': 3.5, 'You, Me and Dupree': 2.5,
 'The Night Listener': 3.0},
'Gene Seymour': {'Lady in the Water': 3.0, 'Snakes on a Plane': 3.5,
 'Just My Luck': 1.5, 'Superman Returns': 5.0, 'The Night Listener': 3.0,
 'You, Me and Dupree': 3.5},
'Michael Phillips': {'Lady in the Water': 2.5, 'Snakes on a Plane': 3.0,
 'Superman Returns': 3.5, 'The Night Listener': 4.0},
'Claudia Puig': {'Snakes on a Plane': 3.5, 'Just My Luck': 3.0,
 'The Night Listener': 4.5, 'Superman Returns': 4.0,
 'You, Me and Dupree': 2.5},
'Mick LaSalle': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
 'Just My Luck': 2.0, 'Superman Returns': 3.0, 'The Night Listener': 3.0,
 'You, Me and Dupree': 2.0},
'Jack Matthews': {'Lady in the Water': 3.0, 'Snakes on a Plane': 4.0,
 'The Night Listener': 3.0, 'Superman Returns': 5.0, 'You, Me and Dupree': 3.5},
'Toby': {'Snakes on a Plane':4.5,'You, Me and Dupree':1.0,'Superman Returns':4.0}}

二、相似度评价方法

#计算两个向量的欧氏距离来评价用户的相似度
def sim_distance(prefs,person1,person2):
    si={}
    for item in prefs[person1]:
        if item in prefs[person2]:
            si[item]=1

    if len(si)==0:
        return 0
    sum_of_squares=sum([pow(prefs[person1][item]-prefs[person2][item],2) for item in si])
    return 1/(1+sqrt(sum_of_squares))#使得越相似,距离越近,评价指数越高

#计算两个向量的皮尔逊相关系数,数值越大,相似度越高
def sim_pearson(prefs,person1,person2):
    si={}
    for item in prefs[person1]:
        if item in prefs[person2]:
            si[item]=1

    n=len(si)
    if n==0:
        return 1
    sum1=sum([prefs[person1][it] for it in si])
    sum2=sum([prefs[person2][it] for it in si])
    sum1sq=sum([pow(prefs[person1][it],2) for it in si])
    sum2sq=sum([pow(prefs[person2][it],2) for it in si])
    pSum=sum([prefs[person1][it]*prefs[person2][it] for it in si])

    num=pSum-(sum1*sum2/n)
    den=sqrt((sum1sq-pow(sum1,2)/n)*(sum2sq-pow(sum2,2)/n))
    if den==0:
        return 0
    r=num/den
    return r

#返回相似度最高的前n个向量
def topMatches(prefs,person,n=5,similarity=sim_pearson):
    scores=[(similarity(prefs,person,other),other) for other in prefs if other!=person]
    scores.sort()
    scores.reverse()
    return scores[0:n]

三、根据相似度评价加权推荐

#根据用户的相似度来加权电影评分进行推荐
def getRecommendations(prefs,person,similarity=sim_pearson):
    totals={}
    simSums={}
    for other in prefs:
        if other==person:
            continue
        sim=similarity(prefs,person,other)#得到相似度评价值
        if sim<=0:
            continue
        for item in prefs[other]:
            if item not in prefs[person] or prefs[person][item]==0:
                totals.setdefault(item,0)
                totals[item]+=prefs[other][item]*sim#用相似度加权评分
                simSums.setdefault(item,0)
                simSums[item]+=sim

    rankings=[(total/simSums[item],item) for item,total in totals.items()]
    rankings.sort()
    rankings.reverse()
    return rankings#返回排好序的推荐列表

#将数据中人和电影的位置互换,可以根据电影的相似度来推荐品味相似的用户
def transformPrefs(prefs):
    result={}
    for person in prefs:
        for item in prefs[person]:
            result.setdefault(item,{})
            result[item][person]=prefs[person][item]
    return result

四、测试

print(topMatches(critics,'Toby',n=3))
print(getRecommendations(critics,'Toby'))
print(getRecommendations(critics,'Toby',similarity=sim_distance))

movies=transformPrefs(critics)
print(topMatches(movies,'Superman Returns'))
print(getRecommendations(movies,'Just My Luck'))
print(getRecommendations(movies,'Just My Luck',similarity=sim_distance))

结果输出

[(0.9912407071619299, 'Lisa Rose'), (0.9244734516419049, 'Mick LaSalle'), (0.8934051474415647, 'Claudia Puig')]
[(3.3477895267131013, 'The Night Listener'), (2.832549918264162, 'Lady in the Water'), (2.530980703765565, 'Just My Luck')]
[(3.4571286944914235, 'The Night Listener'), (2.778584003814924, 'Lady in the Water'), (2.422482042361917, 'Just My Luck')]
[(0.6579516949597695, 'You, Me and Dupree'), (0.4879500364742689, 'Lady in the Water'), (0.11180339887498941, 'Snakes on a Plane'), (-0.1798471947990544, 'The Night Listener'), (-0.42289003161103106, 'Just My Luck')]
[(4.0, 'Michael Phillips'), (3.0, 'Jack Matthews')]
[(3.5810970647618663, 'Jack Matthews'), (3.2059731906295044, 'Michael Phillips'), (2.936629402844435, 'Toby')]