推荐算法

最新推荐文章于 2020-02-24 16:58:52 发布

原创最新推荐文章于 2020-02-24 16:58:52 发布 · 346 阅读

CC 4.0 BY-SA版权

文章标签：

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}}

from math import sqrt

def sim_distance(prefs,person1,person2):#欧式距离计算相似度
    sim={}
    for item in prefs[person1]:
        if item in prefs[person2]:
            sim[item]=1#判断是否来个用户相关
    if len(sim)==0:#如果不先关则返回0
        return 0
    #连个用户相关则计算他们的相似度，用欧式距离
    sum_of_squares=sum([pow(prefs[person1][item] - prefs[person2][item],2) 
                            for item in prefs[person1] if item in prefs[person2]])
    return  1/(1+sqrt(sum_of_squares))
    
def sim_pearson(prefs,p1,p2):#皮尔逊相关系数计算相似度
    si={}
    for item in prefs[p1]:
        if item in prefs[p2]:
            si[item]=1
    n=len(si)
    if n==0:return -1
    sum1=sum([prefs[p1][it] for it in si])
    sum2=sum([prefs[p2][it] for it in si])
    sum1sq=sum([pow(prefs[p1][it],2) for it in si])
    sum2sq=sum([pow(prefs[p2][it],2) for it in si])
    psum=sum([prefs[p1][it]*prefs[p2][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#返回0为了防止除0错误
    r=num/den
    return r
    
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]


def getRecommenddations(prefs,person,similarity=sim_pearson):
    totals={}
    simsums={}
    for other in prefs:
        if other==person:continue
        sim=similarity(prefs,person,other)
        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
                simsums.setdefault(item,0)
                simsums[item]+=sim
    ranking=[(total/simsums[item],item) for item,total in totals.items()]
    ranking.sort()
    ranking.reverse()
    return ranking

def transformPrefs(prefs):
    result={}
    for person in prefs:
        for item in prefs[person]:
            result.setdefault(item,{})
            result[item][person]=prefs[person][item]
    return result

    
def calculatesimilaritems(prefs,n=10):
    result={}
    itemPrefs=transformPrefs(prefs)
    c=0
    for item in itemPrefs:
        c+=1
        if c%100==0:print '%d,%d'%(c,len(itemPrefs))
        scores=topmatches(itemPrefs,item,n,similarity=sim_pearson)
        result[item]=scores
    return result

def getRecommendeditems(prefs,itemPrefs,user):
    userRating=prefs[user]
    scores={}
    totalsim={}
    for (item,rating) in userRating.items():
       for (similarity,item2) in itemPrefs[item]:
           if item2 in userRating:continue
           scores.setdefault(item2,0)
           scores[item2]+=similarity*rating
           totalsim.setdefault(item2,0)
           totalsim[item2]+=similarity
    ranking=[(score/totalsim[item],item) for item,score in scores.items()]
    ranking.sort()
    ranking.reverse()
    return ranking

https://promotion.aliyun.com/ntms/act/enterprise-discount.html?userCode=1qylypgj

【助力企业上云】性能级主机2-5折

阿里云活动，服务器便宜卖哦，通过此链接注册购买，可联系作者协助部署搭建服务器环境。QQ（814341142）