slopeOne推荐算法：最基础的推荐算法

#coding=utf8

def loadData():
    items={
        'candy':{'Bob':1.0,'Jane':1.0,'Jo':0.9,'SJo':0.1},
        'dog'  :{'Bob':0.5,'Jo':0.4},
        'cat'  :{'Jane':0.5,'Jo':0.5},
        'war'  :{'Bob':0.1,'Jane':0.2,'Jo':0.1,'SJo':1.0},
        'food' :{'SJo':0.4}
    }
    
    users={
        'Bob':{'candy':1.0,'dog':0.5,'war':0.1},
        'Jane':{'candy':1.0,'cat':0.5,'war':0.2},
        'Jo':{'candy':0.9,'dog':0.4,'cat':0.5,'war':0.1},
        'SJo':{'candy':0.1,'war':1.0,'food':0.4}
    }
    
    return items,users

#***计算物品之间的评分差 
#items:从物品角度，考虑评分 
#users:从用户角度，考虑评分 
def buildAverageDiffs(items,users,averages): 
    #遍历每条物品-用户评分数据 
    for itemId in items: 
        for otherItemId in items: 
            average=0.0 #物品间的评分偏差均值 
            userRatingPairCount=0 #两件物品均评过分的用户数 
            if itemId!=otherItemId: #若无不同的物品项 
            # 上条代码可以改进成如下方式
            # if itemId!=otherItemId and (itemId,otherItemId) not in averages.keys() and (otherItemId,itemId) not in averages.keys(): #若无不同的物品项 
                for userId in users: #遍历用户-物品评分数 
                    userRatings=users[userId] #每条数据为用户对物品的评分 
                    #当前物品项在用户的评分数据中，且用户也对其他物品由评分 
                    if itemId in userRatings and otherItemId in userRatings: 
                        #两件物品均评过分的用户数加1 
                        userRatingPairCount+=1 
                        #评分偏差为每项当前物品评分-其他物品评分求和 
                        average+=(userRatings[otherItemId]-userRatings[itemId]) 
                if(userRatingPairCount!=0):
                    averages[(itemId,otherItemId)]=average/userRatingPairCount
                
#统计量物品共同评分的用户数
# 物品itemId1与itemId2共同有多少用户评分 
def userWhoRatedBoth(users,itemId1,itemId2): 
    count=0 
    #用户-物品评分数据 
    for userId in users: 
        #用户对物品itemId1与itemId2都评过分则计数加1 
        if itemId1 in users[userId] and itemId2 in users[userId]: 
            count+=1 
    return count

#***预测评分 
#users:用户对物品的评分数据 
#items：物品由哪些用户评分的数据 
#averages：计算的评分偏差 
#targetUserId：被推荐的用户 
#targetItemId：被推荐的物品 
def suggestedRating(users,items,averages,targetUserId,targetItemId): 
    runningRatingCount=0 #预测评分的分母 
    weightedRatingTotal=0.0 #分子 
    for i in users[targetUserId]: 
        #物品i和物品targetItemId共同评分的用户数 
        ratingCount=userWhoRatedBoth(users,i,targetItemId) 
        #分子 
        if(ratingCount!=0):
            weightedRatingTotal+=(users[targetUserId][i]-averages[(targetItemId,i)])*ratingCount 
        #分母 
        runningRatingCount+=ratingCount 
    #返回预测评分 
    return weightedRatingTotal/runningRatingCount

if __name__=='__main__': 
    items,users = loadData() 
    averages={} 

    #计算物品之间的平均评分差 
    buildAverageDiffs(items,users,averages) 

    #预测评分:用户2对物品C的评分 
    predictRating=suggestedRating(users,items,averages,'Jo','food') 
    print ('Guess the user will rate the score :'+ str(round(predictRating,2)))
    ```