#-[i]- coding: utf-8 -[/i]-  

import json  

import sys  

reload(sys)  

sys.setdefaultencoding( "utf-8" )  

  

user_info = {}  

  

#爬取到的数据  

user_dict = {  

             'ns2250225':[4,3,4,5,4],  

             'justin':[3,4,3,4,2],  

             'totox':[2,3,5,1,4],  

             'fabrice':[4,1,3,4,5],  

             'doreen':[3,4,2,5,3]  

             }  

  

#录入用户数据  

def user_data(user_dict):  

    for name in user_dict:  

        user_info[name] = {u'消失的爱人' : user_dict[name][0]}  

        user_info[name][u'霍比特人3'] = user_dict[name][1]  

        user_info[name][u'神去村'] = user_dict[name][2]  

        user_info[name][u'泰坦尼克号'] = user_dict[name][3]  

        user_info[name][u'这个杀手不太冷'] = user_dict[name][4]  

          

  

user_data(user_dict)      

  

#存放用户数据  

try:  

    with open('user_data.txt', 'w') as data:  

        for key in user_info:  

            data.write(key)  

            for key2 in user_info[key]:  

                data.write('\t')  

                data.write(key2)  

                data.write('\t')  

                data.write('\t')  

                data.write(str(user_info[key][key2]))  

                data.write('\n')  

            data.write('\n')  

except IOError as err:  

    print('File error: ' + str(err))  

from math import sqrt   

  

#计算皮尔逊相关度(1为完全正相关，-1为完成负相关)  

def sim_pearson(prefs, p1, p2):    

    # Get the list of mutually rated items    

    si = {}    

    for item in prefs[p1]:    

        if item in prefs[p2]:    

            si[item] = 1    

    

    # if they are no ratings in common, return 0    

    if len(si) == 0:    

        return 0    

    

    # Sum calculations    

    n = len(si)    

    

    # Sums of all the preferences    

    sum1 = sum([prefs[p1][it] for it in si])    

    sum2 = sum([prefs[p2][it] for it in si])    

    

    # Sums of the squares    

    sum1Sq = sum([pow(prefs[p1][it], 2) for it in si])    

    sum2Sq = sum([pow(prefs[p2][it], 2) for it in si])    

    

    # Sum of the products    

    pSum = sum([prefs[p1][it] * prefs[p2][it] for it in si])    

    

    # Calculate r (Pearson score)    

    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  

  

  

#插入自己的数据  

user_info['me'] = {u'消失的爱人' : 5,  

                   u'神去村' : 3,  

                   u'炸裂鼓手' : 5}  

  

  

            

#找出皮尔逊相关系数>0的用户，说明该用户与自己的电影品味比较相近  

for user in user_info:  

    res = sim_pearson(user_info, 'me', user)  

    if res > 0:  

        print('the user like %s is : %s' % ('me', user))  

        print('result :%f\n' % res)  

#向某个用户推荐电影(加权平均所有人的评价值)  

def getRecommendations(prefs,person,similarity=sim_pearson):  

  totals={}  

  simSums={}  

  for other in prefs:  

    # don't compare me to myself  

    if other==person: continue  

    sim=similarity(prefs,person,other)  

  

    # ignore scores of zero or lower  

    if sim<=0: continue  

    for item in prefs[other]:  

          

      # only score movies I haven't seen yet  

      if item not in prefs[person] or prefs[person][item]==0:  

        # Similarity * Score  

        totals.setdefault(item,0)  

        totals[item]+=prefs[other][item]*sim  

        # Sum of similarities  

        simSums.setdefault(item,0)  

        simSums[item]+=sim  

  

  # Create the normalized list  

  rankings=[(total/simSums[item],item) for item,total in totals.items()]  

  

  # Return the sorted list  

  rankings.sort()  

  rankings.reverse()  

  return rankings  

  

  

#向我推荐电影  

res = getRecommendations(user_info, "me")  

print('Recommand watching the movie:')  

print json.dumps(res, encoding='UTF-8', ensure_ascii=False)