返回顶部

收藏

基于用户的协同过滤算法

更多

本代码是在学习《推荐系统实践》一书时完成的,参考了原书作者项亮的算法完成了程序,并且可运行和测试,本部分是基于用户的协同过滤算法的实现,基本与书上结论一致, 希望对于学习推荐的同学有帮助。

import random
import math
class UserBasedCF:
    def __init__(self,datafile = None):
        self.datafile = datafile
        self.readData()
        self.splitData(3,47)
    def readData(self,datafile = None):
        """
        read the data from the data file which is a data set
        """
        self.datafile = datafile or self.datafile
        self.data = []
        for line in open(self.datafile):
            userid,itemid,record,_ = line.split()
            self.data.append((userid,itemid,int(record)))
    def splitData(self,k,seed,data=None,M = 8):
        """
        split the data set
        testdata is a test data set
        traindata is a train set 
        test data set / train data set is 1:M-1
        """
        self.testdata = {}
        self.traindata = {}
        data = data or self.data
        random.seed(seed)
        for user,item, record in self.data:
            if random.randint(0,M) == k:
                self.testdata.setdefault(user,{})
                self.testdata[user][item] = record 
            else:
                self.traindata.setdefault(user,{})
                self.traindata[user][item] = record
    def userSimilarity(self,train = None):
        """
        One method of getting user similarity matrix
        """
        train = train or self.traindata
        self.userSim = dict()
        for u in train.keys():
            for v in train.keys():
                if u == v:
                    continue
                self.userSim.setdefault(u,{})
                self.userSim[u][v] = len(set(train[u].keys()) & set(train[v].keys()))
                self.userSim[u][v] /=math.sqrt(len(train[u]) * len(train[v]) *1.0)
    def userSimilarityBest(self,train = None):
        """
        the other method of getting user similarity which is better than above
        you can get the method on page 46
        In this experiment,we use this method
        """
        train = train or self.traindata
        self.userSimBest = dict()
        item_users = dict()
        for u,item in train.items():
            for i in item.keys():
                item_users.setdefault(i,set())
                item_users[i].add(u)
        user_item_count = dict()
        count = dict()
        for item,users in item_users.items():
            for u in users:
                user_item_count.setdefault(u,0)
                user_item_count[u] += 1
                for v in users:
                    if u == v:continue
                    count.setdefault(u,{})
                    count[u].setdefault(v,0)
                    count[u][v] += 1
        for u ,related_users in count.items():
            self.userSimBest.setdefault(u,dict())
            for v, cuv in related_users.items():
                self.userSimBest[u][v] = cuv / math.sqrt(user_item_count[u] * user_item_count[v] * 1.0)

    def recommend(self,user,train = None,k = 8,nitem = 40):
        train = train or self.traindata
        rank = dict()
        interacted_items = train.get(user,{})
        for v ,wuv in sorted(self.userSimBest[user].items(),key = lambda x : x[1],reverse = True)[0:k]:
            for i , rvi in train[v].items():
                if i in interacted_items:
                    continue
                rank.setdefault(i,0)
                rank[i] += wuv
        return dict(sorted(rank.items(),key = lambda x :x[1],reverse = True)[0:nitem])
    def recallAndPrecision(self,train = None,test = None,k = 8,nitem = 10):
        """
        Get the recall and precision, the method you want to know is listed 
        in the page 43
        """
        train  = train or self.traindata
        test = test or self.testdata
        hit = 0
        recall = 0
        precision = 0
        for user in train.keys():
            tu = test.get(user,{})
            rank = self.recommend(user, train = train,k = k,nitem = nitem) 
            for item,_ in rank.items():
                if item in tu:
                    hit += 1
            recall += len(tu)
            precision += nitem
        return (hit / (recall * 1.0),hit / (precision * 1.0))
    def coverage(self,train = None,test = None,k = 8,nitem = 10):
        train = train or self.traindata
        test = test or self.testdata
        recommend_items = set()
        all_items  = set()
        for user in train.keys():
            for item in train[user].keys():
                all_items.add(item)
            rank = self.recommend(user, train, k = k, nitem = nitem)
            for item,_ in rank.items():
                recommend_items.add(item)
        return len(recommend_items) / (len(all_items) * 1.0)
    def popularity(self,train = None,test = None,k = 8,nitem = 10):
        """
        Get the popularity
        the algorithm on page 44
        """
        train = train or self.traindata
        test = test or self.testdata
        item_popularity = dict()
        for user ,items in train.items():
            for item in items.keys():
                item_popularity.setdefault(item,0)
                item_popularity[item] += 1
        ret = 0
        n = 0
        for user in train.keys():
            rank = self.recommend(user, train, k = k, nitem = nitem)
            for item ,_ in rank.items():
                ret += math.log(1+item_popularity[item])
                n += 1
        return ret / (n * 1.0)

def testRecommend():
    ubcf = UserBasedCF('u.data')
    ubcf.readData()
    ubcf.splitData(4,100)
    ubcf.userSimilarity()
    user = "345"
    rank = ubcf.recommend(user,k = 3)
    for i,rvi in rank.items():

        items = ubcf.testdata.get(user,{})
        record = items.get(i,0)
        print "%5s: %.4f--%.4f" %(i,rvi,record)
def testUserBasedCF():
    cf  =  UserBasedCF('u.data')
    cf.userSimilarityBest()
    print "%3s%20s%20s%20s%20s" % ('K',"recall",'precision','coverage','popularity')
    for k in [5,10,20,40,80,160]:
        recall,precision = cf.recallAndPrecision( k = k)
        coverage = cf.coverage(k = k)
        popularity = cf.popularity(k = k)
        print "%3d%19.3f%%%19.3f%%%19.3f%%%20.3f" % (k,recall * 100,precision * 100,coverage * 100,popularity)

if __name__ == "__main__":
    testUserBasedCF()
#该片段来自于http://outofmemory.cn

标签:python,算法

收藏

0人收藏

支持

0

反对

0

相关聚客文章
  1. TLHL28 发表 2011-05-23 03:20:37 triple_des(des3) 算法 - php,python 实现
  2. 小数点 发表 2017-04-18 02:43:37 python学习之路——python切片模拟LRU算法
  3. youngsterxyf 发表 2012-11-21 16:00:00 pi的一种并行算法
  4. 0X55AA 发表 2014-08-12 07:09:15 pyrasite项目总结为一条命令
  5. 0X55AA 发表 2015-01-05 03:42:41 python的__slots__
  6. rainy 发表 2015-09-02 15:52:26 网页正文及内容图片提取算法
  7. 数控小V 发表 2016-02-17 03:14:02 机器学习算法 Python&R 速查表
  8. 上官 江 发表 2012-12-02 11:18:18 RC4算法Python实现
  9. 博主 发表 2012-02-29 23:24:00 AStar算法的python实现
  10. 0X55AA 发表 2016-10-26 06:14:30 用antlr生成Python语言的mysql语法解析器
  11. 0X55AA 发表 2015-04-29 05:29:52 DHT爬虫站-芭蕉细雨
  12. 姚 广远 发表 2015-06-19 00:23:25 用Python实现各种排序算法

发表评论