UBCF和IBCF的python实现和比较

进行实验的源代码参考了项亮的《推荐系统实践》和http://my.oschina.net/zhangjiawen/blog/185625

1.版本1——核心代码为书中代码

import random
import math
import time
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
        把文件中的内容读到data中"""
        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):
        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: