经典推荐算法实现

目录1.基于ItemCF算法2.基于UserCF算法3.基于时间上下文的个性化推荐4.基于LFM算法的个性化推荐5.基于图的推荐算法1.基于ItemCF算法#!/usr/sbin/env python# -*- coding:utf-8 -*-import math# ItemCF算法def ItemSimilarity(train):...

hejp_123

1412人浏览 · 2019-06-20 09:49:13

hejp_123 · 2019-06-20 09:49:13 发布

1.基于ItemCF算法

#!/usr/sbin/env python
# -*- coding:utf-8 -*-
 
import math
 
# ItemCF算法
def ItemSimilarity(train):
    C = dict()
    N = dict()
    for u,items in train.items():
        for i in items.keys():
            N[i] += 1
            for j in items.keys():
                if i == j:
                    continue
                C[i][j] += 1
    W = dict()
    for i,related_items in C.items():
        for j,cij in related_items.items():
            W[i][j] = cij / math.sqrt( N[i] * N[j])
    return W
 
# ItemCF-IUF算法
def ItemSimilarity_v2(train):
    C = dict()
    N = dict()
    for u,items in train.items():
        for i in items.keys():
            N[i] += 1
            for j in items.keys():
                if i == j:
                    continue
                C[i][j] += 1 / math.log(1+len(items)*1.0)
    W = dict()
    for i,related_items in C.items():
        for j,cij in related_items.items():
            W[i][j] = cij / math.sqrt( N[i] * N[j])
    return W
 
def Recommend(train,user_id,W,K):
    rank = dict()
    ru = train[user_id]
    for i,pi in ru.items():
        for j,wj in sorted(W[i].items,key=itemgetter(1),reverse=True)[0:K]:
            if j in ru:
                continue
            rank[j] += pi*wj
    return rank

2.基于UserCF算法

import math
'''
基于UserCF的推荐算法
'''
# UserCF算法
def UserSimilarity(train):
    item_users = dict()
    for u,items in train.items():
        for i in items.keys():
            if i not in item_users:
                item_users[i] = set()
            item_users[i].add(u)
    C = dict()
    N = dict()
    for i,users in item_users.items():
        for u in users:
            N[u] += 1
            for v in users:
                if u == v:
                    continue
                C[u][v] += 1
    W = dict()
    for u,related_users in C.items():
        for v,cuv in related_users.items():
            W[u][v] = cuv / math.sqrt(N[u] * N[v])
    return W
 
# User-IIF算法
def UserSimilarity_v2(train):
    item_users = dict()
    for u,items in train.items():
        for i in items.keys():
            if i not in item_users:
                item_users[i] = set()
            item_users[i].add(u)
    C = dict()
    N = dict()
    for i,users in item_users.items():
        for u in users:
            N[u] += 1
            for v in users:
                if u == v:
                    continue
                C[u][v] += 1 / math.log(1+len(users))
    W = dict()
    for u,related_users in C.items():
        for v,cuv in related_users.items():
            W[u][v] = cuv / math.sqrt(N[u] * N[v])
    return W
 
def Recommend(user,train,W):
    rank = dict()
    interacted_items = train[user]
    for v,wuv in sorted(W[u].items,key=itemgetter(1),reverse=True)[0:K]:
        for i,rvi in train[v].items:
            if i in interacted_items:
                continue
            rank[i] += wuv*rvi
    return rank

3.基于时间上下文的个性化推荐

import math
 
 
def RecentPopularity(records,alpha,T):
    ret = dict()
    for user,item,tm in records:
        if tm >= T:
            continue
        addToDict(ret,item,1/(1.0+alpha*(T-tm)))
    return ret
 
def addToDict(dicts,item,value):
    pass
 
def ItemSimilarity(train,alpha):
    C = dict()
    N = dict()
    for u,items in train.items():
        for i,tui in items.items():
            N[i] += 1
            for j,tuj in items.items():
                if i == j:
                    continue
                C[i][j] += 1 / (1+alpha*abs(tui-tuj))
    W = dict()
    for i,related_items in C.items():
        for j,cij in related_items.items():
            W[i][j] = cij / math.sqrt(N[i] * N[j])
    return W
 
def RecommendItemCF(train,user_id,W,K,t0):
    rank = dict()
    ru = train[user_id]
    for i,pi in ru.items():
        for j,wj in sorted(W[i].items(),\
                key=itemgetter(1),reverse=True)[0:K]:
            if j,tuj in ru.items():
                continue
            rank[j] += pi * wj / (1 + alpha * (t0 - tuj))
    return rank
 
 
def UserSimilarity(train):
    item_users = dict()
    for u,items in train.items():
        for i,tui in items.items():
            if i not in item_users:
                item_users[i] = dict()
            item_users[i][u] = tui
 
    C = dict()
    N = dict()
    for i,users in item_users.items():
        for u,tui in users.items():
            N[u] += 1
            for v,tvi in users.items():
                if u == v:
                    continue
                C[u][v] += 1 / (1 + alpha * abs(tui - tvi))
    W = dict()
    for u,related_users in C.items():
        for v,cuv in related_users.items():
            W[u][v] = cuv / math.sqrt(N[u] * N[v])
    return W
 
def RecommendUserCF(user,T,train,W):
    rank = dict()
    interacted_items = train[user]
    for v,wuv in sorted(W[u].items,key=itemgetter(1),\
            reverse=True)[0:K]:
        for i,tvi in train[v].items:
            if i in interacted_items:
                continue
            rank[i] += wuv / (1 + alpha * (T - tvi))
    return rank

4.基于LFM算法的个性化推荐

import random
 
'''
items => {'12':'PHP','1203':'Storm','123':'Ubuntu'}
items_pool => [12,32,121,324,532,123,53,1203,429,2932]
user_items => {'1010':[12,1203,123,429]}
'''
def RandomSelectNagativeSample(items):
    ret = dict()
    for i in items.keys():
        ret[i] = 1
    n = 0
    for i in range(0,len(items)*3):
        item = items_pool[random.randint(0,len(items_pool)-1)]
        if item in ret:
            continue
        ret[item] = 0
        n += 1
        if n > len(items):
            break
    return ret
 
 
def InitModel(user_items,F):
    P = dict()
    Q = dict()
    for u in user_items.keys():
        if u not in P:
            P[u] = {}
        for f in range(0,F):
            P[u][f] = 1
 
    items = user_items.values()
    itemLen = len(items[0])
    i = 0
    while i< itemLen:
        ii = items[0][i]
        if ii not in Q:
            Q[ii] = {}
        for f in range(0,F):
            Q[ii][f] = 1
        i += 1
    return [P,Q]
 
 
def LatentFactorModel(user_items,F,N,alpha,lambda1):
    [P,Q] = InitModel(user_items,F)
    for setup in range(0,N):
        for user,items in user_items.items():
            samples = RandomSelectNagativeSample(items)
            for item,rui in samples.items():
                eui = rui - Predict(user,item)
                for f in range(0,F):
                    P[user][f] += alpha * (eui * Q[item][f] - lambda1 * P[user][f])
                    Q[item][f] += alpha * (eui * P[user][f] - lambda1 * Q[item][f])
        alpha *= 0.9
    return [P,Q]
 
 
def Recommend(user,P,Q):
    rank = dict()
    for f,puf in P[user].items():
        for i,pfi in Q[f].items():
            if i not in rank:
                rank[i] += puf * qfi
    return rank
 
 
 
def PersonalRank(G,alpha,root,maxsetup):
    rank = dict()
    #rank = {x:0 for x in G.keys()}
    rank = rank.fromkeys(G.keys(),0)
    rank[root] = 1
    for k in range(maxsetup):
        tmp = dict()
        #tmp = {x:0 for x in G.keys()}
        tmp = tmp.fromkeys(G.keys(),0)
        for i,ri in G.items():
            for j,wij in ri.items():
                if j not in tmp:
                    tmp[j] = 0
                tmp[j] += alpha * rank[i]/(1.0*len(ri))
                if j == root:
                    tmp[j] += 1 - alpha
        rank = tmp
 
        print 'iter:' + str(k) + "\t",
        for key,value in rank.items():
            print "%s:%.3f,\t" % (key,value),
        print
    return rank
 
if __name__ == '__main__':
    G = {'A':{'a':1,'c':1},
     'B':{'a':1,'b':1,'c':1,'d':1},
     'C':{'c':1,'d':1},
     'a':{'A':1,'B':1},
     'b':{'B':1},
     'c':{'A':1,'B':1,'C':1},
     'd':{'B':1,'C':1}}
    PersonalRank(G,0.85,'A',20)
 
'''
#items_pool = {'12':'PHP','32':'Nginx','121':'Apache','324':'Erlang','532':'Linux','123':'Ubuntu','53':'Java','1203':'Storm','429':'Kafka','2932':'Flume'}
items_pool = [12,32,121,324,532,123,53,1203,429,2932]
items = {'12':'PHP','1203':'Storm','123':'Ubuntu'}
user_items = {'1010':[12,1203,123,429]}
#print RandomSelectNagativeSample(items)
print InitModel(user_items,4)
'''

5.基于图的推荐算法

'''
    基于图的推荐算法,二分图
'''
 
 
def PersonalRank(G,alpha,root,maxsetup):
    rank = dict()
    #rank = {x:0 for x in G.keys()}
    rank = rank.fromkeys(G.keys(),0)
    rank[root] = 1
    for k in range(maxsetup):
        tmp = dict()
        #tmp = {x:0 for x in G.keys()}
        tmp = tmp.fromkeys(G.keys(),0)
        for i,ri in G.items():
            for j,wij in ri.items():
                if j not in tmp:
                    tmp[j] = 0
                tmp[j] += alpha * rank[i]/(1.0*len(ri))
                if j == root:
                    tmp[j] += 1 - alpha
        rank = tmp
 
        print 'iter:' + str(k) + "\t",
        for key,value in rank.items():
            print "%s:%.3f,\t" % (key,value),
        print
    return rank
 
if __name__ == '__main__':
    G = {'A':{'a':1,'c':1},
     'B':{'a':1,'b':1,'c':1,'d':1},
     'C':{'c':1,'d':1},
     'a':{'A':1,'B':1},
     'b':{'B':1},
     'c':{'A':1,'B':1,'C':1},
     'd':{'B':1,'C':1}}
    PersonalRank(G,0.85,'C',20)

CSDN学习社区

CSDN联合极客时间，共同打造面向开发者的精品内容学习社区，助力成长！

更多推荐

嵌入式作业（七）：基于Ardunio的STM32串口通信

嵌入式作业（七）0作业要求1Ardunio 完成STM32的串口通信（1）安装Ardunio IDE（2）stm32串口通信2关于 stduino IDE0作业要求安装 Ardunio IDE 和相关软件支持库，在Ardunio 完成STM32板子的串口通信程序：（1）持续向串口输出“Hello world！”；（2）当接收到“stop!”时，停止输出。网上有一个国人版的MCU集成开发平台， st

CSDN学习社区

JDBC详解

JDBC文章目录JDBC什么是JDBC?JDBC驱动程序:Java使用JDBC访问数据库的步骤:设置classpath:Oracle连接字符串的书写格式:简单的例子:常用数据库的驱动程序及JDBC URL:Oracle数据库:SQL Server数据库MySQL数据库Access数据库PreparedStatement接口:JNDI-数据源（Data Source）与连接池（Connection

CSDN学习社区

“模式识别与机器学习”学习笔记no2.再谈感知机

接**上篇：上篇主要进行了PLA，Pocket算法的理论过程分析和在给定数据集上利用pocket算法对数据集进行分类学习，得到错分数量最少的分类面。上篇中pocket算法的过程已经进行了编程和测试，框架已经建立了起来，这一篇主要上篇中没有提到或涉及不深的几个问题。1.数据集的构造。上篇是直接使用了题目给的向量，这次来根据正态分布来产生数据集。np.random.normal函数可以根据均值和方差生