一.加权SlopeOne算法公式：
(1).求得所有item之间的评分偏差
上式中分子部分为项目j与项目i的偏差和，分母部分为所有同时对项目j与项目i评分的用户数
(2).加权预测评分
项目j与项目i
上式中表示用户u对项目j的评分预测，分子为项目j对项目i的偏差加上用户对项目i的评分，cji表示同时对项目j与项目i评分的用户数
二.python实现
1 #!/usr/bin/python
2 # -*- coding: utf-8 -*-
3
4 user_data = {"小明": {"张学友": 4, "周杰伦": 3, "刘德华": 4},
5 "小海": {"张学友": 5, "周杰伦": 2},
6 "李梅": {"周杰伦": 3.5, "刘德华": 4},
7 "李磊": {"张学友": 5, "刘德华": 3}}
8
9 class recommender:
10
11 def __init__(self,data):
12 self.frequency={}
13 self.deviation={}
14 self.data=data
15
16 #计算所有item之间评分偏差
17 def computeDeviation(self):
18 for ratings in self.data.values():
19 for item,rating in ratings.items():
20 self.frequency.setdefault(item,{})
21 self.deviation.setdefault(item,{})
22 for item2,rating2 in ratings.items():
23 if item!=item2:
24 self.frequency[item].setdefault(item2,0)
25 self.deviation[item].setdefault(item2,0.0)
26 self.frequency[item][item2]+=1#两个项目的用户数
27 self.deviation[item][item2]+=(rating-rating2)#累加两个评分差值
28 for item,ratings in self.deviation.items():
29 for item2 in ratings:
30 ratings[item2]/=self.frequency[item][item2]
31
32 #评分预测
33 def predictRating(self,userRatings,k):
34 recommendations={}
35 frequencies={}
36 for item,rating in userRatings.items():
37 for diffItem,diffRating in self.deviation.items():
38 if diffItem not in userRatings and item in self.deviation[diffItem]:
39 fre=self.frequency[diffItem][item]
40 recommendations.setdefault(diffItem,0.0)
41 frequencies.setdefault(diffItem,0)
42 #分子部分
43 recommendations[diffItem]+=(diffRating[item]+rating)*fre
44 #分母部分
45 frequencies[diffItem]+=fre
46 recommendations=[(k,v/frequencies[k]) for (k,v) in recommendations.items()]
47 #排序返回前k个
48 recommendations.sort(key=lambda a_tuple:a_tuple[1],reverse=True)
49 return recommendations[:k]
50
51 if __name__==‘__main__‘:
52 r=recommender(user_data)
53 r.computeDeviation()
54 u=user_data[‘李磊‘]
55 print(r.predictRating(u,5))
56
三.java实现
1 import java.util.HashMap;
2 import java.util.Map;
3 import java.util.List;
4 import java.util.ArrayList;
5 import java.util.Comparator;
6 import java.util.Collections;
7
8 /**
9 * Created by on 2016/12/8.ShiYan
10 * 一.计算所有物品对的偏差
11 * 二.利用偏差进行预测
12 */
13 public class SlopeOne {
14 Map<String,Map<String,Integer>> frequency=null;
15 Map<String,Map<String,Double>> deviation=null;
16 Map<String,Map<String,Integer>> user_rating=null;
17
18 public SlopeOne( Map<String,Map<String,Integer>> user_rating){
19 frequency=new HashMap<String,Map<String,Integer>>();
20 deviation=new HashMap<String,Map<String,Double>>();
21 this.user_rating=user_rating;
22 }
23
24 /**
25 * 所有有item间的评分偏差
26 */
27 public void computeDeviation(){
28 for(Map.Entry<String,Map<String,Integer>> ratingsEntry:user_rating.entrySet()){
29 for(Map.Entry<String,Integer> ratingEntry:ratingsEntry.getValue().entrySet()){
30 String item=ratingEntry.getKey();
31 int rating=ratingEntry.getValue();
32 Map<String,Integer> itemFrequency=null;
33 if(!frequency.containsKey(item)){
34 itemFrequency=new HashMap<String, Integer>();
35 frequency.put(item,itemFrequency);
36 }else{
37 itemFrequency=frequency.get(item);
38 }
39
40 Map<String,Double> itemDeviation=null;
41 if(!deviation.containsKey(item)){
42 itemDeviation=new HashMap<String, Double>();
43 deviation.put(item,itemDeviation);
44 }else{
45 itemDeviation=deviation.get(item);
46 }
47
48 for(Map.Entry<String,Integer> ratingEntry2:ratingsEntry.getValue().entrySet()){
49 String item2=ratingEntry2.getKey();
50 int rating2=ratingEntry2.getValue();
51 if(!item.equals(item2)){
52 //两个项目的用户数
53 itemFrequency.put(item2,itemFrequency.containsKey(item2)?itemFrequency.get(item2)+1:0);
54 //两个项目的评分偏差，累加
55 itemDeviation.put(item2,itemDeviation.containsKey(item2)?itemDeviation.get(item2)+(rating-rating2):0.0);
56 }
57 }
58 }
59 }
60
61 for(Map.Entry<String,Map<String,Double>> itemsDeviation:deviation.entrySet()){
62 String item=itemsDeviation.getKey();
63 Map<String,Double> itemDev=itemsDeviation.getValue();
64 Map<String,Integer> itemFre=frequency.get(item);
65 for(String itemName:itemDev.keySet()){
66 itemDev.put(itemName,itemDev.get(itemName)/itemFre.get(itemName));
67 }
68 }
69 }
70
71 /**
72 * 评分预测
73 * @param userRating 目标用户的评分
74 * @param k 返回前k个
75 * @return
76 */
77 public List<Map.Entry<String,Double>> predictRating(Map<String,Integer> userRating,int k){
78 Map<String,Double> recommendations=new HashMap<String,Double>();
79 Map<String,Integer> frequencies=new HashMap<String, Integer>();
80 for(Map.Entry<String,Integer> userEntry:userRating.entrySet()){
81 String userItem=userEntry.getKey();
82 double rating=userEntry.getValue();
83 for(Map.Entry<String,Map<String,Double>> deviationEntry:deviation.entrySet()){
84 String item=deviationEntry.getKey();
85 Map<String,Double> itemDeviation=deviationEntry.getValue();
86 Map<String,Integer> itemFrequency=frequency.get(item);
87 if(!userRating.containsKey(item) && itemDeviation.containsKey(userItem)){
88 int fre=itemFrequency.get(userItem);
89 if(!recommendations.containsKey(item))
90 recommendations.put(item,0.0);
91 if(!frequencies.containsKey(item))
92 frequencies.put(item,0);
93 //分子部分
94 recommendations.put(item,recommendations.get(item)+(itemDeviation.get(userItem)+rating)*fre);
95 //分母部分
96 frequencies.put(item,frequencies.get(item)+fre);
97 }
98 }
99 }
100 for(Map.Entry<String,Double> recoEntry:recommendations.entrySet()){
101 String key=recoEntry.getKey();
102 double value=recoEntry.getValue()/frequencies.get(key);
103 recommendations.put(key,value);
104 }
105 //排序，这里还可以使用优先队列返回top_k
106 List<Map.Entry<String,Double>> list_map=new ArrayList<Map.Entry<String,Double>>(recommendations.entrySet());
107 Collections.sort(list_map,new Comparator<Map.Entry<String,Double>>(){
108 @Override
109 public int compare(Map.Entry<String, Double> o1, Map.Entry<String, Double> o2) {
110 if(o2.getValue()>o1.getValue())
111 return 1;
112 else if(o2.getValue()<o1.getValue())
113 return -1;
114 else
115 return 0;
116 }
117 }
118 );
119 List<Map.Entry<String,Double>> top_k=new ArrayList<Map.Entry<String, Double>>();
120 if(list_map.size()<k) k=list_map.size();
121 for(int i=0;i<k;i++){
122 top_k.add(list_map.get(i));
123 }
124 return top_k;
125 }
126
127 public static void main(String[] args){
128 Map<String,Map<String,Integer>> userRatings=new HashMap<String, Map<String, Integer>>();
129 Map<String,Integer> xiMingRating=new HashMap<String, Integer>();
130 xiMingRating.put("张学友",4);
131 xiMingRating.put("周杰伦",3);
132 xiMingRating.put("刘德华",4);
133 Map<String,Integer> xiHaiRating=new HashMap<String, Integer>();
134 xiHaiRating.put("张学友",5);
135 xiHaiRating.put("周杰伦",2);
136 Map<String,Integer> liMeiRating=new HashMap<String, Integer>();
137 liMeiRating.put("周杰伦",3);
138 liMeiRating.put( "刘德华",4);
139 Map<String,Integer> liLeiRating=new HashMap<String, Integer>();
140 liLeiRating.put("张学友",5);
141 liLeiRating.put("刘德华",3);
142 userRatings.put("xiMing",xiMingRating);
143 userRatings.put("xiHai",xiHaiRating);
144 userRatings.put("liMei", liMeiRating);
145 userRatings.put("liLei",liLeiRating);
146
147 SlopeOne slopOne=new SlopeOne(userRatings);
148 slopOne.computeDeviation();
149 List<Map.Entry<String,Double>> top_k=slopOne.predictRating(userRatings.get("liLei"),5);
150 for(Map.Entry<String,Double> item:top_k){
151 System.out.println(item.getKey()+" "+item.getValue());
152 }
153 }
154 }
时间： 2024-08-29 15:14:27