mahout 推荐系统示例

建立java工程，导入需要的jar包



准备好测试的数据：D:\text.txt

1,101,5

1,102,3

1,103,2.5

2,101,2

2,102,2.5

2,103,5

2,104,2

3,101,2.5

3,104,4

3,105,4.5

3,107,5

4,101,5

4,103,3

4,104,4.5

4,106,4

5,101,4

5,102,3

5,103,2

5,104,4

5,105,3.5

5,106,4

java代码
import java.io.*;

import java.util.*;

import org.apache.mahout.cf.taste.common.TasteException;

import org.apache.mahout.cf.taste.impl.model.file.*;

import org.apache.mahout.cf.taste.impl.neighborhood.*;

import org.apache.mahout.cf.taste.impl.recommender.*;

import org.apache.mahout.cf.taste.impl.recommender.slopeone.SlopeOneRecommender;

import org.apache.mahout.cf.taste.impl.similarity.*;

import org.apache.mahout.cf.taste.model.*;

import org.apache.mahout.cf.taste.neighborhood.*;

import org.apache.mahout.cf.taste.recommender.*;

import org.apache.mahout.cf.taste.similarity.*;

public class TestMahout {

// private TestMahout(){};

public static void main(String args[]) throws Exception {

TestMahout testMahout = new TestMahout();

System.out.println("The baseUserCF Result:");

testMahout.baseUserCF();

System.out.println("The baseItemCF Result:");

testMahout.baseItemCF();

System.out.println("The baseSlopOne Result:");

testMahout.baseSlopOne();

}

//基于用户相似度的协同过滤推荐实现

public void baseUserCF(){

// 1,构建模型

DataModel dataModel;

try {

dataModel = new FileDataModel(new File("d://test.txt"));

// 2,计算相似度

UserSimilarity userSimilarity = new PearsonCorrelationSimilarity(dataModel);

// 3,查找k紧邻

UserNeighborhood userNeighborhood = new NearestNUserNeighborhood(2,

userSimilarity, dataModel);

// 4,构造推荐引擎

Recommender recommender = new GenericUserBasedRecommender(dataModel,

userNeighborhood, userSimilarity);

// 为用户i推荐两个Item

for (int i = 1; i < 6; i++) {

System.out.println("recommand for user:" + i);

List<RecommendedItem> recommendations = recommender.recommend(i,
2);

for (RecommendedItem recommendation : recommendations) {

System.out.println(recommendation);

}

}

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (TasteException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

//基于内容相似度的协同过滤推荐实现

public void baseItemCF(){

DataModel model;

try {

model = new FileDataModel(new File("d://test.txt"));

ItemSimilarity itemsimilarity =new PearsonCorrelationSimilarity(model);

Recommender recommender= new GenericItemBasedRecommender(model,itemsimilarity);

List<RecommendedItem> recommendations =recommender.recommend(1,
1);

for(RecommendedItem recommendation :recommendations){

System.out.println(recommendation);

}

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (TasteException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

//基于SlopOne的推荐实现

public void baseSlopOne(){

DataModel model;

try {

model = new FileDataModel(new File("d://test.txt"));

Recommender recommender= new SlopeOneRecommender(model);

List<RecommendedItem> recommendations =recommender.recommend(1,
1);

for(RecommendedItem recommendation :recommendations){

System.out.println(recommendation);

}

} catch (IOException e) {

// TODO Auto-generated catch block

System.out.println("Io Error");

e.printStackTrace();

} catch (TasteException e) {

// TODO Auto-generated catch block

System.out.println("Taste Error");

e.printStackTrace();

}

}

}

运行结果：

The baseUserCF Result:----------------------------------

2013-2-26 19:18:09 org.slf4j.impl.JCLLoggerAdapter info

信息: Creating FileDataModel for file d:\test.txt

2013-2-26 19:18:09 org.slf4j.impl.JCLLoggerAdapter info

信息: Reading file info...

2013-2-26 19:18:09 org.slf4j.impl.JCLLoggerAdapter info

信息: Read lines: 21

2013-2-26 19:18:09 org.slf4j.impl.JCLLoggerAdapter info

信息: Reading file info...

2013-2-26 19:18:09 org.slf4j.impl.JCLLoggerAdapter info

信息: Read lines: 21

2013-2-26 19:18:09 org.slf4j.impl.JCLLoggerAdapter info

信息: Processed 5 users

recommand for user:1

RecommendedItem[item:104, value:4.257081]

RecommendedItem[item:106, value:4.0]

recommand for user:2

recommand for user:3

RecommendedItem[item:106, value:4.0]

RecommendedItem[item:103, value:2.5905366]

recommand for user:4

RecommendedItem[item:102, value:3.0]

recommand for user:5

The baseItemCF Result:----------------------------------

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Creating FileDataModel for file d:\test.txt

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Reading file info...

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Read lines: 21

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Reading file info...

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Read lines: 21

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Processed 5 users

RecommendedItem[item:104, value:5.0]

The baseSlopOne Result:---------------------------------

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Creating FileDataModel for file d:\test.txt

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Reading file info...

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Read lines: 21

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Reading file info...

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Read lines: 21

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Processed 5 users

2013-2-26 19:18:10 org.slf4j.impl.JCLLoggerAdapter info

信息: Building average diffs...

RecommendedItem[item:105, value:5.75]