西瓜书6.2 使用libsvm

西瓜书6.2 使用libsvm

试使用LIBSVM，在西瓜数据集上分别用线性核和高斯核训练svm，并比较支持向量的差别

1. 导入依赖

<dependencies>
        <dependency>
            <groupId>tw.edu.ntu.csie</groupId>
            <artifactId>libsvm</artifactId>
            <version>3.17</version>
        </dependency>
</dependencies>

2. 将svm_predict，svm_train放入工程中

3. 调用代码

   package com.fly.svm;
   
   import java.io.IOException;
   import java.net.URL;
   
   
   
   public class Main {
       public static void main(String[] args) throws IOException {
           URL resource = Main.class.getClassLoader().getResource("");
           String url = resource.toString().substring(5);
           String testFile=url+"test.txt";
           String trainFile=url+"train.txt";
           String linerModel=url+"liner_model.txt";
           String gaussModel=url+"gauss_model.txt";
           String lineOut=url+"line_out.txt";
           String gaussOut=url+"gauss_out.txt";
           String[] arg1 = { "-t","0","-c","10000",trainFile,linerModel };
           String[] arg2={"-t","2","-c","10000",trainFile,gaussModel};
           String[] parg1 = { testFile, linerModel, lineOut};
           String[] parg2 = { testFile, gaussModel, gaussOut};
           // 创建训练对象
           svm_train t = new svm_train();
           svm_train t2=new svm_train();
           // 创建预测对象
           svm_predict p = new svm_predict();
           svm_predict p2=new svm_predict();
           //调用
           //线性核
           System.out.println("线性核");
           t.main(arg1);
           p.main(parg1);
   
           //高斯核
           System.out.println("高斯核");
           t2.main(arg2);
           p2.main(parg2);
   
       }
   }
   
   

   其中test.txt

   1 1:.774 2:.376
   1 1:.608 2:.318
   1 1:.403 2:.237
   1 1:.437 2:.211
   -1 1:.243 2:.267
   -1 1:.343 2:.099
   -1 1:.657 2:.198
   -1 1:.593 2:.042
   1 1:.697 2:.46
   1 1:.634 2:.264
   1 1:.556 2:.215
   1 1:.481 2:.149
   -1 1:.666 2:.091
   -1 1:.245 2:.057
   -1 1:.639 2:.161
   -1 1:.36 2:.37
   -1 1:.719 2:.103
   

   train.txt

   1 1:.774 2:.376
   1 1:.608 2:.318
   1 1:.403 2:.237
   1 1:.437 2:.211
   -1 1:.243 2:.267
   -1 1:.343 2:.099
   -1 1:.657 2:.198
   -1 1:.593 2:.042
   1 1:.697 2:.46
   1 1:.634 2:.264
   1 1:.556 2:.215
   1 1:.481 2:.149
   -1 1:.666 2:.091
   -1 1:.245 2:.057
   -1 1:.639 2:.161
   -1 1:.36 2:.37
   -1 1:.719 2:.103
   

4. 结果分析

   惩罚系数C较低时高斯核与线性核准确率一致，当惩罚系数较高时高斯核明显优于线性核

   C=1时

   

   C=100时

   

   C=10000时