使用Java在Weka中对单个实例进行分类

Question

我使用WEKA gui训练并创建了Nativebases。 我将模型文件保存到计算机上，现在我想用它来对Java代码中的单个实例进行分类。 我想对“集群”属性进行预测。 我要做的是以下几点：

package level_4_project_weka;

import java.util.ArrayList;
import weka.classifiers.Classifier;
import weka.core.Attribute;
import weka.core.DenseInstance;
import weka.core.Instance;
import weka.core.Instances;

 public class wekaClass2 {



 private Instance inst_co;



 String classify(
        float area_of_disease1,
        float length_of_disease1,
        int s_area_count1, 
        float sd_disease_r1, 
        float sd_disease_g1, 
        float sd_disease_b1, 
        float sd_background_r1, 
        float sd_background_g1, 
        float sd_background_b1, 
        int m_disease_r1, 
        int m_disease_g1, 
        int m_disease_b1, 
        int m_background_r1, 
        int m_background_g1, 
        int m_background_b1, 
        String fluid_filled_blisters1, 
        String feel_itchy1) {

    String result = null;
    try {

        ArrayList<Attribute> attributeList = new ArrayList<>(17);

        Attribute area_of_disease = new Attribute("area_of_disease");
        Attribute length_of_disease = new Attribute("length_of_disease");
        Attribute s_area_count = new Attribute("s_area_count");
        Attribute sd_disease_r = new Attribute("sd_disease_r");
        Attribute sd_disease_g = new Attribute("sd_disease_g");
        Attribute sd_disease_b = new Attribute("sd_disease_b");
        Attribute sd_background_r = new Attribute("sd_background_r");
        Attribute sd_background_g = new Attribute("sd_background_g");
        Attribute sd_background_b = new Attribute("sd_background_b");
        Attribute m_disease_r = new Attribute("m_disease_r");
        Attribute m_disease_g = new Attribute("m_disease_g");
        Attribute m_disease_b = new Attribute("m_disease_b");
        Attribute m_background_r = new Attribute("m_background_r");
        Attribute m_background_g = new Attribute("m_background_g");
        Attribute m_background_b = new Attribute("m_background_b");
        Attribute fluid_filled_blisters = new Attribute("fluid_filled_blisters");
        Attribute feel_itchy = new Attribute("feel_itchy");

        ArrayList<String> classVal = new ArrayList<>();
        classVal.add("melanoma");
        classVal.add("eczema");
        classVal.add("impetigo");
        //classVal.add("ClassB");


        attributeList.add(area_of_disease);
        attributeList.add(length_of_disease);
        attributeList.add(s_area_count);
        attributeList.add(sd_disease_r);
        attributeList.add(sd_disease_g);
        attributeList.add(sd_disease_b);
        attributeList.add(sd_background_r);
        attributeList.add(sd_background_g);
        attributeList.add(sd_background_b);
        attributeList.add(m_disease_r);
        attributeList.add(m_disease_g);
        attributeList.add(m_disease_b);            
        attributeList.add(m_background_r);
        attributeList.add(m_background_g);
        attributeList.add(m_background_b);
        attributeList.add(fluid_filled_blisters);
        attributeList.add(feel_itchy);

        attributeList.add(new Attribute("@@type@@",classVal));

        Instances data = new Instances("TestInstances",attributeList,0);


        // Create instances for each pollutant with attribute values latitude,
        // longitude and pollutant itself
        inst_co = new DenseInstance(data.numAttributes());
        data.add(inst_co);

        // Set instance's values for the attributes "latitude", "longitude", and
        // "pollutant concentration"
         inst_co.setValue(area_of_disease,area_of_disease1);
         inst_co.setValue(length_of_disease,length_of_disease1);
         inst_co.setValue(s_area_count,s_area_count1);
         inst_co.setValue(sd_disease_r,sd_disease_r1);
         inst_co.setValue(sd_disease_g,sd_disease_g1);
         inst_co.setValue(sd_disease_b,sd_disease_b1);
         inst_co.setValue(sd_background_r,sd_background_r1);
         inst_co.setValue(sd_background_g,sd_background_g1);
         inst_co.setValue(sd_background_b,sd_background_b1);
         inst_co.setValue(m_disease_r,m_disease_r1);
         inst_co.setValue(m_disease_g,m_disease_g1);
         inst_co.setValue(m_disease_b,m_disease_b1);            
         inst_co.setValue(m_background_r,m_background_r1);
         inst_co.setValue(m_background_g,m_background_g1);
         inst_co.setValue(m_background_b,m_background_b1);
         inst_co.setValue(fluid_filled_blisters,fluid_filled_blisters1);
         inst_co.setValue(feel_itchy,feel_itchy1);
        // inst_co.setMissing(cluster);

        // load classifier from file
        Classifier cls_co = (Classifier) weka.core.SerializationHelper
                .read("C:/Users/Lahiru/Documents/NetBeansProjects/level_4_project_weka/diseases.model");

       double result1 = cls_co.classifyInstance(inst_co);
        System.out.println("a" + result1);
    } catch (Exception e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
     }
     return result;
   }


   }

但是当我添加

        `inst_co.setValue(fluid_filled_blisters,fluid_filled_blisters1);
         inst_co.setValue(feel_itchy,feel_itchy1);`

我收到以下错误。

java.lang.IllegalArgumentException: Attribute neither nominal nor string!
at weka.core.AbstractInstance.setValue(AbstractInstance.java:518)
at level_4_project_weka.wekaClass2.classify(wekaClass2.java:112)
at   level_4_project_weka.Level_4_project_weka.PredictDisease(Level_4_project_weka.java:102)
at level_4_project_weka.Level_4_project_weka.main(Level_4_project_weka.java:27)

我知道，由于这两个是字符串变量而发生此错误。 但是我不知道如何处理字符串。 谁能告诉我正确的方法？

Answer 1

请参阅Weka文档：

http://weka.wikispaces.com/Creating+an+ARFF+file

其中详细介绍了如何使用适当的类型信息创建属性。

另请参阅： 在weka Java API中创建字符串属性