Question

我有一个从weka分类器获得的模型，我想在java代码中测试它，但是当我读取实例时，会出现错误：

Exception in thread "main" java.io.IOException: keyword @relation expected, read Token[Word], line 1
at weka.core.Instances.errms(Instances.java:1863)
at weka.core.Instances.readHeader(Instances.java:1740)
at weka.core.Instances.<init>(Instances.java:119)
at licenta1.LoadModelWeka.main(LoadModelWeka.java:18)

我的代码是：

package licenta1;

import weka.core.Instances;
import weka.classifiers.bayes.NaiveBayes;
import weka.classifiers.trees.J48;
import weka.classifiers.Evaluation;

import java.util.Random;
import java.io.BufferedReader;
import java.io.FileReader ;

public class LoadModelWeka
{
   public static void main(String[] args) throws Exception {
   // training
      BufferedReader reader = null;
      reader=new BufferedReader(new FileReader("D:\\aaaaaaaaaaaaaaaaaaaaaa\\Licenta\\BioArtLicTrainSetTask1.csv"));
      Instances train =new Instances (reader);
      train.setClassIndex(0);     
      reader.close();

      NaiveBayes nb = new NaiveBayes();
      nb.buildClassifier(train);
      Evaluation eval = new Evaluation(train);
      eval.crossValidateModel(nb, train, 10 , new Random(1));

      System.out.println(eval.toSummaryString("\n Results \n=====\n",true));
      System.out.println(eval.fMeasure(1)+" "+eval.precision(1)+" "+eval.recall(1)+" ");           
   }   
}

有人能帮助我吗？ Mt训练集采用.csv格式

Answer 1

您可以尝试

，而不是使用Buffered Reader

DataSource source = new DataSource("/some/where/data.arff");

有关详细信息，请访问此链接http://weka.wikispaces.com/Use+WEKA+in+your+Java+code

Answer 2

此代码段可用于直接加载csv内容并将其转换为实例。通常.arff用于weka操作，并且此加载程序直接将csv文件在内部转换为arff，然后转换为Instances类。

 CSVLoader loader = new CSVLoader();
 loader.setSource(new File("filename.csv"));
 Instances trainingDataSet = loader.getDataSet();

如何在java代码中加载.csv文件以使用weka进行测试？

2 个答案: