java调用weka，读取csv及arff文件，将csv转化为arff文件

最新推荐文章于 2021-02-23 20:42:14 发布

xuanhan3

最新推荐文章于 2021-02-23 20:42:14 发布

阅读量1.8k

点赞数

CC 4.0 BY-SA版权

文章标签： java weka

本文链接：https://blog.youkuaiyun.com/xuanhan3/article/details/78555509

本文介绍使用Weka库中的多种分类器进行数据分类的过程。包括从CSV文件读取数据、转换为ARFF格式、设置分类目标变量，并以随机森林为例展示如何进行交叉验证及输出混淆矩阵。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

package classifier;

import weka.classifiers.trees.J48;
import weka.classifiers.trees.RandomForest;
import weka.classifiers.lazy.IBk;
import weka.classifiers.bayes.*;
import weka.core.Instances;
import weka.classifiers.Evaluation;
import weka.core.converters.ConverterUtils.DataSource;
import weka.core.converters.ArffSaver;

import java.util.Random;
import java.io.File;

public class Classifiers {

    public static void main(String[] args) throws Exception
    {
        // read data from *.csv
        Instances allData = DataSource.read("**.csv");

        ArffSaver saver = new ArffSaver();
        // Sets instances that should be stored.
        saver.setInstances(allData);
        // Sets the destination file.
        saver.setFile(new File("**.arff"));
        // Sets the destination output stream.
        // saver.setDestination(new File("**.arff"));
        // Writes a Batch of instances
        saver.writeBatch();


        Instances allData_arff = DataSource.read("**.arff");

        /*
        set class index of for your dataset before passing              
        it into classifier. Your classifier must know which 
        is your outcome variable. 
        */      
        allData_arff.setClassIndex(allData_arff.numAttributes() - 1);

        RandomForest clsRF = new RandomForest();
        evaluation.crossValidateModel(clsRF, allData_arff, 10, new Random(1234));
        System.out.println("随机森林");
        // Output confusion matrix
        System.out.println(evaluation.toMatrixString());
    }


}