Question

我在Weka框架中很新。到目前为止，我发现它非常简单易用，易于理解，但我遇到了一些我无法理解的问题。我正在尝试从csv文件中聚类数据集。我有一个使用kmeans聚类数据集的类，就我在Weka的wiki（http://weka.wikispaces.com/）中读到的那样，该类工作正常。唯一的问题是它正在读取一个arff文件，我需要从csv文件中读取。到现在为止还挺好。问题是当我将数据集中的实例分配给kmeans.buildClusterer（data）方法时。然后我得到以下例外：

Exception in thread "main" java.lang.NoClassDefFoundError: org/pentaho/packageManagement/PackageManager 
        at weka.core.WekaPackageManager.<clinit>(WekaPackageManager.java:86) 
        at weka.core.Utils.readProperties(Utils.java:142) 
        at weka.core.Capabilities.<init>(Capabilities.java:261) 
        at weka.clusterers.AbstractClusterer.getCapabilities(AbstractClusterer.java:179) 
        at weka.clusterers.SimpleKMeans.getCapabilities(SimpleKMeans.java:289) 
        at weka.clusterers.SimpleKMeans.buildClusterer(SimpleKMeans.java:441) 
        at weka_examples.ClusteringDemo.<init>(ClusteringDemo.java:48) 
        at weka_examples.ClusteringDemo.main(ClusteringDemo.java:70) 
Caused by: java.lang.ClassNotFoundException: org.pentaho.packageManagement.PackageManager 
        at java.net.URLClassLoader$1.run(URLClassLoader.java:366) 
        at java.net.URLClassLoader$1.run(URLClassLoader.java:355) 
        at java.security.AccessController.doPrivileged(Native Method) 
        at java.net.URLClassLoader.findClass(URLClassLoader.java:354) 
        at java.lang.ClassLoader.loadClass(ClassLoader.java:425) 
        at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308) 
        at java.lang.ClassLoader.loadClass(ClassLoader.java:358) 
        ... 8 more 
Java Result: 1

代码如下：

import weka.core.Instances; 
import weka.clusterers.DensityBasedClusterer; 
import weka.clusterers.ClusterEvaluation; 
import java.io.File; 
import weka.clusterers.SimpleKMeans; 
import weka.core.converters.CSVLoader; 

/** 
 * An example class that shows the use of Weka clusterers from Java. 
 * 
 * @author FracPete 
 */ 
public class ClusteringDemo { 

    /** 
     * Run clusterers 
     * 
     * @param filename the name of the ARFF file to run on 
     */ 
    public ClusteringDemo(String filename) throws Exception { 
        ClusterEvaluation eval; 
        Instances data; 
        String[] options; 
        DensityBasedClusterer cl; 

        String Origem = filename; 

   // data = new Instances(new BufferedReader(new FileReader(filename))); 
        // load CSV 
        CSVLoader loader = new CSVLoader(); 
        loader.setSource(new File(Origem)); 
        data = loader.getDataSet(); 

        SimpleKMeans kmeans = new SimpleKMeans(); 

        kmeans.setSeed(10); 

// This is the important parameter to set 
        kmeans.setPreserveInstancesOrder(true); 
        kmeans.setNumClusters(5); 
        kmeans.buildClusterer(data); 

// This array returns the cluster number (starting with 0) for each instance 
// The array has as many elements as the number of instances 
        int[] assignments = kmeans.getAssignments(); 

        int i = 0; 
        for (int clusterNum : assignments) { 
            System.out.printf("Instance %d -> Cluster %d", i, clusterNum); 
            i++; 
        } 
    } 

    /** 
     * usage: ClusteringDemo arff-file 
     */ 
    public static void main(String[] args) throws Exception { 

        /*if (args.length != 1) { 
         System.out.println("usage: " + ClusteringDemo.class.getName() + " <arff-file>"); 
         System.exit(1); 
         }*/ 
        new ClusteringDemo("Teste/Query1.csv"); 
    } 
}

我包含了二进制文件：weka-dev-3.7.10 我错过了重要的事情吗？

亲切的问候

Answer 1

我终于设法回答了这个问题。事实证明，从版本3.7.2开始，weka核心更紧凑，这意味着我需要的一些软件包不存在于weka-dev中。解决方案很简单：将类路径添加到weka.jar而不是weka-dev包。或者，也可以安装缺少的包http://weka.wikispaces.com/How+do+I+use+the+package+manager%3F

祝你好运

WEKA - 将实例分配给kmeans.buildClusterer时出错

1 个答案: