类在KmeanClustering中找不到异常--Mahout

Question

嗨，我正在尝试运行来自Github的SimpleKmeanClustering代码，看看集群是如何工作的，我可以在我的windows Eclipse上编译这些代码。

我对我的项目做了一个jar，我想在一个单节点Hadoop集群(CHD-4.2.1)上运行它，并在上面安装mahout。mahout示例在该集群上运行良好，因此没有安装方面的问题。

我使用command Promt中的以下命令来运行我的jar，我不确定我的尝试是否正确。

User@INFPH01463U:~$mahout jar/home/user/apurv/kmean.jar tryout.SimplekMeansClustering

我得到了相应的错误

下面是我正在使用的代码：

代码

package tryout;

import java.io.File;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;
import org.apache.mahout.clustering.kmeans.Kluster;
import org.apache.mahout.clustering.classify.WeightedVectorWritable;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.common.distance.EuclideanDistanceMeasure;

public class SimpleKMeansClustering {
    public static final double[][] points = { {1, 1}, {2, 1}, {1, 2}, 
                                              {2, 2}, {3, 3}, {8, 8},
                                              {9, 8}, {8, 9}, {9, 9}};    


    public static void writePointsToFile(List<Vector> points,
            String fileName,FileSystem fs,Configuration conf) throws IOException {    
        Path path = new Path(fileName);    
        @SuppressWarnings("deprecation")
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,path, LongWritable.class, VectorWritable.class);    

        long recNum = 0;    
        VectorWritable vec = new VectorWritable();    
        for (Vector point : points) {       
         vec.set(point);      
          writer.append(new LongWritable(recNum++), vec);    
        }    writer.close();  
    }    

    public static List<Vector> getPoints(double[][] raw) {    
        List<Vector> points = new ArrayList<Vector>();    
        for (int i = 0; i < raw.length; i++) {      
            double[] fr = raw[i];      
            Vector vec = new RandomAccessSparseVector(fr.length);      
            vec.assign(fr);      
            points.add(vec);    
        }    
        return points;  
    }    
    public static void main(String args[]) throws Exception {        
        int k = 2;        
        List<Vector> vectors = getPoints(points);        
        File testData = new File("testdata");    
        if (!testData.exists()) {      
            testData.mkdir();    
        }    
        testData = new File("testdata/points");    
        if (!testData.exists()) {      
            testData.mkdir();    
        }        
        Configuration conf = new Configuration();    
        FileSystem fs = FileSystem.get(conf);    
        writePointsToFile(vectors, "testdata/points/file1", fs, conf);        
        Path path = new Path("testdata/clusters/part-00000");    
        @SuppressWarnings("deprecation")
        SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,path, Text.class, Kluster.class);
        for (int i = 0; i < k; i++) {      
            Vector vec = vectors.get(i);      
            Kluster cluster = new Kluster(vec, i, new EuclideanDistanceMeasure());      
            writer.append(new Text(cluster.getIdentifier()), cluster);    
        }    
        writer.close();        

        KMeansDriver.run(conf, new Path("testdata/points"), new Path("testdata/clusters"),      
                new Path("output"), new EuclideanDistanceMeasure(), 0.001, 10,
                true,0.0, false);        
        @SuppressWarnings("deprecation")
        SequenceFile.Reader reader = new SequenceFile.Reader(fs,new Path("output/" + Kluster.CLUSTERED_POINTS_DIR+ "/part-m-00000"), conf);        
        IntWritable key = new IntWritable();   
        WeightedVectorWritable value = new WeightedVectorWritable();    
        while (reader.next(key, value)) {      
            System.out.println(value.toString() + " belongs to cluster " + key.toString());    
        }    
        reader.close();  
    }
}

有没有人能为我指点一下...

Answer 1

我认为该命令应该读mahout kmeans，而不是mahout jar。

https://cwiki.apache.org/mahout/k-means-clustering.html