org.apache.mahout.math.function.IntDoubleProcedure

原创
2014/01/21 16:56
阅读数 546

学习<mahout in action > SimpleKMeansClustering测试例子的时候,运行报错

环境列表

软件明称 版本

hadoop

0.20.2

mahout

0.4

eclipse

Kepler Service Release 1

报错代码:

ClassNotFoundException: org.apache.mahout.math.function.IntDoubleProcedure

解决办法:

开始的主观认为IntDoubleProcedure在mahout-math-0.4.jar包里,可是经测试确实没有在这个包里面.

后来发现IntDoubleProcedure在mahout-collections-1.0.jar里面,增加mahout-collections-1.0.jar这个包,就不会报出上面的错误了.

文件内容:

package com.mahout.cluster;

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.clustering.WeightedVectorWritable;
import org.apache.mahout.clustering.kmeans.Cluster;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.common.distance.EuclideanDistanceMeasure;
import org.apache.mahout.math.RandomAccessSparseVector;
import org.apache.mahout.math.Vector;
import org.apache.mahout.math.VectorWritable;

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);
    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 = 3;
    
    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");
    SequenceFile.Writer writer = new SequenceFile.Writer(fs, conf,
        path, Text.class, Cluster.class);
    
    for (int i = 0; i < k; i++) {
      Vector vec = vectors.get(i);
      Cluster cluster = new Cluster(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, false);
    
    SequenceFile.Reader reader = new SequenceFile.Reader(fs,
        new Path("output/" + Cluster.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();
  }
  
}




展开阅读全文
打赏
0
1 收藏
分享
加载中
更多评论
打赏
0 评论
1 收藏
0
分享
返回顶部
顶部