mahout1.0 入门笔记1

一个运行在伪分布式上的聚类例子

CSDN终于支持用markdown了，但是还是不支持直接从剪贴版粘贴图片。我决定把自己写的一些笔记搬出来和大家共享。

找到mahout1.0的api文档了：
https://builds.apache.org/job/Mahout-Quality/javadoc/

这样就修复了之前的找不到CLUSTERED_POINTS_DIRECTORY的问题。
在mahout新的版本中将它放在PathDirectory.CLUSTERED_POINTS_DIRECTORY中，同时要导入包：import org.apache.mahout.clustering.topdown.PathDirectory;
在mahout0.7的版本中，Kmeans算法可以通过kmeansClusterer 或KMeansDriver类来运行，但是我在1.0的版本中怎么也找不到前者,

另外，它的参数也发生了改变：
http://blog.csdn.net/fansy1990/article/details/9671977
对比可以看见，没有了measure的参数。

anyway，下面我还是在内存中生成一组数，然后将它们保存在分布式文件系统中，再从中读取进行聚类工作。

package myKmeans;
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.Cluster;
import org.apache.mahout.clustering.topdown.PathDirectory;
import org.apache.mahout.clustering.classify.WeightedPropertyVectorWritable;
import org.apache.mahout.clustering.kmeans.KMeansDriver;
import org.apache.mahout.clustering.kmeans.Kluster;
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;

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

public class KmeansMR{

    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 = 2;

        List<Vector> vectors = getPoints(points);

        File testData = new File("clustering/testdata");
        if (!testData.exists()) {
            testData.mkdir();
        }
        testData = new File("clustering/testdata/points");
        if (!testData.exists()) {
            testData.mkdir();
        }
        //注意把配置文件放在java文件夹下可以省很多工作
        Configuration conf=new Configuration();  
         Path input=new Path("clustering/testdata/points");  
        Path clustersIn=new Path("clustering/testdata/clusters");  
        Path output =new Path("clustering/output");    

        FileSystem fs = FileSystem.get(conf);
        writePointsToFile(vectors, "clustering/testdata/points/file1", fs, conf);
        Path path = new Path("clustering/testdata/clusters/part-00000");


        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,
                input,
                clustersIn  ,
                output,
                0.001,
                10,
                true,
                0,
                true);


        SequenceFile.Reader reader = new SequenceFile.Reader(fs,
                new Path(output+"/" + PathDirectory.CLUSTERED_POINTS_DIRECTORY+ "/part-m-0"), conf);

        IntWritable key = new IntWritable();
        WeightedPropertyVectorWritable value = new WeightedPropertyVectorWritable();
        while (reader.next(key, value)) {
            System.out.println(value.toString() + " belongs to cluster " + key.toString());
        }
        reader.close();
    }

}

如果将配置文件放在Java文件夹下，可以省去很多工作，如果在代码中添加，那么应该写成：

      Path input=new Path("hdfs://localhost:9000/user/clustering/testdata/points");          Path clustersIn=new Path("hdfs://localhost:9000/user/clustering/testdata/clusters");  
 Path output =new Path("hdfs://localhost:9000/user/clustering/output"); 

这个是和map-reduce的location配置对应的，运行结果可见：