Package org.apache.mahout.common.distance

Examples of org.apache.mahout.common.distance.ManhattanDistanceMeasure

150
151
152
153
154
155
156
157
158
159
 
  private void runClustering(Path pointsPath, Configuration conf,
      Boolean runSequential) throws IOException, InterruptedException,
      ClassNotFoundException {
    CanopyDriver.run(conf, pointsPath, clusteringOutputPath,
        new ManhattanDistanceMeasure(), 3.1, 2.1, false, 0.0, runSequential);
    Path finalClustersPath = new Path(clusteringOutputPath, "clusters-0-final");
    ClusterClassifier.writePolicy(new CanopyClusteringPolicy(),
        finalClustersPath);
  }
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
public final class TestClusterClassifier extends MahoutTestCase {
 
  private static ClusterClassifier newDMClassifier() {
    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new DistanceMeasureCluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new DistanceMeasureCluster(new DenseVector(2), 1, measure));
    models.add(new DistanceMeasureCluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }
 
  private static ClusterClassifier newKlusterClassifier() {
    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2), 1, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }

  private static ClusterClassifier newSoftClusterClassifier() {
    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new SoftCluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new SoftCluster(new DenseVector(2), 1, measure));
    models.add(new SoftCluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new FuzzyKMeansClusteringPolicy());
  }
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
    initialize();
    this.setTitle("Spectral k-Means Clusters (>" + (int) (significance * 100) + "% of population)");
  }

  public static void main(String[] args) throws Exception {
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    Path samples = new Path(SAMPLES);
    Path output = new Path(OUTPUT);
    Configuration conf = new Configuration();
    HadoopUtil.delete(conf, samples);
    HadoopUtil.delete(conf, output);

    RandomUtils.useTestSeed();
    DisplayClustering.generateSamples();
    writeSampleData(samples);
    Path affinities = new Path(output, AFFINITIES);
    FileSystem fs = FileSystem.get(output.toUri(), conf);
    if (!fs.exists(output)) {
      fs.mkdirs(output);
    }
    Writer writer = Files.newWriter(new File(affinities.toString()), Charsets.UTF_8);
    try {
      for (int i = 0; i < SAMPLE_DATA.size(); i++) {
        for (int j = 0; j < SAMPLE_DATA.size(); j++) {
          writer.write(i + "," + j + ',' + measure.distance(SAMPLE_DATA.get(i).get(), SAMPLE_DATA.get(j).get()) + '\n');
        }
      }
    } finally {
      Closeables.closeQuietly(writer);
    }
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
    initialize();
    this.setTitle("k-Means Clusters (>" + (int) (significance * 100) + "% of population)");
  }
 
  public static void main(String[] args) throws Exception {
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    Path samples = new Path("samples");
    Path output = new Path("output");
    Configuration conf = new Configuration();
    HadoopUtil.delete(conf, samples);
    HadoopUtil.delete(conf, output);
View Full Code Here
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
      mark.serializeBenchmark();
      mark.deserializeBenchmark();
      mark.distanceMeasureBenchmark(new CosineDistanceMeasure());
      mark.distanceMeasureBenchmark(new SquaredEuclideanDistanceMeasure());
      mark.distanceMeasureBenchmark(new EuclideanDistanceMeasure());
      mark.distanceMeasureBenchmark(new ManhattanDistanceMeasure());
      mark.distanceMeasureBenchmark(new TanimotoDistanceMeasure());
     
      mark.closestCentroidBenchmark(new CosineDistanceMeasure());
      mark.closestCentroidBenchmark(new SquaredEuclideanDistanceMeasure());
      mark.closestCentroidBenchmark(new EuclideanDistanceMeasure());
      mark.closestCentroidBenchmark(new ManhattanDistanceMeasure());
      mark.closestCentroidBenchmark(new TanimotoDistanceMeasure());
     
      log.info("\n{}", mark);
    } catch (OptionException e) {
      CommandLineUtil.printHelp(group);
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
    job.setMapOutputValueClass(VectorWritable.class);
    Path input = getTestTempFilePath("eigen-input");
    Path output = getTestTempDirPath("eigen-output");
    ClusteringTestUtils.writePointsToFile(points, input, fs, conf);

    EigenSeedGenerator.buildFromEigens(conf, input, output, 3, new ManhattanDistanceMeasure());

    int clusterCount = 0;
    Collection<Integer> set = new HashSet<Integer>();
    Vector v[] = new Vector[3];
    for (ClusterWritable clusterWritable :
View Full Code Here
306
307
308
309
310
311
312
313
314
315
316
    ClusteringTestUtils.writePointsToFile(points, true, new Path(pointsPath, "file1"), fs, conf);
    ClusteringTestUtils.writePointsToFile(points, true, new Path(pointsPath, "file2"), fs, conf);
   
    Path outputPath = getTestTempDirPath("output");
    // now run the Canopy job
    CanopyDriver.run(conf, pointsPath, outputPath, new ManhattanDistanceMeasure(), 3.1, 2.1, false, 0.0, false);
   
    DummyOutputCollector<Text, ClusterWritable> collector1 =
        new DummyOutputCollector<Text, ClusterWritable>();

    FileStatus[] outParts = FileSystem.get(conf).globStatus(
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
public final class TestClusterClassifier extends MahoutTestCase {
 
  private static ClusterClassifier newDMClassifier() {
    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new DistanceMeasureCluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new DistanceMeasureCluster(new DenseVector(2), 1, measure));
    models.add(new DistanceMeasureCluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }
View Full Code Here
TOP

Related Classes of org.apache.mahout.common.distance.ManhattanDistanceMeasure

  • mia.clustering.ch09.NewsFuzzyKMeansClustering
  • org.apache.mahout.benchmark.VectorBenchmarks
  • org.apache.mahout.clustering.canopy.DisplayCanopy
  • org.apache.mahout.clustering.canopy.TestCanopyCreation
  • org.apache.mahout.clustering.classify.ClusterClassificationDriverTest
  • org.apache.mahout.clustering.dirichlet.models.DistanceMeasureClusterDistribution
  • org.apache.mahout.clustering.display.DisplayCanopy
  • org.apache.mahout.clustering.display.DisplayFuzzyKMeans
  • org.apache.mahout.clustering.display.DisplayKMeans
  • org.apache.mahout.clustering.display.DisplaySpectralKMeans
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.