Package org.apache.mahout.common.distance

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

88
89
90
91
92
93
94
95
96
97
    double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
    double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
    double convergenceDelta = Double.parseDouble(getOption(DefaultOptionCreator.CONVERGENCE_DELTA_OPTION));
    int maxIterations = Integer.parseInt(getOption(DefaultOptionCreator.MAX_ITERATIONS_OPTION));
    ClassLoader ccl = Thread.currentThread().getContextClassLoader();
    DistanceMeasure measure = ccl.loadClass(measureClass).asSubclass(DistanceMeasure.class).newInstance();

    run(getConf(), input, output, measure, t1, t2, convergenceDelta, maxIterations);
    return 0;
  }
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
        .create());
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
      HadoopUtil.overwriteOutput(output);
    }
    ClassLoader ccl = Thread.currentThread().getContextClassLoader();
    DistanceMeasure measure = ccl.loadClass(measureClass).asSubclass(DistanceMeasure.class).newInstance();
    double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
    double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
    run(getConf(), input, output, measure, t1, t2, maxIterations, fuzziness, convergenceDelta);
    return 0;
  }
View Full Code Here
37
38
39
40
41
42
43
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
    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");
    HadoopUtil.overwriteOutput(samples);
    HadoopUtil.overwriteOutput(output);

    RandomUtils.useTestSeed();
    DisplayClustering.generateSamples();
    writeSampleData(samples);
    int maxIter = 10;
    double convergenceDelta = 0.001;
    Path affinities = new Path(output, "affinities");
    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(output.toUri(), conf);
    if (!fs.exists(output)) {
      fs.mkdirs(output);
    }
    FileWriter writer = new FileWriter(affinities.toString());
    PrintWriter out = new PrintWriter(writer);
    try {
      for (int i = 0; i < SAMPLE_DATA.size(); i++) {
        for (int j = 0; j < SAMPLE_DATA.size(); j++) {
          out.println(i + "," + j + "," + measure.distance(SAMPLE_DATA.get(i).get(), SAMPLE_DATA.get(j).get()));
        }
      }
    } finally {
      out.close();
    }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
    int maxIterations = Integer.parseInt(getOption(DefaultOptionCreator.MAX_ITERATIONS_OPTION));
    if (hasOption(DefaultOptionCreator.OVERWRITE_OPTION)) {
      HadoopUtil.overwriteOutput(output);
    }
    ClassLoader ccl = Thread.currentThread().getContextClassLoader();
    DistanceMeasure measure = ccl.loadClass(measureClass).asSubclass(DistanceMeasure.class).newInstance();

    if (hasOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION)) {
      clusters = RandomSeedGenerator.buildRandom(input, clusters, Integer
          .parseInt(getOption(DefaultOptionCreator.NUM_CLUSTERS_OPTION)), measure);
    }
View Full Code Here
84
85
86
87
88
89
90
91
92
93
    double t1 = Double.parseDouble(getOption(DefaultOptionCreator.T1_OPTION));
    double t2 = Double.parseDouble(getOption(DefaultOptionCreator.T2_OPTION));
    boolean runClustering = hasOption(DefaultOptionCreator.CLUSTERING_OPTION);
    boolean runSequential = (getOption(DefaultOptionCreator.METHOD_OPTION).equalsIgnoreCase(DefaultOptionCreator.SEQUENTIAL_METHOD));
    ClassLoader ccl = Thread.currentThread().getContextClassLoader();
    DistanceMeasure measure = ccl.loadClass(measureClass).asSubclass(DistanceMeasure.class).newInstance();

    run(getConf(), input, output, measure, t1, t2, runClustering, runSequential);
    return 0;
  }
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
58
  protected void setup(Context context) throws IOException, InterruptedException {
    super.setup(context);
    Configuration conf = context.getConfiguration();
    try {
      ClassLoader ccl = Thread.currentThread().getContextClassLoader();
      DistanceMeasure measure = ccl.loadClass(conf.get(KMeansConfigKeys.DISTANCE_MEASURE_KEY))
          .asSubclass(DistanceMeasure.class).newInstance();
      measure.configure(conf);

      this.clusterer = new KMeansClusterer(measure);

      String clusterPath = conf.get(KMeansConfigKeys.CLUSTER_PATH_KEY);
      if ((clusterPath != null) && (clusterPath.length() > 0)) {
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
56
  protected void setup(Context context) throws IOException, InterruptedException {
    super.setup(context);
    Configuration conf = context.getConfiguration();
    try {
      ClassLoader ccl = Thread.currentThread().getContextClassLoader();
      DistanceMeasure measure = ccl.loadClass(conf.get(KMeansConfigKeys.DISTANCE_MEASURE_KEY))
          .asSubclass(DistanceMeasure.class).newInstance();
      measure.configure(conf);
     
      String clusterPath = conf.get(KMeansConfigKeys.CLUSTER_PATH_KEY);
      if ((clusterPath != null) && (clusterPath.length() > 0)) {
        KMeansUtil.configureWithClusterInfo(new Path(clusterPath), clusters);
        if (clusters.isEmpty()) {
View Full Code Here
93
94
95
96
97
98
99
100
101
102
103
  /** Story: Test the reference implementation */
  @Test
  public void testReferenceImplementation() throws Exception {
    List<Vector> points = getPoints(REFERENCE);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    // try all possible values of k
    for (int k = 0; k < points.size(); k++) {
      System.out.println("Test k=" + (k + 1) + ':');
      // pick k initial cluster centers at random
      List<Cluster> clusters = new ArrayList<Cluster>();
View Full Code Here
323
324
325
326
327
328
329
330
331
332
333
  }

  /** Story: User wishes to run kmeans job on reference data */
  @Test
  public void testKMeansSeqJob() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    List<VectorWritable> points = getPointsWritable(REFERENCE);

    Path pointsPath = getTestTempDirPath("points");
    Path clustersPath = getTestTempDirPath("clusters");
    Configuration conf = new Configuration();
View Full Code Here
380
381
382
383
384
385
386
387
388
389
390
  }

  /** Story: User wishes to run kmeans job on reference data */
  @Test
  public void testKMeansMRJob() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    List<VectorWritable> points = getPointsWritable(REFERENCE);

    Path pointsPath = getTestTempDirPath("points");
    Path clustersPath = getTestTempDirPath("clusters");
    Configuration conf = new Configuration();
View Full Code Here
TOP

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

  • mia.clustering.ch10.InterClusterDistances
  • org.apache.mahout.clustering.canopy.CanopyConfigKeys
  • org.apache.mahout.clustering.canopy.CanopyDriver
  • org.apache.mahout.clustering.cdbw.TestCDbwEvaluator
  • org.apache.mahout.clustering.classify.ClusterClassificationDriver
  • org.apache.mahout.clustering.classify.ClusterClassificationMapper
  • org.apache.mahout.clustering.ClusteringUtils
  • org.apache.mahout.clustering.dirichlet.DirichletDriver
  • org.apache.mahout.clustering.dirichlet.models.DistributionDescription
  • org.apache.mahout.clustering.display.DisplayFuzzyKMeans
    • 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.