Examples of GaussianClusterDistribution

org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution
An implementation of the ModelDistribution interface suitable for testing the DirichletCluster algorithm. Uses a Normal Distribution to sample the prior model values. Model values have a vector standard deviation, allowing assymetrical regions to be covered by a model.

Examples of org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution

    generateSamples(40, 1, 1, 3);
    generateSamples(30, 1, 0, 0.1);
    generateSamples(30, 0, 1, 0.1);


    DirichletClusterer dc = new DirichletClusterer(sampleData,
                                                   new GaussianClusterDistribution(new VectorWritable(new DenseVector(2))),
                                                   1.0,
                                                   10,
                                                   1,
                                                   0);
    List<Cluster[]> result = dc.cluster(30);

View Full Code Here

Examples of org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution

  /** Test the basic Mapper */
  @Test
  public void testMapper() throws Exception {
    generateSamples(10, 0, 0, 1);
    DirichletState state =
        new DirichletState(new GaussianClusterDistribution(new VectorWritable(new DenseVector(2))), 5, 1);
    DirichletMapper mapper = new DirichletMapper();
    mapper.setup(state);


    RecordWriter<Text, VectorWritable> writer = new DummyRecordWriter<Text, VectorWritable>();
    Mapper<WritableComparable<?>,VectorWritable,Text,VectorWritable>.Context context =

View Full Code Here

Examples of org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution

    generateSamples(100, 0, 0, 1);
    generateSamples(100, 2, 0, 1);
    generateSamples(100, 0, 2, 1);
    generateSamples(100, 2, 2, 1);
    DirichletState state =
        new DirichletState(new GaussianClusterDistribution(new VectorWritable(new DenseVector(2))), 20, 1);
    DirichletMapper mapper = new DirichletMapper();
    mapper.setup(state);


    DummyRecordWriter<Text, VectorWritable> mapWriter = new DummyRecordWriter<Text, VectorWritable>();
    Mapper<WritableComparable<?>,VectorWritable,Text,VectorWritable>.Context mapContext =

View Full Code Here

Examples of org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution

    generateSamples(100, 0, 0, 1);
    generateSamples(100, 2, 0, 1);
    generateSamples(100, 0, 2, 1);
    generateSamples(100, 2, 2, 1);
    DirichletState state =
        new DirichletState(new GaussianClusterDistribution(new VectorWritable(new DenseVector(2))), 20, 1.0);


    Collection<Model<VectorWritable>[]> models = new ArrayList<Model<VectorWritable>[]>();


    for (int iteration = 0; iteration < 10; iteration++) {
      DirichletMapper mapper = new DirichletMapper();

View Full Code Here

Examples of org.apache.mahout.clustering.dirichlet.models.GaussianClusterDistribution

        true, 0, true);
  }
  
  public static void main(String[] args) throws Exception {
    VectorWritable modelPrototype = new VectorWritable(new DenseVector(2));
    ModelDistribution<VectorWritable> modelDist = new GaussianClusterDistribution(modelPrototype);
    Configuration conf = new Configuration();
    Path output = new Path("output");
    HadoopUtil.delete(conf, output);
    Path samples = new Path("samples");
    HadoopUtil.delete(conf, samples);

View Full Code Here

0 1 2

TOP

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.