Examples of org.apache.mahout.clustering.canopy.Canopy

Package org.apache.mahout.clustering.canopy

Examples of org.apache.mahout.clustering.canopy.Canopy

org.apache.mahout.clustering.canopy.Canopy
This class models a canopy as a center point, the number of points that are contained within it according to the application of some distance metric, and a point total which is the sum of all the points and is used to compute the centroid when needed.

      } else if (valueClass.equals(SoftCluster.class)) {
        // get the cluster info
        clusters.add((SoftCluster) value);
      } else if (valueClass.equals(Canopy.class)) {
        // get the cluster info
        Canopy canopy = (Canopy) value;
        clusters.add(new SoftCluster(canopy.getCenter(), canopy.getId(), canopy.getMeasure()));
      } else {
        throw new IllegalStateException("Bad value class: " + valueClass);
      }
    }

View Full Code Here


  @Test
  public void testCanopyAsFormatString() {
    double[] d = { 1.1, 2.2, 3.3 };
    Vector m = new DenseVector(d);
    Cluster cluster = new Canopy(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("C-123{n=0 c=[1.100, 2.200, 3.300] r=[]}", formatString);
  }

View Full Code Here

  @Test
  public void testCanopyAsFormatStringSparse() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new Canopy(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("C-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here


  @Test
  public void testCanopyAsFormatStringWithBindings() {
    double[] d = { 1.1, 2.2, 3.3 };
    Vector m = new DenseVector(d);
    Cluster cluster = new Canopy(m, 123, measure);
    String[] bindings = { "fee", null, null };
    String formatString = cluster.asFormatString(bindings);
    assertEquals("C-123{n=0 c=[fee:1.100, 1:2.200, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  @Test
  public void testCanopyAsFormatStringSparseWithBindings() {
    double[] d = { 1.1, 0.0, 3.3 };
    Vector m = new SequentialAccessSparseVector(3);
    m.assign(d);
    Cluster cluster = new Canopy(m, 123, measure);
    String formatString = cluster.asFormatString(null);
    assertEquals("C-123{n=0 c=[0:1.100, 2:3.300] r=[]}", formatString);
  }

View Full Code Here

  
  @Test
  public void testCanopyClassification() {
    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    models.add(new Canopy(new DenseVector(2).assign(1), 0, measure));
    models.add(new Canopy(new DenseVector(2), 1, measure));
    models.add(new Canopy(new DenseVector(2).assign(-1), 2, measure));
    ClusterClassifier classifier = new ClusterClassifier(models);
    Vector pdf = classifier.classify(new DenseVector(2));
    assertEquals("[0,0]", "[0.200, 0.600, 0.200]",
        AbstractCluster.formatVector(pdf, null));
    pdf = classifier.classify(new DenseVector(2).assign(2));

View Full Code Here

              // get the cluster info
              clusters.add(value);
              value = new Cluster();
            }
          } else if (valueClass.equals(Canopy.class)) {
            Canopy value = new Canopy();
            while (reader.next(key, value)) {
              // get the cluster info
              Cluster cluster = new Cluster(value.getCenter(), value.getId(), value.getMeasure());
              clusters.add(cluster);
              value = new Canopy();
            }
          }
        } finally {
          IOUtils.quietClose(reader);
        }

View Full Code Here

   * @param measure
   *          the DistanceMeasure
   */
  private void initData(double dC, double dP, DistanceMeasure measure) {
    clusters = Lists.newArrayList();
    clusters.add(new Canopy(new DenseVector(new double[] {-dC, -dC}), 1,
        measure));
    clusters
        .add(new Canopy(new DenseVector(new double[] {-dC, dC}), 3, measure));
    clusters
        .add(new Canopy(new DenseVector(new double[] {dC, dC}), 5, measure));
    clusters
        .add(new Canopy(new DenseVector(new double[] {dC, -dC}), 7, measure));
    representativePoints = Maps.newHashMap();
    for (Cluster cluster : clusters) {
      List<VectorWritable> points = Lists.newArrayList();
      representativePoints.put(cluster.getId(), points);
      points.add(new VectorWritable(cluster.getCenter().clone()));

View Full Code Here

  public void testEmptyCluster() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, new Path(testdata,
        "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.25, measure);
    Canopy cluster = new Canopy(new DenseVector(new double[] {10, 10}), 19,
        measure);
    clusters.add(cluster);
    List<VectorWritable> points = Lists.newArrayList();
    representativePoints.put(cluster.getId(), points);
    ClusterEvaluator evaluator = new ClusterEvaluator(representativePoints,
        clusters, measure);
    assertEquals("inter cluster density", 0.33333333333333315,
        evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381,

View Full Code Here

  public void testSingleValueCluster() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, new Path(testdata,
        "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.25, measure);
    Canopy cluster = new Canopy(new DenseVector(new double[] {0, 0}), 19,
        measure);
    clusters.add(cluster);
    List<VectorWritable> points = Lists.newArrayList();
    points.add(new VectorWritable(cluster.getCenter().plus(
        new DenseVector(new double[] {1, 1}))));
    representativePoints.put(cluster.getId(), points);
    ClusterEvaluator evaluator = new ClusterEvaluator(representativePoints,
        clusters, measure);
    assertEquals("inter cluster density", 0.33333333333333315,
        evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381,

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.mahout.clustering.canopy.Canopy

org.apache.hadoop.io.Text

org.apache.mahout.clustering.cdbw.TestCDbwEvaluator

org.apache.mahout.clustering.fuzzykmeans.DisplayFuzzyKMeans

org.apache.mahout.clustering.fuzzykmeans.FuzzyKMeansUtil

org.apache.mahout.clustering.iterator.TestClusterClassifier

org.apache.mahout.clustering.kmeans.DisplayKMeans

org.apache.mahout.clustering.kmeans.KMeansUtil

org.apache.mahout.clustering.syntheticcontrol.canopy.OutputMapper

org.apache.mahout.clustering.TestClusterClassifier

org.apache.mahout.clustering.TestClusterEvaluator

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.