Package org.apache.mahout.clustering.canopy

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

54
55
56
57
58
59
60
61
62
63
  @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
65
66
67
68
69
70
71
72
73
  @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
130
131
132
133
134
135
136
137
138
139
140
141
142
 
  @Test
  public void testCanopyClassification() {
    List<Cluster> models = new ArrayList<Cluster>();
    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]", "[0.107, 0.787, 0.107]",
        AbstractCluster.formatVector(pdf, null));
    pdf = classifier.classify(new DenseVector(2).assign(2));
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
        } 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
61
62
63
64
65
66
67
68
69
70
71
72
        if (valueClass.equals(Cluster.class)) {
          // get the cluster info
          clusters.add((Cluster) value);
        } else if (valueClass.equals(Canopy.class)) {
          // get the cluster info
          Canopy canopy = (Canopy) value;
          clusters.add(new Cluster(canopy.getCenter(), canopy.getId(), canopy.getMeasure()));
        } else {
          throw new IllegalStateException("Bad value class: " + valueClass);
        }
      }
    }
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
133
134
   * @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
203
204
205
206
207
208
209
210
211
212
213
214
215
  @Test
  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", 0.371534146934532, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
223
224
225
226
227
228
229
230
231
232
233
234
235
236
  @Test
  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", 0.3656854249492381, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
  @Test
  public void testAllSameValueCluster() 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()));
    points.add(new VectorWritable(cluster.getCenter()));
    points.add(new VectorWritable(cluster.getCenter()));
    representativePoints.put(cluster.getId(), points);
    ClusterEvaluator evaluator = new ClusterEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.3656854249492381, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
95
96
97
98
99
100
101
102
103
104
105
106
107
108
   * @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
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
    • 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.