Package org.apache.mahout.clustering.canopy

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

128
129
130
131
132
133
134
135
136
137
138
139
140
141
   * @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
204
205
206
207
208
209
210
211
212
213
214
215
216
  @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", 0.33333333333333315, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
218
219
220
221
222
223
224
225
226
227
228
229
230
231
  @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", 0.33333333333333315, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
  @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", 0.33333333333333315, evaluator.interClusterDensity(), EPSILON);
    assertEquals("intra cluster density", 0.3656854249492381, evaluator.intraClusterDensity(), EPSILON);
  }
View Full Code Here
108
109
110
111
112
113
114
115
116
117
118
119
120
 
  @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, new CanopyClusteringPolicy());
    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));
    assertEquals("[2,2]", "[0.493, 0.296, 0.211]", AbstractCluster.formatVector(pdf, null));
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
   * @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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
  @Test
  public void testEmptyCluster() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("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);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 20.485281374238568, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.8, evaluator.intraClusterDensity(), EPSILON);
    assertEquals("CDbw", 16.388225099390855, evaluator.getCDbw(), EPSILON);
View Full Code Here
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
  @Test
  public void testSingleValueCluster() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("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);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 20.485281374238568, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.8, evaluator.intraClusterDensity(), EPSILON);
    assertEquals("CDbw", 16.388225099390855, evaluator.getCDbw(), EPSILON);
View Full Code Here
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
  @Test
  public void testAllSameValueCluster() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("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);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 20.485281374238568, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.8, evaluator.intraClusterDensity(), EPSILON);
    assertEquals("CDbw", 16.388225099390855, evaluator.getCDbw(), EPSILON);
View Full Code Here
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
  @Test
  public void testAlmostSameValueCluster() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("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();
    Vector delta = new DenseVector(new double[] {0, Double.MIN_NORMAL});
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    points.add(new VectorWritable(delta.clone()));
    representativePoints.put(cluster.getId(), points);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.0, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 28.970562748477143, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 1.8, evaluator.intraClusterDensity(), EPSILON);
    assertEquals("CDbw", 52.147012947258865, evaluator.getCDbw(), EPSILON);
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.