Package org.apache.mahout.clustering.canopy

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

218
219
220
221
222
223
224
225
226
227
228
229
230
  @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 = new ArrayList<VectorWritable>();
    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
232
233
234
235
236
237
238
239
240
241
242
243
244
245
  @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 = new ArrayList<VectorWritable>();
    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
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
  @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 = new ArrayList<VectorWritable>();
    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
122
123
124
125
126
127
128
129
130
131
132
133
134
135
   * @param dP a double representative point offset
   * @param measure the DistanceMeasure
   */
  private void initData(double dC, double dP, DistanceMeasure measure) {
    clusters = new ArrayList<Cluster>();
    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 = new HashMap<Integer, List<VectorWritable>>();
    for (Cluster cluster : clusters) {
      List<VectorWritable> points = new ArrayList<VectorWritable>();
      representativePoints.put(cluster.getId(), points);
      points.add(new VectorWritable(cluster.getCenter().clone()));
View Full Code Here
206
207
208
209
210
211
212
213
214
215
216
217
218
219
  @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 = new ArrayList<VectorWritable>();
    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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
  @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 = new ArrayList<VectorWritable>();
    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
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
  @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 = new ArrayList<VectorWritable>();
    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
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
  @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 = new ArrayList<VectorWritable>();
    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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
              // get the cluster info
              clusters.add(value);
              value = new SoftCluster();
            }
          } else if (valueClass.equals(Canopy.class)) {
            Canopy value = new Canopy();
            while (reader.next(key, value)) {
              // get the cluster info
              SoftCluster theCluster = new SoftCluster(value.getCenter(), value.getId(), value.getMeasure());
              clusters.add(theCluster);
              value = new Canopy();
            }
          }
        } finally {
          reader.close();
        }
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
      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
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.