Package org.apache.mahout.common.distance

Examples of org.apache.mahout.common.distance.DistanceMeasure

284
285
286
287
288
289
290
291
292
293
294
  }

  @Test
  public void testKmeans() throws Exception {
    ClusteringTestUtils.writePointsToFile(sampleData, new Path(testdata, "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    // now run the Canopy job to prime kMeans canopies
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, testdata, output, measure, 3.1, 1.1, false, true);
    // now run the KMeans job
    KMeansDriver.run(testdata, new Path(output, "clusters-0"), output, measure, 0.001, 10, true, true);
View Full Code Here
303
304
305
306
307
308
309
310
311
312
313
  }

  @Test
  public void testFuzzyKmeans() throws Exception {
    ClusteringTestUtils.writePointsToFile(sampleData, new Path(testdata, "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    // now run the Canopy job to prime kMeans canopies
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, testdata, output, measure, 3.1, 1.1, false, true);
    // now run the KMeans job
    FuzzyKMeansDriver.run(testdata, new Path(output, "clusters-0"), output, measure, 0.001, 10, 2, true, true, 0, true);
View Full Code Here
168
169
170
171
172
173
174
175
176
177
178
  }

  @Test
  public void testCDbw0() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("testdata/file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.25, measure);
    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);
View Full Code Here
322
323
324
325
326
327
328
329
330
331
332
  }

  @Test
  public void testMeanShift() throws Exception {
    ClusteringTestUtils.writePointsToFile(sampleData, new Path(testdata, "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    Configuration conf = new Configuration();
    new MeanShiftCanopyDriver().run(conf, testdata, output, measure, 2.1, 1.0, 0.001, 10, false, true, true);
    int numIterations = 10;
    Path clustersIn = new Path(output, "clusters-10");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure, numIterations, true);
View Full Code Here
180
181
182
183
184
185
186
187
188
189
190
  }

  @Test
  public void testCDbw1() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("testdata/file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.5, measure);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 1.2, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 6.207661022496537, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.4, evaluator.intraClusterDensity(), EPSILON);
View Full Code Here
192
193
194
195
196
197
198
199
200
201
202
  }

  @Test
  public void testCDbw2() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, getTestTempFilePath("testdata/file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.75, measure);
    CDbwEvaluator evaluator = new CDbwEvaluator(representativePoints, clusters, measure);
    assertEquals("inter cluster density", 0.682842712474619, evaluator.interClusterDensity(), EPSILON);
    assertEquals("separation", 4.0576740025245694, evaluator.separation(), EPSILON);
    assertEquals("intra cluster density", 0.26666666666666666, evaluator.intraClusterDensity(), EPSILON);
View Full Code Here
204
205
206
207
208
209
210
211
212
213
214
  }

  @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);
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
  }

  @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 }))));
View Full Code Here
242
243
244
245
246
247
248
249
250
251
252
   * @throws IOException
   */
  @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()));
View Full Code Here
266
267
268
269
270
271
272
273
274
275
276
   * @throws IOException
   */
  @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 });
View Full Code Here
TOP

Related Classes of org.apache.mahout.common.distance.DistanceMeasure

  • mia.clustering.ch10.InterClusterDistances
  • org.apache.mahout.clustering.canopy.CanopyConfigKeys
  • org.apache.mahout.clustering.canopy.CanopyDriver
  • org.apache.mahout.clustering.cdbw.TestCDbwEvaluator
  • org.apache.mahout.clustering.classify.ClusterClassificationDriver
  • org.apache.mahout.clustering.classify.ClusterClassificationMapper
  • org.apache.mahout.clustering.ClusteringUtils
  • org.apache.mahout.clustering.dirichlet.DirichletDriver
  • org.apache.mahout.clustering.dirichlet.models.DistributionDescription
  • org.apache.mahout.clustering.display.DisplayFuzzyKMeans
    • 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.