Package org.apache.mahout.clustering.evaluation

Examples of org.apache.mahout.clustering.evaluation.ClusterEvaluator

305
306
307
308
309
310
311
312
313
314
    int numIterations = 10;
    Path clustersIn = new Path(fuzzyKMeansOutput, "clusters-4");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(fuzzyKMeansOutput, "clusteredPoints"), fuzzyKMeansOutput,
        measure, numIterations, true);
    RepresentativePointsDriver.printRepresentativePoints(fuzzyKMeansOutput, numIterations);
    ClusterEvaluator evaluator = new ClusterEvaluator(conf, clustersIn);
    // now print out the Results
    System.out.println("Intra-cluster density = " + evaluator.intraClusterDensity());
    System.out.println("Inter-cluster density = " + evaluator.interClusterDensity());
  }
View Full Code Here
323
324
325
326
327
328
329
330
331
332
    int numIterations = 10;
    Path clustersIn = new Path(output, "clusters-7-final");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure,
        numIterations, true);
    printRepPoints(numIterations);
    ClusterEvaluator evaluator = new ClusterEvaluator(conf, clustersIn);
    // now print out the Results
    System.out.println("Intra-cluster density = " + evaluator.intraClusterDensity());
    System.out.println("Inter-cluster density = " + evaluator.interClusterDensity());
  }
View Full Code Here
341
342
343
344
345
346
347
348
349
350
    Configuration conf = new Configuration();
    Path clustersIn = new Path(output, "clusters-5-final");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output,
        new EuclideanDistanceMeasure(), numIterations, true);
    printRepPoints(numIterations);
    ClusterEvaluator evaluator = new ClusterEvaluator(conf, clustersIn);
    // now print out the Results
    System.out.println("Intra-cluster density = " + evaluator.intraClusterDensity());
    System.out.println("Inter-cluster density = " + evaluator.interClusterDensity());
  }
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
208
209
210
                "--distanceMeasure", measure.getClass().getName(),
                "--maxIter", String.valueOf(numIters)//
        });
        conf.set(RepresentativePointsDriver.DISTANCE_MEASURE_KEY, measure.getClass().getName());
        conf.set(RepresentativePointsDriver.STATE_IN_KEY, "tmp/representative/representativePoints-" + numIters);
        ClusterEvaluator ce = new ClusterEvaluator(conf, seqFileDir);
        writer.append("\n");
        writer.append("Inter-Cluster Density: ").append(String.valueOf(ce.interClusterDensity())).append("\n");
        writer.append("Intra-Cluster Density: ").append(String.valueOf(ce.intraClusterDensity())).append("\n");
        CDbwEvaluator cdbw = new CDbwEvaluator(conf, seqFileDir);
        writer.append("CDbw Inter-Cluster Density: ").append(String.valueOf(cdbw.interClusterDensity())).append("\n");
        writer.append("CDbw Intra-Cluster Density: ").append(String.valueOf(cdbw.intraClusterDensity())).append("\n");
        writer.append("CDbw Separation: ").append(String.valueOf(cdbw.separation())).append("\n");
        writer.flush();
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
    int numIterations = 2;
    Path clustersIn = new Path(output, "clusters-0-final");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure,
        numIterations, false);
    printRepPoints(numIterations);
    ClusterEvaluator evaluatorMR = new ClusterEvaluator(conf, clustersIn);
    // now run again using sequential reference point calculation
    HadoopUtil.delete(conf, output);
    CanopyDriver.run(conf, testdata, output, measure, 3.1, 1.1, true, 0.0, true);
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure,
        numIterations, true);
    printRepPoints(numIterations);
    ClusterEvaluator evaluatorSeq = new ClusterEvaluator(conf, clustersIn);
    // compare results
    assertEquals("InterCluster Density", evaluatorMR.interClusterDensity(), evaluatorSeq.interClusterDensity(), EPSILON);
    assertEquals("IntraCluster Density", evaluatorMR.intraClusterDensity(), evaluatorSeq.intraClusterDensity(), EPSILON);
  }
View Full Code Here
167
168
169
170
171
172
173
174
175
  @Test
  public void testCluster0() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, new Path(testdata, "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.25, measure);
    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
177
178
179
180
181
182
183
184
185
  @Test
  public void testCluster1() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, new Path(testdata, "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.5, measure);
    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
187
188
189
190
191
192
193
194
195
  @Test
  public void testCluster2() throws IOException {
    ClusteringTestUtils.writePointsToFile(referenceData, new Path(testdata, "file1"), fs, conf);
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    initData(1, 0.75, measure);
    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
207
208
209
210
211
212
213
214
215
    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
228
229
230
231
232
233
234
235
236
    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
TOP

Related Classes of org.apache.mahout.clustering.evaluation.ClusterEvaluator

  • org.apache.hadoop.fs.FileSystem
  • org.apache.hadoop.fs.Path
  • org.apache.hadoop.io.Writable
  • org.apache.mahout.clustering.Cluster
  • org.apache.mahout.clustering.TestClusterEvaluator
  • org.apache.mahout.math.RandomAccessSparseVector
  • org.apache.mahout.math.Vector
  • org.apache.mahout.utils.clustering.ClusterDumper
    • 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.