Package org.apache.mahout.clustering.evaluation

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

171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
    CanopyDriver.run(conf, testdata, output, measure, 3.1, 1.1, true, true);
    int numIterations = 2;
    Path clustersIn = new Path(output, "clusters-0");
    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.overwriteOutput(output);
    CanopyDriver.run(conf, testdata, output, measure, 3.1, 1.1, true, 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
188
189
190
191
192
193
194
195
196
  @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
198
199
200
201
202
203
204
205
206
  @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
208
209
210
211
212
213
214
215
216
  @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
222
223
224
225
226
227
228
229
230
    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
237
238
239
240
241
242
243
244
245
    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
259
260
261
262
263
264
265
266
267
    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
273
274
275
276
277
278
279
280
281
282
283
284
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, testdata, output, measure, 3.1, 1.1, true, true);
    int numIterations = 10;
    Path clustersIn = new Path(output, "clusters-0");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure, numIterations, true);
    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());

    printRepPoints(numIterations);
  }
View Full Code Here
293
294
295
296
297
298
299
300
301
302
303
    // now run the KMeans job
    KMeansDriver.run(testdata, new Path(output, "clusters-0"), output, measure, 0.001, 10, true, true);
    int numIterations = 10;
    Path clustersIn = new Path(output, "clusters-2");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure, numIterations, true);
    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());
    printRepPoints(numIterations);
  }
View Full Code Here
312
313
314
315
316
317
318
319
320
321
322
    // now run the KMeans job
    FuzzyKMeansDriver.run(testdata, new Path(output, "clusters-0"), output, measure, 0.001, 10, 2, true, true, 0, true);
    int numIterations = 10;
    Path clustersIn = new Path(output, "clusters-4");
    RepresentativePointsDriver.run(conf, clustersIn, new Path(output, "clusteredPoints"), output, measure, numIterations, true);
    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());
    printRepPoints(numIterations);
  }
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.