Package org.apache.mahout.common.distance

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

360
361
362
363
364
365
366
367
368
369
370
  }

  /** Story: User wishes to run kmeans job on reference data */
  @Test
  public void testKMeansSeqJob() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    List<VectorWritable> points = getPointsWritable(REFERENCE);

    Path pointsPath = getTestTempDirPath("points");
    Path clustersPath = getTestTempDirPath("clusters");
    Configuration conf = new Configuration();
View Full Code Here
415
416
417
418
419
420
421
422
423
424
425
  }

  /** Story: User wishes to run kmeans job on reference data */
  @Test
  public void testKMeansMRJob() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    List<VectorWritable> points = getPointsWritable(REFERENCE);

    Path pointsPath = getTestTempDirPath("points");
    Path clustersPath = getTestTempDirPath("clusters");
    Configuration conf = new Configuration();
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
    initialize();
    this.setTitle("k-Means Clusters (>" + (int) (significance * 100) + "% of population)");
  }
 
  public static void main(String[] args) throws Exception {
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    Path samples = new Path("samples");
    Path output = new Path("output");
    Configuration conf = new Configuration();
    HadoopUtil.delete(conf, samples);
    HadoopUtil.delete(conf, output);
View Full Code Here
83
84
85
86
87
88
89
90
91
92
    Path output = getOutputPath();
    String distanceMeasureClass = getOption(DefaultOptionCreator.DISTANCE_MEASURE_OPTION);
    int maxIterations = Integer.parseInt(getOption(DefaultOptionCreator.MAX_ITERATIONS_OPTION));
    boolean runSequential = getOption(DefaultOptionCreator.METHOD_OPTION).equalsIgnoreCase(
        DefaultOptionCreator.SEQUENTIAL_METHOD);
    DistanceMeasure measure = ClassUtils.instantiateAs(distanceMeasureClass, DistanceMeasure.class);
    Path clusteredPoints = new Path(getOption("clusteredPoints"));
    run(getConf(), input, clusteredPoints, output, measure, maxIterations, runSequential);
    return 0;
  }
View Full Code Here
184
185
186
187
188
189
190
191
192
193
194
    return null;
  }
 
  @Test
  public void testCanopy() throws Exception { // now run the Job
    DistanceMeasure measure = new EuclideanDistanceMeasure();
   
    Path output = getTestTempDirPath("output");
    CanopyDriver.run(new Configuration(), getTestTempDirPath("testdata"),
        output, measure, 8, 4, true, true);
    // run ClusterDumper
View Full Code Here
197
198
199
200
201
202
203
204
205
206
207
    clusterDumper.printClusters(termDictionary);
  }
 
  @Test
  public void testKmeans() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    // now run the Canopy job to prime kMeans canopies
    Path output = getTestTempDirPath("output");
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, getTestTempDirPath("testdata"), output, measure, 8,
        4, false, true);
View Full Code Here
214
215
216
217
218
219
220
221
222
223
224
    clusterDumper.printClusters(termDictionary);
  }
 
  @Test
  public void testFuzzyKmeans() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    // now run the Canopy job to prime kMeans canopies
    Path output = getTestTempDirPath("output");
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, getTestTempDirPath("testdata"), output, measure, 8,
        4, false, true);
View Full Code Here
232
233
234
235
236
237
238
239
240
241
242
    clusterDumper.printClusters(termDictionary);
  }
 
  @Test
  public void testMeanShift() throws Exception {
    DistanceMeasure measure = new CosineDistanceMeasure();
    IKernelProfile kernelProfile = new TriangularKernelProfile();
    Path output = getTestTempDirPath("output");
    Configuration conf = new Configuration();
    MeanShiftCanopyDriver.run(conf, getTestTempDirPath("testdata"), output,
        measure, kernelProfile, 0.5, 0.01, 0.05, 10, false, true, true);
View Full Code Here
281
282
283
284
285
286
287
288
289
290
291
    clusterDumper.printClusters(termDictionary);
  }
 
  // @Test
  public void testKmeansSVD() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    Path output = getTestTempDirPath("output");
    Path tmp = getTestTempDirPath("tmp");
    DistributedLanczosSolver solver = new DistributedLanczosSolver();
    Configuration conf = new Configuration();
    solver.setConf(conf);
View Full Code Here
344
345
346
347
348
349
350
351
352
353
354
    clusterDumper.printClusters(termDictionary);
  }
 
  // @Test
  public void testKmeansDSVD() throws Exception {
    DistanceMeasure measure = new EuclideanDistanceMeasure();
    Path output = getTestTempDirPath("output");
    Path tmp = getTestTempDirPath("tmp");
    DistributedLanczosSolver solver = new DistributedLanczosSolver();
    Configuration config = new Configuration();
    solver.setConf(config);
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.