Package org.apache.mahout.clustering.dirichlet.models

Examples of org.apache.mahout.clustering.dirichlet.models.DistributionDescription

254
255
256
257
258
259
260
261
262
263
264
265
  @Test
  public void testDirichlet3() throws Exception {
    Path output = getTestTempDirPath("output");
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    DistributionDescription description =
        new DistributionDescription(DistanceMeasureClusterDistribution.class.getName(),
                                    RandomAccessSparseVector.class.getName(),
                                    ManhattanDistanceMeasure.class.getName(),
                                    prototype.getDelegate().size());
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output, description, 15, 10, 1.0, true, true, 0, true);
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
    boolean runClustering = hasOption(DefaultOptionCreator.CLUSTERING_OPTION);
    boolean runSequential =
        getOption(DefaultOptionCreator.METHOD_OPTION).equalsIgnoreCase(DefaultOptionCreator.SEQUENTIAL_METHOD);
    int prototypeSize = readPrototypeSize(input);

    DistributionDescription description =
        new DistributionDescription(modelFactory, modelPrototype, distanceMeasure, prototypeSize);

    run(getConf(),
        input,
        output,
        description,
View Full Code Here
67
68
69
70
71
72
73
74
    String statePath = conf.get(DirichletDriver.STATE_IN_KEY);
    String descriptionString = conf.get(DirichletDriver.MODEL_DISTRIBUTION_KEY);
    String numClusters = conf.get(DirichletDriver.NUM_CLUSTERS_KEY);
    String alpha0 = conf.get(DirichletDriver.ALPHA_0_KEY);

    DistributionDescription description = DistributionDescription.fromString(descriptionString);
    return loadState(conf, statePath, description, Double.parseDouble(alpha0), Integer.parseInt(numClusters));
  }
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
  }
 
  @Test
  public void testDocs() throws Exception {
    getSampleData(DOCS);
    DistributionDescription description = new DistributionDescription(GaussianClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(), ManhattanDistanceMeasure.class.getName(), sampleData.get(0).size());
   
    List<Cluster> models = Lists.newArrayList();
    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
   
    ClusterIterator iterator = new ClusterIterator();
View Full Code Here
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
 
  @Test
  public void testDMDocs() throws Exception {
   
    getSampleData(DOCS);
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(), RandomAccessSparseVector.class.getName(),
        CosineDistanceMeasure.class.getName(), sampleData.get(0).size());
   
    List<Cluster> models = Lists.newArrayList();
    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
   
    ClusterIterator iterator = new ClusterIterator();
View Full Code Here
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
  }
 
  @Test
  public void testDocs2() throws Exception {
    getSampleData(DOCS2);
    DistributionDescription description = new DistributionDescription(GaussianClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(), ManhattanDistanceMeasure.class.getName(), sampleData.get(0).size());
   
    List<Cluster> models = Lists.newArrayList();
    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
   
    ClusterIterator iterator = new ClusterIterator();
View Full Code Here
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
 
  @Test
  public void testDMDocs2() throws Exception {
   
    getSampleData(DOCS);
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(), RandomAccessSparseVector.class.getName(),
        CosineDistanceMeasure.class.getName(), sampleData.get(0).size());
   
    List<Cluster> models = Lists.newArrayList();
    ModelDistribution<VectorWritable> modelDist = description.createModelDistribution(new Configuration());
    for (Model<VectorWritable> cluster : modelDist.sampleFromPrior(15)) {
      models.add((Cluster) cluster);
    }
   
    ClusterIterator iterator = new ClusterIterator();
View Full Code Here
250
251
252
253
254
255
256
257
258
259
260
 
  @Test
  public void testDirichlet2() throws Exception {
    Path output = getTestTempDirPath("output");
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    DistributionDescription description = new DistributionDescription(
        GaussianClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(), null, prototype.getDelegate()
            .size());
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output,
View Full Code Here
267
268
269
270
271
272
273
274
275
276
277
 
  @Test
  public void testDirichlet3() throws Exception {
    Path output = getTestTempDirPath("output");
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    DistributionDescription description = new DistributionDescription(
        DistanceMeasureClusterDistribution.class.getName(),
        RandomAccessSparseVector.class.getName(),
        ManhattanDistanceMeasure.class.getName(), prototype.getDelegate()
            .size());
    Configuration conf = new Configuration();
View Full Code Here
332
333
334
335
336
337
338
339
340
341
342
  }
 
  @Test
  public void testDirichlet() throws Exception {
    ClusteringTestUtils.writePointsToFile(sampleData, new Path(testdata, "file1"), fs, conf);
    DistributionDescription description = new DistributionDescription(GaussianClusterDistribution.class.getName(),
        DenseVector.class.getName(), null, 2);
    DirichletDriver.run(new Configuration(), testdata, output, description, 15, 5, 1.0, true, true, (double) 0, true);
    int numIterations = 10;
    Configuration conf = new Configuration();
    Path clustersIn = new Path(output, "clusters-5-final");
View Full Code Here
TOP

Related Classes of org.apache.mahout.clustering.dirichlet.models.DistributionDescription

  • org.apache.mahout.clustering.cdbw.TestCDbwEvaluator
  • org.apache.mahout.clustering.dirichlet.DirichletDriver
  • org.apache.mahout.clustering.dirichlet.DirichletMapper
  • org.apache.mahout.clustering.dirichlet.TestDirichletClustering
  • org.apache.mahout.clustering.dirichlet.TestL1ModelClustering
  • org.apache.mahout.clustering.dirichlet.TestMapReduce
  • org.apache.mahout.clustering.display.DisplayDirichlet
  • org.apache.mahout.clustering.syntheticcontrol.dirichlet.Job
  • org.apache.mahout.clustering.TestClusterDumper
  • 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.