Package org.apache.mahout.utils.clustering

Examples of org.apache.mahout.utils.clustering.ClusterDumper$TermIndexWeight

120
121
122
123
124
125
126
127
    this.maxLabels = maxLabels;
    init();
  }
 
  private void init() throws IOException {
    ClusterDumper clusterDumper = new ClusterDumper(seqFileDir, pointsDir);
    this.clusterIdToPoints = clusterDumper.getClusterIdToPoints();
  }
View Full Code Here
320
321
322
323
324
325
326
327
    // now run the Canopy job to prime kMeans canopies
    CanopyDriver.run(conf, svdData, output, measure, 8, 4, false, false);
    // now run the KMeans job
    KMeansDriver.run(svdData, new Path(output, "clusters-0"), output, measure, 0.001, 10, true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
353
354
355
356
357
358
359
360
    // now run the Canopy job to prime kMeans canopies
    CanopyDriver.run(conf, sData.getRowPath(), output, measure, 8, 4, false, false);
    // now run the KMeans job
    KMeansDriver.run(sData.getRowPath(), new Path(output, "clusters-0"), output, measure, 0.001, 10, true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
388
389
390
391
392
393
394
395
    // now run the Canopy job to prime kMeans canopies
    CanopyDriver.run(conf, sData.getRowPath(), output, measure, 8, 4, false, false);
    // now run the KMeans job
    KMeansDriver.run(sData.getRowPath(), new Path(output, "clusters-0"), output, measure, 0.001, 10, true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
169
170
171
172
173
174
175
176
    DistanceMeasure measure = new EuclideanDistanceMeasure();

    Path output = getTestTempDirPath("output");
    CanopyDriver.run(new Configuration(), getTestTempDirPath("testdata"), output, measure, 8, 4, true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-0"), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
183
184
185
186
187
188
189
190
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, getTestTempDirPath("testdata"), output, measure, 8, 4, false, false);
    // now run the KMeans job
    KMeansDriver.run(conf, getTestTempDirPath("testdata"), new Path(output, "clusters-0"), output, measure, 0.001, 10, true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
208
209
210
211
212
213
214
215
                          true,
                          true,
                          0,
                          false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
219
220
221
222
223
224
225
226
    DistanceMeasure measure = new CosineDistanceMeasure();
    Path output = getTestTempDirPath("output");
    Configuration conf = new Configuration();
    new MeanShiftCanopyDriver().run(conf, getTestTempDirPath("testdata"), output, measure, 0.5, 0.01, 0.05, 10, false, true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
231
232
233
234
235
236
237
238
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    AbstractVectorModelDistribution modelDistribution = new SampledNormalDistribution(new VectorWritable(prototype));
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output, modelDistribution, 15, 10, 1.0, true, true, 0, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
243
244
245
246
247
248
249
250
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    AbstractVectorModelDistribution modelDistribution = new GaussianClusterDistribution(new VectorWritable(prototype));
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output, modelDistribution, 15, 10, 1.0, true, true, 0, true);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
TOP

Related Classes of org.apache.mahout.utils.clustering.ClusterDumper$TermIndexWeight

  • org.apache.commons.cli2.builder.ArgumentBuilder
  • org.apache.commons.cli2.builder.DefaultOptionBuilder
  • org.apache.commons.cli2.builder.GroupBuilder
  • org.apache.commons.cli2.CommandLine
  • org.apache.commons.cli2.commandline.Parser
  • org.apache.commons.cli2.Group
  • org.apache.commons.cli2.Option
  • org.apache.hadoop.conf.Configuration
  • org.apache.hadoop.fs.FileSystem
  • org.apache.hadoop.fs.Path
    • 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.