Package org.apache.mahout.utils.clustering

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

93
94
95
96
97
98
99
100
    this.contentField = contentField;
    this.minNumIds = minNumIds;
    this.maxLabels = maxLabels;
    this.minNumIds = DEFAULT_MIN_IDS;
    this.maxLabels = DEFAULT_MAX_LABELS;
    ClusterDumper clusterDumper = new ClusterDumper(seqFileDir, pointsDir);
    this.clusterIdToPoints = clusterDumper.getClusterIdToPoints();
  }
View Full Code Here
178
179
180
181
182
183
184
185
186
    DistanceMeasure measure = new EuclideanDistanceMeasure();

    Path output = getTestTempDirPath("output");
    CanopyDriver.run(new Configuration(), getTestTempDirPath("testdata"), output, measure, 8, 4, true, true);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-0"), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
    assertTrue(true);
  }
View Full Code Here
193
194
195
196
197
198
199
200
    Configuration conf = new Configuration();
    CanopyDriver.run(conf, getTestTempDirPath("testdata"), output, measure, 8, 4, false, true);
    // 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
218
219
220
221
222
223
224
225
                          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
229
230
231
232
233
234
235
236
    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, true);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
245
246
247
248
249
250
251
252
253
                                    null,
                                    prototype.getDelegate().size());
    Configuration conf = new Configuration();
    DirichletDriver.run(conf, getTestTempDirPath("testdata"), output, description, 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
262
263
264
265
266
267
268
269
270
                                    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);
    // run ClusterDumper
    ClusterDumper clusterDumper =
        new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
321
322
323
324
325
326
327
328
329
    // now run the Canopy job to prime kMeans canopies
    CanopyDriver.run(conf, svdData, output, measure, 8, 4, false, true);
    // now run the KMeans job
    KMeansDriver.run(svdData, new Path(output, "clusters-0"), output, measure, 0.001, 10, true, true);
    // run ClusterDumper
    ClusterDumper clusterDumper =
        new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
358
359
360
361
362
363
364
365
366
    // now run the Canopy job to prime kMeans canopies
    CanopyDriver.run(conf, sData.getRowPath(), output, measure, 8, 4, false, true);
    // now run the KMeans job
    KMeansDriver.run(sData.getRowPath(), new Path(output, "clusters-0"), output, measure, 0.001, 10, true, true);
    // run ClusterDumper
    ClusterDumper clusterDumper =
        new ClusterDumper(finalClusterPath(conf, output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
397
398
399
400
401
402
403
404
405
    CanopyDriver.run(conf, sData.getRowPath(), output, measure, 8, 4, false, true);
    // now run the KMeans job
    KMeansDriver.run(sData.getRowPath(), new Path(output, "clusters-0"), output, measure,
        0.001, 10, true, 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

  • 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.