Package org.apache.mahout.utils.clustering

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

255
256
257
258
259
260
261
262
    NamedVector prototype = (NamedVector) sampleData.get(0).get();
    AbstractVectorModelDistribution modelDistribution = new DistanceMeasureClusterDistribution(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
95
96
97
98
99
100
101
102
    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
190
191
192
193
194
195
196
197
198
   
    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);
  }
View Full Code Here
207
208
209
210
211
212
213
214
215
        4, false, true);
    // now run the KMeans job
    KMeansDriver.run(conf, getTestTempDirPath("testdata"), new Path(output,
        "clusters-0-final"), 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
225
226
227
228
229
230
231
232
233
    // now run the Fuzzy KMeans job
    FuzzyKMeansDriver.run(conf, getTestTempDirPath("testdata"), new Path(
        output, "clusters-0-final"), output, measure, 0.001, 10, 1.1f, 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
239
240
241
242
243
244
245
246
247
    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);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf,
        output, 10), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
256
257
258
259
260
261
262
263
264
            .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
274
275
276
277
278
279
280
281
282
            .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
337
338
339
340
341
342
343
344
345
    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
378
379
380
381
382
383
384
385
386
        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$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.