Package org.apache.mahout.utils.clustering

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

140
141
142
143
144
145
146
147
148
    Path directoryContainingConvertedInput = new Path(output, DIRECTORY_CONTAINING_CONVERTED_INPUT);
    InputDriver.runJob(input, directoryContainingConvertedInput, "org.apache.mahout.math.RandomAccessSparseVector");
    DirichletDriver.run(new Configuration(), directoryContainingConvertedInput, output, description, numModels,
        maxIterations, alpha0, true, emitMostLikely, threshold, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-*-final"), new Path(output,
        "clusteredPoints"));
    clusterDumper.printClusters(null);
  }
View Full Code Here
139
140
141
142
143
144
145
146
147
    InputDriver.runJob(input, directoryContainingConvertedInput);
    MeanShiftCanopyDriver.run(conf, directoryContainingConvertedInput, output,
        measure, kernelProfile, t1, t2, convergenceDelta, maxIterations, true,
        true, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output,
        "clusters-*-final"), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(null);
  }
View Full Code Here
85
86
87
88
89
90
91
92
93
    InputDriver.runJob(input, directoryContainingConvertedInput,
        "org.apache.mahout.math.RandomAccessSparseVector");
    CanopyDriver.run(new Configuration(), directoryContainingConvertedInput,
        output, measure, t1, t2, true, 0.0, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output,
        "clusters-0-final"), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(null);
  }
View Full Code Here
132
133
134
135
136
137
138
139
140
    clusters = RandomSeedGenerator.buildRandom(conf, directoryContainingConvertedInput, clusters, k, measure);
    log.info("Running KMeans");
    KMeansDriver.run(conf, directoryContainingConvertedInput, clusters, output, measure, convergenceDelta,
        maxIterations, true, 0.0, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-*-final"), new Path(output,
        "clusteredPoints"));
    clusterDumper.printClusters(null);
  }
View Full Code Here
175
176
177
178
179
180
181
182
183
        false);
    log.info("Running KMeans");
    KMeansDriver.run(conf, directoryContainingConvertedInput, new Path(canopyOutput, Cluster.INITIAL_CLUSTERS_DIR
        + "-final"), output, measure, convergenceDelta, maxIterations, true, 0.0, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output, "clusters-*-final"), new Path(output,
        "clusteredPoints"));
    clusterDumper.printClusters(null);
  }
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
    RandomSeedGenerator.buildRandom(conf, input, initialPoints, 8, measure, 1L);
    // Run k-means
    Path kMeansOutput = new Path(output, "kmeans");
    KMeansDriver.run(conf, getTestTempDirPath("testdata"), initialPoints, kMeansOutput, 0.001, 10, true, 0.0, false);
    // Print out clusters
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf,
            output, 10), new Path(kMeansOutput, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
211
212
213
214
215
216
217
218
219
220
    RandomSeedGenerator.buildRandom(conf, input, initialPoints, 8, measure, 1L);
    // Run k-means
    Path kmeansOutput = new Path(output, "kmeans");
    KMeansDriver.run(conf, getTestTempDirPath("testdata"), initialPoints, kmeansOutput, 0.001, 10, true, 0.0, false);
    // Print out clusters
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf,
        output, 10), new Path(kmeansOutput, "clusteredPoints"));
    clusterDumper.setOutputFormat(ClusterDumper.OUTPUT_FORMAT.JSON);
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
234
235
236
237
238
239
240
241
242
    // Run k-means
    Path kMeansOutput = new Path(output, "kmeans");
    FuzzyKMeansDriver.run(conf, getTestTempDirPath("testdata"), initialPoints, kMeansOutput, 0.001, 10, 1.1f, true,
        true, 0, true);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(finalClusterPath(conf,
        output, 10), new Path(kMeansOutput, "clusteredPoints"));
    clusterDumper.printClusters(termDictionary);
  }
View Full Code Here
86
87
88
89
90
91
92
93
94
    InputDriver.runJob(input, directoryContainingConvertedInput,
        "org.apache.mahout.math.RandomAccessSparseVector");
    CanopyDriver.run(new Configuration(), directoryContainingConvertedInput,
        output, measure, t1, t2, true, 0.0, false);
    // run ClusterDumper
    ClusterDumper clusterDumper = new ClusterDumper(new Path(output,
        "clusters-0-final"), new Path(output, "clusteredPoints"));
    clusterDumper.printClusters(null);
  }
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.