Package org.apache.mahout.common.distance

Examples of org.apache.mahout.common.distance.ManhattanDistanceMeasure

37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
    initialize();
    this.setTitle("Spectral k-Means Clusters (>" + (int) (significance * 100) + "% of population)");
  }

  public static void main(String[] args) throws Exception {
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    Path samples = new Path("samples");
    Path output = new Path("output");
    HadoopUtil.overwriteOutput(samples);
    HadoopUtil.overwriteOutput(output);

    RandomUtils.useTestSeed();
    DisplayClustering.generateSamples();
    writeSampleData(samples);
    int maxIter = 10;
    double convergenceDelta = 0.001;
    Path affinities = new Path(output, "affinities");
    Configuration conf = new Configuration();
    FileSystem fs = FileSystem.get(output.toUri(), conf);
    if (!fs.exists(output)) {
      fs.mkdirs(output);
    }
    FileWriter writer = new FileWriter(affinities.toString());
    PrintWriter out = new PrintWriter(writer);
    try {
      for (int i = 0; i < SAMPLE_DATA.size(); i++) {
        for (int j = 0; j < SAMPLE_DATA.size(); j++) {
          out.println(i + "," + j + "," + measure.distance(SAMPLE_DATA.get(i).get(), SAMPLE_DATA.get(j).get()));
        }
      }
    } finally {
      out.close();
    }
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
    job.setMapOutputValueClass(VectorWritable.class);
    Path input = getTestTempFilePath("random-input");
    Path output = getTestTempDirPath("random-output");
    ClusteringTestUtils.writePointsToFile(points, input, fs, conf);
   
    RandomSeedGenerator.buildRandom(input, output, 4, new ManhattanDistanceMeasure());
   
    SequenceFile.Reader reader = new SequenceFile.Reader(fs, new Path(output, "part-randomSeed"), conf);
    Writable key = reader.getKeyClass().asSubclass(Writable.class).newInstance();
    AbstractCluster value = (AbstractCluster) reader.getValueClass().newInstance();
   
View Full Code Here
451
452
453
454
455
456
457
458
459
460
461
    ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file1"), fs, conf);
    ClusteringTestUtils.writePointsToFile(points, new Path(pointsPath, "file2"), fs, conf);

    Path outputPath = getTestTempDirPath("output");
    // now run the Canopy job
    CanopyDriver.run(conf, pointsPath, outputPath, new ManhattanDistanceMeasure(), 3.1, 2.1, false, false);

    // now run the KMeans job
    KMeansDriver.run(pointsPath,
                     new Path(outputPath, "clusters-0"),
                     outputPath,
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
    initialize();
    setTitle("Spectral k-Means Clusters (>" + (int) (significance * 100) + "% of population)");
  }

  public static void main(String[] args) throws Exception {
    DistanceMeasure measure = new ManhattanDistanceMeasure();
    Path samples = new Path(SAMPLES);
    Path output = new Path(OUTPUT);
    Path tempDir = new Path(TEMP);
    Configuration conf = new Configuration();
    HadoopUtil.delete(conf, samples);
    HadoopUtil.delete(conf, output);

    RandomUtils.useTestSeed();
    DisplayClustering.generateSamples();
    writeSampleData(samples);
    Path affinities = new Path(output, AFFINITIES);
    FileSystem fs = FileSystem.get(output.toUri(), conf);
    if (!fs.exists(output)) {
      fs.mkdirs(output);
    }
    Writer writer = null;
    try {
      writer = Files.newWriter(new File(affinities.toString()), Charsets.UTF_8);
      for (int i = 0; i < SAMPLE_DATA.size(); i++) {
        for (int j = 0; j < SAMPLE_DATA.size(); j++) {
          writer.write(i + "," + j + ',' + measure.distance(SAMPLE_DATA.get(i).get(), SAMPLE_DATA.get(j).get()) + '\n');
        }
      }
    } finally {
      Closeables.close(writer, false);
    }
View Full Code Here
76
77
78
79
80
81
82
83
84
85
    HadoopUtil.delete(conf, samples);
    HadoopUtil.delete(conf, output);
    RandomUtils.useTestSeed();
    generateSamples();
    writeSampleData(samples);
    CanopyDriver.buildClusters(conf, samples, output, new ManhattanDistanceMeasure(), T1, T2, 0, true);
    loadClustersWritable(output);

    new DisplayCanopy();
  }
View Full Code Here
140
141
142
143
144
145
146
147
148
149
  private void runClustering(Path pointsPath, Configuration conf,
      Boolean runSequential) throws IOException, InterruptedException,
      ClassNotFoundException {
    CanopyDriver.run(conf, pointsPath, clusteringOutputPath,
        new ManhattanDistanceMeasure(), 3.1, 2.1, false, 0.0, runSequential);
    Path finalClustersPath = new Path(clusteringOutputPath, "clusters-0-final");
    ClusterClassifier.writePolicy(new CanopyClusteringPolicy(),
        finalClustersPath);
  }
View Full Code Here
157
158
159
160
161
162
163
164
165
166
    for (Entry<String,Path> topLevelCluster : postProcessedClusterDirectories.entrySet()) {
      String clusterId = topLevelCluster.getKey();
      Path topLevelclusterPath = topLevelCluster.getValue();

      Path bottomLevelCluster = PathDirectory.getBottomLevelClusterPath(outputPath, clusterId);
      CanopyDriver.run(conf, topLevelclusterPath, bottomLevelCluster, new ManhattanDistanceMeasure(), 2.1,
        2.0, true, 0.0, true);
      assertBottomLevelCluster(bottomLevelCluster);
    }
  }
View Full Code Here
197
198
199
200
201
202
203
  }

  private void topLevelClustering(Path pointsPath, Configuration conf) throws IOException,
                                                                      InterruptedException,
                                                                      ClassNotFoundException {
    CanopyDriver.run(conf, pointsPath, outputPath, new ManhattanDistanceMeasure(), 3.1, 2.1, true, 0.0, true);
  }
View Full Code Here
38
39
40
41
42
43
44
  public DistanceMeasureClusterDistribution() {
  }

  public DistanceMeasureClusterDistribution(VectorWritable modelPrototype) {
    super(modelPrototype);
    this.measure = new ManhattanDistanceMeasure();
  }
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
    ClusteringTestUtils.writePointsToFile(points, true, new Path(pointsPath, "file1"), fs, conf);
    ClusteringTestUtils.writePointsToFile(points, true, new Path(pointsPath, "file2"), fs, conf);
   
    Path outputPath = getTestTempDirPath("output");
    // now run the Canopy job
    CanopyDriver.run(conf, pointsPath, outputPath, new ManhattanDistanceMeasure(), 3.1, 2.1, false, 0.0, false);
   
    DummyOutputCollector<Text, ClusterWritable> collector1 =
        new DummyOutputCollector<Text, ClusterWritable>();

    FileStatus[] outParts = FileSystem.get(conf).globStatus(
View Full Code Here
TOP

Related Classes of org.apache.mahout.common.distance.ManhattanDistanceMeasure

  • mia.clustering.ch09.NewsFuzzyKMeansClustering
  • org.apache.mahout.benchmark.VectorBenchmarks
  • org.apache.mahout.clustering.canopy.DisplayCanopy
  • org.apache.mahout.clustering.canopy.TestCanopyCreation
  • org.apache.mahout.clustering.classify.ClusterClassificationDriverTest
  • org.apache.mahout.clustering.dirichlet.models.DistanceMeasureClusterDistribution
  • org.apache.mahout.clustering.display.DisplayCanopy
  • org.apache.mahout.clustering.display.DisplayFuzzyKMeans
  • org.apache.mahout.clustering.display.DisplayKMeans
  • org.apache.mahout.clustering.display.DisplaySpectralKMeans
    • 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.