Package org.apache.mahout.common.distance

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

214
215
216
217
218
219
220
221
222
223
224
    clusterDumper.printClusters(termDictionary);
  }

  @Test
  public void testMeanShift() throws Exception {
    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"));
View Full Code Here
232
233
234
235
236
237
238
239
240
241
242
    clusterDumper.printClusters(termDictionary);
  }
 
  @Test
  public void testMeanShift() throws Exception {
    DistanceMeasure measure = new CosineDistanceMeasure();
    IKernelProfile kernelProfile = new TriangularKernelProfile();
    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);
View Full Code Here
709
710
711
712
713
714
715
716
717
718
719
      mark.incrementalCreateBenchmark();
      mark.cloneBenchmark();
      mark.dotBenchmark();
      mark.serializeBenchmark();
      mark.deserializeBenchmark();
      mark.distanceMeasureBenchmark(new CosineDistanceMeasure());
      mark.distanceMeasureBenchmark(new SquaredEuclideanDistanceMeasure());
      mark.distanceMeasureBenchmark(new EuclideanDistanceMeasure());
      mark.distanceMeasureBenchmark(new ManhattanDistanceMeasure());
      mark.distanceMeasureBenchmark(new TanimotoDistanceMeasure());
     
View Full Code Here
63
64
65
66
67
68
69
70
71
72
73
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }
 
  private static ClusterClassifier newCosineKlusterClassifier() {
    List<Cluster> models = Lists.newArrayList();
    DistanceMeasure measure = new CosineDistanceMeasure();
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(1), 0, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2), 1, measure));
    models.add(new org.apache.mahout.clustering.kmeans.Kluster(new DenseVector(2).assign(-1), 2, measure));
    return new ClusterClassifier(models, new KMeansClusteringPolicy());
  }
View Full Code Here
230
231
232
233
234
235
236
237
238
239
240
    clusterDumper.printClusters(termDictionary);
  }
 
  @Test
  public void testMeanShift() throws Exception {
    DistanceMeasure measure = new CosineDistanceMeasure();
    IKernelProfile kernelProfile = new TriangularKernelProfile();
    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);
View Full Code Here
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
    new MinusBenchmark(mark).benchmark();
    new TimesBenchmark(mark).benchmark();
    new SerializationBenchmark(mark).benchmark();

    DistanceBenchmark distanceBenchmark = new DistanceBenchmark(mark);
    distanceBenchmark.benchmark(new CosineDistanceMeasure());
    distanceBenchmark.benchmark(new SquaredEuclideanDistanceMeasure());
    distanceBenchmark.benchmark(new EuclideanDistanceMeasure());
    distanceBenchmark.benchmark(new ManhattanDistanceMeasure());
    distanceBenchmark.benchmark(new TanimotoDistanceMeasure());
    distanceBenchmark.benchmark(new ChebyshevDistanceMeasure());
    distanceBenchmark.benchmark(new MinkowskiDistanceMeasure());

    if (mark.numClusters > 0) {
      ClosestCentroidBenchmark centroidBenchmark = new ClosestCentroidBenchmark(mark);
      centroidBenchmark.benchmark(new CosineDistanceMeasure());
      centroidBenchmark.benchmark(new SquaredEuclideanDistanceMeasure());
      centroidBenchmark.benchmark(new EuclideanDistanceMeasure());
      centroidBenchmark.benchmark(new ManhattanDistanceMeasure());
      centroidBenchmark.benchmark(new TanimotoDistanceMeasure());
      centroidBenchmark.benchmark(new ChebyshevDistanceMeasure());
View Full Code Here
37
38
39
40
41
42
43
44
45
46
47
  public static List<Object[]> generateData() {
    RandomUtils.useTestSeed();
    Matrix dataPoints = LumpyData.lumpyRandomData(NUM_DATA_POINTS, NUM_DIMENSIONS);
    Matrix queries = LumpyData.lumpyRandomData(NUM_QUERIES, NUM_DIMENSIONS);

    DistanceMeasure distanceMeasure = new CosineDistanceMeasure();

    Searcher bruteSearcher = new BruteSearch(distanceMeasure);
    bruteSearcher.addAll(dataPoints);
    Pair<List<List<WeightedThing<Vector>>>, Long> reference = getResultsAndRuntime(bruteSearcher, queries);
View Full Code Here
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
      mark.incrementalCreateBenchmark();
      mark.cloneBenchmark();
      mark.dotBenchmark();
      mark.serializeBenchmark();
      mark.deserializeBenchmark();
      mark.distanceMeasureBenchmark(new CosineDistanceMeasure());
      mark.distanceMeasureBenchmark(new SquaredEuclideanDistanceMeasure());
      mark.distanceMeasureBenchmark(new EuclideanDistanceMeasure());
      mark.distanceMeasureBenchmark(new ManhattanDistanceMeasure());
      mark.distanceMeasureBenchmark(new TanimotoDistanceMeasure());
     
      mark.closestCentroidBenchmark(new CosineDistanceMeasure());
      mark.closestCentroidBenchmark(new SquaredEuclideanDistanceMeasure());
      mark.closestCentroidBenchmark(new EuclideanDistanceMeasure());
      mark.closestCentroidBenchmark(new ManhattanDistanceMeasure());
      mark.closestCentroidBenchmark(new TanimotoDistanceMeasure());
     
View Full Code Here
224
225
226
227
228
229
230
231
232
233
234
    clusterDumper.printClusters(termDictionary);
  }

  @Test
  public void testMeanShift() throws Exception {
    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"));
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
  public static List<Object[]> generateData() {
    RandomUtils.useTestSeed();
    Matrix dataPoints = LumpyData.lumpyRandomData(NUM_DATA_POINTS, NUM_DIMENSIONS);
    Matrix queries = LumpyData.lumpyRandomData(NUM_QUERIES, NUM_DIMENSIONS);

    DistanceMeasure distanceMeasure = new CosineDistanceMeasure();

    Searcher bruteSearcher = new BruteSearch(distanceMeasure);
    bruteSearcher.addAll(dataPoints);
    Pair<List<List<WeightedThing<Vector>>>, Long> reference = getResultsAndRuntime(bruteSearcher, queries);
View Full Code Here
TOP

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

  • com.fb2pdf.hadoop.cluster.OutputClusterResults$OutputClusterResultsMapper
  • mia.clustering.ch09.CanopyClustering
  • mia.clustering.ch09.FuzzyKMeansClustering
  • mia.clustering.ch09.KMeansClustering
  • mia.clustering.ch09.KMeansWithCanopyClustering
  • mia.clustering.ch10.InterClusterDistances
  • mia.clustering.ch10.MyDistanceNewsClustering
  • mia.clustering.ch10.NewsKMeansClustering
  • org.apache.mahout.benchmark.VectorBenchmarks
  • org.apache.mahout.clustering.iterator.TestClusterClassifier
    • 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.