Examples of SquaredEuclideanDistanceMeasure

org.apache.mahout.common.distance.SquaredEuclideanDistanceMeasure
Like {@link EuclideanDistanceMeasure} but it does not take the square root.
Thus, it is not actually the Euclidean Distance, but it is saves on computation when you only need the distance for comparison and don't care about the actual value as a distance.

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

    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());
      centroidBenchmark.benchmark(new MinkowskiDistanceMeasure());

View Full Code Here

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

      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());
      
      log.info("\n{}", mark);

View Full Code Here

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

          new SequenceFileDirValueIterable<VectorWritable>(new Path(trainFile), PathType.GLOB, conf);
      Iterable<Vector> trainDatapoints = IOUtils.getVectorsFromVectorWritableIterable(trainIterable);
      Iterable<Vector> datapoints = trainDatapoints;


      printSummaries(ClusteringUtils.summarizeClusterDistances(trainDatapoints, centroids,
          new SquaredEuclideanDistanceMeasure()), "train");


      // Also adding in the "test" set.
      if (testFile != null) {
        SequenceFileDirValueIterable<VectorWritable> testIterable =
            new SequenceFileDirValueIterable<VectorWritable>(new Path(testFile), PathType.GLOB, conf);
        Iterable<Vector> testDatapoints = IOUtils.getVectorsFromVectorWritableIterable(testIterable);


        printSummaries(ClusteringUtils.summarizeClusterDistances(testDatapoints, centroids,
            new SquaredEuclideanDistanceMeasure()), "test");


        datapoints = Iterables.concat(trainDatapoints, testDatapoints);
      }


      // At this point, all train/test CSVs have been written. We now compute quality metrics.

View Full Code Here

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




  @Test
  public void testClusteringMultipleRuns() {
    for (int i = 1; i <= 10; ++i) {
      BallKMeans clusterer = new BallKMeans(new BruteSearch(new SquaredEuclideanDistanceMeasure()),
          1 << NUM_DIMENSIONS, NUM_ITERATIONS, true, i);
      clusterer.cluster(syntheticData.getFirst());
      double costKMeansPlusPlus = ClusteringUtils.totalClusterCost(syntheticData.getFirst(), clusterer);


      clusterer = new BallKMeans(new BruteSearch(new SquaredEuclideanDistanceMeasure()),
          1 << NUM_DIMENSIONS, NUM_ITERATIONS, false, i);
      clusterer.cluster(syntheticData.getFirst());
      double costKMeansRandom = ClusteringUtils.totalClusterCost(syntheticData.getFirst(), clusterer);


      System.out.printf("%d runs; kmeans++: %f; random: %f\n", i, costKMeansPlusPlus, costKMeansRandom);

View Full Code Here

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

    }
  }


  @Test
  public void testClustering() {
    UpdatableSearcher searcher = new BruteSearch(new SquaredEuclideanDistanceMeasure());
    BallKMeans clusterer = new BallKMeans(searcher, 1 << NUM_DIMENSIONS, NUM_ITERATIONS);


    long startTime = System.currentTimeMillis();
    Pair<List<Centroid>, List<Centroid>> data = syntheticData;
    clusterer.cluster(data.getFirst());

View Full Code Here

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

  public void testInitialization() {
    // Start with super clusterable data.
    List<? extends WeightedVector> data = cubishTestData(0.01);


    // Just do initialization of ball k-means. This should drop a point into each of the clusters.
    BallKMeans r = new BallKMeans(new BruteSearch(new SquaredEuclideanDistanceMeasure()), 6, 20);
    r.cluster(data);


    // Put the centroids into a matrix.
    Matrix x = new DenseMatrix(6, 5);
    int row = 0;

View Full Code Here

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

        mapDriver.getConfiguration().get(StreamingKMeansDriver.SEARCHER_CLASS_OPTION));
    for (Centroid datapoint : syntheticData.getFirst()) {
      mapDriver.addInput(new IntWritable(0), new VectorWritable(datapoint));
    }
    List<org.apache.hadoop.mrunit.types.Pair<IntWritable,CentroidWritable>> results = mapDriver.run();
    BruteSearch resultSearcher = new BruteSearch(new SquaredEuclideanDistanceMeasure());
    for (org.apache.hadoop.mrunit.types.Pair<IntWritable, CentroidWritable> result : results) {
      resultSearcher.add(result.getSecond().getCentroid());
    }
    System.out.printf("Clustered the data into %d clusters\n", results.size());
    for (Vector mean : syntheticData.getSecond()) {

View Full Code Here

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

  }


  @Parameters
  public static List<Object[]> generateData() {
    return Arrays.asList(new Object[][] {
        {new ProjectionSearch(new SquaredEuclideanDistanceMeasure(), NUM_PROJECTIONS, SEARCH_SIZE), true},
        {new FastProjectionSearch(new SquaredEuclideanDistanceMeasure(), NUM_PROJECTIONS, SEARCH_SIZE),
            true},
        {new ProjectionSearch(new SquaredEuclideanDistanceMeasure(), NUM_PROJECTIONS, SEARCH_SIZE), false},
        {new FastProjectionSearch(new SquaredEuclideanDistanceMeasure(), NUM_PROJECTIONS, SEARCH_SIZE),
            false},
    });
  }

View Full Code Here

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

      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());
      
      log.info("\n{}", mark);

View Full Code Here

0 1

TOP

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.