Examples of FastProjectionSearch

org.apache.mahout.knn.search.FastProjectionSearch
Does approximate nearest neighbor search by projecting the vectors similar to ProjectionSearch. The main difference between this class and the ProjectionSearch is the use of sorted arrays instead of binary search trees to implement the sets of scalar projections. Instead of taking log n time to add a vector to each of the vectors, * the pending additions are kept separate and are searched using a brute search. When there are "enough" pending additions, they're committed into the main pool of vectors.
org.apache.mahout.math.neighborhood.FastProjectionSearch
Does approximate nearest neighbor search by projecting the vectors similar to ProjectionSearch. The main difference between this class and the ProjectionSearch is the use of sorted arrays instead of binary search trees to implement the sets of scalar projections. Instead of taking log n time to add a vector to each of the vectors, * the pending additions are kept separate and are searched using a brute search. When there are "enough" pending additions, they're committed into the main pool of vectors.

Examples of org.apache.mahout.knn.search.FastProjectionSearch

      radius.add(furthest);
    }
    log.warn("Reference data stored");
    log.warn("Starting add with speedup of {}", numDataVectors / (dimension * 2.0 * depth * 4.0));


    Searcher sut = new FastProjectionSearch(new SquaredEuclideanDistanceMeasure(), dimension * 2, depth * 4);
    sut.addAllMatrixSlicesAsWeightedVectors(data);
    log.warn("Added data with speedup of {}", numDataVectors / (dimension * 2.0 * depth * 4.0));


    long t0 = System.nanoTime();
    for (MatrixSlice query : queries) {
      List<WeightedThing<Vector>> r = sut.search(query.vector(), depth);
      Set<Integer> x = Sets.newHashSet();
      for (WeightedThing<Vector> vector : r) {
        x.add(((WeightedVector)vector.getValue()).getIndex());
      }
      double overlap = Sets.intersection(reference.get(query.index()), x).size() / (double) depth;

View Full Code Here

Examples of org.apache.mahout.math.neighborhood.FastProjectionSearch


  @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.math.neighborhood.FastProjectionSearch


  @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

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.