Examples of BruteSearch

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

44
45
46
47
48
49
50
    return data;
  }

  @Override
  public UpdatableSearcher getSearch(int n) {
    return new BruteSearch(new EuclideanDistanceMeasure());
  }
View Full Code Here

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

50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
  }

  @Test
  public void testMatrixSearch() {
    List<WeightedVector> referenceVectors = Lists.newArrayListWithExpectedSize(8);
    BruteSearch searcher = new BruteSearch(new EuclideanDistanceMeasure());
    for (int i = 0; i < 8; i++) {
      referenceVectors.add(new WeightedVector(
          new DenseVector(new double[]{0.125 * (i & 4), i & 2, i & 1}), 1, i));
      searcher.add(referenceVectors.get(referenceVectors.size() - 1));
    }

    final List<List<WeightedThing<Vector>>> searchResults =
        searcher.search(referenceVectors, 3);
    for (List<WeightedThing<Vector>> r : searchResults) {
      assertEquals(0, r.get(0).getWeight(), 1e-8);
      assertEquals(0.5, r.get(1).getWeight(), 1e-8);
      assertEquals(1, r.get(2).getWeight(), 1e-8);
    }
View Full Code Here

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

37
38
39
40
41
42
43
44
45
46
47
  @Test
  public void testBasicClustering() {
    List<? extends WeightedVector> data = cubishTestData(1);

    BallKMeans r = new BallKMeans(new BruteSearch(new EuclideanDistanceMeasure()), 6, 20);
    r.cluster(data);
    for (Centroid centroid : r) {
      for (int i = 0; i < 10; i++) {
        System.out.printf("%10.4f", centroid.get(i));
      }
View Full Code Here

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

53
54
55
56
57
58
59
60
61
62
63
  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 EuclideanDistanceMeasure()), 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.knn.search.BruteSearch

50
51
52
53
54
55
56
57
58
59
60
61
62
63
    }
    System.out.printf("Generated query matrix.\n");

    for (int threads : new int[]{1, 2, 3, 4, 5, 6, 10, 20, 50}) {
      for (int block : new int[]{1, 10, 50}) {
        BruteSearch search = new BruteSearch(new EuclideanDistanceMeasure());
        search.addAll(referenceVectors);
        long t0 = System.nanoTime();
        search.search(queryVectors, block, threads);
        long t1 = System.nanoTime();
        System.out.printf("%d\t%d\t%.2f\n", threads, block, (t1 - t0) / 1e9);
      }
    }
  }
View Full Code Here

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

90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
   * @param distanceMeasure the distance measure used to compute the distance between two points.
   * @return the minimum distance between the first sampleLimit points
   * @see org.apache.mahout.clustering.streaming.cluster.StreamingKMeans#clusterInternal(Iterable, boolean)
   */
  public static double estimateDistanceCutoff(List<? extends Vector> data, DistanceMeasure distanceMeasure) {
    BruteSearch searcher = new BruteSearch(distanceMeasure);
    searcher.addAll(data);
    double minDistance = Double.POSITIVE_INFINITY;
    for (Vector vector : data) {
      double closest = searcher.searchFirst(vector, true).getWeight();
      if (minDistance > 0 && closest < minDistance) {
        minDistance = closest;
      }
      searcher.add(vector);
    }
    return minDistance;
  }
View Full Code Here

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

207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
   * @param distanceMeasure distance measure to use
   * @return the confusion matrix
   */
  public static Matrix getConfusionMatrix(List<? extends Vector> rowCentroids, List<? extends  Vector> columnCentroids,
                                          Iterable<? extends Vector> datapoints, DistanceMeasure distanceMeasure) {
    Searcher rowSearcher = new BruteSearch(distanceMeasure);
    rowSearcher.addAll(rowCentroids);
    Searcher columnSearcher = new BruteSearch(distanceMeasure);
    columnSearcher.addAll(columnCentroids);

    int numRows = rowCentroids.size();
    int numCols = columnCentroids.size();
    Matrix confusionMatrix = new DenseMatrix(numRows, numCols);

    for (Vector vector : datapoints) {
      WeightedThing<Vector> closestRowCentroid = rowSearcher.search(vector, 1).get(0);
      WeightedThing<Vector> closestColumnCentroid = columnSearcher.search(vector, 1).get(0);
      int row = ((Centroid) closestRowCentroid.getValue()).getIndex();
      int column = ((Centroid) closestColumnCentroid.getValue()).getIndex();
      double vectorWeight;
      if (vector instanceof WeightedVector) {
        vectorWeight = ((WeightedVector) vector).getWeight();
View Full Code Here

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

106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
        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()) {
      WeightedThing<Vector> closest = resultSearcher.search(mean, 1).get(0);
      assertTrue("Weight " + closest.getWeight() + " not less than 0.5", closest.getWeight() < 0.5);
    }
  }
View Full Code Here

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

57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
  private static final int K1 = 100;

  @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.math.neighborhood.BruteSearch

74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
    }
  }

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

    long startTime = System.currentTimeMillis();
    clusterer.cluster(syntheticData.getFirst());
    long endTime = System.currentTimeMillis();

    assertEquals("Total weight not preserved", totalWeight(syntheticData.getFirst()), totalWeight(clusterer), 1.0e-9);

    // Verify that each corner of the cube has a centroid very nearby.
    // This is probably FALSE for large-dimensional spaces!
    OnlineSummarizer summarizer = new OnlineSummarizer();
    for (Vector mean : syntheticData.getSecond()) {
      WeightedThing<Vector> v = searcher.search(mean, 1).get(0);
      summarizer.add(v.getWeight());
    }
    assertTrue(String.format("Median weight [%f] too large [>%f]", summarizer.getMedian(),
        DISTRIBUTION_RADIUS), summarizer.getMedian() < DISTRIBUTION_RADIUS);

    double clusterTime = (endTime - startTime) / 1000.0;
    System.out.printf("%s\n%.2f for clustering\n%.1f us per row\n\n",
        searcher.getClass().getName(), clusterTime,
        clusterTime / syntheticData.getFirst().size() * 1.0e6);

    // Verify that the total weight of the centroids near each corner is correct.
    double[] cornerWeights = new double[1 << NUM_DIMENSIONS];
    Searcher trueFinder = new BruteSearch(new EuclideanDistanceMeasure());
    for (Vector trueCluster : syntheticData.getSecond()) {
      trueFinder.add(trueCluster);
    }
    for (Centroid centroid : clusterer) {
      WeightedThing<Vector> closest = trueFinder.search(centroid, 1).get(0);
      cornerWeights[((Centroid)closest.getValue()).getIndex()] += centroid.getWeight();
    }
    int expectedNumPoints = NUM_DATA_POINTS / (1 << NUM_DIMENSIONS);
    for (double v : cornerWeights) {
      System.out.printf("%f ", v);
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.