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

Package org.apache.mahout.math.neighborhood

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

org.apache.mahout.math.neighborhood.Searcher
Describes how to search a bunch of vectors. The vectors can be of any type (weighted, sparse, ...) but only the values of the vector matter when searching (weights, indices, ...) will not. When iterating through a Searcher, the Vectors added to it are returned.

   * @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

        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

        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

   * @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

        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

        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

   * @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

TOP

Related Classes of org.apache.mahout.math.neighborhood.Searcher

org.apache.mahout.clustering.ClusteringUtils

org.apache.mahout.clustering.streaming.cluster.BallKMeansTest

org.apache.mahout.clustering.streaming.cluster.StreamingKMeansTest

org.apache.mahout.math.WeightedVector

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.