List of usage examples for org.apache.commons.math.stat.clustering Cluster getCenter
public T getCenter()
From source file:org.basketball.MyKMeansPlusPlusClusterer.java
/** * Runs the K-means++ clustering algorithm. * * @param points the points to cluster//from w w w .ja va 2 s .c o m * @param k the number of clusters to split the data into * @param maxIterations the maximum number of iterations to run the algorithm * for. If negative, no maximum will be used * @return a list of clusters containing the points */ public List<Cluster<T>> cluster(final Collection<T> points, final int k, final int maxIterations) { // create the initial clusters List<Cluster<T>> clusters = chooseInitialCenters(points, k, random); assignPointsToClusters(clusters, points); // iterate through updating the centers until we're done final int max = (maxIterations < 0) ? Integer.MAX_VALUE : maxIterations; for (int count = 0; count < max; count++) { boolean clusteringChanged = false; List<Cluster<T>> newClusters = new ArrayList<Cluster<T>>(); for (final Cluster<T> cluster : clusters) { final T newCenter; if (cluster.getPoints().isEmpty()) { switch (emptyStrategy) { case LARGEST_VARIANCE: newCenter = getPointFromLargestVarianceCluster(clusters); break; case LARGEST_POINTS_NUMBER: newCenter = getPointFromLargestNumberCluster(clusters); break; case FARTHEST_POINT: newCenter = getFarthestPoint(clusters); break; case IGNORE: continue; default: throw new ConvergenceException(LocalizedFormats.EMPTY_CLUSTER_IN_K_MEANS); } clusteringChanged = true; } else { newCenter = cluster.getCenter().centroidOf(cluster.getPoints()); if (!newCenter.equals(cluster.getCenter())) { clusteringChanged = true; } } newClusters.add(new Cluster<T>(newCenter)); } if (!clusteringChanged) { return clusters; } assignPointsToClusters(newClusters, points); clusters = newClusters; } return clusters; }
From source file:org.basketball.MyKMeansPlusPlusClusterer.java
/** * Use K-means++ to choose the initial centers. * * @param <T> type of the points to cluster * @param points the points to choose the initial centers from * @param k the number of centers to choose * @param random random generator to use * @return the initial centers//from ww w . ja v a2 s . com */ private static <T extends Clusterable<T>> List<Cluster<T>> chooseInitialCenters(final Collection<T> points, final int k, final Random random) { final List<T> pointSet = new ArrayList<T>(points); final List<Cluster<T>> resultSet = new ArrayList<Cluster<T>>(); // Choose one center uniformly at random from among the data points. final T firstPoint = pointSet.remove(random.nextInt(pointSet.size())); resultSet.add(new Cluster<T>(firstPoint)); final double[] dx2 = new double[pointSet.size()]; while (resultSet.size() < k) { // For each data point x, compute D(x), the distance between x and // the nearest center that has already been chosen. int sum = 0; for (int i = 0; i < pointSet.size(); i++) { final T p = pointSet.get(i); final Cluster<T> nearest = getNearestCluster(resultSet, p); final double d = p.distanceFrom(nearest.getCenter()); sum += d * d; dx2[i] = sum; } // Add one new data point as a center. Each point x is chosen with // probability proportional to D(x)2 final double r = random.nextDouble() * sum; for (int i = 0; i < dx2.length; i++) { if (dx2[i] >= r) { final T p = pointSet.remove(i); resultSet.add(new Cluster<T>(p)); break; } } } return resultSet; }
From source file:org.basketball.MyKMeansPlusPlusClusterer.java
/** * Get a random point from the {@link Cluster} with the largest distance variance. * * @param clusters the {@link Cluster}s to search * @return a random point from the selected cluster *///w ww . j a va2 s.c om private T getPointFromLargestVarianceCluster(final Collection<Cluster<T>> clusters) { double maxVariance = Double.NEGATIVE_INFINITY; Cluster<T> selected = null; for (final Cluster<T> cluster : clusters) { if (!cluster.getPoints().isEmpty()) { // compute the distance variance of the current cluster final T center = cluster.getCenter(); final Variance stat = new Variance(); for (final T point : cluster.getPoints()) { stat.increment(point.distanceFrom(center)); } final double variance = stat.getResult(); // select the cluster with the largest variance if (variance > maxVariance) { maxVariance = variance; selected = cluster; } } } // did we find at least one non-empty cluster ? if (selected == null) { throw new ConvergenceException(LocalizedFormats.EMPTY_CLUSTER_IN_K_MEANS); } // extract a random point from the cluster final List<T> selectedPoints = selected.getPoints(); return selectedPoints.remove(random.nextInt(selectedPoints.size())); }
From source file:org.basketball.MyKMeansPlusPlusClusterer.java
/** * Get the point farthest to its cluster center * * @param clusters the {@link Cluster}s to search * @return point farthest to its cluster center *///from ww w .j a v a 2 s . c o m private T getFarthestPoint(final Collection<Cluster<T>> clusters) { double maxDistance = Double.NEGATIVE_INFINITY; Cluster<T> selectedCluster = null; int selectedPoint = -1; for (final Cluster<T> cluster : clusters) { // get the farthest point final T center = cluster.getCenter(); final List<T> points = cluster.getPoints(); for (int i = 0; i < points.size(); ++i) { final double distance = points.get(i).distanceFrom(center); if (distance > maxDistance) { maxDistance = distance; selectedCluster = cluster; selectedPoint = i; } } } // did we find at least one non-empty cluster ? if (selectedCluster == null) { throw new ConvergenceException(LocalizedFormats.EMPTY_CLUSTER_IN_K_MEANS); } return selectedCluster.getPoints().remove(selectedPoint); }
From source file:org.basketball.MyKMeansPlusPlusClusterer.java
/** * Returns the nearest {@link Cluster} to the given point * * @param <T> type of the points to cluster * @param clusters the {@link Cluster}s to search * @param point the point to find the nearest {@link Cluster} for * @return the nearest {@link Cluster} to the given point *//*from w ww .ja v a 2s .c o m*/ private static <T extends Clusterable<T>> Cluster<T> getNearestCluster(final Collection<Cluster<T>> clusters, final T point) { double minDistance = Double.MAX_VALUE; Cluster<T> minCluster = null; for (final Cluster<T> c : clusters) { final double distance = point.distanceFrom(c.getCenter()); if (distance < minDistance) { minDistance = distance; minCluster = c; } } return minCluster; }
From source file:playground.christoph.evacuation.analysis.EvacuationTimeClusterer.java
Map<BasicLocation, List<Double>> buildCluster(int numClusters, int iterations) { createCostMap();// www.java 2 s. c o m KMeansPlusPlusClusterer<ClusterableLocation> clusterer = new KMeansPlusPlusClusterer<ClusterableLocation>( MatsimRandom.getLocalInstance()); List<ClusterableLocation> points = getClusterableLocations(); buildQuadTree(points); log.info("do clustering..."); List<Cluster<ClusterableLocation>> list = clusterer.cluster(points, numClusters, iterations); Map<BasicLocation, List<Double>> map = new HashMap<BasicLocation, List<Double>>(); for (Cluster<ClusterableLocation> cluster : list) { BasicLocation center = cluster.getCenter().getBasicLocation(); List<Double> evacuationTimes = new ArrayList<Double>(); for (ClusterableLocation location : cluster.getPoints()) { List<Double> pointTravelTimes = locationMap.get(location.getBasicLocation()); evacuationTimes.addAll(pointTravelTimes); } map.put(center, evacuationTimes); } log.info("done."); return map; }