Examples with DoubleStatistic de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic used on opensource projects

Example 31 with DoubleStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic in project elki by elki-project.

the class EvaluateDaviesBouldin method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param c Clustering
 * @return DB-index
 */
public double evaluateClustering(Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    NumberVector[] centroids = new NumberVector[clusters.size()];
    int noisecount = EvaluateSimplifiedSilhouette.centroids(rel, clusters, centroids, noiseOption);
    double[] withinGroupDistance = withinGroupDistances(rel, clusters, centroids);
    Mean daviesBouldin = new Mean();
    for (int i = 0; i < clusters.size(); i++) {
        final NumberVector centroid = centroids[i];
        final double withinGroupDistancei = withinGroupDistance[i];
        // maximum within-to-between cluster spread
        double max = 0;
        for (int j = 0; j < clusters.size(); j++) {
            NumberVector ocentroid = centroids[j];
            if (ocentroid == centroid) {
                continue;
            }
            // Both are real clusters:
            if (centroid != null && ocentroid != null) {
                // bD = between group distance
                double bD = distanceFunction.distance(centroid, ocentroid);
                // d = within-to-between cluster spread
                double d = (withinGroupDistancei + withinGroupDistance[j]) / bD;
                max = d > max ? d : max;
            } else if (noiseOption != NoiseHandling.IGNORE_NOISE) {
                if (centroid != null) {
                    double d = Double.POSITIVE_INFINITY;
                    // Find the closest element
                    for (DBIDIter it = clusters.get(j).getIDs().iter(); it.valid(); it.advance()) {
                        double d2 = distanceFunction.distance(centroid, rel.get(it));
                        d = d2 < d ? d2 : d;
                    }
                    d = withinGroupDistancei / d;
                    max = d > max ? d : max;
                } else if (ocentroid != null) {
                    double d = Double.POSITIVE_INFINITY;
                    // Find the closest element
                    for (DBIDIter it = clusters.get(i).getIDs().iter(); it.valid(); it.advance()) {
                        double d2 = distanceFunction.distance(rel.get(it), ocentroid);
                        d = d2 < d ? d2 : d;
                    }
                    d = withinGroupDistance[j] / d;
                    max = d > max ? d : max;
                }
            // else: (0+0) / d = 0.
            }
        }
        daviesBouldin.put(max);
    }
    // For a single cluster, we return 2 (result for equidistant points)
    final double daviesBouldinMean = daviesBouldin.getCount() > 1 ? daviesBouldin.getMean() : 2.;
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(key + ".db-index.noise-handling", noiseOption.toString()));
        if (noisecount > 0) {
            LOG.statistics(new LongStatistic(key + ".db-index.ignored", noisecount));
        }
        LOG.statistics(new DoubleStatistic(key + ".db-index", daviesBouldinMean));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
    g.addMeasure("Davies Bouldin Index", daviesBouldinMean, 0., Double.POSITIVE_INFINITY, 0., true);
    db.getHierarchy().resultChanged(ev);
    return daviesBouldinMean;
}

Example 32 with DoubleStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic in project elki by elki-project.

the class EvaluateCIndex method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param c Clustering
 * @return C-Index
 */
public double evaluateClustering(Database db, Relation<? extends O> rel, DistanceQuery<O> dq, Clustering<?> c) {
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    // Count ignored noise, and within-cluster distances
    int ignorednoise = 0, w = 0;
    for (Cluster<?> cluster : clusters) {
        if (cluster.size() <= 1 || cluster.isNoise()) {
            switch(noiseOption) {
                case IGNORE_NOISE:
                    ignorednoise += cluster.size();
                    // Ignore
                    continue;
                case TREAT_NOISE_AS_SINGLETONS:
                    // No within-cluster distances!
                    continue;
                case MERGE_NOISE:
                    // Treat like a cluster
                    break;
                default:
                    LOG.warning("Unknown noise handling option: " + noiseOption);
            }
        }
        w += (cluster.size() * (cluster.size() - 1)) >>> 1;
    }
    // TODO: for small k=2, and balanced clusters, it may be more efficient to
    // just build a long array with all distances, and select the quantiles.
    // The heaps used below pay off in memory consumption for k > 2
    // Yes, maxDists is supposed to be a min heap, and the other way.
    // Because we want to replace the smallest of the current k-largest
    // distances.
    DoubleHeap maxDists = new DoubleMinHeap(w);
    DoubleHeap minDists = new DoubleMaxHeap(w);
    // Sum of within-cluster distances
    double theta = 0.;
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Processing clusters for C-Index", clusters.size(), LOG) : null;
    for (int i = 0; i < clusters.size(); i++) {
        Cluster<?> cluster = clusters.get(i);
        if (cluster.size() <= 1 || cluster.isNoise()) {
            switch(noiseOption) {
                case IGNORE_NOISE:
                    LOG.incrementProcessed(prog);
                    // Ignore
                    continue;
                case TREAT_NOISE_AS_SINGLETONS:
                    processSingleton(cluster, rel, dq, maxDists, minDists, w);
                    LOG.incrementProcessed(prog);
                    continue;
                case MERGE_NOISE:
                    // Treat like a cluster, below
                    break;
            }
        }
        theta += processCluster(cluster, clusters, i, dq, maxDists, minDists, w);
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    // Simulate best and worst cases:
    // Sum of largest and smallest
    double min = 0, max = 0;
    assert (minDists.size() == w);
    assert (maxDists.size() == w);
    for (DoubleHeap.UnsortedIter it = minDists.unsortedIter(); it.valid(); it.advance()) {
        min += it.get();
    }
    for (DoubleHeap.UnsortedIter it = maxDists.unsortedIter(); it.valid(); it.advance()) {
        max += it.get();
    }
    assert (max >= min);
    double cIndex = (max > min) ? (theta - min) / (max - min) : 1.;
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(key + ".c-index.noise-handling", noiseOption.toString()));
        if (ignorednoise > 0) {
            LOG.statistics(new LongStatistic(key + ".c-index.ignored", ignorednoise));
        }
        LOG.statistics(new DoubleStatistic(key + ".c-index", cIndex));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
    g.addMeasure("C-Index", cIndex, 0., 1., 0., true);
    db.getHierarchy().resultChanged(ev);
    return cIndex;
}

Example 33 with DoubleStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic in project elki by elki-project.

the class EvaluatePBMIndex method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param c Clustering
 * @return PBM
 */
public double evaluateClustering(Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    NumberVector[] centroids = new NumberVector[clusters.size()];
    int ignorednoise = EvaluateSimplifiedSilhouette.centroids(rel, clusters, centroids, noiseHandling);
    // Build global centroid and cluster count:
    final int dim = RelationUtil.dimensionality(rel);
    Centroid overallCentroid = new Centroid(dim);
    EvaluateVarianceRatioCriteria.globalCentroid(overallCentroid, rel, clusters, centroids, noiseHandling);
    // Maximum distance between centroids:
    double max = 0;
    for (int i = 0; i < centroids.length; i++) {
        if (centroids[i] == null && noiseHandling != NoiseHandling.TREAT_NOISE_AS_SINGLETONS) {
            continue;
        }
        for (int j = i + 1; j < centroids.length; j++) {
            if (centroids[j] == null && noiseHandling != NoiseHandling.TREAT_NOISE_AS_SINGLETONS) {
                continue;
            }
            if (centroids[i] == null && centroids[j] == null) {
                // Need to compute pairwise distances of noise clusters.
                for (DBIDIter iti = clusters.get(i).getIDs().iter(); iti.valid(); iti.advance()) {
                    for (DBIDIter itj = clusters.get(j).getIDs().iter(); itj.valid(); itj.advance()) {
                        double dist = distanceFunction.distance(rel.get(iti), rel.get(itj));
                        max = dist > max ? dist : max;
                    }
                }
            } else if (centroids[i] == null) {
                for (DBIDIter iti = clusters.get(i).getIDs().iter(); iti.valid(); iti.advance()) {
                    double dist = distanceFunction.distance(rel.get(iti), centroids[j]);
                    max = dist > max ? dist : max;
                }
            } else if (centroids[j] == null) {
                for (DBIDIter itj = clusters.get(j).getIDs().iter(); itj.valid(); itj.advance()) {
                    double dist = distanceFunction.distance(centroids[i], rel.get(itj));
                    max = dist > max ? dist : max;
                }
            } else {
                double dist = distanceFunction.distance(centroids[i], centroids[j]);
                max = dist > max ? dist : max;
            }
        }
    }
    // a: Distance to own centroid
    // b: Distance to overall centroid
    double a = 0, b = 0;
    Iterator<? extends Cluster<?>> ci = clusters.iterator();
    for (int i = 0; ci.hasNext(); i++) {
        Cluster<?> cluster = ci.next();
        if (cluster.size() <= 1 || cluster.isNoise()) {
            switch(noiseHandling) {
                case IGNORE_NOISE:
                    // Ignored
                    continue;
                case TREAT_NOISE_AS_SINGLETONS:
                    // Singletons: a = 0 by definition.
                    for (DBIDIter it = cluster.getIDs().iter(); it.valid(); it.advance()) {
                        b += SquaredEuclideanDistanceFunction.STATIC.distance(overallCentroid, rel.get(it));
                    }
                    // with NEXT cluster.
                    continue;
                case MERGE_NOISE:
                    // Treat like a cluster below:
                    break;
            }
        }
        for (DBIDIter it = cluster.getIDs().iter(); it.valid(); it.advance()) {
            NumberVector obj = rel.get(it);
            a += distanceFunction.distance(centroids[i], obj);
            b += distanceFunction.distance(overallCentroid, obj);
        }
    }
    final double pbm = FastMath.pow((1. / centroids.length) * (b / a) * max, 2.);
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(key + ".pbm.noise-handling", noiseHandling.toString()));
        if (ignorednoise > 0) {
            LOG.statistics(new LongStatistic(key + ".pbm.ignored", ignorednoise));
        }
        LOG.statistics(new DoubleStatistic(key + ".pbm", pbm));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
    g.addMeasure("PBM-Index", pbm, 0., Double.POSITIVE_INFINITY, 0., false);
    db.getHierarchy().resultChanged(ev);
    return pbm;
}

Example 34 with DoubleStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic in project elki by elki-project.

the class EvaluateSilhouette method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param dq Distance query
 * @param c Clustering
 * @return Average silhouette
 */
public double evaluateClustering(Database db, Relation<O> rel, DistanceQuery<O> dq, Clustering<?> c) {
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    MeanVariance msil = new MeanVariance();
    int ignorednoise = 0;
    for (Cluster<?> cluster : clusters) {
        // Note: we treat 1-element clusters the same as noise.
        if (cluster.size() <= 1 || cluster.isNoise()) {
            switch(noiseOption) {
                case IGNORE_NOISE:
                    ignorednoise += cluster.size();
                    // Ignore noise elements
                    continue;
                case TREAT_NOISE_AS_SINGLETONS:
                    // As suggested in Rousseeuw, we use 0 for singletons.
                    msil.put(0., cluster.size());
                    continue;
                case MERGE_NOISE:
                    // Treat as cluster below
                    break;
            }
        }
        ArrayDBIDs ids = DBIDUtil.ensureArray(cluster.getIDs());
        // temporary storage.
        double[] as = new double[ids.size()];
        DBIDArrayIter it1 = ids.iter(), it2 = ids.iter();
        for (it1.seek(0); it1.valid(); it1.advance()) {
            // a: In-cluster distances
            // Already computed distances
            double a = as[it1.getOffset()];
            for (it2.seek(it1.getOffset() + 1); it2.valid(); it2.advance()) {
                final double dist = dq.distance(it1, it2);
                a += dist;
                as[it2.getOffset()] += dist;
            }
            a /= (ids.size() - 1);
            // b: minimum average distance to other clusters:
            double b = Double.POSITIVE_INFINITY;
            for (Cluster<?> ocluster : clusters) {
                if (ocluster == /* yes, reference identity */
                cluster) {
                    // Same cluster
                    continue;
                }
                if (ocluster.size() <= 1 || ocluster.isNoise()) {
                    switch(noiseOption) {
                        case IGNORE_NOISE:
                            // Ignore noise elements
                            continue;
                        case TREAT_NOISE_AS_SINGLETONS:
                            // Treat noise cluster as singletons:
                            for (DBIDIter it3 = ocluster.getIDs().iter(); it3.valid(); it3.advance()) {
                                final double dist = dq.distance(it1, it3);
                                // Minimum average
                                b = dist < b ? dist : b;
                            }
                            continue;
                        case MERGE_NOISE:
                            // Treat as cluster below
                            break;
                    }
                }
                final DBIDs oids = ocluster.getIDs();
                double btmp = 0.;
                for (DBIDIter it3 = oids.iter(); it3.valid(); it3.advance()) {
                    btmp += dq.distance(it1, it3);
                }
                // Average
                btmp /= oids.size();
                // Minimum average
                b = btmp < b ? btmp : b;
            }
            // One cluster only?
            b = b < Double.POSITIVE_INFINITY ? b : a;
            msil.put((b - a) / (b > a ? b : a));
        }
    }
    double penalty = 1.;
    // Only if {@link NoiseHandling#IGNORE_NOISE}:
    if (penalize && ignorednoise > 0) {
        penalty = (rel.size() - ignorednoise) / (double) rel.size();
    }
    final double meansil = penalty * msil.getMean();
    final double stdsil = penalty * msil.getSampleStddev();
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(key + ".silhouette.noise-handling", noiseOption.toString()));
        if (ignorednoise > 0) {
            LOG.statistics(new LongStatistic(key + ".silhouette.noise", ignorednoise));
        }
        LOG.statistics(new DoubleStatistic(key + ".silhouette.mean", meansil));
        LOG.statistics(new DoubleStatistic(key + ".silhouette.stddev", stdsil));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
    g.addMeasure("Silhouette +-" + FormatUtil.NF2.format(stdsil), meansil, -1., 1., 0., false);
    db.getHierarchy().resultChanged(ev);
    return meansil;
}

Example 35 with DoubleStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic in project elki by elki-project.

the class EvaluateSimplifiedSilhouette method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param c Clustering
 * @return Mean simplified silhouette
 */
public double evaluateClustering(Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    NumberVector[] centroids = new NumberVector[clusters.size()];
    int ignorednoise = centroids(rel, clusters, centroids, noiseOption);
    MeanVariance mssil = new MeanVariance();
    Iterator<? extends Cluster<?>> ci = clusters.iterator();
    for (int i = 0; ci.hasNext(); i++) {
        Cluster<?> cluster = ci.next();
        if (cluster.size() <= 1) {
            // As suggested in Rousseeuw, we use 0 for singletons.
            mssil.put(0., cluster.size());
            continue;
        }
        if (cluster.isNoise()) {
            switch(noiseOption) {
                case IGNORE_NOISE:
                    // Ignore elements
                    continue;
                case TREAT_NOISE_AS_SINGLETONS:
                    // As suggested in Rousseeuw, we use 0 for singletons.
                    mssil.put(0., cluster.size());
                    continue;
                case MERGE_NOISE:
                    // Treat as cluster below
                    break;
            }
        }
        // Cluster center:
        final NumberVector center = centroids[i];
        assert (center != null);
        for (DBIDIter it = cluster.getIDs().iter(); it.valid(); it.advance()) {
            NumberVector obj = rel.get(it);
            // a: Distance to own centroid
            double a = distance.distance(center, obj);
            // b: Distance to other clusters centroids:
            double min = Double.POSITIVE_INFINITY;
            Iterator<? extends Cluster<?>> cj = clusters.iterator();
            for (int j = 0; cj.hasNext(); j++) {
                Cluster<?> ocluster = cj.next();
                if (i == j) {
                    continue;
                }
                NumberVector other = centroids[j];
                if (other == null) {
                    // Noise!
                    switch(noiseOption) {
                        case IGNORE_NOISE:
                            continue;
                        case TREAT_NOISE_AS_SINGLETONS:
                            // Treat each object like a centroid!
                            for (DBIDIter it2 = ocluster.getIDs().iter(); it2.valid(); it2.advance()) {
                                double dist = distance.distance(rel.get(it2), obj);
                                min = dist < min ? dist : min;
                            }
                            continue;
                        case MERGE_NOISE:
                            // Treat as cluster below, but should not be reachable.
                            break;
                    }
                }
                // Clusters: use centroid.
                double dist = distance.distance(other, obj);
                min = dist < min ? dist : min;
            }
            // One 'real' cluster only?
            min = min < Double.POSITIVE_INFINITY ? min : a;
            mssil.put((min - a) / (min > a ? min : a));
        }
    }
    double penalty = 1.;
    // Only if {@link NoiseHandling#IGNORE_NOISE}:
    if (penalize && ignorednoise > 0) {
        penalty = (rel.size() - ignorednoise) / (double) rel.size();
    }
    final double meanssil = penalty * mssil.getMean();
    final double stdssil = penalty * mssil.getSampleStddev();
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(key + ".simplified-silhouette.noise-handling", noiseOption.toString()));
        if (ignorednoise > 0) {
            LOG.statistics(new LongStatistic(key + ".simplified-silhouette.ignored", ignorednoise));
        }
        LOG.statistics(new DoubleStatistic(key + ".simplified-silhouette.mean", meanssil));
        LOG.statistics(new DoubleStatistic(key + ".simplified-silhouette.stddev", stdssil));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
    g.addMeasure("Simp. Silhouette +-" + FormatUtil.NF2.format(stdssil), meanssil, -1., 1., 0., false);
    db.getHierarchy().resultChanged(ev);
    return meanssil;
}