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

Example 26 with DoubleStatistic

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

the class KMeansCompare method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("k-Means Clustering", "kmeans-clustering");
    }
    // Choose initial means
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
    // Setup cluster assignment store
    List<ModifiableDBIDs> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
    }
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    double[] varsum = new double[k];
    // Cluster distances
    double[][] cdist = new double[k][k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    DoubleStatistic varstat = LOG.isStatistics() ? new DoubleStatistic(this.getClass().getName() + ".variance-sum") : null;
    LongStatistic diststat = LOG.isStatistics() ? new LongStatistic(KEY + ".distance-computations") : null;
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        recomputeSeperation(means, cdist, diststat);
        boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum, cdist, diststat);
        logVarstat(varstat, varsum);
        if (LOG.isStatistics()) {
            LOG.statistics(diststat);
        }
        // Stop if no cluster assignment changed.
        if (!changed) {
            break;
        }
        // Recompute means.
        means = means(clusters, means, relation);
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        DBIDs ids = clusters.get(i);
        if (ids.size() == 0) {
            continue;
        }
        KMeansModel model = new KMeansModel(means[i], varsum[i]);
        result.addToplevelCluster(new Cluster<>(ids, model));
    }
    return result;
}

Example 27 with DoubleStatistic

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

the class KMeansHamerly method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("k-Means Clustering", "kmeans-clustering");
    }
    // Choose initial means
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
    // Setup cluster assignment store
    List<ModifiableDBIDs> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
    }
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    // Hamerly bounds
    WritableDoubleDataStore upper = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, Double.POSITIVE_INFINITY);
    WritableDoubleDataStore lower = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, 0.);
    // Storage for updated means:
    final int dim = means[0].length;
    double[][] sums = new double[k][dim];
    // Separation of means / distance moved.
    double[] sep = new double[k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    LongStatistic rstat = LOG.isStatistics() ? new LongStatistic(KEY + ".reassignments") : null;
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        int changed;
        if (iteration == 0) {
            changed = initialAssignToNearestCluster(relation, means, sums, clusters, assignment, upper, lower);
        } else {
            recomputeSeperation(means, sep);
            changed = assignToNearestCluster(relation, means, sums, clusters, assignment, sep, upper, lower);
        }
        if (rstat != null) {
            rstat.setLong(changed);
            LOG.statistics(rstat);
        }
        // Stop if no cluster assignment changed.
        if (changed == 0) {
            break;
        }
        // Recompute means.
        for (int i = 0; i < k; i++) {
            final int s = clusters.get(i).size();
            timesEquals(sums[i], s > 0 ? 1. / s : 1.);
        }
        double delta = maxMoved(means, sums, sep);
        updateBounds(relation, assignment, upper, lower, sep, delta);
        for (int i = 0; i < k; i++) {
            final int s = clusters.get(i).size();
            System.arraycopy(sums[i], 0, means[i], 0, dim);
            // Restore to sum for next iteration
            timesEquals(sums[i], s > 0 ? s : 1.);
        }
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    upper.destroy();
    lower.destroy();
    // Wrap result
    double totalvariance = 0.;
    Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        DBIDs ids = clusters.get(i);
        if (ids.size() == 0) {
            continue;
        }
        double[] mean = means[i];
        double varsum = 0.;
        if (varstat) {
            DoubleVector mvec = DoubleVector.wrap(mean);
            for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
                varsum += distanceFunction.distance(mvec, relation.get(it));
            }
            totalvariance += varsum;
        }
        KMeansModel model = new KMeansModel(mean, varsum);
        result.addToplevelCluster(new Cluster<>(ids, model));
    }
    if (LOG.isStatistics() && varstat) {
        LOG.statistics(new DoubleStatistic(this.getClass().getName() + ".variance-sum", totalvariance));
    }
    return result;
}

Example 28 with DoubleStatistic

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

the class KMeansLloyd method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("k-Means Clustering", "kmeans-clustering");
    }
    // Choose initial means
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
    // Setup cluster assignment store
    List<ModifiableDBIDs> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        clusters.add(DBIDUtil.newHashSet((int) (relation.size() * 2. / k)));
    }
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    double[] varsum = new double[k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    DoubleStatistic varstat = LOG.isStatistics() ? new DoubleStatistic(this.getClass().getName() + ".variance-sum") : null;
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum);
        logVarstat(varstat, varsum);
        // Stop if no cluster assignment changed.
        if (!changed) {
            break;
        }
        // Recompute means.
        means = means(clusters, means, relation);
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        DBIDs ids = clusters.get(i);
        if (ids.size() == 0) {
            continue;
        }
        KMeansModel model = new KMeansModel(means[i], varsum[i]);
        result.addToplevelCluster(new Cluster<>(ids, model));
    }
    return result;
}

Example 29 with DoubleStatistic

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

the class KMeansMinusMinus method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("k-Means Clustering", "kmeans-clustering");
    }
    // Choose initial means
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    // Intialisieren der means
    double[][] means = initializer.chooseInitialMeans(database, relation, k, getDistanceFunction());
    // initialisieren vom Heap
    final int heapsize = (int) (rate < 1. ? Math.ceil(relation.size() * rate) : rate);
    DoubleMinHeap minHeap = new DoubleMinHeap(heapsize);
    // Setup cluster assignment store
    List<ModifiableDoubleDBIDList> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        clusters.add(DBIDUtil.newDistanceDBIDList((int) (relation.size() * 2. / k)));
    }
    WritableIntegerDataStore assignment = DataStoreUtil.makeIntegerStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, -1);
    double[] varsum = new double[k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    DoubleStatistic varstat = new DoubleStatistic(this.getClass().getName() + ".variance-sum");
    // Otherwise, the vartotal break below will fail!
    assert (varstat != null);
    int iteration = 0;
    double prevvartotal = Double.POSITIVE_INFINITY;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        minHeap.clear();
        for (int i = 0; i < k; i++) {
            clusters.get(i).clear();
        }
        LOG.incrementProcessed(prog);
        boolean changed = assignToNearestCluster(relation, means, clusters, assignment, varsum, minHeap, heapsize);
        double vartotal = logVarstat(varstat, varsum);
        // than the previous value.
        if (!changed || vartotal > prevvartotal) {
            break;
        }
        prevvartotal = vartotal;
        // Recompute means.
        means = meansWithTreshhold(clusters, means, relation, heapsize > 0 ? minHeap.peek() : Double.POSITIVE_INFINITY);
    }
    // create noisecluster if wanted
    ModifiableDoubleDBIDList noiseids = null;
    if (noiseFlag && heapsize > 0) {
        clusters.add(noiseids = DBIDUtil.newDistanceDBIDList((int) (relation.size() * 2. / k)));
        double tresh = minHeap.peek();
        for (int i = 0; i < k; i++) {
            for (DoubleDBIDListMIter it = clusters.get(i).iter(); it.valid(); it.advance()) {
                final double dist = it.doubleValue();
                // Add to the noise cluster:
                if (dist >= tresh) {
                    noiseids.add(dist, it);
                    assignment.putInt(it, k);
                    it.remove();
                }
            }
        }
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<KMeansModel> result = new Clustering<>("k-Means Clustering", "kmeans-clustering");
    for (int i = 0; i < k; i++) {
        DBIDs ids = clusters.get(i);
        if (ids.size() == 0) {
            continue;
        }
        KMeansModel model = new KMeansModel(means[i], varsum[i]);
        result.addToplevelCluster(new Cluster<>(ids, model));
    }
    // Noise Cluster
    if (noiseFlag) {
        KMeansModel model = new KMeansModel(null, 0);
        DBIDs ids = noiseids;
        if (ids.size() == 0) {
            return result;
        }
        result.addToplevelCluster(new Cluster<>(ids, true, model));
    }
    return result;
}

Example 30 with DoubleStatistic

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

the class EvaluateConcordantPairs method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param c Clustering
 * @return Gamma index
 */
public double evaluateClustering(Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    int ignorednoise = 0, withinPairs = 0;
    for (Cluster<?> cluster : clusters) {
        if ((cluster.size() <= 1 || cluster.isNoise())) {
            switch(noiseHandling) {
                case IGNORE_NOISE:
                    ignorednoise += cluster.size();
                    continue;
                case TREAT_NOISE_AS_SINGLETONS:
                    // No concordant distances.
                    continue;
                case MERGE_NOISE:
                    // Treat like a cluster below.
                    break;
            }
        }
        withinPairs += (cluster.size() * (cluster.size() - 1)) >>> 1;
        if (withinPairs < 0) {
            throw new AbortException("Integer overflow - clusters too large to compute pairwise distances.");
        }
    }
    // Materialize within-cluster distances (sorted):
    double[] withinDistances = computeWithinDistances(rel, clusters, withinPairs);
    int[] withinTies = new int[withinDistances.length];
    // Count ties within
    countTies(withinDistances, withinTies);
    long concordantPairs = 0, discordantPairs = 0, betweenPairs = 0;
    // Step two, compute discordant distances:
    for (int i = 0; i < clusters.size(); i++) {
        Cluster<?> ocluster1 = clusters.get(i);
        if (// 
        (ocluster1.size() <= 1 || ocluster1.isNoise()) && noiseHandling.equals(NoiseHandling.IGNORE_NOISE)) {
            continue;
        }
        for (int j = i + 1; j < clusters.size(); j++) {
            Cluster<?> ocluster2 = clusters.get(j);
            if (// 
            (ocluster2.size() <= 1 || ocluster2.isNoise()) && noiseHandling.equals(NoiseHandling.IGNORE_NOISE)) {
                continue;
            }
            betweenPairs += ocluster1.size() * ocluster2.size();
            for (DBIDIter oit1 = ocluster1.getIDs().iter(); oit1.valid(); oit1.advance()) {
                NumberVector obj = rel.get(oit1);
                for (DBIDIter oit2 = ocluster2.getIDs().iter(); oit2.valid(); oit2.advance()) {
                    double dist = distanceFunction.distance(obj, rel.get(oit2));
                    int p = Arrays.binarySearch(withinDistances, dist);
                    if (p >= 0) {
                        // Tied distances:
                        while (p > 0 && withinDistances[p - 1] >= dist) {
                            --p;
                        }
                        concordantPairs += p;
                        discordantPairs += withinDistances.length - p - withinTies[p];
                        continue;
                    }
                    p = -p - 1;
                    concordantPairs += p;
                    discordantPairs += withinDistances.length - p;
                }
            }
        }
    }
    // Total number of pairs possible:
    final long t = ((rel.size() - ignorednoise) * (long) (rel.size() - ignorednoise - 1)) >>> 1;
    final long tt = (t * (t - 1)) >>> 1;
    double gamma = (concordantPairs - discordantPairs) / (double) (concordantPairs + discordantPairs);
    double tau = computeTau(concordantPairs, discordantPairs, tt, withinDistances.length, betweenPairs);
    // Avoid NaN when everything is in a single cluster:
    gamma = gamma > 0. ? gamma : 0.;
    tau = tau > 0. ? tau : 0.;
    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 + ".gamma", gamma));
        LOG.statistics(new DoubleStatistic(key + ".tau", tau));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Concordance-based Evaluation");
    g.addMeasure("Gamma", gamma, -1., 1., 0., false);
    g.addMeasure("Tau", tau, -1., +1., 0., false);
    db.getHierarchy().resultChanged(ev);
    return gamma;
}