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

Example 1 with StringStatistic

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

the class EvaluateVarianceRatioCriteria method evaluateClustering.

/**
 * Evaluate a single clustering.
 *
 * @param db Database
 * @param rel Data relation
 * @param c Clustering
 * @return Variance Ratio Criteria
 */
public double evaluateClustering(Database db, Relation<? extends NumberVector> rel, Clustering<?> c) {
    // FIXME: allow using a precomputed distance matrix!
    final SquaredEuclideanDistanceFunction df = SquaredEuclideanDistanceFunction.STATIC;
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    double vrc = 0.;
    int ignorednoise = 0;
    if (clusters.size() > 1) {
        NumberVector[] centroids = new NumberVector[clusters.size()];
        ignorednoise = EvaluateSimplifiedSilhouette.centroids(rel, clusters, centroids, noiseOption);
        // Build global centroid and cluster count:
        final int dim = RelationUtil.dimensionality(rel);
        Centroid overallCentroid = new Centroid(dim);
        int clustercount = globalCentroid(overallCentroid, rel, clusters, centroids, noiseOption);
        // 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(noiseOption) {
                    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 += df.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 vec = rel.get(it);
                a += df.distance(centroids[i], vec);
                b += df.distance(overallCentroid, vec);
            }
        }
        vrc = ((b - a) / a) * ((rel.size() - clustercount) / (clustercount - 1.));
        // Only if {@link NoiseHandling#IGNORE_NOISE}:
        if (penalize && ignorednoise > 0) {
            vrc *= (rel.size() - ignorednoise) / (double) rel.size();
        }
    }
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(key + ".vrc.noise-handling", noiseOption.toString()));
        if (ignorednoise > 0) {
            LOG.statistics(new LongStatistic(key + ".vrc.ignored", ignorednoise));
        }
        LOG.statistics(new DoubleStatistic(key + ".vrc", vrc));
    }
    EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), c, "Internal Clustering Evaluation", "internal evaluation");
    MeasurementGroup g = ev.findOrCreateGroup("Distance-based Evaluation");
    g.addMeasure("Variance Ratio Criteria", vrc, 0., 1., 0., false);
    return vrc;
}

Example 2 with StringStatistic

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

the class XMeans method run.

/**
 * Run the algorithm on a database and relation.
 *
 * @param database Database to process
 * @param relation Data relation
 * @return Clustering result.
 */
@Override
public Clustering<M> run(Database database, Relation<V> relation) {
    MutableProgress prog = LOG.isVerbose() ? new MutableProgress("X-means number of clusters", k_max, LOG) : null;
    // Run initial k-means to find at least k_min clusters
    innerKMeans.setK(k_min);
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    splitInitializer.setInitialMeans(initializer.chooseInitialMeans(database, relation, k_min, getDistanceFunction()));
    Clustering<M> clustering = innerKMeans.run(database, relation);
    if (prog != null) {
        prog.setProcessed(k_min, LOG);
    }
    ArrayList<Cluster<M>> clusters = new ArrayList<>(clustering.getAllClusters());
    while (clusters.size() <= k_max) {
        // Improve-Structure:
        ArrayList<Cluster<M>> nextClusters = new ArrayList<>();
        for (Cluster<M> cluster : clusters) {
            // Try to split this cluster:
            List<Cluster<M>> childClusterList = splitCluster(cluster, database, relation);
            nextClusters.addAll(childClusterList);
            if (childClusterList.size() > 1) {
                k += childClusterList.size() - 1;
                if (prog != null) {
                    if (k >= k_max) {
                        prog.setTotal(k + 1);
                    }
                    prog.setProcessed(k, LOG);
                }
            }
        }
        if (clusters.size() == nextClusters.size()) {
            break;
        }
        // Improve-Params:
        splitInitializer.setInitialClusters(nextClusters);
        innerKMeans.setK(nextClusters.size());
        clustering = innerKMeans.run(database, relation);
        clusters.clear();
        clusters.addAll(clustering.getAllClusters());
    }
    // Ensure that the progress bar finished.
    if (prog != null) {
        prog.setTotal(k);
        prog.setProcessed(k, LOG);
    }
    if (LOG.isDebugging()) {
        LOG.debug("X-means returned k=" + k + " clusters.");
    }
    // add all current clusters to the result
    Clustering<M> result = new Clustering<>("X-Means Result", "X-Means", clusters);
    return result;
}

Example 3 with StringStatistic

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

the class KMedoidsEM method run.

/**
 * Run k-medoids
 *
 * @param database Database
 * @param relation relation to use
 * @return result
 */
public Clustering<MedoidModel> run(Database database, Relation<V> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("k-Medoids Clustering", "kmedoids-clustering");
    }
    DistanceQuery<V> distQ = null;
    // Only enforce a distance matrix for PAM initialization, which is slow.
    if (initializer instanceof PAMInitialMeans) {
        distQ = DatabaseUtil.precomputedDistanceQuery(database, relation, getDistanceFunction(), LOG);
    } else {
        distQ = database.getDistanceQuery(relation, getDistanceFunction());
    }
    // Choose initial medoids
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    ArrayModifiableDBIDs medoids = DBIDUtil.newArray(initializer.chooseInitialMedoids(k, relation.getDBIDs(), distQ));
    DBIDArrayMIter miter = medoids.iter();
    double[] mdists = new double[k];
    // Setup cluster assignment store
    List<ModifiableDBIDs> clusters = new ArrayList<>();
    for (int i = 0; i < k; i++) {
        HashSetModifiableDBIDs set = DBIDUtil.newHashSet(relation.size() / k);
        // Add medoids.
        set.add(miter.seek(i));
        clusters.add(set);
    }
    // Initial assignment to nearest medoids
    // TODO: reuse this information, from the build phase, when possible?
    double tc = assignToNearestCluster(miter, mdists, clusters, distQ);
    if (LOG.isStatistics()) {
        LOG.statistics(new DoubleStatistic(KEY + ".iteration-" + 0 + ".cost", tc));
    }
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Medoids EM iteration", LOG) : null;
    // Swap phase
    int iteration = 0;
    DBIDVar best = DBIDUtil.newVar();
    while (true) {
        boolean changed = false;
        // Try to swap the medoid with a better cluster member:
        int i = 0;
        for (miter.seek(0); miter.valid(); miter.advance(), i++) {
            best.unset();
            double bestm = mdists[i];
            for (DBIDIter iter = clusters.get(i).iter(); iter.valid(); iter.advance()) {
                if (DBIDUtil.equal(miter, iter)) {
                    continue;
                }
                double sum = 0;
                for (DBIDIter iter2 = clusters.get(i).iter(); iter2.valid(); iter2.advance()) {
                    sum += distQ.distance(iter, iter2);
                }
                if (sum < bestm) {
                    best.set(iter);
                    bestm = sum;
                }
            }
            if (best.isSet() && !DBIDUtil.equal(miter, best)) {
                changed = true;
                assert (clusters.get(i).contains(best));
                medoids.set(i, best);
                mdists[i] = bestm;
            }
        }
        // Reassign
        if (!changed) {
            break;
        }
        double nc = assignToNearestCluster(miter, mdists, clusters, distQ);
        ++iteration;
        if (LOG.isStatistics()) {
            LOG.statistics(new DoubleStatistic(KEY + ".iteration-" + iteration + ".cost", nc));
        }
        LOG.incrementProcessed(prog);
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<MedoidModel> result = new Clustering<>("k-Medoids Clustering", "kmedoids-clustering");
    for (DBIDArrayIter it = medoids.iter(); it.valid(); it.advance()) {
        result.addToplevelCluster(new Cluster<>(clusters.get(it.getOffset()), new MedoidModel(DBIDUtil.deref(it))));
    }
    return result;
}

Example 4 with StringStatistic

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

the class KMeansBatchedLloyd method run.

@Override
public Clustering<KMeansModel> run(Database database, Relation<V> relation) {
    final int dim = RelationUtil.dimensionality(relation);
    // Choose initial means
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initializer", 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);
    ArrayDBIDs[] parts = DBIDUtil.randomSplit(relation.getDBIDs(), blocks, random);
    double[][] meanshift = new double[k][dim];
    int[] changesize = new int[k];
    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 = false;
        FiniteProgress pprog = LOG.isVerbose() ? new FiniteProgress("Batch", parts.length, LOG) : null;
        for (int p = 0; p < parts.length; p++) {
            // Initialize new means scratch space.
            for (int i = 0; i < k; i++) {
                Arrays.fill(meanshift[i], 0.);
            }
            Arrays.fill(changesize, 0);
            Arrays.fill(varsum, 0.);
            changed |= assignToNearestCluster(relation, parts[p], means, meanshift, changesize, clusters, assignment, varsum);
            // Recompute means.
            updateMeans(means, meanshift, clusters, changesize);
            LOG.incrementProcessed(pprog);
        }
        LOG.ensureCompleted(pprog);
        logVarstat(varstat, varsum);
        // Stop if no cluster assignment changed.
        if (!changed) {
            break;
        }
    }
    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 5 with StringStatistic

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

the class KMediansLloyd method run.

@Override
public Clustering<MeanModel> run(Database database, Relation<V> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("k-Medians Clustering", "kmedians-clustering");
    }
    // Choose initial medians
    if (LOG.isStatistics()) {
        LOG.statistics(new StringStatistic(KEY + ".initialization", initializer.toString()));
    }
    double[][] medians = 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[] distsum = new double[k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Medians iteration", LOG) : null;
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        boolean changed = assignToNearestCluster(relation, medians, clusters, assignment, distsum);
        // Stop if no cluster assignment changed.
        if (!changed) {
            break;
        }
        // Recompute medians.
        medians = medians(clusters, medians, relation);
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    // Wrap result
    Clustering<MeanModel> result = new Clustering<>("k-Medians Clustering", "kmedians-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        MeanModel model = new MeanModel(medians[i]);
        result.addToplevelCluster(new Cluster<>(clusters.get(i), model));
    }
    return result;
}