Search in sources :

Example 61 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs in project elki by elki-project.

the class SNNClustering method run.

/**
 * Perform SNN clustering
 *
 * @param database Database
 * @param relation Relation
 * @return Result
 */
public Clustering<Model> run(Database database, Relation<O> relation) {
    SimilarityQuery<O> snnInstance = similarityFunction.instantiate(relation);
    FiniteProgress objprog = LOG.isVerbose() ? new FiniteProgress("SNNClustering", relation.size(), LOG) : null;
    IndefiniteProgress clusprog = LOG.isVerbose() ? new IndefiniteProgress("Number of clusters", LOG) : null;
    resultList = new ArrayList<>();
    noise = DBIDUtil.newHashSet();
    processedIDs = DBIDUtil.newHashSet(relation.size());
    if (relation.size() >= minpts) {
        for (DBIDIter id = relation.iterDBIDs(); id.valid(); id.advance()) {
            if (!processedIDs.contains(id)) {
                expandCluster(snnInstance, id, objprog, clusprog);
                if (processedIDs.size() == relation.size() && noise.size() == 0) {
                    break;
                }
            }
            if (objprog != null && clusprog != null) {
                objprog.setProcessed(processedIDs.size(), LOG);
                clusprog.setProcessed(resultList.size(), LOG);
            }
        }
    } else {
        for (DBIDIter id = relation.iterDBIDs(); id.valid(); id.advance()) {
            noise.add(id);
            if (objprog != null && clusprog != null) {
                objprog.setProcessed(noise.size(), LOG);
                clusprog.setProcessed(resultList.size(), LOG);
            }
        }
    }
    // Finish progress logging
    LOG.ensureCompleted(objprog);
    LOG.setCompleted(clusprog);
    Clustering<Model> result = new Clustering<>("Shared-Nearest-Neighbor Clustering", "snn-clustering");
    for (Iterator<ModifiableDBIDs> resultListIter = resultList.iterator(); resultListIter.hasNext(); ) {
        result.addToplevelCluster(new Cluster<Model>(resultListIter.next(), ClusterModel.CLUSTER));
    }
    result.addToplevelCluster(new Cluster<Model>(noise, true, ClusterModel.CLUSTER));
    return result;
}
Also used : IndefiniteProgress(de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress) FiniteProgress(de.lmu.ifi.dbs.elki.logging.progress.FiniteProgress) ClusterModel(de.lmu.ifi.dbs.elki.data.model.ClusterModel) Model(de.lmu.ifi.dbs.elki.data.model.Model) ArrayModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ArrayModifiableDBIDs) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs) Clustering(de.lmu.ifi.dbs.elki.data.Clustering) DBIDIter(de.lmu.ifi.dbs.elki.database.ids.DBIDIter)

Example 62 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs in project elki by elki-project.

the class NaiveMeanShiftClustering method run.

/**
 * Run the mean-shift clustering algorithm.
 *
 * @param database Database
 * @param relation Data relation
 * @return Clustering result
 */
public Clustering<MeanModel> run(Database database, Relation<V> relation) {
    final DistanceQuery<V> distq = database.getDistanceQuery(relation, getDistanceFunction());
    final RangeQuery<V> rangeq = database.getRangeQuery(distq);
    final NumberVector.Factory<V> factory = RelationUtil.getNumberVectorFactory(relation);
    final int dim = RelationUtil.dimensionality(relation);
    // Stopping threshold
    final double threshold = bandwidth * 1E-10;
    // Result store:
    ArrayList<Pair<V, ModifiableDBIDs>> clusters = new ArrayList<>();
    ModifiableDBIDs noise = DBIDUtil.newArray();
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Mean-shift clustering", relation.size(), LOG) : null;
    for (DBIDIter iter = relation.iterDBIDs(); iter.valid(); iter.advance()) {
        // Initial position:
        V position = relation.get(iter);
        iterations: for (int j = 1; j <= MAXITER; j++) {
            // Compute new position:
            V newvec = null;
            {
                DoubleDBIDList neigh = rangeq.getRangeForObject(position, bandwidth);
                boolean okay = (neigh.size() > 1) || (neigh.size() >= 1 && j > 1);
                if (okay) {
                    Centroid newpos = new Centroid(dim);
                    for (DoubleDBIDListIter niter = neigh.iter(); niter.valid(); niter.advance()) {
                        final double weight = kernel.density(niter.doubleValue() / bandwidth);
                        newpos.put(relation.get(niter), weight);
                    }
                    newvec = factory.newNumberVector(newpos.getArrayRef());
                // TODO: detect 0 weight!
                }
                if (!okay) {
                    noise.add(iter);
                    break iterations;
                }
            }
            // Test if we are close to one of the known clusters:
            double bestd = Double.POSITIVE_INFINITY;
            Pair<V, ModifiableDBIDs> bestp = null;
            for (Pair<V, ModifiableDBIDs> pair : clusters) {
                final double merged = distq.distance(newvec, pair.first);
                if (merged < bestd) {
                    bestd = merged;
                    bestp = pair;
                }
            }
            // Check for convergence:
            double delta = distq.distance(position, newvec);
            if (bestd < 10 * threshold || bestd * 2 < delta) {
                bestp.second.add(iter);
                break iterations;
            }
            if (j == MAXITER) {
                LOG.warning("No convergence after " + MAXITER + " iterations. Distance: " + delta);
            }
            if (Double.isNaN(delta)) {
                LOG.warning("Encountered NaN distance. Invalid center vector? " + newvec.toString());
                break iterations;
            }
            if (j == MAXITER || delta < threshold) {
                if (LOG.isDebuggingFine()) {
                    LOG.debugFine("New cluster:" + newvec + " delta: " + delta + " threshold: " + threshold + " bestd: " + bestd);
                }
                ArrayModifiableDBIDs cids = DBIDUtil.newArray();
                cids.add(iter);
                clusters.add(new Pair<V, ModifiableDBIDs>(newvec, cids));
                break iterations;
            }
            position = newvec;
        }
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    ArrayList<Cluster<MeanModel>> cs = new ArrayList<>(clusters.size());
    for (Pair<V, ModifiableDBIDs> pair : clusters) {
        cs.add(new Cluster<>(pair.second, new MeanModel(pair.first.toArray())));
    }
    if (noise.size() > 0) {
        cs.add(new Cluster<MeanModel>(noise, true));
    }
    Clustering<MeanModel> c = new Clustering<>("Mean-shift Clustering", "mean-shift-clustering", cs);
    return c;
}
Also used : ArrayList(java.util.ArrayList) MeanModel(de.lmu.ifi.dbs.elki.data.model.MeanModel) DBIDIter(de.lmu.ifi.dbs.elki.database.ids.DBIDIter) ArrayModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ArrayModifiableDBIDs) DoubleDBIDList(de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDList) Pair(de.lmu.ifi.dbs.elki.utilities.pairs.Pair) DoubleDBIDListIter(de.lmu.ifi.dbs.elki.database.ids.DoubleDBIDListIter) FiniteProgress(de.lmu.ifi.dbs.elki.logging.progress.FiniteProgress) Cluster(de.lmu.ifi.dbs.elki.data.Cluster) Clustering(de.lmu.ifi.dbs.elki.data.Clustering) Centroid(de.lmu.ifi.dbs.elki.math.linearalgebra.Centroid) NumberVector(de.lmu.ifi.dbs.elki.data.NumberVector) ArrayModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ArrayModifiableDBIDs) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs)

Example 63 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs in project elki by elki-project.

the class KMeansElkan 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);
    // Elkan bounds
    WritableDoubleDataStore upper = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, Double.POSITIVE_INFINITY);
    WritableDataStore<double[]> lower = DataStoreUtil.makeStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT, double[].class);
    for (DBIDIter it = relation.iterDBIDs(); it.valid(); it.advance()) {
        // Filled with 0.
        lower.put(it, new double[k]);
    }
    // Storage for updated means:
    final int dim = means[0].length;
    double[][] sums = new double[k][dim];
    // Cluster separation
    double[] sep = new double[k];
    // Cluster distances
    double[][] cdist = new double[k][k];
    IndefiniteProgress prog = LOG.isVerbose() ? new IndefiniteProgress("K-Means iteration", LOG) : null;
    LongStatistic rstat = LOG.isStatistics() ? new LongStatistic(this.getClass().getName() + ".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 {
            // #1
            recomputeSeperation(means, sep, cdist);
            changed = assignToNearestCluster(relation, means, sums, clusters, assignment, sep, cdist, 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.);
        }
        // Overwrites sep
        maxMoved(means, sums, sep);
        updateBounds(relation, assignment, upper, lower, sep);
        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;
}
Also used : WritableIntegerDataStore(de.lmu.ifi.dbs.elki.database.datastore.WritableIntegerDataStore) KMeansModel(de.lmu.ifi.dbs.elki.data.model.KMeansModel) WritableDoubleDataStore(de.lmu.ifi.dbs.elki.database.datastore.WritableDoubleDataStore) DBIDs(de.lmu.ifi.dbs.elki.database.ids.DBIDs) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs) ArrayList(java.util.ArrayList) Clustering(de.lmu.ifi.dbs.elki.data.Clustering) DBIDIter(de.lmu.ifi.dbs.elki.database.ids.DBIDIter) DoubleStatistic(de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic) StringStatistic(de.lmu.ifi.dbs.elki.logging.statistics.StringStatistic) IndefiniteProgress(de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress) LongStatistic(de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs) DoubleVector(de.lmu.ifi.dbs.elki.data.DoubleVector)

Example 64 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs in project elki by elki-project.

the class KMeansHybridLloydMacQueen 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 += 2) {
        {
            // MacQueen
            LOG.incrementProcessed(prog);
            boolean changed = macQueenIterate(relation, means, clusters, assignment, varsum);
            logVarstat(varstat, varsum);
            if (!changed) {
                break;
            }
        }
        {
            // Lloyd
            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;
}
Also used : WritableIntegerDataStore(de.lmu.ifi.dbs.elki.database.datastore.WritableIntegerDataStore) KMeansModel(de.lmu.ifi.dbs.elki.data.model.KMeansModel) DBIDs(de.lmu.ifi.dbs.elki.database.ids.DBIDs) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs) ArrayList(java.util.ArrayList) Clustering(de.lmu.ifi.dbs.elki.data.Clustering) DoubleStatistic(de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic) StringStatistic(de.lmu.ifi.dbs.elki.logging.statistics.StringStatistic) IndefiniteProgress(de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress) LongStatistic(de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs)

Example 65 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs in project elki by elki-project.

the class KMeansMacQueen 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());
    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;
    // Iterate MacQueen
    int iteration = 0;
    for (; maxiter <= 0 || iteration < maxiter; iteration++) {
        LOG.incrementProcessed(prog);
        boolean changed = macQueenIterate(relation, means, clusters, assignment, varsum);
        logVarstat(varstat, varsum);
        if (!changed) {
            break;
        }
    }
    LOG.setCompleted(prog);
    if (LOG.isStatistics()) {
        LOG.statistics(new LongStatistic(KEY + ".iterations", iteration));
    }
    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;
}
Also used : WritableIntegerDataStore(de.lmu.ifi.dbs.elki.database.datastore.WritableIntegerDataStore) KMeansModel(de.lmu.ifi.dbs.elki.data.model.KMeansModel) DBIDs(de.lmu.ifi.dbs.elki.database.ids.DBIDs) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs) ArrayList(java.util.ArrayList) Clustering(de.lmu.ifi.dbs.elki.data.Clustering) DoubleStatistic(de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic) StringStatistic(de.lmu.ifi.dbs.elki.logging.statistics.StringStatistic) IndefiniteProgress(de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress) LongStatistic(de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic) ModifiableDBIDs(de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs)

Aggregations

ModifiableDBIDs (de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs)80 DBIDIter (de.lmu.ifi.dbs.elki.database.ids.DBIDIter)44 Clustering (de.lmu.ifi.dbs.elki.data.Clustering)30 ArrayList (java.util.ArrayList)30 DBIDs (de.lmu.ifi.dbs.elki.database.ids.DBIDs)28 ArrayModifiableDBIDs (de.lmu.ifi.dbs.elki.database.ids.ArrayModifiableDBIDs)18 FiniteProgress (de.lmu.ifi.dbs.elki.logging.progress.FiniteProgress)15 WritableIntegerDataStore (de.lmu.ifi.dbs.elki.database.datastore.WritableIntegerDataStore)14 IndefiniteProgress (de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress)14 DoubleStatistic (de.lmu.ifi.dbs.elki.logging.statistics.DoubleStatistic)12 LongStatistic (de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic)12 Model (de.lmu.ifi.dbs.elki.data.model.Model)11 DBID (de.lmu.ifi.dbs.elki.database.ids.DBID)11 KMeansModel (de.lmu.ifi.dbs.elki.data.model.KMeansModel)10 StringStatistic (de.lmu.ifi.dbs.elki.logging.statistics.StringStatistic)10 Cluster (de.lmu.ifi.dbs.elki.data.Cluster)9 WritableDoubleDataStore (de.lmu.ifi.dbs.elki.database.datastore.WritableDoubleDataStore)9 HashSetModifiableDBIDs (de.lmu.ifi.dbs.elki.database.ids.HashSetModifiableDBIDs)8 KNNList (de.lmu.ifi.dbs.elki.database.ids.KNNList)8 ClusterModel (de.lmu.ifi.dbs.elki.data.model.ClusterModel)7