Examples with ModifiableDBIDs de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs used on opensource projects

Example 71 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs 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 72 with ModifiableDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs 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 73 with ModifiableDBIDs

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

the class CLIQUESubspace method determineClusters.

/**
 * Determines all clusters in this subspace by performing a depth-first search
 * algorithm to find connected dense units.
 *
 * @return the clusters in this subspace and the corresponding cluster models
 */
public List<Pair<Subspace, ModifiableDBIDs>> determineClusters() {
    List<Pair<Subspace, ModifiableDBIDs>> clusters = new ArrayList<>();
    for (CLIQUEUnit<V> unit : getDenseUnits()) {
        if (!unit.isAssigned()) {
            ModifiableDBIDs cluster = DBIDUtil.newHashSet();
            CLIQUESubspace<V> model = new CLIQUESubspace<>(getDimensions());
            clusters.add(new Pair<Subspace, ModifiableDBIDs>(model, cluster));
            dfs(unit, cluster, model);
        }
    }
    return clusters;
}

Example 74 with ModifiableDBIDs

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

the class ByLabelClustering method run.

/**
 * Run the actual clustering algorithm.
 *
 * @param relation The data input we use
 */
public Clustering<Model> run(Relation<?> relation) {
    HashMap<String, DBIDs> labelMap = multiple ? multipleAssignment(relation) : singleAssignment(relation);
    ModifiableDBIDs noiseids = DBIDUtil.newArray();
    Clustering<Model> result = new Clustering<>("By Label Clustering", "bylabel-clustering");
    for (Entry<String, DBIDs> entry : labelMap.entrySet()) {
        DBIDs ids = entry.getValue();
        if (ids.size() <= 1) {
            noiseids.addDBIDs(ids);
            continue;
        }
        // Build a cluster
        Cluster<Model> c = new Cluster<Model>(entry.getKey(), ids, ClusterModel.CLUSTER);
        if (noisepattern != null && noisepattern.matcher(entry.getKey()).find()) {
            c.setNoise(true);
        }
        result.addToplevelCluster(c);
    }
    // Collected noise IDs.
    if (noiseids.size() > 0) {
        Cluster<Model> c = new Cluster<Model>("Noise", noiseids, ClusterModel.CLUSTER);
        c.setNoise(true);
        result.addToplevelCluster(c);
    }
    return result;
}

Example 75 with ModifiableDBIDs

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

the class ByLabelClustering method assign.

/**
 * Assigns the specified id to the labelMap according to its label
 *
 * @param labelMap the mapping of label to ids
 * @param label the label of the object to be assigned
 * @param id the id of the object to be assigned
 */
private void assign(HashMap<String, DBIDs> labelMap, String label, DBIDRef id) {
    if (labelMap.containsKey(label)) {
        DBIDs exist = labelMap.get(label);
        if (exist instanceof DBID) {
            ModifiableDBIDs n = DBIDUtil.newHashSet();
            n.add((DBID) exist);
            n.add(id);
            labelMap.put(label, n);
        } else {
            assert (exist instanceof HashSetModifiableDBIDs);
            assert (exist.size() > 1);
            ((ModifiableDBIDs) exist).add(id);
        }
    } else {
        labelMap.put(label, DBIDUtil.deref(id));
    }
}