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

Example 51 with DBIDs

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

the class FastOPTICS method run.

/**
 * Run the algorithm.
 *
 * @param db Database
 * @param rel Relation
 */
public ClusterOrder run(Database db, Relation<V> rel) {
    DBIDs ids = rel.getDBIDs();
    DistanceQuery<V> dq = db.getDistanceQuery(rel, EuclideanDistanceFunction.STATIC);
    // initialize points used and reachability distance
    reachDist = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, UNDEFINED_DISTANCE);
    // compute projections, density estimates and neighborhoods
    // project points
    index.computeSetsBounds(rel, minPts, ids);
    // compute densities
    inverseDensities = index.computeAverageDistInSet();
    // get neighbors of points
    neighs = index.getNeighs();
    // compute ordering as for OPTICS
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("FastOPTICS clustering", ids.size(), LOG) : null;
    processed = DBIDUtil.newHashSet(ids.size());
    order = new ClusterOrder(ids, "FastOPTICS Cluster Order", "fast-optics");
    for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
        if (!processed.contains(it)) {
            expandClusterOrder(DBIDUtil.deref(it), order, dq, prog);
        }
    }
    index.logStatistics();
    LOG.ensureCompleted(prog);
    return order;
}

Example 52 with DBIDs

use of de.lmu.ifi.dbs.elki.database.ids.DBIDs 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 53 with DBIDs

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

the class FarthestSumPointsInitialMeans method chooseInitialMeans.

@Override
public <T extends NumberVector> double[][] chooseInitialMeans(Database database, Relation<T> relation, int k, NumberVectorDistanceFunction<? super T> distanceFunction) {
    // Get a distance query
    DistanceQuery<T> distQ = database.getDistanceQuery(relation, distanceFunction);
    DBIDs ids = relation.getDBIDs();
    WritableDoubleDataStore store = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP, 0.);
    // Chose first mean
    List<T> means = new ArrayList<>(k);
    DBIDRef first = DBIDUtil.randomSample(ids, rnd);
    T prevmean = relation.get(first);
    means.add(prevmean);
    // Find farthest object each.
    DBIDVar best = DBIDUtil.newVar(first);
    for (int i = (dropfirst ? 0 : 1); i < k; i++) {
        double maxdist = Double.NEGATIVE_INFINITY;
        for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
            final double prev = store.doubleValue(it);
            if (prev != prev) {
                // NaN: already chosen!
                continue;
            }
            double dsum = prev + distQ.distance(prevmean, it);
            // Don't store distance to first mean, when it will be dropped below.
            if (i > 0) {
                store.putDouble(it, dsum);
            }
            if (dsum > maxdist) {
                maxdist = dsum;
                best.set(it);
            }
        }
        // Add new mean (and drop the initial mean when desired)
        if (i == 0) {
            // Remove temporary first element.
            means.clear();
        }
        // So it won't be chosen twice.
        store.putDouble(best, Double.NaN);
        prevmean = relation.get(best);
        means.add(prevmean);
    }
    // Explicitly destroy temporary data.
    store.destroy();
    return unboxVectors(means);
}

Example 54 with DBIDs

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

the class ByLabelClustering method singleAssignment.

/**
 * Assigns the objects of the database to single clusters according to their
 * labels.
 *
 * @param data the database storing the objects
 * @return a mapping of labels to ids
 */
private HashMap<String, DBIDs> singleAssignment(Relation<?> data) {
    HashMap<String, DBIDs> labelMap = new HashMap<>();
    for (DBIDIter iditer = data.iterDBIDs(); iditer.valid(); iditer.advance()) {
        final Object val = data.get(iditer);
        String label = (val != null) ? val.toString() : null;
        assign(labelMap, label, iditer);
    }
    return labelMap;
}

Example 55 with DBIDs

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

the class ByLabelOrAllInOneClustering method run.

@Override
public Clustering<Model> run(Database database) {
    // Prefer a true class label
    try {
        Relation<ClassLabel> relation = database.getRelation(TypeUtil.CLASSLABEL);
        return run(relation);
    } catch (NoSupportedDataTypeException e) {
    // Ignore.
    }
    try {
        Relation<ClassLabel> relation = database.getRelation(TypeUtil.GUESSED_LABEL);
        return run(relation);
    } catch (NoSupportedDataTypeException e) {
    // Ignore.
    }
    final DBIDs ids = database.getRelation(TypeUtil.ANY).getDBIDs();
    Clustering<Model> result = new Clustering<>("All-in-one trivial Clustering", "allinone-clustering");
    Cluster<Model> c = new Cluster<Model>(ids, ClusterModel.CLUSTER);
    result.addToplevelCluster(c);
    return result;
}