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

Example 21 with ArrayDBIDs

use of de.lmu.ifi.dbs.elki.database.ids.ArrayDBIDs 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 22 with ArrayDBIDs

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

the class LinearScanRKNNQuery method getRKNNForBulkDBIDs.

@Override
public List<? extends DoubleDBIDList> getRKNNForBulkDBIDs(ArrayDBIDs ids, int k) {
    List<ModifiableDoubleDBIDList> rNNList = new ArrayList<>(ids.size());
    for (int i = 0; i < ids.size(); i++) {
        rNNList.add(DBIDUtil.newDistanceDBIDList());
    }
    ArrayDBIDs allIDs = DBIDUtil.ensureArray(relation.getDBIDs());
    List<? extends KNNList> kNNList = knnQuery.getKNNForBulkDBIDs(allIDs, k);
    int i = 0;
    for (DBIDIter iter = allIDs.iter(); iter.valid(); iter.advance()) {
        KNNList knn = kNNList.get(i);
        for (DoubleDBIDListIter n = knn.iter(); n.valid(); n.advance()) {
            int j = 0;
            for (DBIDIter iter2 = ids.iter(); iter2.valid(); iter2.advance()) {
                if (DBIDUtil.equal(n, iter2)) {
                    ModifiableDoubleDBIDList rNN = rNNList.get(j);
                    rNN.add(n.doubleValue(), iter);
                }
                j++;
            }
        }
        i++;
    }
    for (int j = 0; j < ids.size(); j++) {
        rNNList.get(j).sort();
    }
    return rNNList;
}

Example 23 with ArrayDBIDs

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

the class SigmoidOutlierScalingFunction method prepare.

@Override
public void prepare(OutlierResult or) {
    // Initial parameters - are these defaults sounds?
    MeanVariance mv = new MeanVariance();
    DoubleRelation scores = or.getScores();
    for (DBIDIter id = scores.iterDBIDs(); id.valid(); id.advance()) {
        double val = scores.doubleValue(id);
        mv.put(val);
    }
    double a = 1.0;
    double b = -mv.getMean();
    int iter = 0;
    ArrayDBIDs ids = DBIDUtil.ensureArray(or.getScores().getDBIDs());
    DBIDArrayIter it = ids.iter();
    long[] t = BitsUtil.zero(ids.size());
    boolean changing = true;
    while (changing) {
        changing = false;
        // E-Step
        it.seek(0);
        for (int i = 0; i < ids.size(); i++, it.advance()) {
            double val = or.getScores().doubleValue(it);
            double targ = a * val + b;
            if (targ > 0) {
                if (!BitsUtil.get(t, i)) {
                    BitsUtil.setI(t, i);
                    changing = true;
                }
            } else {
                if (BitsUtil.get(t, i)) {
                    BitsUtil.clearI(t, i);
                    changing = true;
                }
            }
        }
        if (!changing) {
            break;
        }
        // logger.debugFine("Number of outliers in sigmoid: " + t.cardinality());
        // M-Step
        // Implementation based on:<br />
        // H.-T. Lin, C.-J. Lin, R. C. Weng:<br />
        // A Note on Platt’s Probabilistic Outputs for Support Vector Machines
        {
            double[] newab = MStepLevenbergMarquardt(a, b, ids, t, or.getScores());
            a = newab[0];
            b = newab[1];
        }
        iter++;
        if (iter > 100) {
            LOG.warning("Max iterations met in sigmoid fitting.");
            break;
        }
    }
    Afinal = a;
    Bfinal = b;
    LOG.debugFine("A = " + Afinal + " B = " + Bfinal);
}

Example 24 with ArrayDBIDs

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

the class PerplexityAffinityMatrixBuilder method computeAffinityMatrix.

@Override
public <T extends O> AffinityMatrix computeAffinityMatrix(Relation<T> relation, double initialScale) {
    DistanceQuery<T> dq = relation.getDistanceQuery(distanceFunction);
    ArrayDBIDs ids = DBIDUtil.ensureArray(relation.getDBIDs());
    // Compute desired affinities.
    double[][] dist = buildDistanceMatrix(ids, dq);
    return new DenseAffinityMatrix(computePij(dist, perplexity, initialScale), ids);
}

Example 25 with ArrayDBIDs

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

the class DistanceQuantileSampler method run.

/**
 * Run the distance quantile sampler.
 *
 * @param database
 * @param rel
 * @return Distances sample
 */
public CollectionResult<double[]> run(Database database, Relation<O> rel) {
    DistanceQuery<O> dq = rel.getDistanceQuery(getDistanceFunction());
    int size = rel.size();
    long pairs = (size * (long) size) >> 1;
    final long ssize = sampling <= 1 ? (long) Math.ceil(sampling * pairs) : (long) sampling;
    if (ssize > Integer.MAX_VALUE) {
        throw new AbortException("Sampling size too large.");
    }
    final int qsize = quantile <= 0 ? 1 : (int) Math.ceil(quantile * ssize);
    DoubleMaxHeap heap = new DoubleMaxHeap(qsize);
    ArrayDBIDs ids = DBIDUtil.ensureArray(rel.getDBIDs());
    DBIDArrayIter i1 = ids.iter(), i2 = ids.iter();
    Random r = rand.getSingleThreadedRandom();
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Sampling", (int) ssize, LOG) : null;
    for (long i = 0; i < ssize; i++) {
        int x = r.nextInt(size - 1) + 1, y = r.nextInt(x);
        double dist = dq.distance(i1.seek(x), i2.seek(y));
        // Skip NaN, and/or zeros.
        if (dist != dist || (nozeros && dist < Double.MIN_NORMAL)) {
            continue;
        }
        heap.add(dist, qsize);
        LOG.incrementProcessed(prog);
    }
    LOG.statistics(new DoubleStatistic(PREFIX + ".quantile", quantile));
    LOG.statistics(new LongStatistic(PREFIX + ".samplesize", ssize));
    LOG.statistics(new DoubleStatistic(PREFIX + ".distance", heap.peek()));
    LOG.ensureCompleted(prog);
    Collection<String> header = Arrays.asList(new String[] { "Distance" });
    Collection<double[]> data = Arrays.asList(new double[][] { new double[] { heap.peek() } });
    return new CollectionResult<double[]>("Distances sample", "distance-sample", data, header);
}