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

Example 6 with DBIDArrayIter

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

the class AbstractHDBSCAN method convertToPointerRepresentation.

/**
 * Convert spanning tree to a pointer representation.
 *
 * Note: the heap must use the correct encoding of indexes.
 *
 * @param ids IDs indexed
 * @param heap Heap
 * @param pi Parent array
 * @param lambda Distance array
 */
protected void convertToPointerRepresentation(ArrayDBIDs ids, DoubleLongHeap heap, WritableDBIDDataStore pi, WritableDoubleDataStore lambda) {
    final Logging LOG = getLogger();
    // Initialize parent array:
    for (DBIDArrayIter iter = ids.iter(); iter.valid(); iter.advance()) {
        // Initialize
        pi.put(iter, iter);
    }
    DBIDVar p = DBIDUtil.newVar(), q = DBIDUtil.newVar(), n = DBIDUtil.newVar();
    FiniteProgress pprog = LOG.isVerbose() ? new FiniteProgress("Converting MST to pointer representation", heap.size(), LOG) : null;
    while (!heap.isEmpty()) {
        final double dist = heap.peekKey();
        final long pair = heap.peekValue();
        final int i = (int) (pair >>> 31), j = (int) (pair & 0x7FFFFFFFL);
        ids.assignVar(i, p);
        // Follow p to its parent.
        while (!DBIDUtil.equal(p, pi.assignVar(p, n))) {
            p.set(n);
        }
        // Follow q to its parent.
        ids.assignVar(j, q);
        while (!DBIDUtil.equal(q, pi.assignVar(q, n))) {
            q.set(n);
        }
        // By definition of the pointer representation, the largest element in
        // each cluster is the cluster lead.
        // The extraction methods currently rely on this!
        int c = DBIDUtil.compare(p, q);
        if (c < 0) {
            // p joins q:
            pi.put(p, q);
            lambda.put(p, dist);
        } else {
            assert (c != 0) : "This should never happen!";
            // q joins p:
            pi.put(q, p);
            lambda.put(q, dist);
        }
        heap.poll();
        LOG.incrementProcessed(pprog);
    }
    LOG.ensureCompleted(pprog);
    // does not fulfill the property that the last element has the largest id.
    for (DBIDArrayIter iter = ids.iter(); iter.valid(); iter.advance()) {
        double d = lambda.doubleValue(iter);
        // Parent:
        pi.assignVar(iter, p);
        q.set(p);
        // Follow parent while tied.
        while (d >= lambda.doubleValue(q) && !DBIDUtil.equal(q, pi.assignVar(q, n))) {
            q.set(n);
        }
        if (!DBIDUtil.equal(p, q)) {
            if (LOG.isDebuggingFinest()) {
                LOG.finest("Correcting parent: " + p + " -> " + q);
            }
            pi.put(iter, q);
        }
    }
}

Example 7 with DBIDArrayIter

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

the class ABOD method run.

/**
 * Run ABOD on the data set.
 *
 * @param relation Relation to process
 * @return Outlier detection result
 */
public OutlierResult run(Database db, Relation<V> relation) {
    ArrayDBIDs ids = DBIDUtil.ensureArray(relation.getDBIDs());
    // Build a kernel matrix, to make O(n^3) slightly less bad.
    SimilarityQuery<V> sq = db.getSimilarityQuery(relation, kernelFunction);
    KernelMatrix kernelMatrix = new KernelMatrix(sq, relation, ids);
    WritableDoubleDataStore abodvalues = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_STATIC);
    DoubleMinMax minmaxabod = new DoubleMinMax();
    MeanVariance s = new MeanVariance();
    DBIDArrayIter pA = ids.iter(), pB = ids.iter(), pC = ids.iter();
    for (; pA.valid(); pA.advance()) {
        final double abof = computeABOF(kernelMatrix, pA, pB, pC, s);
        minmaxabod.put(abof);
        abodvalues.putDouble(pA, abof);
    }
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Angle-Based Outlier Degree", "abod-outlier", abodvalues, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new InvertedOutlierScoreMeta(minmaxabod.getMin(), minmaxabod.getMax(), 0.0, Double.POSITIVE_INFINITY);
    return new OutlierResult(scoreMeta, scoreResult);
}

Example 8 with DBIDArrayIter

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

the class LBABOD method run.

/**
 * Run LB-ABOD on the data set.
 *
 * @param relation Relation to process
 * @return Outlier detection result
 */
@Override
public OutlierResult run(Database db, Relation<V> relation) {
    ArrayDBIDs ids = DBIDUtil.ensureArray(relation.getDBIDs());
    DBIDArrayIter pB = ids.iter(), pC = ids.iter();
    SimilarityQuery<V> sq = db.getSimilarityQuery(relation, kernelFunction);
    KernelMatrix kernelMatrix = new KernelMatrix(sq, relation, ids);
    // Output storage.
    WritableDoubleDataStore abodvalues = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_STATIC);
    DoubleMinMax minmaxabod = new DoubleMinMax();
    double max = 0.;
    // Storage for squared distances (will be reused!)
    WritableDoubleDataStore sqDists = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT);
    // Nearest neighbor heap (will be reused!)
    KNNHeap nn = DBIDUtil.newHeap(k);
    // Priority queue for candidates
    ModifiableDoubleDBIDList candidates = DBIDUtil.newDistanceDBIDList(relation.size());
    // get Candidate Ranking
    for (DBIDIter pA = relation.iterDBIDs(); pA.valid(); pA.advance()) {
        // Compute nearest neighbors and distances.
        nn.clear();
        double simAA = kernelMatrix.getSimilarity(pA, pA);
        // Sum of 1./(|AB|) and 1./(|AB|^2); for computing R2.
        double sumid = 0., sumisqd = 0.;
        for (pB.seek(0); pB.valid(); pB.advance()) {
            if (DBIDUtil.equal(pB, pA)) {
                continue;
            }
            double simBB = kernelMatrix.getSimilarity(pB, pB);
            double simAB = kernelMatrix.getSimilarity(pA, pB);
            double sqdAB = simAA + simBB - simAB - simAB;
            sqDists.putDouble(pB, sqdAB);
            final double isqdAB = 1. / sqdAB;
            sumid += FastMath.sqrt(isqdAB);
            sumisqd += isqdAB;
            // Update heap
            nn.insert(sqdAB, pB);
        }
        // Compute FastABOD approximation, adjust for lower bound.
        // LB-ABOF is defined via a numerically unstable formula.
        // Variance as E(X^2)-E(X)^2 suffers from catastrophic cancellation!
        // TODO: ensure numerical precision!
        double nnsum = 0., nnsumsq = 0., nnsumisqd = 0.;
        KNNList nl = nn.toKNNList();
        DoubleDBIDListIter iB = nl.iter(), iC = nl.iter();
        for (; iB.valid(); iB.advance()) {
            double sqdAB = iB.doubleValue();
            double simAB = kernelMatrix.getSimilarity(pA, iB);
            if (!(sqdAB > 0.)) {
                continue;
            }
            for (iC.seek(iB.getOffset() + 1); iC.valid(); iC.advance()) {
                double sqdAC = iC.doubleValue();
                double simAC = kernelMatrix.getSimilarity(pA, iC);
                if (!(sqdAC > 0.)) {
                    continue;
                }
                // Exploit bilinearity of scalar product:
                // <B-A, C-A> = <B, C-A> - <A,C-A>
                // = <B,C> - <B,A> - <A,C> + <A,A>
                double simBC = kernelMatrix.getSimilarity(iB, iC);
                double numerator = simBC - simAB - simAC + simAA;
                double sqweight = 1. / (sqdAB * sqdAC);
                double weight = FastMath.sqrt(sqweight);
                double val = numerator * sqweight;
                nnsum += val * weight;
                nnsumsq += val * val * weight;
                nnsumisqd += sqweight;
            }
        }
        // Remaining weight, term R2:
        double r2 = sumisqd * sumisqd - 2. * nnsumisqd;
        double tmp = (2. * nnsum + r2) / (sumid * sumid);
        double lbabof = 2. * nnsumsq / (sumid * sumid) - tmp * tmp;
        // Track maximum?
        if (lbabof > max) {
            max = lbabof;
        }
        abodvalues.putDouble(pA, lbabof);
        candidates.add(lbabof, pA);
    }
    // Put maximum from approximate values.
    minmaxabod.put(max);
    candidates.sort();
    // refine Candidates
    int refinements = 0;
    DoubleMinHeap topscores = new DoubleMinHeap(l);
    MeanVariance s = new MeanVariance();
    for (DoubleDBIDListIter pA = candidates.iter(); pA.valid(); pA.advance()) {
        // Stop refining
        if (topscores.size() >= k && pA.doubleValue() > topscores.peek()) {
            break;
        }
        final double abof = computeABOF(kernelMatrix, pA, pB, pC, s);
        // Store refined score:
        abodvalues.putDouble(pA, abof);
        minmaxabod.put(abof);
        // Update the heap tracking the top scores.
        if (topscores.size() < k) {
            topscores.add(abof);
        } else {
            if (topscores.peek() > abof) {
                topscores.replaceTopElement(abof);
            }
        }
        refinements += 1;
    }
    if (LOG.isStatistics()) {
        LoggingConfiguration.setVerbose(Level.VERYVERBOSE);
        LOG.statistics(new LongStatistic("lb-abod.refinements", refinements));
    }
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Angle-based Outlier Detection", "abod-outlier", abodvalues, ids);
    OutlierScoreMeta scoreMeta = new InvertedOutlierScoreMeta(minmaxabod.getMin(), minmaxabod.getMax(), 0.0, Double.POSITIVE_INFINITY);
    return new OutlierResult(scoreMeta, scoreResult);
}

Example 9 with DBIDArrayIter

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

the class SilhouetteOutlierDetection method run.

@Override
public OutlierResult run(Database database) {
    Relation<O> relation = database.getRelation(getDistanceFunction().getInputTypeRestriction());
    DistanceQuery<O> dq = database.getDistanceQuery(relation, getDistanceFunction());
    // TODO: improve ELKI api to ensure we're using the same DBIDs!
    Clustering<?> c = clusterer.run(database);
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_DB);
    DoubleMinMax mm = new DoubleMinMax();
    List<? extends Cluster<?>> clusters = c.getAllClusters();
    for (Cluster<?> cluster : clusters) {
        if (cluster.size() <= 1 || cluster.isNoise()) {
            switch(noiseOption) {
                case IGNORE_NOISE:
                case TREAT_NOISE_AS_SINGLETONS:
                    // As suggested in Rousseeuw, we use 0 for singletons.
                    for (DBIDIter iter = cluster.getIDs().iter(); iter.valid(); iter.advance()) {
                        scores.put(iter, 0.);
                    }
                    mm.put(0.);
                    continue;
                case MERGE_NOISE:
                    // Treat as cluster below
                    break;
            }
        }
        ArrayDBIDs ids = DBIDUtil.ensureArray(cluster.getIDs());
        // temporary storage.
        double[] as = new double[ids.size()];
        DBIDArrayIter it1 = ids.iter(), it2 = ids.iter();
        for (it1.seek(0); it1.valid(); it1.advance()) {
            // a: In-cluster distances
            // Already computed distances
            double a = as[it1.getOffset()];
            for (it2.seek(it1.getOffset() + 1); it2.valid(); it2.advance()) {
                final double dist = dq.distance(it1, it2);
                a += dist;
                as[it2.getOffset()] += dist;
            }
            a /= (ids.size() - 1);
            // b: other clusters:
            double min = Double.POSITIVE_INFINITY;
            for (Cluster<?> ocluster : clusters) {
                if (ocluster == /* yes, reference identity */
                cluster) {
                    continue;
                }
                if (ocluster.isNoise()) {
                    switch(noiseOption) {
                        case IGNORE_NOISE:
                            continue;
                        case MERGE_NOISE:
                            // No special treatment
                            break;
                        case TREAT_NOISE_AS_SINGLETONS:
                            // Treat noise cluster as singletons:
                            for (DBIDIter it3 = ocluster.getIDs().iter(); it3.valid(); it3.advance()) {
                                double dist = dq.distance(it1, it3);
                                if (dist < min) {
                                    min = dist;
                                }
                            }
                            continue;
                    }
                }
                final DBIDs oids = ocluster.getIDs();
                double b = 0.;
                for (DBIDIter it3 = oids.iter(); it3.valid(); it3.advance()) {
                    b += dq.distance(it1, it3);
                }
                b /= oids.size();
                if (b < min) {
                    min = b;
                }
            }
            final double score = (min - a) / Math.max(min, a);
            scores.put(it1, score);
            mm.put(score);
        }
    }
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Silhouette Coefficients", "silhouette-outlier", scores, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new InvertedOutlierScoreMeta(mm.getMin(), mm.getMax(), -1., 1., .5);
    return new OutlierResult(scoreMeta, scoreResult);
}

Example 10 with DBIDArrayIter

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

the class TSNE method run.

public Relation<DoubleVector> run(Relation<O> relation) {
    AffinityMatrix pij = affinity.computeAffinityMatrix(relation, EARLY_EXAGGERATION);
    // Create initial solution.
    final int size = pij.size();
    double[][] sol = randomInitialSolution(size, dim, random.getSingleThreadedRandom());
    projectedDistances.setLong(0L);
    optimizetSNE(pij, sol);
    LOG.statistics(projectedDistances);
    // Remove the original (unprojected) data unless configured otherwise.
    removePreviousRelation(relation);
    // Transform into output data format.
    DBIDs ids = relation.getDBIDs();
    WritableDataStore<DoubleVector> proj = DataStoreFactory.FACTORY.makeStorage(ids, DataStoreFactory.HINT_DB | DataStoreFactory.HINT_SORTED, DoubleVector.class);
    VectorFieldTypeInformation<DoubleVector> otype = new VectorFieldTypeInformation<>(DoubleVector.FACTORY, dim);
    for (DBIDArrayIter it = pij.iterDBIDs(); it.valid(); it.advance()) {
        proj.put(it, DoubleVector.wrap(sol[it.getOffset()]));
    }
    return new MaterializedRelation<>("tSNE", "t-SNE", otype, proj, ids);
}