Examples with LongStatistic de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic used on opensource projects

Example 6 with LongStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic 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 7 with LongStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic in project elki by elki-project.

the class UKMeans method run.

/**
 * Run the clustering.
 *
 * @param database the Database
 * @param relation the Relation
 * @return Clustering result
 */
public Clustering<?> run(final Database database, final Relation<DiscreteUncertainObject> relation) {
    if (relation.size() <= 0) {
        return new Clustering<>("Uk-Means Clustering", "ukmeans-clustering");
    }
    // Choose initial means randomly
    DBIDs sampleids = DBIDUtil.randomSample(relation.getDBIDs(), k, rnd);
    List<double[]> means = new ArrayList<>(k);
    for (DBIDIter iter = sampleids.iter(); iter.valid(); iter.advance()) {
        means.add(ArrayLikeUtil.toPrimitiveDoubleArray(relation.get(iter).getCenterOfMass()));
    }
    // 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("UK-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<>("Uk-Means Clustering", "ukmeans-clustering");
    for (int i = 0; i < clusters.size(); i++) {
        DBIDs ids = clusters.get(i);
        if (ids.isEmpty()) {
            continue;
        }
        result.addToplevelCluster(new Cluster<>(ids, new KMeansModel(means.get(i), varsum[i])));
    }
    return result;
}

Example 8 with LongStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic in project elki by elki-project.

the class Leader method run.

/**
 * Run the leader clustering algorithm.
 *
 * @param relation Data set
 * @return Clustering result
 */
public Clustering<PrototypeModel<O>> run(Relation<O> relation) {
    RangeQuery<O> rq = relation.getRangeQuery(getDistanceFunction(), threshold);
    ModifiableDBIDs seen = DBIDUtil.newHashSet(relation.size());
    Clustering<PrototypeModel<O>> clustering = new Clustering<>("Prototype clustering", "prototype-clustering");
    int queries = 0;
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Leader clustering", relation.size(), LOG) : null;
    for (DBIDIter it = relation.iterDBIDs(); it.valid() && seen.size() < relation.size(); it.advance()) {
        if (seen.contains(it)) {
            continue;
        }
        DoubleDBIDList res = rq.getRangeForDBID(it, threshold);
        ++queries;
        ModifiableDBIDs ids = DBIDUtil.newArray(res.size());
        for (DBIDIter cand = res.iter(); cand.valid(); cand.advance()) {
            if (seen.add(cand)) {
                LOG.incrementProcessed(prog);
                ids.add(cand);
            }
        }
        assert (ids.size() > 0 && ids.contains(it));
        PrototypeModel<O> mod = new SimplePrototypeModel<>(relation.get(it));
        clustering.addToplevelCluster(new Cluster<>(ids, mod));
    }
    LOG.statistics(new LongStatistic(this.getClass().getName() + ".queries", queries));
    LOG.ensureCompleted(prog);
    return clustering;
}

Example 9 with LongStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic in project elki by elki-project.

the class SimplifiedCoverTree method initialize.

@Override
public void initialize() {
    bulkLoad(relation.getDBIDs());
    if (LOG.isVerbose()) {
        int[] counts = new int[5];
        checkCoverTree(root, counts, 0);
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".nodes", counts[0]));
        LOG.statistics(new DoubleStatistic(this.getClass().getName() + ".avg-depth", counts[1] / (double) counts[0]));
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".max-depth", counts[2]));
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".singletons", counts[3]));
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".entries", counts[4]));
    }
}

Example 10 with LongStatistic

use of de.lmu.ifi.dbs.elki.logging.statistics.LongStatistic in project elki by elki-project.

the class CoverTree method initialize.

@Override
public void initialize() {
    bulkLoad(relation.getDBIDs());
    if (LOG.isVerbose()) {
        int[] counts = new int[5];
        checkCoverTree(root, counts, 0);
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".nodes", counts[0]));
        LOG.statistics(new DoubleStatistic(this.getClass().getName() + ".avg-depth", counts[1] / (double) counts[0]));
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".max-depth", counts[2]));
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".singletons", counts[3]));
        LOG.statistics(new LongStatistic(this.getClass().getName() + ".entries", counts[4]));
    }
}