Examples with InvertedOutlierScoreMeta de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta used on opensource projects

Example 6 with InvertedOutlierScoreMeta

use of de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta 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 InvertedOutlierScoreMeta

use of de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta 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 8 with InvertedOutlierScoreMeta

use of de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta in project elki by elki-project.

the class OutRankS1 method run.

@Override
public OutlierResult run(Database database) {
    DBIDs ids = database.getRelation(TypeUtil.ANY).getDBIDs();
    // Run the primary algorithm
    Clustering<? extends SubspaceModel> clustering = clusteralg.run(database);
    WritableDoubleDataStore score = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT);
    for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
        score.putDouble(iter, 0);
    }
    int maxdim = 0, maxsize = 0;
    // Find maximum dimensionality and cluster size
    for (Cluster<? extends SubspaceModel> cluster : clustering.getAllClusters()) {
        maxsize = Math.max(maxsize, cluster.size());
        maxdim = Math.max(maxdim, BitsUtil.cardinality(cluster.getModel().getDimensions()));
    }
    // Iterate over all clusters:
    DoubleMinMax minmax = new DoubleMinMax();
    for (Cluster<? extends SubspaceModel> cluster : clustering.getAllClusters()) {
        double relsize = cluster.size() / (double) maxsize;
        double reldim = BitsUtil.cardinality(cluster.getModel().getDimensions()) / (double) maxdim;
        // Process objects in the cluster
        for (DBIDIter iter = cluster.getIDs().iter(); iter.valid(); iter.advance()) {
            double newscore = score.doubleValue(iter) + alpha * relsize + (1 - alpha) * reldim;
            score.putDouble(iter, newscore);
            minmax.put(newscore);
        }
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("OutRank-S1", "OUTRANK_S1", score, ids);
    OutlierScoreMeta meta = new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0, Double.POSITIVE_INFINITY);
    OutlierResult res = new OutlierResult(meta, scoreResult);
    res.addChildResult(clustering);
    return res;
}

Example 9 with InvertedOutlierScoreMeta

use of de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta in project elki by elki-project.

the class AggarwalYuEvolutionary method run.

/**
 * Performs the evolutionary algorithm on the given database.
 *
 * @param database Database
 * @param relation Relation
 * @return Result
 */
public OutlierResult run(Database database, Relation<V> relation) {
    final int dbsize = relation.size();
    ArrayList<ArrayList<DBIDs>> ranges = buildRanges(relation);
    Heap<Individuum>.UnorderedIter individuums = (new EvolutionarySearch(relation, ranges, m, rnd.getSingleThreadedRandom())).run();
    WritableDoubleDataStore outlierScore = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
    for (; individuums.valid(); individuums.advance()) {
        DBIDs ids = computeSubspaceForGene(individuums.get().getGene(), ranges);
        double sparsityC = sparsity(ids.size(), dbsize, k, phi);
        for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
            double prev = outlierScore.doubleValue(iter);
            if (Double.isNaN(prev) || sparsityC < prev) {
                outlierScore.putDouble(iter, sparsityC);
            }
        }
    }
    DoubleMinMax minmax = new DoubleMinMax();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double val = outlierScore.doubleValue(iditer);
        if (Double.isNaN(val)) {
            outlierScore.putDouble(iditer, 0.0);
            val = 0.0;
        }
        minmax.put(val);
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("AggarwalYuEvolutionary", "aggarwal-yu-outlier", outlierScore, relation.getDBIDs());
    OutlierScoreMeta meta = new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax(), Double.NEGATIVE_INFINITY, 0.0);
    return new OutlierResult(meta, scoreResult);
}

Example 10 with InvertedOutlierScoreMeta

use of de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta in project elki by elki-project.

the class OUTRES method run.

/**
 * Main loop for OUTRES
 *
 * @param relation Relation to process
 * @return Outlier detection result
 */
public OutlierResult run(Relation<V> relation) {
    WritableDoubleDataStore ranks = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    DoubleMinMax minmax = new DoubleMinMax();
    KernelDensityEstimator kernel = new KernelDensityEstimator(relation);
    long[] subspace = BitsUtil.zero(kernel.dim);
    FiniteProgress progress = LOG.isVerbose() ? new FiniteProgress("OUTRES scores", relation.size(), LOG) : null;
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        BitsUtil.zeroI(subspace);
        double score = outresScore(0, subspace, iditer, kernel);
        ranks.putDouble(iditer, score);
        minmax.put(score);
        LOG.incrementProcessed(progress);
    }
    LOG.ensureCompleted(progress);
    OutlierScoreMeta meta = new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0., 1., 1.);
    OutlierResult outresResult = new OutlierResult(meta, new MaterializedDoubleRelation("OUTRES", "outres-score", ranks, relation.getDBIDs()));
    return outresResult;
}