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

Example 16 with OutlierResult

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

the class GaussianUniformMixture method run.

/**
 * Run the algorithm
 *
 * @param relation Data relation
 * @return Outlier result
 */
public OutlierResult run(Relation<V> relation) {
    // Use an array list of object IDs for fast random access by an offset
    ArrayDBIDs objids = DBIDUtil.ensureArray(relation.getDBIDs());
    // A bit set to flag objects as anomalous, none at the beginning
    long[] bits = BitsUtil.zero(objids.size());
    // Positive masked collection
    DBIDs normalObjs = new MaskedDBIDs(objids, bits, true);
    // Positive masked collection
    DBIDs anomalousObjs = new MaskedDBIDs(objids, bits, false);
    // resulting scores
    WritableDoubleDataStore oscores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT);
    // compute loglikelihood
    double logLike = relation.size() * logml + loglikelihoodNormal(normalObjs, relation);
    // LOG.debugFine("normalsize " + normalObjs.size() + " anormalsize " +
    // anomalousObjs.size() + " all " + (anomalousObjs.size() +
    // normalObjs.size()));
    // LOG.debugFine(logLike + " loglike beginning" +
    // loglikelihoodNormal(normalObjs, database));
    DoubleMinMax minmax = new DoubleMinMax();
    DBIDIter iter = objids.iter();
    for (int i = 0; i < objids.size(); i++, iter.advance()) {
        // LOG.debugFine("i " + i);
        // Change mask to make the current object anomalous
        BitsUtil.setI(bits, i);
        // Compute new likelihoods
        double currentLogLike = normalObjs.size() * logml + loglikelihoodNormal(normalObjs, relation) + anomalousObjs.size() * logl + loglikelihoodAnomalous(anomalousObjs);
        // if the loglike increases more than a threshold, object stays in
        // anomalous set and is flagged as outlier
        final double loglikeGain = currentLogLike - logLike;
        oscores.putDouble(iter, loglikeGain);
        minmax.put(loglikeGain);
        if (loglikeGain > c) {
            // flag as outlier
            // LOG.debugFine("Outlier: " + curid + " " + (currentLogLike -
            // logLike));
            // Update best logLike
            logLike = currentLogLike;
        } else {
            // LOG.debugFine("Inlier: " + curid + " " + (currentLogLike - logLike));
            // undo bit set
            BitsUtil.clearI(bits, i);
        }
    }
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), Double.NEGATIVE_INFINITY, Double.POSITIVE_INFINITY, 0.0);
    DoubleRelation res = new MaterializedDoubleRelation("Gaussian Mixture Outlier Score", "gaussian-mixture-outlier", oscores, relation.getDBIDs());
    return new OutlierResult(meta, res);
}

Example 17 with OutlierResult

use of de.lmu.ifi.dbs.elki.result.outlier.OutlierResult 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 18 with OutlierResult

use of de.lmu.ifi.dbs.elki.result.outlier.OutlierResult 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 19 with OutlierResult

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

the class AbstractDBOutlier method run.

/**
 * Runs the algorithm in the timed evaluation part.
 *
 * @param database Database to process
 * @param relation Relation to process
 * @return Outlier result
 */
public OutlierResult run(Database database, Relation<O> relation) {
    // Run the actual score process
    DoubleDataStore dbodscore = computeOutlierScores(database, relation, d);
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Density-Based Outlier Detection", "db-outlier", dbodscore, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new ProbabilisticOutlierScore();
    return new OutlierResult(scoreMeta, scoreResult);
}

Example 20 with OutlierResult

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

the class LocalIsolationCoefficient method run.

/**
 * Runs the algorithm in the timed evaluation part.
 *
 * @param database Database context
 * @param relation Data relation
 */
public OutlierResult run(Database database, Relation<O> relation) {
    final DistanceQuery<O> distanceQuery = database.getDistanceQuery(relation, getDistanceFunction());
    // + query point
    KNNQuery<O> knnQuery = database.getKNNQuery(distanceQuery, k + 1);
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Compute Local Isolation Coefficients", relation.size(), LOG) : null;
    DoubleMinMax minmax = new DoubleMinMax();
    WritableDoubleDataStore lic_score = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        // + query point
        final KNNList knn = knnQuery.getKNNForDBID(iditer, k + 1);
        // sum of the distances to the k nearest neighbors
        double skn = 0;
        // number of neighbors so far
        int i = 0;
        for (DoubleDBIDListIter neighbor = knn.iter(); i < k && neighbor.valid(); neighbor.advance()) {
            if (DBIDUtil.equal(iditer, neighbor)) {
                continue;
            }
            skn += neighbor.doubleValue();
            ++i;
        }
        double lic = knn.getKNNDistance() + (i > 0 ? skn / i : 0);
        lic_score.putDouble(iditer, lic);
        minmax.put(skn);
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    DoubleRelation res = new MaterializedDoubleRelation("Local Isolation Coefficient", "lic-outlier", lic_score, relation.getDBIDs());
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0., Double.POSITIVE_INFINITY, 0.);
    return new OutlierResult(meta, res);
}