Examples with MeanVariance de.lmu.ifi.dbs.elki.math.MeanVariance used on opensource projects

Example 6 with MeanVariance

use of de.lmu.ifi.dbs.elki.math.MeanVariance in project elki by elki-project.

the class LOCI method run.

/**
 * Run the algorithm
 *
 * @param database Database to process
 * @param relation Relation to process
 * @return Outlier result
 */
public OutlierResult run(Database database, Relation<O> relation) {
    DistanceQuery<O> distFunc = database.getDistanceQuery(relation, getDistanceFunction());
    RangeQuery<O> rangeQuery = database.getRangeQuery(distFunc);
    DBIDs ids = relation.getDBIDs();
    // LOCI preprocessing step
    WritableDataStore<DoubleIntArrayList> interestingDistances = DataStoreUtil.makeStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_SORTED, DoubleIntArrayList.class);
    precomputeInterestingRadii(ids, rangeQuery, interestingDistances);
    // LOCI main step
    FiniteProgress progressLOCI = LOG.isVerbose() ? new FiniteProgress("LOCI scores", relation.size(), LOG) : null;
    WritableDoubleDataStore mdef_norm = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    WritableDoubleDataStore mdef_radius = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    DoubleMinMax minmax = new DoubleMinMax();
    // Shared instance, to save allocations.
    MeanVariance mv_n_r_alpha = new MeanVariance();
    for (DBIDIter iditer = ids.iter(); iditer.valid(); iditer.advance()) {
        final DoubleIntArrayList cdist = interestingDistances.get(iditer);
        final double maxdist = cdist.getDouble(cdist.size() - 1);
        final int maxneig = cdist.getInt(cdist.size() - 1);
        double maxmdefnorm = 0.0;
        double maxnormr = 0;
        if (maxneig >= nmin) {
            // Compute the largest neighborhood we will need.
            DoubleDBIDList maxneighbors = rangeQuery.getRangeForDBID(iditer, maxdist);
            // For any critical distance, compute the normalized MDEF score.
            for (int i = 0, size = cdist.size(); i < size; i++) {
                // Only start when minimum size is fulfilled
                if (cdist.getInt(i) < nmin) {
                    continue;
                }
                final double r = cdist.getDouble(i);
                final double alpha_r = alpha * r;
                // compute n(p_i, \alpha * r) from list (note: alpha_r is not cdist!)
                final int n_alphar = cdist.getInt(cdist.find(alpha_r));
                // compute \hat{n}(p_i, r, \alpha) and the corresponding \simga_{MDEF}
                mv_n_r_alpha.reset();
                for (DoubleDBIDListIter neighbor = maxneighbors.iter(); neighbor.valid(); neighbor.advance()) {
                    // Stop at radius r
                    if (neighbor.doubleValue() > r) {
                        break;
                    }
                    DoubleIntArrayList cdist2 = interestingDistances.get(neighbor);
                    int rn_alphar = cdist2.getInt(cdist2.find(alpha_r));
                    mv_n_r_alpha.put(rn_alphar);
                }
                // We only use the average and standard deviation
                final double nhat_r_alpha = mv_n_r_alpha.getMean();
                final double sigma_nhat_r_alpha = mv_n_r_alpha.getNaiveStddev();
                // Redundant divisions by nhat_r_alpha removed.
                final double mdef = nhat_r_alpha - n_alphar;
                final double sigmamdef = sigma_nhat_r_alpha;
                final double mdefnorm = mdef / sigmamdef;
                if (mdefnorm > maxmdefnorm) {
                    maxmdefnorm = mdefnorm;
                    maxnormr = r;
                }
            }
        } else {
            // FIXME: when nmin was not fulfilled - what is the proper value then?
            maxmdefnorm = Double.POSITIVE_INFINITY;
            maxnormr = maxdist;
        }
        mdef_norm.putDouble(iditer, maxmdefnorm);
        mdef_radius.putDouble(iditer, maxnormr);
        minmax.put(maxmdefnorm);
        LOG.incrementProcessed(progressLOCI);
    }
    LOG.ensureCompleted(progressLOCI);
    DoubleRelation scoreResult = new MaterializedDoubleRelation("LOCI normalized MDEF", "loci-mdef-outlier", mdef_norm, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new QuotientOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0.0);
    OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
    result.addChildResult(new MaterializedDoubleRelation("LOCI MDEF Radius", "loci-critical-radius", mdef_radius, relation.getDBIDs()));
    return result;
}

Example 7 with MeanVariance

use of de.lmu.ifi.dbs.elki.math.MeanVariance in project elki by elki-project.

the class CTLuMedianAlgorithm method run.

/**
 * Main method.
 *
 * @param database Database
 * @param nrel Neighborhood relation
 * @param relation Data relation (1d!)
 * @return Outlier detection result
 */
public OutlierResult run(Database database, Relation<N> nrel, Relation<? extends NumberVector> relation) {
    final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(database, nrel);
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    MeanVariance mv = new MeanVariance();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        DBIDs neighbors = npred.getNeighborDBIDs(iditer);
        final double median;
        {
            double[] fi = new double[neighbors.size()];
            // calculate and store Median of neighborhood
            int c = 0;
            for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
                if (DBIDUtil.equal(iditer, iter)) {
                    continue;
                }
                fi[c] = relation.get(iter).doubleValue(0);
                c++;
            }
            if (c > 0) {
                median = QuickSelect.median(fi, 0, c);
            } else {
                median = relation.get(iditer).doubleValue(0);
            }
        }
        double h = relation.get(iditer).doubleValue(0) - median;
        scores.putDouble(iditer, h);
        mv.put(h);
    }
    // Normalize scores
    final double mean = mv.getMean();
    final double stddev = mv.getNaiveStddev();
    DoubleMinMax minmax = new DoubleMinMax();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double score = Math.abs((scores.doubleValue(iditer) - mean) / stddev);
        minmax.put(score);
        scores.putDouble(iditer, score);
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("MO", "Median-outlier", scores, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0);
    OutlierResult or = new OutlierResult(scoreMeta, scoreResult);
    or.addChildResult(npred);
    return or;
}

Example 8 with MeanVariance

use of de.lmu.ifi.dbs.elki.math.MeanVariance 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 9 with MeanVariance

use of de.lmu.ifi.dbs.elki.math.MeanVariance 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 10 with MeanVariance

use of de.lmu.ifi.dbs.elki.math.MeanVariance in project elki by elki-project.

the class CTLuScatterplotOutlier method run.

/**
 * Main method.
 *
 * @param database Database
 * @param nrel Neighborhood relation
 * @param relation Data relation (1d!)
 * @return Outlier detection result
 */
public OutlierResult run(Database database, Relation<N> nrel, Relation<? extends NumberVector> relation) {
    final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(database, nrel);
    WritableDoubleDataStore means = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP);
    // Calculate average of neighborhood for each object and perform a linear
    // regression using the covariance matrix
    CovarianceMatrix covm = new CovarianceMatrix(2);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        final double local = relation.get(iditer).doubleValue(0);
        // Compute mean of neighbors
        Mean mean = new Mean();
        DBIDs neighbors = npred.getNeighborDBIDs(iditer);
        for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
            if (DBIDUtil.equal(iditer, iter)) {
                continue;
            }
            mean.put(relation.get(iter).doubleValue(0));
        }
        final double m;
        if (mean.getCount() > 0) {
            m = mean.getMean();
        } else {
            // if object id has no neighbors ==> avg = non-spatial attribute of id
            m = local;
        }
        // Store the mean for the score calculation
        means.putDouble(iditer, m);
        covm.put(new double[] { local, m });
    }
    // Finalize covariance matrix, compute linear regression
    final double slope, inter;
    {
        double[] meanv = covm.getMeanVector();
        double[][] fmat = covm.destroyToSampleMatrix();
        final double covxx = fmat[0][0], covxy = fmat[0][1];
        slope = covxy / covxx;
        inter = meanv[1] - slope * meanv[0];
    }
    // calculate mean and variance for error
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    MeanVariance mv = new MeanVariance();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        // Compute the error from the linear regression
        double y_i = relation.get(iditer).doubleValue(0);
        double e = means.doubleValue(iditer) - (slope * y_i + inter);
        scores.putDouble(iditer, e);
        mv.put(e);
    }
    // Normalize scores
    DoubleMinMax minmax = new DoubleMinMax();
    {
        final double mean = mv.getMean();
        final double variance = mv.getNaiveStddev();
        for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
            double score = Math.abs((scores.doubleValue(iditer) - mean) / variance);
            minmax.put(score);
            scores.putDouble(iditer, score);
        }
    }
    // build representation
    DoubleRelation scoreResult = new MaterializedDoubleRelation("SPO", "Scatterplot-Outlier", scores, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0);
    OutlierResult or = new OutlierResult(scoreMeta, scoreResult);
    or.addChildResult(npred);
    return or;
}