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

Example 91 with DBIDs

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

the class UnweightedNeighborhoodAdapter method getWeightedNeighbors.

@Override
public Collection<DoubleDBIDPair> getWeightedNeighbors(DBIDRef reference) {
    DBIDs neighbors = inner.getNeighborDBIDs(reference);
    ArrayList<DoubleDBIDPair> adapted = new ArrayList<>(neighbors.size());
    for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
        adapted.add(DBIDUtil.newPair(1.0, iter));
    }
    return adapted;
}

Example 92 with DBIDs

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

the class AbstractAggarwalYuOutlier method buildRanges.

/**
 * Grid discretization of the data:<br />
 * Each attribute of data is divided into phi equi-depth ranges.<br />
 * Each range contains a fraction f=1/phi of the records.
 *
 * @param relation Relation to process
 * @return range map
 */
protected ArrayList<ArrayList<DBIDs>> buildRanges(Relation<V> relation) {
    final int dim = RelationUtil.dimensionality(relation);
    final int size = relation.size();
    final ArrayList<ArrayList<DBIDs>> ranges = new ArrayList<>();
    ArrayModifiableDBIDs ids = DBIDUtil.newArray(relation.getDBIDs());
    SortDBIDsBySingleDimension sorter = new SortDBIDsBySingleDimension(relation);
    // Split into cells
    final double part = size * 1.0 / phi;
    for (int d = 0; d < dim; d++) {
        sorter.setDimension(d);
        ids.sort(sorter);
        ArrayList<DBIDs> dimranges = new ArrayList<>(phi + 1);
        int start = 0;
        DBIDArrayIter iter = ids.iter();
        for (int r = 1; r <= phi; r++) {
            int end = (r < phi) ? (int) (part * r) : size;
            ArrayModifiableDBIDs currange = DBIDUtil.newArray(end - start);
            for (iter.seek(start); iter.getOffset() < end; iter.advance()) {
                currange.add(iter);
            }
            start = end;
            dimranges.add(currange);
        }
        ranges.add(dimranges);
    }
    return ranges;
}

Example 93 with DBIDs

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

the class AggarwalYuNaive method run.

/**
 * Run the algorithm on the given relation.
 *
 * @param relation Relation
 * @return Outlier detection result
 */
public OutlierResult run(Relation<V> relation) {
    final int dimensionality = RelationUtil.dimensionality(relation);
    final int size = relation.size();
    ArrayList<ArrayList<DBIDs>> ranges = buildRanges(relation);
    ArrayList<ArrayList<IntIntPair>> Rk;
    // Build a list of all subspaces
    {
        // R1 initial one-dimensional subspaces.
        Rk = new ArrayList<>();
        // Set of all dim*phi ranges
        ArrayList<IntIntPair> q = new ArrayList<>();
        for (int i = 0; i < dimensionality; i++) {
            for (int j = 0; j < phi; j++) {
                IntIntPair s = new IntIntPair(i, j);
                q.add(s);
                // Add to first Rk
                ArrayList<IntIntPair> v = new ArrayList<>();
                v.add(s);
                Rk.add(v);
            }
        }
        // build Ri
        for (int i = 2; i <= k; i++) {
            ArrayList<ArrayList<IntIntPair>> Rnew = new ArrayList<>();
            for (int j = 0; j < Rk.size(); j++) {
                ArrayList<IntIntPair> c = Rk.get(j);
                for (IntIntPair pair : q) {
                    boolean invalid = false;
                    for (int t = 0; t < c.size(); t++) {
                        if (c.get(t).first == pair.first) {
                            invalid = true;
                            break;
                        }
                    }
                    if (!invalid) {
                        ArrayList<IntIntPair> neu = new ArrayList<>(c);
                        neu.add(pair);
                        Rnew.add(neu);
                    }
                }
            }
            Rk = Rnew;
        }
    }
    WritableDoubleDataStore sparsity = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_STATIC);
    // calculate the sparsity coefficient
    for (ArrayList<IntIntPair> sub : Rk) {
        DBIDs ids = computeSubspace(sub, ranges);
        final double sparsityC = sparsity(ids.size(), size, k, phi);
        if (sparsityC < 0) {
            for (DBIDIter iter = ids.iter(); iter.valid(); iter.advance()) {
                double prev = sparsity.doubleValue(iter);
                if (Double.isNaN(prev) || sparsityC < prev) {
                    sparsity.putDouble(iter, sparsityC);
                }
            }
        }
    }
    DoubleMinMax minmax = new DoubleMinMax();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double val = sparsity.doubleValue(iditer);
        if (Double.isNaN(val)) {
            sparsity.putDouble(iditer, 0.0);
            val = 0.0;
        }
        minmax.put(val);
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("AggarwalYuNaive", "aggarwal-yu-outlier", sparsity, relation.getDBIDs());
    OutlierScoreMeta meta = new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax(), Double.NEGATIVE_INFINITY, 0.0);
    return new OutlierResult(meta, scoreResult);
}

Example 94 with DBIDs

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

the class SLOM method run.

/**
 * @param database Database to process
 * @param spatial Spatial Relation to use.
 * @param relation Relation to use.
 * @return Outlier detection result
 */
public OutlierResult run(Database database, Relation<N> spatial, Relation<O> relation) {
    final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(database, spatial);
    DistanceQuery<O> distFunc = getNonSpatialDistanceFunction().instantiate(relation);
    WritableDoubleDataStore modifiedDistance = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    // calculate D-Tilde
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double sum = 0;
        double maxDist = 0;
        int cnt = 0;
        final DBIDs neighbors = npred.getNeighborDBIDs(iditer);
        for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
            if (DBIDUtil.equal(iditer, iter)) {
                continue;
            }
            double dist = distFunc.distance(iditer, iter);
            sum += dist;
            cnt++;
            maxDist = Math.max(maxDist, dist);
        }
        if (cnt > 1) {
            modifiedDistance.putDouble(iditer, ((sum - maxDist) / (cnt - 1)));
        } else {
            // Use regular distance when the d-tilde trick is undefined.
            // Note: this can be 0 when there were no neighbors.
            modifiedDistance.putDouble(iditer, maxDist);
        }
    }
    // Second step - compute actual SLOM values
    DoubleMinMax slomminmax = new DoubleMinMax();
    WritableDoubleDataStore sloms = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double sum = 0;
        int cnt = 0;
        final DBIDs neighbors = npred.getNeighborDBIDs(iditer);
        for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
            if (DBIDUtil.equal(iditer, iter)) {
                continue;
            }
            sum += modifiedDistance.doubleValue(iter);
            cnt++;
        }
        double slom;
        if (cnt > 0) {
            // With and without the object itself:
            double avgPlus = (sum + modifiedDistance.doubleValue(iditer)) / (cnt + 1);
            double avg = sum / cnt;
            double beta = 0;
            for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
                final double dist = modifiedDistance.doubleValue(iter);
                if (dist > avgPlus) {
                    beta += 1;
                } else if (dist < avgPlus) {
                    beta -= 1;
                }
            }
            // Include object itself
            if (!neighbors.contains(iditer)) {
                final double dist = modifiedDistance.doubleValue(iditer);
                if (dist > avgPlus) {
                    beta += 1;
                } else if (dist < avgPlus) {
                    beta -= 1;
                }
            }
            beta = Math.abs(beta);
            // note: cnt == size of N(x), not N+(x)
            if (cnt > 1) {
                beta = Math.max(beta, 1.0) / (cnt - 1);
            } else {
                // Workaround insufficiency in SLOM paper - div by zero
                beta = 1.0;
            }
            beta = beta / (1 + avg);
            slom = beta * modifiedDistance.doubleValue(iditer);
        } else {
            // No neighbors to compare to - no score.
            slom = 0.0;
        }
        sloms.putDouble(iditer, slom);
        slomminmax.put(slom);
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("SLOM", "slom-outlier", sloms, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(slomminmax.getMin(), slomminmax.getMax(), 0.0, Double.POSITIVE_INFINITY);
    OutlierResult or = new OutlierResult(scoreMeta, scoreResult);
    or.addChildResult(npred);
    return or;
}

Example 95 with DBIDs

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

the class FastABOD method run.

/**
 * Run Fast-ABOD on the data set.
 *
 * @param relation Relation to process
 * @return Outlier detection result
 */
@Override
public OutlierResult run(Database db, Relation<V> relation) {
    DBIDs ids = 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();
    KNNHeap nn = DBIDUtil.newHeap(k);
    for (DBIDIter pA = ids.iter(); pA.valid(); pA.advance()) {
        final double simAA = kernelMatrix.getSimilarity(pA, pA);
        // Choose the k-min nearest
        nn.clear();
        for (DBIDIter nB = relation.iterDBIDs(); nB.valid(); nB.advance()) {
            if (DBIDUtil.equal(nB, pA)) {
                continue;
            }
            double simBB = kernelMatrix.getSimilarity(nB, nB);
            double simAB = kernelMatrix.getSimilarity(pA, nB);
            double sqdAB = simAA + simBB - simAB - simAB;
            if (!(sqdAB > 0.)) {
                continue;
            }
            nn.insert(sqdAB, nB);
        }
        KNNList nl = nn.toKNNList();
        s.reset();
        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 div = 1. / (sqdAB * sqdAC);
                s.put(numerator * div, FastMath.sqrt(div));
            }
        }
        // Sample variance probably would probably be better, but the ABOD
        // publication uses the naive variance.
        final double abof = s.getNaiveVariance();
        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);
}