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

Example 86 with DBIDs

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

the class HiCS method run.

/**
 * Perform HiCS on a given database.
 *
 * @param relation the database
 * @return The aggregated resulting scores that were assigned by the given
 *         outlier detection algorithm
 */
public OutlierResult run(Relation<V> relation) {
    final DBIDs ids = relation.getDBIDs();
    ArrayList<ArrayDBIDs> subspaceIndex = buildOneDimIndexes(relation);
    Set<HiCSSubspace> subspaces = calculateSubspaces(relation, subspaceIndex, rnd.getSingleThreadedRandom());
    if (LOG.isVerbose()) {
        LOG.verbose("Number of high-contrast subspaces: " + subspaces.size());
    }
    List<DoubleRelation> results = new ArrayList<>();
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Calculating Outlier scores for high Contrast subspaces", subspaces.size(), LOG) : null;
    // relation instead of SubspaceEuclideanDistanceFunction?)
    for (HiCSSubspace dimset : subspaces) {
        if (LOG.isVerbose()) {
            LOG.verbose("Performing outlier detection in subspace " + dimset);
        }
        ProxyDatabase pdb = new ProxyDatabase(ids);
        pdb.addRelation(new ProjectedView<>(relation, new NumericalFeatureSelection<V>(dimset)));
        // run LOF and collect the result
        OutlierResult result = outlierAlgorithm.run(pdb);
        results.add(result.getScores());
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    DoubleMinMax minmax = new DoubleMinMax();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double sum = 0.0;
        for (DoubleRelation r : results) {
            final double s = r.doubleValue(iditer);
            if (!Double.isNaN(s)) {
                sum += s;
            }
        }
        scores.putDouble(iditer, sum);
        minmax.put(sum);
    }
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax());
    DoubleRelation scoreres = new MaterializedDoubleRelation("HiCS", "HiCS-outlier", scores, relation.getDBIDs());
    return new OutlierResult(meta, scoreres);
}

Example 87 with DBIDs

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

the class HiCS method calculateContrast.

/**
 * Calculates the actual contrast of a given subspace.
 *
 * @param relation Relation to process
 * @param subspace Subspace
 * @param subspaceIndex Subspace indexes
 */
private void calculateContrast(Relation<? extends NumberVector> relation, HiCSSubspace subspace, ArrayList<ArrayDBIDs> subspaceIndex, Random random) {
    final int card = subspace.cardinality();
    final double alpha1 = FastMath.pow(alpha, (1.0 / card));
    final int windowsize = (int) (relation.size() * alpha1);
    final FiniteProgress prog = LOG.isDebugging() ? new FiniteProgress("Monte-Carlo iterations", m, LOG) : null;
    int retries = 0;
    double deviationSum = 0.0;
    for (int i = 0; i < m; i++) {
        // Choose a random set bit.
        int chosen = -1;
        for (int tmp = random.nextInt(card); tmp >= 0; tmp--) {
            chosen = subspace.nextSetBit(chosen + 1);
        }
        // initialize sample
        DBIDs conditionalSample = relation.getDBIDs();
        for (int j = subspace.nextSetBit(0); j >= 0; j = subspace.nextSetBit(j + 1)) {
            if (j == chosen) {
                continue;
            }
            ArrayDBIDs sortedIndices = subspaceIndex.get(j);
            ArrayModifiableDBIDs indexBlock = DBIDUtil.newArray(windowsize);
            // initialize index block
            DBIDArrayIter iter = sortedIndices.iter();
            iter.seek(random.nextInt(relation.size() - windowsize));
            for (int k = 0; k < windowsize; k++, iter.advance()) {
                // select index block
                indexBlock.add(iter);
            }
            conditionalSample = DBIDUtil.intersection(conditionalSample, indexBlock);
        }
        if (conditionalSample.size() < 10) {
            retries++;
            if (LOG.isDebugging()) {
                LOG.debug("Sample size very small. Retry no. " + retries);
            }
            if (retries >= MAX_RETRIES) {
                LOG.warning("Too many retries, for small samples: " + retries);
            } else {
                i--;
                continue;
            }
        }
        // Project conditional set
        double[] sampleValues = new double[conditionalSample.size()];
        {
            int l = 0;
            for (DBIDIter iter = conditionalSample.iter(); iter.valid(); iter.advance()) {
                sampleValues[l] = relation.get(iter).doubleValue(chosen);
                l++;
            }
        }
        // Project full set
        double[] fullValues = new double[relation.size()];
        {
            int l = 0;
            for (DBIDIter iter = subspaceIndex.get(chosen).iter(); iter.valid(); iter.advance()) {
                fullValues[l] = relation.get(iter).doubleValue(chosen);
                l++;
            }
        }
        double contrast = statTest.deviation(fullValues, sampleValues);
        if (Double.isNaN(contrast)) {
            i--;
            LOG.warning("Contrast was NaN");
            continue;
        }
        deviationSum += contrast;
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    subspace.contrast = deviationSum / m;
}

Example 88 with DBIDs

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

the class ParallelSimplifiedLOF method run.

public OutlierResult run(Database database, Relation<O> relation) {
    DBIDs ids = relation.getDBIDs();
    DistanceQuery<O> distq = database.getDistanceQuery(relation, getDistanceFunction());
    KNNQuery<O> knnq = database.getKNNQuery(distq, k + 1);
    // Phase one: KNN and k-dist
    WritableDataStore<KNNList> knns = DataStoreUtil.makeStorage(ids, DataStoreFactory.HINT_DB, KNNList.class);
    {
        // Compute kNN
        KNNProcessor<O> knnm = new KNNProcessor<>(k + 1, knnq);
        SharedObject<KNNList> knnv = new SharedObject<>();
        WriteDataStoreProcessor<KNNList> storek = new WriteDataStoreProcessor<>(knns);
        knnm.connectKNNOutput(knnv);
        storek.connectInput(knnv);
        ParallelExecutor.run(ids, knnm, storek);
    }
    // Phase two: simplified-lrd
    WritableDoubleDataStore lrds = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_DB);
    {
        SimplifiedLRDProcessor lrdm = new SimplifiedLRDProcessor(knns);
        SharedDouble lrdv = new SharedDouble();
        WriteDoubleDataStoreProcessor storelrd = new WriteDoubleDataStoreProcessor(lrds);
        lrdm.connectOutput(lrdv);
        storelrd.connectInput(lrdv);
        ParallelExecutor.run(ids, lrdm, storelrd);
    }
    // Phase three: Simplified-LOF
    WritableDoubleDataStore lofs = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_DB);
    DoubleMinMax minmax;
    {
        LOFProcessor lofm = new LOFProcessor(knns, lrds, true);
        SharedDouble lofv = new SharedDouble();
        DoubleMinMaxProcessor mmm = new DoubleMinMaxProcessor();
        WriteDoubleDataStoreProcessor storelof = new WriteDoubleDataStoreProcessor(lofs);
        lofm.connectOutput(lofv);
        mmm.connectInput(lofv);
        storelof.connectInput(lofv);
        ParallelExecutor.run(ids, lofm, storelof, mmm);
        minmax = mmm.getMinMax();
    }
    DoubleRelation scoreres = new MaterializedDoubleRelation("Simplified Local Outlier Factor", "simplified-lof-outlier", lofs, ids);
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 1.0);
    return new OutlierResult(meta, scoreres);
}

Example 89 with DBIDs

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

the class SimpleKernelDensityLOF method run.

/**
 * Run the naive kernel density LOF algorithm.
 *
 * @param database Database to query
 * @param relation Data to process
 * @return LOF outlier result
 */
public OutlierResult run(Database database, Relation<O> relation) {
    StepProgress stepprog = LOG.isVerbose() ? new StepProgress("KernelDensityLOF", 3) : null;
    final int dim = RelationUtil.dimensionality(relation);
    DBIDs ids = relation.getDBIDs();
    LOG.beginStep(stepprog, 1, "Materializing neighborhoods w.r.t. distance function.");
    KNNQuery<O> knnq = DatabaseUtil.precomputedKNNQuery(database, relation, getDistanceFunction(), k);
    // Compute LRDs
    LOG.beginStep(stepprog, 2, "Computing densities.");
    WritableDoubleDataStore dens = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_HOT | DataStoreFactory.HINT_TEMP);
    FiniteProgress densProgress = LOG.isVerbose() ? new FiniteProgress("Densities", ids.size(), LOG) : null;
    for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
        final KNNList neighbors = knnq.getKNNForDBID(it, k);
        int count = 0;
        double sum = 0.0;
        // Fast version for double distances
        for (DoubleDBIDListIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
            if (DBIDUtil.equal(neighbor, it)) {
                continue;
            }
            double max = knnq.getKNNForDBID(neighbor, k).getKNNDistance();
            if (max == 0) {
                sum = Double.POSITIVE_INFINITY;
                break;
            }
            final double v = neighbor.doubleValue() / max;
            sum += kernel.density(v) / MathUtil.powi(max, dim);
            count++;
        }
        final double density = count > 0 ? sum / count : 0.;
        dens.putDouble(it, density);
        LOG.incrementProcessed(densProgress);
    }
    LOG.ensureCompleted(densProgress);
    // compute LOF_SCORE of each db object
    LOG.beginStep(stepprog, 3, "Computing KLOFs.");
    WritableDoubleDataStore lofs = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_STATIC);
    // track the maximum value for normalization.
    DoubleMinMax lofminmax = new DoubleMinMax();
    FiniteProgress progressLOFs = LOG.isVerbose() ? new FiniteProgress("KLOF_SCORE for objects", ids.size(), LOG) : null;
    for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
        final double lrdp = dens.doubleValue(it);
        final double lof;
        if (lrdp > 0) {
            final KNNList neighbors = knnq.getKNNForDBID(it, k);
            double sum = 0.0;
            int count = 0;
            for (DBIDIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
                // skip the point itself
                if (DBIDUtil.equal(neighbor, it)) {
                    continue;
                }
                sum += dens.doubleValue(neighbor);
                count++;
            }
            lof = (lrdp == Double.POSITIVE_INFINITY) ? (sum == Double.POSITIVE_INFINITY ? 1 : 0.) : sum / (count * lrdp);
        } else {
            lof = 1.0;
        }
        lofs.putDouble(it, lof);
        // update minimum and maximum
        lofminmax.put(lof);
        LOG.incrementProcessed(progressLOFs);
    }
    LOG.ensureCompleted(progressLOFs);
    LOG.setCompleted(stepprog);
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Kernel Density Local Outlier Factor", "kernel-density-slof-outlier", lofs, ids);
    OutlierScoreMeta scoreMeta = new QuotientOutlierScoreMeta(lofminmax.getMin(), lofminmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 1.0);
    OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
    return result;
}

Example 90 with DBIDs

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

the class TrimmedMeanApproach method run.

/**
 * Run the algorithm.
 *
 * @param database Database
 * @param nrel Neighborhood relation
 * @param relation Data Relation (1 dimensional!)
 * @return Outlier detection result
 */
public OutlierResult run(Database database, Relation<N> nrel, Relation<? extends NumberVector> relation) {
    assert (RelationUtil.dimensionality(relation) == 1) : "TrimmedMean can only process one-dimensional data sets.";
    final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(database, nrel);
    WritableDoubleDataStore errors = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP);
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    FiniteProgress progress = LOG.isVerbose() ? new FiniteProgress("Computing trimmed means", relation.size(), LOG) : null;
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        DBIDs neighbors = npred.getNeighborDBIDs(iditer);
        int num = 0;
        double[] values = new double[neighbors.size()];
        // calculate trimmedMean
        for (DBIDIter iter = neighbors.iter(); iter.valid(); iter.advance()) {
            values[num] = relation.get(iter).doubleValue(0);
            num++;
        }
        // calculate local trimmed Mean and error term
        final double tm;
        if (num > 0) {
            int left = (int) Math.floor(p * (num - 1));
            int right = (int) Math.floor((1 - p) * (num - 1));
            Arrays.sort(values, 0, num);
            Mean mean = new Mean();
            for (int i = left; i <= right; i++) {
                mean.put(values[i]);
            }
            tm = mean.getMean();
        } else {
            tm = relation.get(iditer).doubleValue(0);
        }
        // Error: deviation from trimmed mean
        errors.putDouble(iditer, relation.get(iditer).doubleValue(0) - tm);
        LOG.incrementProcessed(progress);
    }
    LOG.ensureCompleted(progress);
    if (LOG.isVerbose()) {
        LOG.verbose("Computing median error.");
    }
    double median_dev_from_median;
    {
        // calculate the median error
        double[] ei = new double[relation.size()];
        {
            int i = 0;
            for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
                ei[i] = errors.doubleValue(iditer);
                i++;
            }
        }
        double median_i = QuickSelect.median(ei);
        // Update to deviation from median
        for (int i = 0; i < ei.length; i++) {
            ei[i] = Math.abs(ei[i] - median_i);
        }
        // Again, extract median
        median_dev_from_median = QuickSelect.median(ei);
    }
    if (LOG.isVerbose()) {
        LOG.verbose("Normalizing scores.");
    }
    // calculate score
    DoubleMinMax minmax = new DoubleMinMax();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double score = Math.abs(errors.doubleValue(iditer)) * 0.6745 / median_dev_from_median;
        scores.putDouble(iditer, score);
        minmax.put(score);
    }
    // 
    DoubleRelation scoreResult = new MaterializedDoubleRelation("TrimmedMean", "Trimmed Mean Score", 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;
}