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

Example 41 with OutlierResult

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

the class DistanceStddevOutlier method run.

/**
 * Run the outlier detection algorithm
 *
 * @param database Database to use
 * @param relation Relation to analyze
 * @return Outlier score result
 */
public OutlierResult run(Database database, Relation<O> relation) {
    // Get a nearest neighbor query on the relation.
    KNNQuery<O> knnq = QueryUtil.getKNNQuery(relation, getDistanceFunction(), k);
    // Output data storage
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_DB);
    // Track minimum and maximum scores
    DoubleMinMax minmax = new DoubleMinMax();
    // Iterate over all objects
    for (DBIDIter iter = relation.iterDBIDs(); iter.valid(); iter.advance()) {
        KNNList neighbors = knnq.getKNNForDBID(iter, k);
        // Aggregate distances
        MeanVariance mv = new MeanVariance();
        for (DoubleDBIDListIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
            // Skip the object itself. The 0 is not very informative.
            if (DBIDUtil.equal(iter, neighbor)) {
                continue;
            }
            mv.put(neighbor.doubleValue());
        }
        // Store score
        scores.putDouble(iter, mv.getSampleStddev());
    }
    // Wrap the result in the standard containers
    // Actual min-max, theoretical min-max!
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0, Double.POSITIVE_INFINITY);
    DoubleRelation rel = new MaterializedDoubleRelation(relation.getDBIDs(), "stddev-outlier", scores);
    return new OutlierResult(meta, rel);
}

Example 42 with OutlierResult

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

the class TrivialGeneratedOutlier method run.

/**
 * Run the algorithm
 *
 * @param models Model relation
 * @param vecs Vector relation
 * @param labels Label relation
 * @return Outlier result
 */
public OutlierResult run(Relation<Model> models, Relation<NumberVector> vecs, Relation<?> labels) {
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(models.getDBIDs(), DataStoreFactory.HINT_HOT);
    HashSet<GeneratorSingleCluster> generators = new HashSet<>();
    for (DBIDIter iditer = models.iterDBIDs(); iditer.valid(); iditer.advance()) {
        Model model = models.get(iditer);
        if (model instanceof GeneratorSingleCluster) {
            generators.add((GeneratorSingleCluster) model);
        }
    }
    if (generators.isEmpty()) {
        LOG.warning("No generator models found for dataset - all points will be considered outliers.");
    }
    for (GeneratorSingleCluster gen : generators) {
        for (int i = 0; i < gen.getDim(); i++) {
            Distribution dist = gen.getDistribution(i);
            if (!(dist instanceof NormalDistribution)) {
                throw new AbortException("TrivialGeneratedOutlier currently only supports normal distributions, got: " + dist);
            }
        }
    }
    for (DBIDIter iditer = models.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double score = 1.;
        double[] v = vecs.get(iditer).toArray();
        for (GeneratorSingleCluster gen : generators) {
            double[] tv = v;
            // Transform backwards
            if (gen.getTransformation() != null) {
                tv = gen.getTransformation().applyInverse(v);
            }
            final int dim = tv.length;
            double lensq = 0.0;
            int norm = 0;
            for (int i = 0; i < dim; i++) {
                Distribution dist = gen.getDistribution(i);
                if (dist instanceof NormalDistribution) {
                    NormalDistribution d = (NormalDistribution) dist;
                    double delta = (tv[i] - d.getMean()) / d.getStddev();
                    lensq += delta * delta;
                    norm += 1;
                } else {
                    throw new AbortException("TrivialGeneratedOutlier currently only supports normal distributions, got: " + dist);
                }
            }
            if (norm > 0.) {
                // The squared distances are ChiSquared distributed
                score = Math.min(score, ChiSquaredDistribution.cdf(lensq, norm));
            } else {
                score = 0.;
            }
        }
        if (expect < 1) {
            score = expect * score / (1 - score + expect);
        }
        scores.putDouble(iditer, score);
    }
    DoubleRelation scoreres = new MaterializedDoubleRelation("Model outlier scores", "model-outlier", scores, models.getDBIDs());
    OutlierScoreMeta meta = new ProbabilisticOutlierScore(0., 1.);
    return new OutlierResult(meta, scoreres);
}

Example 43 with OutlierResult

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

the class ComputeKNNOutlierScores method run.

@Override
public void run() {
    final Database database = inputstep.getDatabase();
    final Relation<O> relation = database.getRelation(distf.getInputTypeRestriction());
    // Ensure we don't go beyond the relation size:
    final int maxk = Math.min(this.maxk, relation.size() - 1);
    // Get a KNN query.
    final int lim = Math.min(maxk + 2, relation.size());
    KNNQuery<O> knnq = QueryUtil.getKNNQuery(relation, distf, lim);
    // Precompute kNN:
    if (!(knnq instanceof PreprocessorKNNQuery)) {
        MaterializeKNNPreprocessor<O> preproc = new MaterializeKNNPreprocessor<>(relation, distf, lim);
        preproc.initialize();
        relation.getHierarchy().add(relation, preproc);
    }
    // Test that we now get a proper index query
    knnq = QueryUtil.getKNNQuery(relation, distf, lim);
    if (!(knnq instanceof PreprocessorKNNQuery)) {
        throw new AbortException("Not using preprocessor knn query -- KNN queries using class: " + knnq.getClass());
    }
    // Warn for some known slow methods and large k:
    if (!isDisabled("LDOF") && maxk > 100) {
        LOG.verbose("Note: LODF needs O(k^2) distance computations. Use -" + Parameterizer.DISABLE_ID.getName() + " LDOF to disable.");
    }
    if (!isDisabled("FastABOD") && maxk > 100) {
        LOG.warning("Note: FastABOD needs quadratic memory. Use -" + Parameterizer.DISABLE_ID.getName() + " FastABOD to disable.");
    }
    if (!isDisabled("DWOF") && maxk > 100) {
        LOG.warning("Note: DWOF needs O(k^2) distance computations. Use -" + Parameterizer.DISABLE_ID.getName() + " DWOF to disable.");
    }
    final DBIDs ids = relation.getDBIDs();
    try (PrintStream fout = new PrintStream(outfile)) {
        // Control: print the DBIDs in case we are seeing an odd iteration
        // 
        fout.append("# Data set size: " + relation.size()).append(" data type: " + relation.getDataTypeInformation()).append(FormatUtil.NEWLINE);
        // Label outlier result (reference)
        writeResult(fout, ids, bylabel.run(database), new IdentityScaling(), "bylabel");
        final int startk = (this.startk > 0) ? this.startk : this.stepk;
        final int startkmin2 = (startk >= 2) ? startk : (startk + stepk);
        final int startkmin3 = (startk >= 3) ? startk : (startkmin2 >= 3) ? startkmin2 : (startkmin2 + stepk);
        // Output function:
        BiConsumer<String, OutlierResult> out = (kstr, result) -> writeResult(fout, ids, result, scaling, kstr);
        // KNN
        runForEachK(// 
        "KNN", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNOutlier<O>(distf, k).run(database, relation), out);
        // KNN Weight
        runForEachK(// 
        "KNNW", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNWeightOutlier<O>(distf, k).run(database, relation), out);
        // Run LOF
        runForEachK(// 
        "LOF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LOF<O>(k, distf).run(database, relation), out);
        // Run Simplified-LOF
        runForEachK(// 
        "SimplifiedLOF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new SimplifiedLOF<O>(k, distf).run(database, relation), out);
        // LoOP
        runForEachK(// 
        "LoOP", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LoOP<O>(k, k, distf, distf, 1.0).run(database, relation), out);
        // LDOF
        runForEachK(// 
        "LDOF", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new LDOF<O>(distf, k).run(database, relation), out);
        // Run ODIN
        runForEachK(// 
        "ODIN", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new ODIN<O>(distf, k).run(database, relation), out);
        // Run FastABOD
        runForEachK(// 
        "FastABOD", // 
        startkmin3, // 
        stepk, // 
        maxk, k -> // 
        new FastABOD<O>(new PolynomialKernelFunction(2), k).run(database, relation), out);
        // Run KDEOS with intrinsic dimensionality 2.
        runForEachK(// 
        "KDEOS", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> new // 
        KDEOS<O>(// 
        distf, // 
        k, // 
        k, // 
        GaussianKernelDensityFunction.KERNEL, // 
        0., 0.5 * GaussianKernelDensityFunction.KERNEL.canonicalBandwidth(), // 
        2).run(database, relation), out);
        // Run LDF
        runForEachK(// 
        "LDF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LDF<O>(k, distf, GaussianKernelDensityFunction.KERNEL, 1., .1).run(database, relation), out);
        // Run INFLO
        runForEachK(// 
        "INFLO", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new INFLO<O>(distf, 1.0, k).run(database, relation), out);
        // Run COF
        runForEachK(// 
        "COF", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new COF<O>(k, distf).run(database, relation), out);
        // Run simple Intrinsic dimensionality
        runForEachK(// 
        "Intrinsic", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new IntrinsicDimensionalityOutlier<O>(distf, k, AggregatedHillEstimator.STATIC).run(database, relation), out);
        // Run IDOS
        runForEachK(// 
        "IDOS", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new IDOS<O>(distf, AggregatedHillEstimator.STATIC, k, k).run(database, relation), out);
        // Run simple kernel-density LOF variant
        runForEachK(// 
        "KDLOF", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new SimpleKernelDensityLOF<O>(k, distf, GaussianKernelDensityFunction.KERNEL).run(database, relation), out);
        // Run DWOF (need pairwise distances, too)
        runForEachK(// 
        "DWOF", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new DWOF<O>(distf, k, 1.1).run(database, relation), out);
        // Run LIC
        runForEachK(// 
        "LIC", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new LocalIsolationCoefficient<O>(distf, k).run(database, relation), out);
        // Run VOV (requires a vector field).
        if (TypeUtil.DOUBLE_VECTOR_FIELD.isAssignableFromType(relation.getDataTypeInformation())) {
            @SuppressWarnings("unchecked") final DistanceFunction<? super DoubleVector> df = (DistanceFunction<? super DoubleVector>) distf;
            @SuppressWarnings("unchecked") final Relation<DoubleVector> rel = (Relation<DoubleVector>) (Relation<?>) relation;
            runForEachK(// 
            "VOV", // 
            startk, // 
            stepk, // 
            maxk, k -> // 
            new VarianceOfVolume<DoubleVector>(k, df).run(database, rel), out);
        }
        // Run KNN DD
        runForEachK(// 
        "KNNDD", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNDD<O>(distf, k).run(database, relation), out);
        // Run KNN SOS
        runForEachK(// 
        "KNNSOS", // 
        startk, // 
        stepk, // 
        maxk, k -> // 
        new KNNSOS<O>(distf, k).run(relation), out);
        // Run ISOS
        runForEachK(// 
        "ISOS", // 
        startkmin2, // 
        stepk, // 
        maxk, k -> // 
        new ISOS<O>(distf, k, AggregatedHillEstimator.STATIC).run(relation), out);
    } catch (FileNotFoundException e) {
        throw new AbortException("Cannot create output file.", e);
    }
}

Example 44 with OutlierResult

use of de.lmu.ifi.dbs.elki.result.outlier.OutlierResult 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 45 with OutlierResult

use of de.lmu.ifi.dbs.elki.result.outlier.OutlierResult 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;
}