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

Example 1 with BasicOutlierScoreMeta

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

the class LDF 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("LDF", 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 LDEs
    LOG.beginStep(stepprog, 2, "Computing LDEs.");
    WritableDoubleDataStore ldes = 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);
        double sum = 0.0;
        int count = 0;
        // Fast version for double distances
        for (DoubleDBIDListIter neighbor = neighbors.iter(); neighbor.valid(); neighbor.advance()) {
            if (DBIDUtil.equal(neighbor, it)) {
                continue;
            }
            final double nkdist = knnq.getKNNForDBID(neighbor, k).getKNNDistance();
            if (!(nkdist > 0.) || nkdist == Double.POSITIVE_INFINITY) {
                sum = Double.POSITIVE_INFINITY;
                count++;
                break;
            }
            final double v = MathUtil.max(nkdist, neighbor.doubleValue()) / (h * nkdist);
            sum += kernel.density(v) / MathUtil.powi(h * nkdist, dim);
            count++;
        }
        ldes.putDouble(it, sum / count);
        LOG.incrementProcessed(densProgress);
    }
    LOG.ensureCompleted(densProgress);
    // Compute local density factors.
    LOG.beginStep(stepprog, 3, "Computing LDFs.");
    WritableDoubleDataStore ldfs = DataStoreUtil.makeDoubleStorage(ids, DataStoreFactory.HINT_STATIC);
    // track the maximum value for normalization.
    DoubleMinMax lofminmax = new DoubleMinMax();
    FiniteProgress progressLOFs = LOG.isVerbose() ? new FiniteProgress("Local Density Factors", ids.size(), LOG) : null;
    for (DBIDIter it = ids.iter(); it.valid(); it.advance()) {
        final double lrdp = ldes.doubleValue(it);
        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 += ldes.doubleValue(neighbor);
            count++;
        }
        sum /= count;
        final double div = lrdp + c * sum;
        double ldf = div == Double.POSITIVE_INFINITY ? (sum < Double.POSITIVE_INFINITY ? 0. : 1) : (div > 0) ? sum / div : 0;
        ldfs.putDouble(it, ldf);
        // update minimum and maximum
        lofminmax.put(ldf);
        LOG.incrementProcessed(progressLOFs);
    }
    LOG.ensureCompleted(progressLOFs);
    LOG.setCompleted(stepprog);
    // Build result representation.
    DoubleRelation scoreResult = new MaterializedDoubleRelation("Local Density Factor", "ldf-outlier", ldfs, ids);
    OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(lofminmax.getMin(), lofminmax.getMax(), 0.0, 1. / c, 1 / (1 + c));
    OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
    return result;
}

Example 2 with BasicOutlierScoreMeta

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

the class HilOut method run.

public OutlierResult run(Database database, Relation<O> relation) {
    distq = database.getDistanceQuery(relation, getDistanceFunction());
    d = RelationUtil.dimensionality(relation);
    WritableDoubleDataStore hilout_weight = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    // Compute extend of dataset.
    double[] min;
    // Actually "length of edge"
    double diameter = 0;
    {
        double[][] hbbs = RelationUtil.computeMinMax(relation);
        min = hbbs[0];
        double[] max = hbbs[1];
        for (int i = 0; i < d; i++) {
            diameter = Math.max(diameter, max[i] - min[i]);
        }
        // Enlarge bounding box to have equal lengths.
        for (int i = 0; i < d; i++) {
            double diff = (diameter - (max[i] - min[i])) * .5;
            min[i] -= diff;
            max[i] += diff;
        }
        if (LOG.isVerbose()) {
            LOG.verbose("Rescaling dataset by " + (1 / diameter) + " to fit the unit cube.");
        }
    }
    // Initialization part
    capital_n_star = capital_n = relation.size();
    HilbertFeatures h = new HilbertFeatures(relation, min, diameter);
    FiniteProgress progressHilOut = LOG.isVerbose() ? new FiniteProgress("HilOut iterations", d + 1, LOG) : null;
    FiniteProgress progressTrueOut = LOG.isVerbose() ? new FiniteProgress("True outliers found", n, LOG) : null;
    // Main part: 1. Phase max. d+1 loops
    for (int j = 0; j <= d && n_star < n; j++) {
        // initialize (clear) out and wlb - not 100% clear in the paper
        h.out.clear();
        h.wlb.clear();
        // Initialize Hilbert values in pf according to current shift
        h.initialize(.5 * j / (d + 1));
        // scan the Data according to the current shift; build out and wlb
        scan(h, (int) (k * capital_n / (double) capital_n_star));
        // determine the true outliers (n_star)
        trueOutliers(h);
        if (progressTrueOut != null) {
            progressTrueOut.setProcessed(n_star, LOG);
        }
        // Build the top Set as out + wlb
        h.top.clear();
        HashSetModifiableDBIDs top_keys = DBIDUtil.newHashSet(h.out.size());
        for (ObjectHeap.UnsortedIter<HilFeature> iter = h.out.unsortedIter(); iter.valid(); iter.advance()) {
            HilFeature entry = iter.get();
            top_keys.add(entry.id);
            h.top.add(entry);
        }
        for (ObjectHeap.UnsortedIter<HilFeature> iter = h.wlb.unsortedIter(); iter.valid(); iter.advance()) {
            HilFeature entry = iter.get();
            if (!top_keys.contains(entry.id)) {
                // No need to update top_keys - discarded
                h.top.add(entry);
            }
        }
        LOG.incrementProcessed(progressHilOut);
    }
    // 2. Phase: Additional Scan if less than n true outliers determined
    if (n_star < n) {
        h.out.clear();
        h.wlb.clear();
        // TODO: reinitialize shift to 0?
        scan(h, capital_n);
    }
    if (progressHilOut != null) {
        progressHilOut.setProcessed(d, LOG);
        progressHilOut.ensureCompleted(LOG);
    }
    if (progressTrueOut != null) {
        progressTrueOut.setProcessed(n, LOG);
        progressTrueOut.ensureCompleted(LOG);
    }
    DoubleMinMax minmax = new DoubleMinMax();
    // Return weights in out
    if (tn == ScoreType.TopN) {
        minmax.put(0.0);
        for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
            hilout_weight.putDouble(iditer, 0.0);
        }
        for (ObjectHeap.UnsortedIter<HilFeature> iter = h.out.unsortedIter(); iter.valid(); iter.advance()) {
            HilFeature ent = iter.get();
            minmax.put(ent.ubound);
            hilout_weight.putDouble(ent.id, ent.ubound);
        }
    } else // Return all weights in pf
    {
        for (HilFeature ent : h.pf) {
            minmax.put(ent.ubound);
            hilout_weight.putDouble(ent.id, ent.ubound);
        }
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("HilOut weight", "hilout-weight", hilout_weight, relation.getDBIDs());
    OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY);
    OutlierResult result = new OutlierResult(scoreMeta, scoreResult);
    return result;
}

Example 3 with BasicOutlierScoreMeta

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

the class KNNWeightOutlier 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 kNN weights", relation.size(), LOG) : null;
    DoubleMinMax minmax = new DoubleMinMax();
    WritableDoubleDataStore knnw_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;
        }
        if (i < k) {
            // Less than k neighbors found
            // Approximative index, or k > data set size!
            skn = Double.POSITIVE_INFINITY;
        }
        knnw_score.putDouble(iditer, skn);
        minmax.put(skn);
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    DoubleRelation res = new MaterializedDoubleRelation("kNN weight Outlier Score", "knnw-outlier", knnw_score, relation.getDBIDs());
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0., Double.POSITIVE_INFINITY, 0.);
    return new OutlierResult(meta, res);
}

Example 4 with BasicOutlierScoreMeta

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

the class IntrinsicDimensionalityOutlier method run.

/**
 * Run the algorithm
 *
 * @param database Database
 * @param relation Data relation
 * @return Outlier result
 */
public OutlierResult run(Database database, Relation<O> relation) {
    final DistanceQuery<O> distanceQuery = database.getDistanceQuery(relation, getDistanceFunction());
    final KNNQuery<O> knnQuery = database.getKNNQuery(distanceQuery, k + 1);
    FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("kNN distance for objects", relation.size(), LOG) : null;
    DoubleMinMax minmax = new DoubleMinMax();
    WritableDoubleDataStore id_score = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double id = 0.;
        try {
            id = estimator.estimate(knnQuery, iditer, k + 1);
        } catch (ArithmeticException e) {
            id = 0.;
        }
        id_score.putDouble(iditer, id);
        minmax.put(id);
        LOG.incrementProcessed(prog);
    }
    LOG.ensureCompleted(prog);
    DoubleRelation scoreres = new MaterializedDoubleRelation("Intrinsic dimensionality", "id-score", id_score, relation.getDBIDs());
    OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax(), 0.0, Double.POSITIVE_INFINITY, 0.0);
    return new OutlierResult(meta, scoreres);
}

Example 5 with BasicOutlierScoreMeta

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

the class ExternalDoubleOutlierScore method run.

/**
 * Run the algorithm.
 *
 * @param database Database to use
 * @param relation Relation to use
 * @return Result
 */
public OutlierResult run(Database database, Relation<?> relation) {
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_STATIC);
    DoubleMinMax minmax = new DoubleMinMax();
    try (// 
    InputStream in = FileUtil.tryGzipInput(new FileInputStream(file));
        TokenizedReader reader = CSVReaderFormat.DEFAULT_FORMAT.makeReader()) {
        Tokenizer tokenizer = reader.getTokenizer();
        CharSequence buf = reader.getBuffer();
        Matcher mi = idpattern.matcher(buf), ms = scorepattern.matcher(buf);
        reader.reset(in);
        while (reader.nextLineExceptComments()) {
            Integer id = null;
            double score = Double.NaN;
            for (; /* initialized by nextLineExceptComments */
            tokenizer.valid(); tokenizer.advance()) {
                mi.region(tokenizer.getStart(), tokenizer.getEnd());
                ms.region(tokenizer.getStart(), tokenizer.getEnd());
                final boolean mif = mi.find();
                final boolean msf = ms.find();
                if (mif && msf) {
                    throw new AbortException("ID pattern and score pattern both match value: " + tokenizer.getSubstring());
                }
                if (mif) {
                    if (id != null) {
                        throw new AbortException("ID pattern matched twice: previous value " + id + " second value: " + tokenizer.getSubstring());
                    }
                    id = ParseUtil.parseIntBase10(buf, mi.end(), tokenizer.getEnd());
                }
                if (msf) {
                    if (!Double.isNaN(score)) {
                        throw new AbortException("Score pattern matched twice: previous value " + score + " second value: " + tokenizer.getSubstring());
                    }
                    score = ParseUtil.parseDouble(buf, ms.end(), tokenizer.getEnd());
                }
            }
            if (id != null && !Double.isNaN(score)) {
                scores.putDouble(DBIDUtil.importInteger(id), score);
                minmax.put(score);
            } else if (id == null && Double.isNaN(score)) {
                LOG.warning("Line did not match either ID nor score nor comment: " + reader.getLineNumber());
            } else {
                throw new AbortException("Line matched only ID or only SCORE patterns: " + reader.getLineNumber());
            }
        }
    } catch (IOException e) {
        throw new AbortException("Could not load outlier scores: " + e.getMessage() + " when loading " + file, e);
    }
    OutlierScoreMeta meta;
    if (inverted) {
        meta = new InvertedOutlierScoreMeta(minmax.getMin(), minmax.getMax());
    } else {
        meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax());
    }
    DoubleRelation scoresult = new MaterializedDoubleRelation("External Outlier", "external-outlier", scores, relation.getDBIDs());
    OutlierResult or = new OutlierResult(meta, scoresult);
    // Apply scaling
    if (scaling instanceof OutlierScalingFunction) {
        ((OutlierScalingFunction) scaling).prepare(or);
    }
    DoubleMinMax mm = new DoubleMinMax();
    for (DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
        double val = scoresult.doubleValue(iditer);
        val = scaling.getScaled(val);
        scores.putDouble(iditer, val);
        mm.put(val);
    }
    meta = new BasicOutlierScoreMeta(mm.getMin(), mm.getMax());
    or = new OutlierResult(meta, scoresult);
    return or;
}