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

Example 96 with DBIDs

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

the class JudgeOutlierScores method processNewResult.

@Override
public void processNewResult(ResultHierarchy hier, Result result) {
    Database db = ResultUtil.findDatabase(hier);
    List<OutlierResult> ors = ResultUtil.filterResults(hier, OutlierResult.class);
    if (ors == null || ors.isEmpty()) {
        // logger.warning("No results found for "+JudgeOutlierScores.class.getSimpleName());
        return;
    }
    ModifiableDBIDs ids = DBIDUtil.newHashSet(ors.iterator().next().getScores().getDBIDs());
    DBIDs outlierIds = DatabaseUtil.getObjectsByLabelMatch(db, positiveClassName);
    ids.removeDBIDs(outlierIds);
    for (OutlierResult or : ors) {
        db.getHierarchy().add(or, computeScore(ids, outlierIds, or));
    }
}

Example 97 with DBIDs

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

the class OutlierPrecisionRecallCurve method processNewResult.

@Override
public void processNewResult(ResultHierarchy hier, Result result) {
    Database db = ResultUtil.findDatabase(hier);
    // Prepare
    SetDBIDs positiveids = DBIDUtil.ensureSet(DatabaseUtil.getObjectsByLabelMatch(db, positiveClassName));
    if (positiveids.size() == 0) {
        LOG.warning("Computing a P/R curve failed - no objects matched.");
        return;
    }
    List<OutlierResult> oresults = OutlierResult.getOutlierResults(result);
    List<OrderingResult> orderings = ResultUtil.getOrderingResults(result);
    // Outlier results are the main use case.
    for (OutlierResult o : oresults) {
        DBIDs sorted = o.getOrdering().order(o.getOrdering().getDBIDs());
        PRCurve curve = computePrecisionResult(o.getScores().size(), positiveids, sorted.iter(), o.getScores());
        db.getHierarchy().add(o, curve);
        EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), o, "Evaluation of ranking", "ranking-evaluation");
        ev.findOrCreateGroup("Evaluation measures").addMeasure(PRAUC_LABEL, curve.getAUC(), 0., 1., false);
        // Process them only once.
        orderings.remove(o.getOrdering());
    }
    // otherwise apply an ordering to the database IDs.
    for (OrderingResult or : orderings) {
        DBIDs sorted = or.order(or.getDBIDs());
        PRCurve curve = computePrecisionResult(or.getDBIDs().size(), positiveids, sorted.iter(), null);
        db.getHierarchy().add(or, curve);
        EvaluationResult ev = EvaluationResult.findOrCreate(db.getHierarchy(), or, "Evaluation of ranking", "ranking-evaluation");
        ev.findOrCreateGroup("Evaluation measures").addMeasure(PRAUC_LABEL, curve.getAUC(), 0., 1., false);
    }
}

Example 98 with DBIDs

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

the class OutlierRankingEvaluation method processNewResult.

@Override
public void processNewResult(ResultHierarchy hier, Result result) {
    Database db = ResultUtil.findDatabase(hier);
    SetDBIDs positiveids = DBIDUtil.ensureSet(DatabaseUtil.getObjectsByLabelMatch(db, positiveClassName));
    if (positiveids.size() == 0) {
        LOG.warning("Cannot evaluate outlier results - no objects matched the given pattern.");
        return;
    }
    boolean nonefound = true;
    List<OutlierResult> oresults = OutlierResult.getOutlierResults(result);
    List<OrderingResult> orderings = ResultUtil.getOrderingResults(result);
    // Outlier results are the main use case.
    for (OutlierResult o : oresults) {
        db.getHierarchy().add(o, evaluateOutlierResult(o.getScores().size(), positiveids, o));
        // Process them only once.
        orderings.remove(o.getOrdering());
        nonefound = false;
    }
    // otherwise apply an ordering to the database IDs.
    for (OrderingResult or : orderings) {
        DBIDs sorted = or.order(or.getDBIDs());
        db.getHierarchy().add(or, evaluateOrderingResult(or.getDBIDs().size(), positiveids, sorted));
        nonefound = false;
    }
    if (nonefound) {
        return;
    // LOG.warning("No results found to process with ROC curve analyzer. Got
    // "+iterables.size()+" iterables, "+orderings.size()+" orderings.");
    }
}

Example 99 with DBIDs

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

the class OutlierPrecisionAtKCurve method processNewResult.

@Override
public void processNewResult(ResultHierarchy hier, Result result) {
    Database db = ResultUtil.findDatabase(hier);
    // Prepare
    SetDBIDs positiveids = DBIDUtil.ensureSet(DatabaseUtil.getObjectsByLabelMatch(db, positiveClassName));
    if (positiveids.size() == 0) {
        LOG.warning("Computing a ROC curve failed - no objects matched.");
        return;
    }
    List<OutlierResult> oresults = OutlierResult.getOutlierResults(result);
    List<OrderingResult> orderings = ResultUtil.getOrderingResults(result);
    // Outlier results are the main use case.
    for (OutlierResult o : oresults) {
        DBIDs sorted = o.getOrdering().order(o.getOrdering().getDBIDs());
        db.getHierarchy().add(o, computePrecisionResult(o.getScores().size(), positiveids, sorted));
        // Process them only once.
        orderings.remove(o.getOrdering());
    }
    // otherwise apply an ordering to the database IDs.
    for (OrderingResult or : orderings) {
        DBIDs sorted = or.order(or.getDBIDs());
        db.getHierarchy().add(or, computePrecisionResult(or.getDBIDs().size(), positiveids, sorted));
    }
}

Example 100 with DBIDs

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

the class CTLuMeanMultipleAttributes method run.

/**
 * Run the algorithm
 *
 * @param database Database
 * @param spatial Spatial relation
 * @param attributes Numerical attributes
 * @return Outlier detection result
 */
public OutlierResult run(Database database, Relation<N> spatial, Relation<O> attributes) {
    if (LOG.isDebugging()) {
        LOG.debug("Dimensionality: " + RelationUtil.dimensionality(attributes));
    }
    final NeighborSetPredicate npred = getNeighborSetPredicateFactory().instantiate(database, spatial);
    CovarianceMatrix covmaker = new CovarianceMatrix(RelationUtil.dimensionality(attributes));
    WritableDataStore<double[]> deltas = DataStoreUtil.makeStorage(attributes.getDBIDs(), DataStoreFactory.HINT_TEMP, double[].class);
    for (DBIDIter iditer = attributes.iterDBIDs(); iditer.valid(); iditer.advance()) {
        final O obj = attributes.get(iditer);
        final DBIDs neighbors = npred.getNeighborDBIDs(iditer);
        // TODO: remove object itself from neighbors?
        // Mean vector "g"
        double[] mean = Centroid.make(attributes, neighbors).getArrayRef();
        // Delta vector "h"
        double[] delta = minusEquals(obj.toArray(), mean);
        deltas.put(iditer, delta);
        covmaker.put(delta);
    }
    // Finalize covariance matrix:
    double[] mean = covmaker.getMeanVector();
    double[][] cmati = inverse(covmaker.destroyToSampleMatrix());
    DoubleMinMax minmax = new DoubleMinMax();
    WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(attributes.getDBIDs(), DataStoreFactory.HINT_STATIC);
    for (DBIDIter iditer = attributes.iterDBIDs(); iditer.valid(); iditer.advance()) {
        final double score = mahalanobisDistance(cmati, deltas.get(iditer), mean);
        minmax.put(score);
        scores.putDouble(iditer, score);
    }
    DoubleRelation scoreResult = new MaterializedDoubleRelation("mean multiple attributes spatial outlier", "mean-multipleattributes-outlier", scores, attributes.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;
}