diff options
Diffstat (limited to 'src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering')
4 files changed, 624 insertions, 0 deletions
diff --git a/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/EMOutlier.java b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/EMOutlier.java new file mode 100644 index 00000000..5a02fb56 --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/EMOutlier.java @@ -0,0 +1,166 @@ +package de.lmu.ifi.dbs.elki.algorithm.outlier.clustering;
+
+/*
+ This file is part of ELKI:
+ Environment for Developing KDD-Applications Supported by Index-Structures +
+ Copyright (C) 2014
+ Ludwig-Maximilians-Universität München
+ Lehr- und Forschungseinheit für Datenbanksysteme
+ ELKI Development Team +
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU Affero General Public License as published by
+ the Free Software Foundation, either version 3 of the License, or
+ (at your option) any later version. +
+ This program is distributed in the hope that it will be useful,
+ but WITHOUT ANY WARRANTY; without even the implied warranty of
+ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ GNU Affero General Public License for more details. +
+ You should have received a copy of the GNU Affero General Public License
+ along with this program. If not, see <http://www.gnu.org/licenses/>.
+ */
+
+import de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm;
+import de.lmu.ifi.dbs.elki.algorithm.clustering.em.EM;
+import de.lmu.ifi.dbs.elki.algorithm.outlier.OutlierAlgorithm;
+import de.lmu.ifi.dbs.elki.data.Clustering;
+import de.lmu.ifi.dbs.elki.data.NumberVector;
+import de.lmu.ifi.dbs.elki.data.type.TypeInformation;
+import de.lmu.ifi.dbs.elki.data.type.TypeUtil;
+import de.lmu.ifi.dbs.elki.database.Database;
+import de.lmu.ifi.dbs.elki.database.datastore.DataStoreFactory;
+import de.lmu.ifi.dbs.elki.database.datastore.DataStoreUtil;
+import de.lmu.ifi.dbs.elki.database.datastore.WritableDoubleDataStore;
+import de.lmu.ifi.dbs.elki.database.ids.DBIDIter;
+import de.lmu.ifi.dbs.elki.database.relation.DoubleRelation;
+import de.lmu.ifi.dbs.elki.database.relation.MaterializedDoubleRelation;
+import de.lmu.ifi.dbs.elki.database.relation.Relation;
+import de.lmu.ifi.dbs.elki.logging.Logging;
+import de.lmu.ifi.dbs.elki.result.Result;
+import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult;
+import de.lmu.ifi.dbs.elki.result.outlier.OutlierScoreMeta;
+import de.lmu.ifi.dbs.elki.result.outlier.ProbabilisticOutlierScore;
+import de.lmu.ifi.dbs.elki.utilities.ClassGenericsUtil;
+import de.lmu.ifi.dbs.elki.utilities.datastructures.hierarchy.Hierarchy.Iter;
+import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
+import de.lmu.ifi.dbs.elki.utilities.documentation.Title;
+import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer;
+import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization;
+
+/**
+ * outlier detection algorithm using EM Clustering. If an object does not belong
+ * to any cluster it is supposed to be an outlier. If the probability for an
+ * object to belong to the most probable cluster is still relatively low this
+ * object is an outlier.
+ *
+ * @author Lisa Reichert
+ *
+ * @apiviz.has EM
+ *
+ * @param <V> Vector type
+ */
+// TODO: re-use an existing EM when present?
+@Title("EM Outlier: Outlier Detection based on the generic EM clustering")
+@Description("The outlier score assigned is based on the highest cluster probability obtained from EM clustering.")
+public class EMOutlier<V extends NumberVector> extends AbstractAlgorithm<OutlierResult> implements OutlierAlgorithm {
+ /**
+ * The logger for this class.
+ */
+ private static final Logging LOG = Logging.getLogger(EMOutlier.class);
+
+ /**
+ * Inner algorithm.
+ */
+ private EM<V, ?> emClustering;
+
+ /**
+ * Constructor with an existing em clustering algorithm.
+ *
+ * @param emClustering EM clustering algorithm to use.
+ */
+ public EMOutlier(EM<V, ?> emClustering) {
+ super();
+ this.emClustering = emClustering;
+ }
+
+ /**
+ * Runs the algorithm in the timed evaluation part.
+ *
+ * @param database Database to process
+ * @param relation Relation to process
+ * @return Outlier result
+ */
+ public OutlierResult run(Database database, Relation<V> relation) {
+ emClustering.setSoft(true);
+ Clustering<?> emresult = emClustering.run(database, relation);
+ Relation<double[]> soft = null;
+ for(Iter<Result> iter = emresult.getHierarchy().iterChildren(emresult); iter.valid(); iter.advance()) {
+ if(!(iter.get() instanceof Relation)) {
+ continue;
+ }
+ if(((Relation<?>) iter.get()).getDataTypeInformation() == EM.SOFT_TYPE) {
+ @SuppressWarnings("unchecked")
+ Relation<double[]> rel = (Relation<double[]>) iter.get();
+ soft = rel;
+ }
+ }
+
+ double globmax = 0.0;
+ WritableDoubleDataStore emo_score = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_TEMP | DataStoreFactory.HINT_HOT);
+ for(DBIDIter iditer = relation.iterDBIDs(); iditer.valid(); iditer.advance()) {
+ double maxProb = Double.POSITIVE_INFINITY;
+ double[] probs = soft.get(iditer);
+ for(double prob : probs) {
+ maxProb = Math.min(1. - prob, maxProb);
+ }
+ emo_score.putDouble(iditer, maxProb);
+ globmax = Math.max(maxProb, globmax);
+ }
+ DoubleRelation scoreres = new MaterializedDoubleRelation("EM outlier scores", "em-outlier", emo_score, relation.getDBIDs());
+ OutlierScoreMeta meta = new ProbabilisticOutlierScore(0.0, globmax);
+ // combine results.
+ OutlierResult result = new OutlierResult(meta, scoreres);
+ // TODO: add a keep-EM flag?
+ result.addChildResult(emresult);
+ return result;
+ }
+
+ @Override
+ public TypeInformation[] getInputTypeRestriction() {
+ return TypeUtil.array(TypeUtil.NUMBER_VECTOR_FIELD);
+ }
+
+ @Override
+ protected Logging getLogger() {
+ return LOG;
+ }
+
+ /**
+ * Parameterization class.
+ *
+ * @author Erich Schubert
+ *
+ * @apiviz.exclude
+ */
+ public static class Parameterizer<V extends NumberVector> extends AbstractParameterizer {
+ /**
+ * EM clustering algorithm to run.
+ */
+ protected EM<V, ?> em;
+
+ @Override
+ protected void makeOptions(Parameterization config) {
+ super.makeOptions(config);
+ Class<EM<V, ?>> cls = ClassGenericsUtil.uglyCastIntoSubclass(EM.class);
+ em = config.tryInstantiate(cls);
+ }
+
+ @Override
+ protected EMOutlier<V> makeInstance() {
+ return new EMOutlier<>(em);
+ }
+ }
+}
diff --git a/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/KMeansOutlierDetection.java b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/KMeansOutlierDetection.java new file mode 100644 index 00000000..c6155527 --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/KMeansOutlierDetection.java @@ -0,0 +1,178 @@ +package de.lmu.ifi.dbs.elki.algorithm.outlier.clustering; + +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2014 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +import java.util.List; + +import de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm; +import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.KMeans; +import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.KMeansLloyd; +import de.lmu.ifi.dbs.elki.algorithm.outlier.OutlierAlgorithm; +import de.lmu.ifi.dbs.elki.data.Cluster; +import de.lmu.ifi.dbs.elki.data.Clustering; +import de.lmu.ifi.dbs.elki.data.NumberVector; +import de.lmu.ifi.dbs.elki.data.model.ModelUtil; +import de.lmu.ifi.dbs.elki.data.type.TypeInformation; +import de.lmu.ifi.dbs.elki.data.type.TypeUtil; +import de.lmu.ifi.dbs.elki.database.Database; +import de.lmu.ifi.dbs.elki.database.datastore.DataStoreFactory; +import de.lmu.ifi.dbs.elki.database.datastore.DataStoreUtil; +import de.lmu.ifi.dbs.elki.database.datastore.WritableDoubleDataStore; +import de.lmu.ifi.dbs.elki.database.ids.DBIDIter; +import de.lmu.ifi.dbs.elki.database.query.distance.DistanceQuery; +import de.lmu.ifi.dbs.elki.database.relation.DoubleRelation; +import de.lmu.ifi.dbs.elki.database.relation.MaterializedDoubleRelation; +import de.lmu.ifi.dbs.elki.database.relation.Relation; +import de.lmu.ifi.dbs.elki.database.relation.RelationUtil; +import de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction; +import de.lmu.ifi.dbs.elki.logging.Logging; +import de.lmu.ifi.dbs.elki.math.DoubleMinMax; +import de.lmu.ifi.dbs.elki.result.outlier.BasicOutlierScoreMeta; +import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult; +import de.lmu.ifi.dbs.elki.result.outlier.OutlierScoreMeta; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.AbstractParameterizer; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.ObjectParameter; + +/** + * Outlier detection by using k-means clustering. + * + * The scores are assigned by the objects distance to the nearest center. + * + * We don't have a clear reference for this approach, but it seems to be a best + * practise in some areas to remove objects that have the largest distance from + * their center. If you need to cite this approach, please cite the ELKI version + * you used (use the <a href="http://elki.dbs.ifi.lmu.de/wiki/Publications">ELKI + * publication list</a> for citation information and BibTeX templates). + * + * @author Erich Schubert + * + * @apiviz.has KMeans + * + * @param <O> Object type + */ +public class KMeansOutlierDetection<O extends NumberVector> extends AbstractAlgorithm<OutlierResult> implements OutlierAlgorithm { + /** + * Class logger. + */ + private static final Logging LOG = Logging.getLogger(KMeansOutlierDetection.class); + + /** + * Clustering algorithm to use + */ + KMeans<O, ?> clusterer; + + /** + * Constructor. + * + * @param clusterer Clustering algorithm + */ + public KMeansOutlierDetection(KMeans<O, ?> clusterer) { + super(); + this.clusterer = clusterer; + } + + /** + * Run the outlier detection algorithm. + * + * @param database Database + * @param relation Relation + * @return Outlier detection result + */ + public OutlierResult run(Database database, Relation<O> relation) { + DistanceFunction<? super O> df = clusterer.getDistanceFunction(); + DistanceQuery<O> dq = database.getDistanceQuery(relation, df); + + // TODO: improve ELKI api to ensure we're using the same DBIDs! + Clustering<?> c = clusterer.run(database, relation); + + WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_DB); + DoubleMinMax mm = new DoubleMinMax(); + + @SuppressWarnings("unchecked") + NumberVector.Factory<O> factory = (NumberVector.Factory<O>) RelationUtil.assumeVectorField(relation).getFactory(); + List<? extends Cluster<?>> clusters = c.getAllClusters(); + for(Cluster<?> cluster : clusters) { + // FIXME: use a primitive distance function on number vectors instead. + O mean = factory.newNumberVector(ModelUtil.getPrototype(cluster.getModel(), relation)); + for(DBIDIter iter = cluster.getIDs().iter(); iter.valid(); iter.advance()) { + double dist = dq.distance(mean, iter); + scores.put(iter, dist); + mm.put(dist); + } + } + + // Build result representation. + DoubleRelation scoreResult = new MaterializedDoubleRelation("KMeans outlier scores", "kmeans-outlier", scores, relation.getDBIDs()); + OutlierScoreMeta scoreMeta = new BasicOutlierScoreMeta(mm.getMin(), mm.getMax(), 0., Double.POSITIVE_INFINITY, 0.); + return new OutlierResult(scoreMeta, scoreResult); + } + + @Override + public TypeInformation[] getInputTypeRestriction() { + return TypeUtil.array(clusterer.getDistanceFunction().getInputTypeRestriction()); + } + + @Override + protected Logging getLogger() { + return LOG; + } + + /** + * Parameterizer. + * + * @author Erich Schubert + * + * @apiviz.exclude + * + * @param <O> Object type + */ + public static class Parameterizer<O extends NumberVector> extends AbstractParameterizer { + /** + * Parameter for choosing the clustering algorithm. + */ + public static final OptionID CLUSTERING_ID = new OptionID("kmeans.algorithm", // + "Clustering algorithm to use for detecting outliers."); + + /** + * Clustering algorithm to use + */ + KMeans<O, ?> clusterer; + + @Override + protected void makeOptions(Parameterization config) { + super.makeOptions(config); + + ObjectParameter<KMeans<O, ?>> clusterP = new ObjectParameter<>(CLUSTERING_ID, KMeans.class, KMeansLloyd.class); + if(config.grab(clusterP)) { + clusterer = clusterP.instantiateClass(config); + } + } + + @Override + protected KMeansOutlierDetection<O> makeInstance() { + return new KMeansOutlierDetection<>(clusterer); + } + } +} diff --git a/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/SilhouetteOutlierDetection.java b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/SilhouetteOutlierDetection.java new file mode 100644 index 00000000..3bd9cf8b --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/SilhouetteOutlierDetection.java @@ -0,0 +1,253 @@ +package de.lmu.ifi.dbs.elki.algorithm.outlier.clustering; + +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2014 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +import java.util.List; + +import de.lmu.ifi.dbs.elki.algorithm.AbstractDistanceBasedAlgorithm; +import de.lmu.ifi.dbs.elki.algorithm.clustering.ClusteringAlgorithm; +import de.lmu.ifi.dbs.elki.algorithm.outlier.OutlierAlgorithm; +import de.lmu.ifi.dbs.elki.data.Cluster; +import de.lmu.ifi.dbs.elki.data.Clustering; +import de.lmu.ifi.dbs.elki.data.type.TypeInformation; +import de.lmu.ifi.dbs.elki.database.Database; +import de.lmu.ifi.dbs.elki.database.datastore.DataStoreFactory; +import de.lmu.ifi.dbs.elki.database.datastore.DataStoreUtil; +import de.lmu.ifi.dbs.elki.database.datastore.WritableDoubleDataStore; +import de.lmu.ifi.dbs.elki.database.ids.ArrayDBIDs; +import de.lmu.ifi.dbs.elki.database.ids.DBIDArrayIter; +import de.lmu.ifi.dbs.elki.database.ids.DBIDIter; +import de.lmu.ifi.dbs.elki.database.ids.DBIDUtil; +import de.lmu.ifi.dbs.elki.database.ids.DBIDs; +import de.lmu.ifi.dbs.elki.database.query.distance.DistanceQuery; +import de.lmu.ifi.dbs.elki.database.relation.DoubleRelation; +import de.lmu.ifi.dbs.elki.database.relation.MaterializedDoubleRelation; +import de.lmu.ifi.dbs.elki.database.relation.Relation; +import de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction; +import de.lmu.ifi.dbs.elki.evaluation.clustering.internal.EvaluateSilhouette; +import de.lmu.ifi.dbs.elki.logging.Logging; +import de.lmu.ifi.dbs.elki.math.DoubleMinMax; +import de.lmu.ifi.dbs.elki.result.outlier.InvertedOutlierScoreMeta; +import de.lmu.ifi.dbs.elki.result.outlier.OutlierResult; +import de.lmu.ifi.dbs.elki.result.outlier.OutlierScoreMeta; +import de.lmu.ifi.dbs.elki.utilities.documentation.Reference; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.OptionID; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameterization.Parameterization; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.Flag; +import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.ObjectParameter; + +/** + * Outlier detection by using the Silhouette Coefficients. + * + * Silhouette values are computed as in: + * <p> + * P. J. Rousseeuw<br /> + * Silhouettes: A graphical aid to the interpretation and validation of cluster + * analysis<br /> + * In: Journal of Computational and Applied Mathematics Volume 20, November 1987 + * </p> + * + * but then used as outlier scores. To cite this outlier detection approach, + * please cite the ELKI version you used (use the <a + * href="http://elki.dbs.ifi.lmu.de/wiki/Publications">ELKI publication list</a> + * for citation information and BibTeX templates). + * + * @author Erich Schubert + * + * @apiviz.has ClusteringAlgorithm + * + * @param <O> Object type + */ +@Reference(authors = "P. J. Rousseeuw", // +title = "Silhouettes: A graphical aid to the interpretation and validation of cluster analysis", // +booktitle = "Journal of Computational and Applied Mathematics, Volume 20", // +url = "http://dx.doi.org/10.1016%2F0377-0427%2887%2990125-7") +public class SilhouetteOutlierDetection<O> extends AbstractDistanceBasedAlgorithm<O, OutlierResult> implements OutlierAlgorithm { + /** + * Class logger. + */ + private static final Logging LOG = Logging.getLogger(SilhouetteOutlierDetection.class); + + /** + * Clustering algorithm to use + */ + ClusteringAlgorithm<?> clusterer; + + /** + * Keep noise "clusters" merged, instead of breaking them into singletons. + */ + private boolean mergenoise = false; + + /** + * Constructor. + * + * @param distanceFunction Distance function + * @param clusterer Clustering algorithm + * @param mergenoise Flag to keep "noise" clusters merged, instead of breaking + * them into singletons. + */ + public SilhouetteOutlierDetection(DistanceFunction<? super O> distanceFunction, ClusteringAlgorithm<?> clusterer, boolean mergenoise) { + super(distanceFunction); + this.clusterer = clusterer; + this.mergenoise = mergenoise; + } + + @Override + public OutlierResult run(Database database) { + Relation<O> relation = database.getRelation(getDistanceFunction().getInputTypeRestriction()); + DistanceQuery<O> dq = database.getDistanceQuery(relation, getDistanceFunction()); + + // TODO: improve ELKI api to ensure we're using the same DBIDs! + Clustering<?> c = clusterer.run(database); + + WritableDoubleDataStore scores = DataStoreUtil.makeDoubleStorage(relation.getDBIDs(), DataStoreFactory.HINT_DB); + DoubleMinMax mm = new DoubleMinMax(); + + List<? extends Cluster<?>> clusters = c.getAllClusters(); + for(Cluster<?> cluster : clusters) { + if(cluster.size() <= 1 || (!mergenoise && cluster.isNoise())) { + // As suggested in Rousseeuw, we use 0 for singletons. + for(DBIDIter iter = cluster.getIDs().iter(); iter.valid(); iter.advance()) { + scores.put(iter, 0.); + } + mm.put(0.); + continue; + } + ArrayDBIDs ids = DBIDUtil.ensureArray(cluster.getIDs()); + double[] as = new double[ids.size()]; // temporary storage. + DBIDArrayIter it1 = ids.iter(), it2 = ids.iter(); + for(it1.seek(0); it1.valid(); it1.advance()) { + // a: In-cluster distances + double a = as[it1.getOffset()]; // Already computed distances + for(it2.seek(it1.getOffset() + 1); it2.valid(); it2.advance()) { + final double dist = dq.distance(it1, it2); + a += dist; + as[it2.getOffset()] += dist; + } + a /= (ids.size() - 1); + // b: other clusters: + double min = Double.POSITIVE_INFINITY; + for(Cluster<?> ocluster : clusters) { + if(ocluster == /* yes, reference identity */cluster) { + continue; + } + if(!mergenoise && ocluster.isNoise()) { + // Treat noise cluster as singletons: + for(DBIDIter it3 = ocluster.getIDs().iter(); it3.valid(); it3.advance()) { + double dist = dq.distance(it1, it3); + if(dist < min) { + min = dist; + } + } + continue; + } + final DBIDs oids = ocluster.getIDs(); + double b = 0.; + for(DBIDIter it3 = oids.iter(); it3.valid(); it3.advance()) { + b += dq.distance(it1, it3); + } + b /= oids.size(); + if(b < min) { + min = b; + } + } + final double score = (min - a) / Math.max(min, a); + scores.put(it1, score); + mm.put(score); + } + } + + // Build result representation. + DoubleRelation scoreResult = new MaterializedDoubleRelation("Silhouette Coefficients", "silhouette-outlier", scores, relation.getDBIDs()); + OutlierScoreMeta scoreMeta = new InvertedOutlierScoreMeta(mm.getMin(), mm.getMax(), -1., 1., .5); + return new OutlierResult(scoreMeta, scoreResult); + } + + @Override + public TypeInformation[] getInputTypeRestriction() { + final TypeInformation dt = getDistanceFunction().getInputTypeRestriction(); + TypeInformation[] t = clusterer.getInputTypeRestriction(); + for(TypeInformation i : t) { + if(dt.isAssignableFromType(i)) { + return t; + } + } + // Prepend distance type: + TypeInformation[] t2 = new TypeInformation[t.length + 1]; + t2[0] = dt; + System.arraycopy(t, 0, t2, 1, t.length); + return t2; + } + + @Override + protected Logging getLogger() { + return LOG; + } + + /** + * Parameterizer. + * + * @author Erich Schubert + * + * @apiviz.exclude + * + * @param <O> Object type + */ + public static class Parameterizer<O> extends AbstractDistanceBasedAlgorithm.Parameterizer<O> { + /** + * Parameter for choosing the clustering algorithm + */ + public static final OptionID CLUSTERING_ID = new OptionID("silhouette.clustering", // + "Clustering algorithm to use for the silhouette coefficients."); + + /** + * Clustering algorithm to use + */ + ClusteringAlgorithm<?> clusterer; + + /** + * Keep noise "clusters" merged, instead of breaking them into singletons. + */ + private boolean mergenoise = false; + + @Override + protected void makeOptions(Parameterization config) { + super.makeOptions(config); + + ObjectParameter<ClusteringAlgorithm<?>> clusterP = new ObjectParameter<>(CLUSTERING_ID, ClusteringAlgorithm.class); + if(config.grab(clusterP)) { + clusterer = clusterP.instantiateClass(config); + } + + Flag noiseP = new Flag(EvaluateSilhouette.Parameterizer.MERGENOISE_ID); + if(config.grab(noiseP)) { + mergenoise = noiseP.isTrue(); + } + } + + @Override + protected SilhouetteOutlierDetection<O> makeInstance() { + return new SilhouetteOutlierDetection<>(distanceFunction, clusterer, mergenoise); + } + } +} diff --git a/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/package-info.java b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/package-info.java new file mode 100644 index 00000000..15ee771e --- /dev/null +++ b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/clustering/package-info.java @@ -0,0 +1,27 @@ +/** + * Clustering based outlier detection. + */ + +/* + This file is part of ELKI: + Environment for Developing KDD-Applications Supported by Index-Structures + + Copyright (C) 2014 + Ludwig-Maximilians-Universität München + Lehr- und Forschungseinheit für Datenbanksysteme + ELKI Development Team + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU Affero General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU Affero General Public License for more details. + + You should have received a copy of the GNU Affero General Public License + along with this program. If not, see <http://www.gnu.org/licenses/>. + */ +package de.lmu.ifi.dbs.elki.algorithm.outlier.clustering;
\ No newline at end of file |