summaryrefslogtreecommitdiff
path: root/src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java
diff options
context:
space:
mode:
Diffstat (limited to 'src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java')
-rw-r--r--src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java59
1 files changed, 22 insertions, 37 deletions
diff --git a/src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java
index f92a8b80..4858e0df 100644
--- a/src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java
+++ b/src/de/lmu/ifi/dbs/elki/algorithm/outlier/meta/HiCS.java
@@ -4,7 +4,7 @@ package de.lmu.ifi.dbs.elki.algorithm.outlier.meta;
This file is part of ELKI:
Environment for Developing KDD-Applications Supported by Index-Structures
- Copyright (C) 2012
+ Copyright (C) 2014
Ludwig-Maximilians-Universität München
Lehr- und Forschungseinheit für Datenbanksysteme
ELKI Development Team
@@ -51,7 +51,8 @@ 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.relation.MaterializedRelation;
+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.ProjectedView;
import de.lmu.ifi.dbs.elki.database.relation.Relation;
import de.lmu.ifi.dbs.elki.database.relation.RelationUtil;
@@ -59,12 +60,12 @@ import de.lmu.ifi.dbs.elki.logging.Logging;
import de.lmu.ifi.dbs.elki.logging.progress.FiniteProgress;
import de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress;
import de.lmu.ifi.dbs.elki.math.DoubleMinMax;
+import de.lmu.ifi.dbs.elki.math.random.RandomFactory;
import de.lmu.ifi.dbs.elki.math.statistics.tests.GoodnessOfFitTest;
import de.lmu.ifi.dbs.elki.math.statistics.tests.KolmogorovSmirnovTest;
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.RandomFactory;
import de.lmu.ifi.dbs.elki.utilities.datastructures.heap.Heap;
import de.lmu.ifi.dbs.elki.utilities.datastructures.heap.TopBoundedHeap;
import de.lmu.ifi.dbs.elki.utilities.documentation.Description;
@@ -102,7 +103,7 @@ import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.RandomParameter;
@Title("HiCS: High Contrast Subspaces for Density-Based Outlier Ranking")
@Description("Algorithm to compute High Contrast Subspaces in a database as a pre-processing step for for density-based outlier ranking methods.")
@Reference(authors = "Fabian Keller, Emmanuel Müller, Klemens Böhm", title = "HiCS: High Contrast Subspaces for Density-Based Outlier Ranking", booktitle = "Proc. IEEE 28th International Conference on Data Engineering (ICDE 2012)", url = "http://dx.doi.org/10.1109/ICDE.2012.88")
-public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierResult> implements OutlierAlgorithm {
+public class HiCS<V extends NumberVector> extends AbstractAlgorithm<OutlierResult> implements OutlierAlgorithm {
/**
* The Logger for this class.
*/
@@ -179,7 +180,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
if(LOG.isVerbose()) {
LOG.verbose("Number of high-contrast subspaces: " + subspaces.size());
}
- List<Relation<Double>> results = new ArrayList<>();
+ List<DoubleRelation> results = new ArrayList<>();
FiniteProgress prog = LOG.isVerbose() ? new FiniteProgress("Calculating Outlier scores for high Contrast subspaces", subspaces.size(), LOG) : null;
// run outlier detection and collect the result
@@ -196,22 +197,18 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
// run LOF and collect the result
OutlierResult result = outlierAlgorithm.run(pdb);
results.add(result.getScores());
- if(prog != null) {
- prog.incrementProcessed(LOG);
- }
- }
- if(prog != null) {
- prog.ensureCompleted(LOG);
+ 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(Relation<Double> r : results) {
- final Double s = r.get(iditer);
- if(s != null && !Double.isNaN(s)) {
+ for(DoubleRelation r : results) {
+ final double s = r.doubleValue(iditer);
+ if(!Double.isNaN(s)) {
sum += s;
}
}
@@ -219,7 +216,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
minmax.put(sum);
}
OutlierScoreMeta meta = new BasicOutlierScoreMeta(minmax.getMin(), minmax.getMax());
- Relation<Double> scoreres = new MaterializedRelation<>("HiCS", "HiCS-outlier", TypeUtil.DOUBLE, scores, relation.getDBIDs());
+ DoubleRelation scoreres = new MaterializedDoubleRelation("HiCS", "HiCS-outlier", scores, relation.getDBIDs());
return new OutlierResult(meta, scoreres);
}
@@ -232,7 +229,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
* @param relation Relation to index
* @return List of sorted objects
*/
- private ArrayList<ArrayDBIDs> buildOneDimIndexes(Relation<? extends NumberVector<?>> relation) {
+ private ArrayList<ArrayDBIDs> buildOneDimIndexes(Relation<? extends NumberVector> relation) {
final int dim = RelationUtil.dimensionality(relation);
ArrayList<ArrayDBIDs> subspaceIndex = new ArrayList<>(dim + 1);
@@ -254,7 +251,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
* @param subspaceIndex Subspace indexes
* @return a set of high contrast subspaces
*/
- private Set<HiCSSubspace> calculateSubspaces(Relation<? extends NumberVector<?>> relation, ArrayList<ArrayDBIDs> subspaceIndex, Random random) {
+ private Set<HiCSSubspace> calculateSubspaces(Relation<? extends NumberVector> relation, ArrayList<ArrayDBIDs> subspaceIndex, Random random) {
final int dbdim = RelationUtil.dimensionality(relation);
FiniteProgress dprog = LOG.isVerbose() ? new FiniteProgress("Subspace dimensionality", dbdim, LOG) : null;
@@ -273,14 +270,10 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
ts.set(j);
calculateContrast(relation, ts, subspaceIndex, random);
dDimensionalList.add(ts);
- if(prog != null) {
- prog.incrementProcessed(LOG);
- }
+ LOG.incrementProcessed(prog);
}
}
- if(prog != null) {
- prog.ensureCompleted(LOG);
- }
+ LOG.ensureCompleted(prog);
IndefiniteProgress qprog = LOG.isVerbose() ? new IndefiniteProgress("Testing subspace candidates", LOG) : null;
for(int d = 3; !dDimensionalList.isEmpty(); d++) {
@@ -313,9 +306,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
calculateContrast(relation, joinedSet, subspaceIndex, random);
dDimensionalList.add(joinedSet);
- if(qprog != null) {
- qprog.incrementProcessed(LOG);
- }
+ LOG.incrementProcessed(qprog);
}
}
// Prune
@@ -328,9 +319,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
}
}
}
- if(qprog != null) {
- qprog.setCompleted(LOG);
- }
+ LOG.setCompleted(qprog);
if(dprog != null) {
dprog.setProcessed(dbdim, LOG);
dprog.ensureCompleted(LOG);
@@ -345,7 +334,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
* @param subspace Subspace
* @param subspaceIndex Subspace indexes
*/
- private void calculateContrast(Relation<? extends NumberVector<?>> relation, HiCSSubspace subspace, ArrayList<ArrayDBIDs> subspaceIndex, Random random) {
+ private void calculateContrast(Relation<? extends NumberVector> relation, HiCSSubspace subspace, ArrayList<ArrayDBIDs> subspaceIndex, Random random) {
final int card = subspace.cardinality();
final double alpha1 = Math.pow(alpha, (1.0 / card));
final int windowsize = (int) (relation.size() * alpha1);
@@ -415,13 +404,9 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
continue;
}
deviationSum += contrast;
- if(prog != null) {
- prog.incrementProcessed(LOG);
- }
- }
- if(prog != null) {
- prog.ensureCompleted(LOG);
+ LOG.incrementProcessed(prog);
}
+ LOG.ensureCompleted(prog);
subspace.contrast = deviationSum / m;
}
@@ -530,7 +515,7 @@ public class HiCS<V extends NumberVector<?>> extends AbstractAlgorithm<OutlierRe
*
* @param <V> vector type
*/
- public static class Parameterizer<V extends NumberVector<?>> extends AbstractParameterizer {
+ public static class Parameterizer<V extends NumberVector> extends AbstractParameterizer {
/**
* Parameter that specifies the number of iterations in the Monte-Carlo
* process of identifying high contrast subspaces.
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-08 11:51:03 +0000