Import Upstream version 0.6.5~20141030

1 files changed, 17 insertions, 23 deletions

diff --git a/src/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/KMedoidsEM.java b/src/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/KMedoidsEM.java
index 41cca225..d2f98466 100644
--- a/src/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/KMedoidsEM.java
+++ b/src/de/lmu/ifi/dbs/elki/algorithm/clustering/kmeans/KMedoidsEM.java
@@ -4,7 +4,7 @@ package de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans;
  This file is part of ELKI:
  Environment for Developing KDD-Applications Supported by Index-Structures
 
- Copyright (C) 2013
+ Copyright (C) 2014
  Ludwig-Maximilians-Universität München
  Lehr- und Forschungseinheit für Datenbanksysteme
  ELKI Development Team
@@ -27,8 +27,9 @@ import java.util.ArrayList;
 import java.util.List;
 
 import de.lmu.ifi.dbs.elki.algorithm.AbstractDistanceBasedAlgorithm;
-import de.lmu.ifi.dbs.elki.algorithm.AbstractPrimitiveDistanceBasedAlgorithm;
 import de.lmu.ifi.dbs.elki.algorithm.clustering.ClusteringAlgorithm;
+import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.FarthestPointsInitialMeans;
+import de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.KMedoidsInitialization;
 import de.lmu.ifi.dbs.elki.data.Cluster;
 import de.lmu.ifi.dbs.elki.data.Clustering;
 import de.lmu.ifi.dbs.elki.data.model.MedoidModel;
@@ -43,8 +44,7 @@ import de.lmu.ifi.dbs.elki.database.ids.DBIDUtil;
 import de.lmu.ifi.dbs.elki.database.ids.ModifiableDBIDs;
 import de.lmu.ifi.dbs.elki.database.query.distance.DistanceQuery;
 import de.lmu.ifi.dbs.elki.database.relation.Relation;
-import de.lmu.ifi.dbs.elki.distance.distancefunction.PrimitiveDistanceFunction;
-import de.lmu.ifi.dbs.elki.distance.distancevalue.NumberDistance;
+import de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction;
 import de.lmu.ifi.dbs.elki.logging.Logging;
 import de.lmu.ifi.dbs.elki.logging.progress.IndefiniteProgress;
 import de.lmu.ifi.dbs.elki.math.Mean;
@@ -54,8 +54,7 @@ import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.IntParameter;
 import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.ObjectParameter;
 
 /**
- * Provides the k-medoids clustering algorithm, using a "bulk" variation of the
- * "Partitioning Around Medoids" approach.
+ * A k-medoids clustering algorithm, implemented as EM-style bulk algorithm.
  * 
  * In contrast to PAM, which will in each iteration update one medoid with one
  * (arbitrary) non-medoid, this implementation follows the EM pattern. In the
@@ -72,9 +71,8 @@ import de.lmu.ifi.dbs.elki.utilities.optionhandling.parameters.ObjectParameter;
  * @apiviz.composedOf KMedoidsInitialization
  * 
  * @param <V> vector datatype
- * @param <D> distance value type
  */
-public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDistanceBasedAlgorithm<V, D, Clustering<MedoidModel>> implements ClusteringAlgorithm<Clustering<MedoidModel>> {
+public class KMedoidsEM<V> extends AbstractDistanceBasedAlgorithm<V, Clustering<MedoidModel>> implements ClusteringAlgorithm<Clustering<MedoidModel>> {
   /**
    * The logger for this class.
    */
@@ -103,7 +101,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
    * @param maxiter Maxiter parameter
    * @param initializer Function to generate the initial means
    */
-  public KMedoidsEM(PrimitiveDistanceFunction<? super V, D> distanceFunction, int k, int maxiter, KMedoidsInitialization<V> initializer) {
+  public KMedoidsEM(DistanceFunction<? super V> distanceFunction, int k, int maxiter, KMedoidsInitialization<V> initializer) {
     super(distanceFunction);
     this.k = k;
     this.maxiter = maxiter;
@@ -121,9 +119,9 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
     if(relation.size() <= 0) {
       return new Clustering<>("k-Medoids Clustering", "kmedoids-clustering");
     }
-    DistanceQuery<V, D> distQ = database.getDistanceQuery(relation, getDistanceFunction());
+    DistanceQuery<V> distQ = database.getDistanceQuery(relation, getDistanceFunction());
     // Choose initial medoids
-    ArrayModifiableDBIDs medoids = DBIDUtil.newArray(initializer.chooseInitialMedoids(k, distQ));
+    ArrayModifiableDBIDs medoids = DBIDUtil.newArray(initializer.chooseInitialMedoids(k, relation.getDBIDs(), distQ));
     // Setup cluster assignment store
     List<ModifiableDBIDs> clusters = new ArrayList<>();
     for(int i = 0; i < k; i++) {
@@ -139,9 +137,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
     // Swap phase
     boolean changed = true;
     while(changed) {
-      if(prog != null) {
-        prog.incrementProcessed(LOG);
-      }
+      LOG.incrementProcessed(prog);
       changed = false;
       // Try to swap the medoid with a better cluster member:
       int i = 0;
@@ -154,7 +150,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
           }
           Mean mdist = new Mean();
           for(DBIDIter iter2 = clusters.get(i).iter(); iter2.valid(); iter2.advance()) {
-            mdist.put(distQ.distance(iter, iter2).doubleValue());
+            mdist.put(distQ.distance(iter, iter2));
           }
           if(mdist.getMean() < bestm.getMean()) {
             best = DBIDUtil.deref(iter);
@@ -172,9 +168,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
         assignToNearestCluster(medoids, mdists, clusters, distQ);
       }
     }
-    if(prog != null) {
-      prog.setCompleted(LOG);
-    }
+    LOG.setCompleted(prog);
 
     // Wrap result
     Clustering<MedoidModel> result = new Clustering<>("k-Medoids Clustering", "kmedoids-clustering");
@@ -195,7 +189,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
    * @param distQ distance query
    * @return true when the object was reassigned
    */
-  protected boolean assignToNearestCluster(ArrayDBIDs means, Mean[] mdist, List<? extends ModifiableDBIDs> clusters, DistanceQuery<V, D> distQ) {
+  protected boolean assignToNearestCluster(ArrayDBIDs means, Mean[] mdist, List<? extends ModifiableDBIDs> clusters, DistanceQuery<V> distQ) {
     boolean changed = false;
 
     double[] dists = new double[k];
@@ -205,7 +199,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
       {
         int i = 0;
         for(DBIDIter miter = means.iter(); miter.valid(); miter.advance(), i++) {
-          dists[i] = distQ.distance(iditer, miter).doubleValue();
+          dists[i] = distQ.distance(iditer, miter);
           if(dists[i] < mindist) {
             minIndex = i;
             mindist = dists[i];
@@ -247,7 +241,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
    * 
    * @apiviz.exclude
    */
-  public static class Parameterizer<V, D extends NumberDistance<D, ?>> extends AbstractPrimitiveDistanceBasedAlgorithm.Parameterizer<V, D> {
+  public static class Parameterizer<V> extends AbstractDistanceBasedAlgorithm.Parameterizer<V> {
     protected int k;
 
     protected int maxiter;
@@ -263,7 +257,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
         k = kP.intValue();
       }
 
-      ObjectParameter<KMedoidsInitialization<V>> initialP = new ObjectParameter<>(KMeans.INIT_ID, KMedoidsInitialization.class, PAMInitialMeans.class);
+      ObjectParameter<KMedoidsInitialization<V>> initialP = new ObjectParameter<>(KMeans.INIT_ID, KMedoidsInitialization.class, FarthestPointsInitialMeans.class);
       if(config.grab(initialP)) {
         initializer = initialP.instantiateClass(config);
       }
@@ -276,7 +270,7 @@ public class KMedoidsEM<V, D extends NumberDistance<D, ?>> extends AbstractDista
     }
 
     @Override
-    protected KMedoidsEM<V, D> makeInstance() {
+    protected KMedoidsEM<V> makeInstance() {
       return new KMedoidsEM<>(distanceFunction, k, maxiter, initializer);
     }
   }