/**
* For each pair of clusters, calculate the score of the {@link
* cc.mallet.cluster.neighbor_evaluator.Neighbor} that would result from merging the two clusters.
* Choose the merge that obtains the highest score. If no merge improves score, return original
* Clustering
*
* @param clustering
* @return
*/
public Clustering improveClustering(Clustering clustering) {
double bestScore = Double.NEGATIVE_INFINITY;
int[] toMerge = new int[] {-1, -1};
for (int i = 0; i < clustering.getNumClusters(); i++) {
for (int j = i + 1; j < clustering.getNumClusters(); j++) {
double score = getScore(clustering, i, j);
if (score > bestScore) {
bestScore = score;
toMerge[0] = i;
toMerge[1] = j;
}
}
}
converged = (bestScore < stoppingThreshold);
if (!(converged)) {
progressLogger.info(
"Merging "
+ toMerge[0]
+ "("
+ clustering.size(toMerge[0])
+ " nodes) and "
+ toMerge[1]
+ "("
+ clustering.size(toMerge[1])
+ " nodes) ["
+ bestScore
+ "] numClusters="
+ clustering.getNumClusters());
updateScoreMatrix(clustering, toMerge[0], toMerge[1]);
clustering = ClusterUtils.mergeClusters(clustering, toMerge[0], toMerge[1]);
} else {
progressLogger.info("Converged with score " + bestScore);
}
return clustering;
}
