@Override
public Clustering<E, C> reduce(
Clustering[] clusts, Algorithm<E, C> alg, ColorGenerator cg, Props props) {
int k = props.getInt(KMeans.K);
Clustering<E, C> result = new ClusterList<>(k); // reducer - find consensus
// vote about final result
E curr;
Iterator<E> it = clusts[0].instancesIterator();
Cluster<E> cluster;
int[][] mapping = findMapping(clusts, k, alg.getDistanceFunction());
if (cg != null) {
cg.reset();
}
int idx;
while (it.hasNext()) {
curr = it.next();
int[] assign = new int[k];
for (int i = 0; i < clusts.length; i++) {
cluster = clusts[i].assignedCluster(curr);
if (i > 0) {
assign[map(mapping, i, cluster.getClusterId())]++;
} else {
assign[cluster.getClusterId()]++;
}
}
idx = findMax(assign);
// check if cluster already exists
if (!result.hasAt(idx)) {
result.createCluster(idx);
if (cg != null) {
result.get(idx).setColor(cg.next());
}
}
// final cluster assignment
result.get(idx).add(curr);
}
result.compact();
return result;
}
@Override
public Clustering updateCutoff(double cutoff) {
this.cutoff = cutoff;
int[] assign = new int[dataset.size()];
int estClusters = (int) Math.sqrt(dataset.size());
colorGenerator.reset();
num = 0; // human readable
Clustering clusters = new ClusterList(estClusters);
DendroNode root = treeData.getRoot();
if (root != null) {
checkCutoff(root, cutoff, clusters, assign);
if (clusters.size() > 0) {
mapping = assign;
} else {
LOG.info("failed to cutoff dendrogram, cut = {}", cutoff);
}
}
// add input dataset to clustering lookup
if (noise != null) {
Cluster clust = new BaseCluster<>(noise.size());
clust.setColor(colorGenerator.next());
clust.setClusterId(num++);
clust.setParent(getDataset());
clust.setName("Noise");
clust.setAttributes(getDataset().getAttributes());
for (Instance ins : noise) {
clust.add(ins);
mapping[ins.getIndex()] = num - 1;
}
clusters.add(clust);
}
clusters.lookupAdd(dataset);
if (dendroMapping != null) {
clusters.lookupAdd(dendroMapping);
}
clusters.lookupAdd(this);
return clusters;
}
