@Override
public Clustering getClustering(Dataset<E> parent) {
setDataset(parent);
int estClusters = (int) Math.sqrt(dataset.size());
Clustering result = new ClusterList(estClusters);
// estimated capacity
int perCluster = (int) (parent.size() / (float) estClusters);
int[] assign = getMapping();
if (assign != null) {
int id;
Cluster clust;
for (int i = 0; i < assign.length; i++) {
id = assign[i];
clust = result.createCluster(id, perCluster);
clust.add(dataset.get(i));
}
} else {
// try some cutoff method?
throw new RuntimeException("don't know how to get clusters..");
}
// proximity.printLower(5, 2);
// similarity.print(4, 2);
result.lookupAdd(dataset);
if (props != null) {
result.setParams(props);
}
return result;
}
/** TODO: make sure this test is correct */
@Ignore
public void testScore() throws ScoreException {
Clustering c = new ClusterList(2);
Dataset<? extends Instance> d = new ArrayDataset(8, 2);
d.builder().create(new double[] {0, 0}, "0");
d.builder().create(new double[] {0, 0}, "0");
d.builder().create(new double[] {0, 0}, "0");
d.builder().create(new double[] {1, 1}, "0");
d.builder().create(new double[] {1, 1}, "1");
d.builder().create(new double[] {1, 1}, "1");
d.builder().create(new double[] {1, 1}, "1");
d.builder().create(new double[] {1, 1}, "1");
assertEquals(8, d.size());
Cluster a = c.createCluster(0, 4);
Cluster b = c.createCluster(1, 4);
for (int i = 0; i < 4; i++) {
a.add(d.get(i));
b.add(d.get(i + 4));
}
assertEquals(2, c.size());
assertEquals(0.14039740914097984, subject.score(c), delta);
}