/**
* Based on "Details of the Adjusted Rand index and Clustering algorithms Supplement to the paper
* “An empirical study on Principal Component Analysis for clustering gene expression data” (to
* appear in Bioinformatics)"
*
* @return
*/
public Clustering<Instance, Cluster<Instance>> pcaData() {
Clustering<Instance, Cluster<Instance>> clustering = new ClusterList<>(3);
Random rand = new Random();
int size = 10;
Dataset<? extends Instance> data = new ArrayDataset<>(size, 2);
data.attributeBuilder().create("x1", "NUMERIC");
data.attributeBuilder().create("x2", "NUMERIC");
InstanceBuilder<? extends Instance> builder = data.builder();
BaseCluster c1 = new BaseCluster(2);
clustering.add(c1);
BaseCluster c2 = new BaseCluster(3);
clustering.add(c2);
BaseCluster c3 = new BaseCluster(5);
clustering.add(c3);
c1.add(next(rand, builder, "u1"));
c1.add(next(rand, builder, "u2"));
c2.add(next(rand, builder, "u1"));
c2.add(next(rand, builder, "u2"));
c2.add(next(rand, builder, "u2"));
c3.add(next(rand, builder, "u2"));
c3.add(next(rand, builder, "u3"));
c3.add(next(rand, builder, "u3"));
c3.add(next(rand, builder, "u3"));
c3.add(next(rand, builder, "u3"));
clustering.lookupAdd(data);
return clustering;
}
public Clustering<Instance, Cluster<Instance>> oneClassPerCluster() {
Clustering<Instance, Cluster<Instance>> oneClass = new ClusterList(3);
int size = 10;
Random rand = new Random();
Dataset<? extends Instance> data = new ArrayDataset<>(size, 2);
data.attributeBuilder().create("x1", "NUMERIC");
data.attributeBuilder().create("x2", "NUMERIC");
for (int i = 0; i < size; i++) {
Instance inst = next(rand, data.builder(), "same class");
// cluster with single class
BaseCluster clust = new BaseCluster(1);
clust.add(inst);
oneClass.add(clust);
}
oneClass.lookupAdd(data);
return oneClass;
}