/**
* Run the algorithm
*
* @param input a list of items to be clustered number of clusters.
* @return a list of clusters
*/
public List<Cluster> runAlgorithm(List<ItemValued> input) {
// Create a list of clusters
List<Cluster> clusters = new ArrayList<Cluster>(k);
// If onely 1 item
if (input.size() == 1) {
// create a cluster with that item
ItemValued item = input.get(0);
Cluster cluster = new Cluster(item);
cluster.addItem(item);
clusters.add(cluster);
// return that cluster
return clusters;
}
// (1) Randomly generate k empty clusters with a random average (cluster
// center)
// (1.1) Find the smallest value and largest value
double higher = input.get(0).getId();
double lower = input.get(0).getId();
// for each item
for (ItemValued item : input) {
// if the largest item until now, remember it
if (item.getValue() > higher) {
higher = item.getValue();
}
// if the smallest item until now, remember it
if (item.getValue() < lower) {
lower = item.getValue();
}
}
// If all items have the same values, we return only one
// cluster.
if (higher == lower) {
// Create a cluster with all items and return it
Cluster cluster = new Cluster(input);
clusters.add(cluster);
return clusters;
}
// (1.2) Generate the k empty clusters with a random average
// between the smallest and largest values.
for (int i = 0; i < k; i++) {
// generate random average
double average = random.nextInt((int) (higher - lower)) + lower;
// create the cluster
Cluster cluster = new Cluster(average);
clusters.add(cluster);
}
// (2) Repeat the two next steps until the assignment hasn't changed
boolean changed;
do {
changed = false;
// (2.1) Assign each point to the nearest cluster center.
// / for each item
for (ItemValued item : input) {
// find the nearest cluster and the cluster containing the item
Cluster nearestCluster = null;
Cluster containingCluster = null;
double distanceToNearestCluster = Double.MAX_VALUE;
// for each cluster
for (Cluster cluster : clusters) {
// calculate the distance to the current item
double distance = averageDistance(cluster, item);
// if the smallest distance until now, remember
// that cluster
if (distance < distanceToNearestCluster) {
nearestCluster = cluster;
distanceToNearestCluster = distance;
}
// if the cluster contains that item,
// then note that this is the cluster
// containing the item.
if (cluster.containsItem(item)) {
containingCluster = cluster;
}
}
// if the closest cluster to the current item
// is not the cluster containing the item
if (containingCluster != nearestCluster) {
// if the item is in a cluster
if (containingCluster != null) {
// remove item from the cluster
removeItem(containingCluster.getItems(), item);
}
// add the item to the nearest cluster
nearestCluster.addItem(item);
changed = true;
}
}
// (2.2) For each cluster, recompute the new cluster average
for (Cluster cluster : clusters) {
cluster.recomputeClusterAverage();
}
} while (changed);
// Computer min and max for all clusters
for (Cluster cluster : clusters) {
cluster.computeHigherAndLower();
}
// return the set of clusters
return clusters;
}
/**
* Calculate the distance between the average of a cluster and a given item
*
* @param cluster1 the cluster
* @param item the item
* @return the distance as a double
*/
private double averageDistance(Cluster cluster1, ItemValued item) {
return Math.abs(cluster1.getaverage() - item.getValue());
}