/**
* Get all objects (as representend by their IDs) in the subtree including the objects located
* directly at this node. Note that objects can occur more than once.
*
* @return Iterator of String
*/
public Collection<Object> getExampleIdsInSubtree() {
Collection<Object> examples = new LinkedList<Object>();
for (HierarchicalClusterNode subNode : subNodes) {
examples.addAll(subNode.getExampleIdsInSubtree());
}
return examples;
}
public void showObject(Object object) {
this.model.removeAllElements();
if (object != null) {
HierarchicalClusterNode node = (HierarchicalClusterNode) object;
for (Object id : node.getExampleIdsInSubtree()) this.model.addElement(id);
}
}
/**
* Returns the number of objects in the subtree including the objects at the current node. Note
* that objects can occur more than once and are counted as such. To get the number of distinct
* objects use the getObjectsInSubtree function first and use the resulting list to calculate the
* number of distinct objects.
*
* @return number of objects
*/
public int getNumberOfExamplesInSubtree() {
int subtreeSum = 0;
for (HierarchicalClusterNode subNode : subNodes) {
subtreeSum += subNode.getNumberOfExamplesInSubtree();
}
return subtreeSum;
}
public int getTotalNumberOfSubnodes() {
if (getNumberOfSubNodes() == 0) {
return 1;
} else {
int count = 0;
for (HierarchicalClusterNode child : getSubNodes()) {
count += child.getTotalNumberOfSubnodes();
}
count++;
return count;
}
}
@Override
public void doWork() throws OperatorException {
ExampleSet exampleSet = exampleSetInput.getData(ExampleSet.class);
DistanceMeasure measure = measureHelper.getInitializedMeasure(exampleSet);
// additional checks
Tools.onlyNonMissingValues(exampleSet, getOperatorClassName(), this, new String[0]);
Tools.checkAndCreateIds(exampleSet);
Attribute idAttribute = exampleSet.getAttributes().getId();
boolean idAttributeIsNominal = idAttribute.isNominal();
DistanceMatrix matrix = new DistanceMatrix(exampleSet.size());
Map<Integer, HierarchicalClusterNode> clusterMap =
new HashMap<Integer, HierarchicalClusterNode>(exampleSet.size());
int[] clusterIds = new int[exampleSet.size()];
// filling the distance matrix
int nextClusterId = 0;
for (Example example1 : exampleSet) {
checkForStop();
clusterIds[nextClusterId] = nextClusterId;
int y = 0;
for (Example example2 : exampleSet) {
if (y > nextClusterId) {
matrix.set(nextClusterId, y, measure.calculateDistance(example1, example2));
}
y++;
}
if (idAttributeIsNominal) {
clusterMap.put(
nextClusterId,
new HierarchicalClusterLeafNode(nextClusterId, example1.getValueAsString(idAttribute)));
} else {
clusterMap.put(
nextClusterId,
new HierarchicalClusterLeafNode(nextClusterId, example1.getValue(idAttribute)));
}
nextClusterId++;
}
// creating linkage method
AbstractLinkageMethod linkage = new SingleLinkageMethod(matrix, clusterIds);
if (getParameterAsString(PARAMETER_MODE).equals(modes[1])) {
linkage = new CompleteLinkageMethod(matrix, clusterIds);
} else if (getParameterAsString(PARAMETER_MODE).equals(modes[2])) {
linkage = new AverageLinkageMethod(matrix, clusterIds);
}
// now building agglomerative tree bottom up
while (clusterMap.size() > 1) {
Agglomeration agglomeration = linkage.getNextAgglomeration(nextClusterId, clusterMap);
HierarchicalClusterNode newNode =
new HierarchicalClusterNode(nextClusterId, agglomeration.getDistance());
newNode.addSubNode(clusterMap.get(agglomeration.getClusterId1()));
newNode.addSubNode(clusterMap.get(agglomeration.getClusterId2()));
clusterMap.remove(agglomeration.getClusterId1());
clusterMap.remove(agglomeration.getClusterId2());
clusterMap.put(nextClusterId, newNode);
nextClusterId++;
}
// creating model
HierarchicalClusterModel model =
new DendogramHierarchicalClusterModel(clusterMap.entrySet().iterator().next().getValue());
// registering visualizer
ObjectVisualizerService.addObjectVisualizer(
model, new ExampleVisualizer((ExampleSet) exampleSet.clone()));
modelOutput.deliver(model);
exampleSetOutput.deliver(exampleSet);
}
