private void BuildHierarchicalClustering(int indexNewCluster, ClusterDistance.Strategy strategy, int k)
{
ClusterPair closestClusterPair = this._GetClosestClusterPairInDissimilarityMatrix();
// create a new cluster by merge the closest cluster pair
Cluster newCluster = new Cluster();
newCluster.AddSubCluster(closestClusterPair.Cluster1);
newCluster.AddSubCluster(closestClusterPair.Cluster2);
newCluster.Id = indexNewCluster;
newCluster.UpdateTotalQuantityOfPatterns(); //update the total quantity of patterns of the new cluster (this quantity is used by UPGMA clustering strategy)
//remove the closest cluster pair from the clustering data structure (clusters)
_clusters.RemoveClusterPair(closestClusterPair);
_UpdateDissimilarityMatrix(newCluster, strategy);
//add the new cluster to clustering
_clusters.AddCluster(newCluster);
closestClusterPair = null;
// recursive call of this method while there is more than 1 cluster (k>2) in the clustering
if (_clusters.Count() > k)
{
this.BuildHierarchicalClustering(indexNewCluster + 1, strategy, k);
}
}
public Clusters ExecuteClustering(ClusterDistance.Strategy strategy, int k)
{
// Step 1
// build a clustering only with singleton clusters
this._BuildSingletonCluster();
//build the dissimilarity matrix
this._BuildDissimilarityMatrixParallel();
// Step 3
// build the hierarchical clustering
this.BuildHierarchicalClustering(_clusters.Count(), strategy, k);
return(_clusters); //represents the clustering data structure
}
public ClusterNodeCollection ExecuteClustering(ClusterDistance.Strategy strategy, int k)
{
nodeCollection.BuildSingletonCluster(leafCollection);
dissimilarityMatrix = new DissimilarityMatrix();
foreach (ClusterNodePair clusterPair in GetClusterPairCollection())
{
double distanceBetweenTwoClusters = ClusterDistance.ComputeLeafDistance(clusterPair.Cluster1, clusterPair.Cluster2);
dissimilarityMatrix.AddClusterPairAndDistance(clusterPair, distanceBetweenTwoClusters);
}
BuildHierarchicalClustering(nodeCollection.Count, strategy, k);
return(nodeCollection);
}
// update dissimilarity matrix with the distance of the new formed cluster
private void _UpdateDissimilarityMatrix(Cluster newCluster, ClusterDistance.Strategy strategie)
{
double distanceBetweenClusters;
for (int i = 0; i < _clusters.Count(); i++)
{
// compute the distance between old clusters to the new cluster
distanceBetweenClusters = ClusterDistance.ComputeDistance(_clusters.GetCluster(i), newCluster, _dissimilarityMatrix, strategie);
// insert the new cluster's distance
_dissimilarityMatrix.AddClusterPairAndDistance(new ClusterPair(newCluster, _clusters.GetCluster(i)), distanceBetweenClusters);
//remove all old distance values of the old clusters (subclusters of the newcluster)
_dissimilarityMatrix.RemoveClusterPair(new ClusterPair(newCluster.GetSubCluster(0), _clusters.GetCluster(i)));
_dissimilarityMatrix.RemoveClusterPair(new ClusterPair(newCluster.GetSubCluster(1), _clusters.GetCluster(i)));
}
// finally, remove the distance of the old cluster pair
_dissimilarityMatrix.RemoveClusterPair(new ClusterPair(newCluster.GetSubCluster(0), newCluster.GetSubCluster(1)));
}
private void UpdateDissimilarityMatrix(ClusterNode newNode, ClusterDistance.Strategy strategie)
{
ClusterNode node1 = newNode.NodeAt(0);
ClusterNode node2 = newNode.NodeAt(1);
for (int i = 0; i < nodeCollection.Count; i++)
{
ClusterNode node = nodeCollection.ElementAt(i);
double distanceBetweenClusters = ClusterDistance.ComputeNodeDistance(node, newNode, dissimilarityMatrix, strategie);
dissimilarityMatrix.AddClusterPairAndDistance(new ClusterNodePair(newNode, node), distanceBetweenClusters);
dissimilarityMatrix.RemoveClusterPair(new ClusterNodePair(node1, node));
dissimilarityMatrix.RemoveClusterPair(new ClusterNodePair(node2, node));
}
dissimilarityMatrix.RemoveClusterPair(new ClusterNodePair(node1, node2));
}
private void BuildHierarchicalClustering(int indexNewNode, ClusterDistance.Strategy strategy, int k)
{
ClusterNodePair closestClusterPair = dissimilarityMatrix.GetClosestClusterPair();
ClusterNode newNode = new ClusterNode();
newNode.Add(closestClusterPair.Cluster1);
newNode.Add(closestClusterPair.Cluster2);
newNode.Id = indexNewNode;
newNode.Distance = dissimilarityMatrix.ReturnClusterPairDistance(closestClusterPair);
newNode.UpdateTotalLeafs();
nodeCollection.Remove(closestClusterPair.Cluster1);
nodeCollection.Remove(closestClusterPair.Cluster2);
UpdateDissimilarityMatrix(newNode, strategy);
nodeCollection.Add(newNode);
if (nodeCollection.Count > k)
{
BuildHierarchicalClustering(indexNewNode + 1, strategy, k);
}
}
