//this functionality is usefull to see the distance matrix computed and to use as in input to other clustering algorithms implementation (R or Python)
public void CreateCSVMatrixFile(string path)
{
File.Delete(path);
this._BuildSingletonCluster();
StringBuilder matrix = new StringBuilder();
string headerLine = "AggloCluster";
foreach (Cluster cluster in _clusters)
{
headerLine = headerLine + ", Cluster" + cluster.Id;
}
bool writeBlank = false;
matrix.Append(headerLine);
double distanceBetweenTwoClusters;
ClusterPair clusterPair;
for (int i = 0; i < _clusters.Count(); i++)
{
matrix.Append("\r\n");
matrix.Append("Cluster" + _clusters.GetCluster(i).Id);
writeBlank = false;
for (int j = 0; j < _clusters.Count(); j++)
{
clusterPair = new ClusterPair();
clusterPair.Cluster1 = _clusters.GetCluster(i);
clusterPair.Cluster2 = _clusters.GetCluster(j);
distanceBetweenTwoClusters = ClusterDistance.ComputeDistance(clusterPair.Cluster1, clusterPair.Cluster2);
if (distanceBetweenTwoClusters == 0)
{
writeBlank = true;
matrix.Append(",0");
}
else
{
if (writeBlank)
{
matrix.Append("," + string.Empty);
}
else
{
matrix.Append("," + distanceBetweenTwoClusters);
}
}
}
}
File.AppendAllText(path, matrix.ToString());
}
// compute the distance between all pair of clusters and store it on the dissimilarity matrix. this algorithm step is done using parallelization to improve performance.
private void _BuildDissimilarityMatrixParallel()
{
double distanceBetweenTwoClusters;
_dissimilarityMatrix = new DissimilarityMatrix();
Parallel.ForEach(_ClusterPairCollection(), clusterPair =>
{
distanceBetweenTwoClusters = ClusterDistance.ComputeDistance(clusterPair.Cluster1, clusterPair.Cluster2);
_dissimilarityMatrix.AddClusterPairAndDistance(clusterPair, distanceBetweenTwoClusters);
});
}
// 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)));
}
// calcula a distancia entre todos os clusters e as armazena na matrix de dissimilaridade
private void CreateDissimilarityMatrix()
{
double distanceBetweenTwoClusters;
_dissimilarityMatrix = new DissimilarityMatrix();
ClusterPair clusterPair;
for (int i = 0; i < _clusters.Count(); i++)
{
for (int j = i + 1; j < _clusters.Count(); j++)
{
clusterPair = new ClusterPair();
clusterPair.Cluster1 = _clusters.GetCluster(i);
clusterPair.Cluster2 = _clusters.GetCluster(j);
distanceBetweenTwoClusters = ClusterDistance.ComputeDistance(clusterPair.Cluster1, clusterPair.Cluster2);
_dissimilarityMatrix.AddClusterPairAndDistance(clusterPair, distanceBetweenTwoClusters);
}
}
}