private void Update(SparseMatrix <double> simMtx, SparseMatrix <double> clustMtxTr, int numClusters, int idx1, int idx2, ArrayList <Cluster> clusters,
IUnlabeledExampleCollection <SparseVector <double> > dataset, double damping)
{
Debug.Assert(idx1 < idx2);
// create new parent
Cluster c1 = clusters[idx1];
Cluster c2 = clusters[idx2];
Cluster parent = new Cluster();
parent.Items.AddRange(c1.Items);
parent.Items.AddRange(c2.Items);
parent.ClusterInfo = Math.Max((int)c1.ClusterInfo, (int)c2.ClusterInfo) + 1;
c1.Parent = parent;
c2.Parent = parent;
parent.AddChild(c1);
parent.AddChild(c2);
SparseVector <double> centroid = ModelUtils.ComputeCentroid(parent.Items, dataset, CentroidType.NrmL2);
centroid = Trim(centroid, 1000, 0.8);
// remove clusters
clusters.RemoveAt(idx2);
clusters.RemoveAt(idx1);
// add new parent
clusters.Add(parent);
// remove rows at idx1 and idx2
simMtx.PurgeRowAt(idx2);
simMtx.PurgeRowAt(idx1);
// remove cols at idx1 and idx2
simMtx.PurgeColAt(idx2);
simMtx.PurgeColAt(idx1);
clustMtxTr.PurgeColAt(idx2);
clustMtxTr.PurgeColAt(idx1);
// update matrices
numClusters -= 2;
foreach (IdxDat <double> item in centroid)
{
if (clustMtxTr[item.Idx] == null)
{
clustMtxTr[item.Idx] = new SparseVector <double>(new IdxDat <double>[] { new IdxDat <double>(numClusters, item.Dat) });
}
else
{
clustMtxTr[item.Idx].InnerIdx.Add(numClusters);
clustMtxTr[item.Idx].InnerDat.Add(item.Dat);
}
}
double[] simVec = ModelUtils.GetDotProductSimilarity(clustMtxTr, numClusters + 1, centroid);
for (int i = 0; i < simVec.Length; i++)
{
simVec[i] *= Math.Pow(damping, (double)((int)parent.ClusterInfo + (int)clusters[i].ClusterInfo) / 2.0);
}
SparseMatrix <double> col = new SparseMatrix <double>();
col[0] = new SparseVector <double>(simVec);
simMtx.AppendCols(col.GetTransposedCopy(), numClusters);
}
public ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < 2 ? new ArgumentValueException("dataset") : null);
ClusteringResult clusteringResult = new ClusteringResult();
Queue <Cluster> queue = new Queue <Cluster>();
// create root
Cluster root = new Cluster();
for (int i = 0; i < dataset.Count; i++)
{
Utils.ThrowException(dataset[i].Count == 0 ? new ArgumentValueException("dataset") : null);
root.Items.Add(i);
}
clusteringResult.AddRoot(root);
// add root to queue
queue.Enqueue(root);
while (queue.Count > 0)
{
// get next cluster
Cluster cluster = queue.Dequeue();
// compute cluster quality
UnlabeledDataset <SparseVector <double> > localDataset = GetDatasetSubset(cluster.Items, dataset);
SparseVector <double> centroid;
double quality = GetClusterQuality(localDataset, out centroid);
cluster.ClusterInfo = new Pair <SparseVector <double>, double>(centroid, quality);
if (quality < mMinQuality)
{
// split cluster, add children to queue
ClusteringResult localResult = mKMeansClustering.Cluster(localDataset);
for (int i = 0; i < 2; i++)
{
cluster.AddChild(localResult.Roots[i]);
localResult.Roots[i].Parent = cluster;
queue.Enqueue(localResult.Roots[i]);
}
}
}
return(clusteringResult);
}
