public ClusteringResult Cluster(IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
Utils.ThrowException(dataset.Count < NumLeaves ? new ArgumentValueException("dataset") : null);
ClusteringResult clusters = mKMeansClustering.Cluster(dataset);
UnlabeledDataset <SparseVector <double> > centroids = new UnlabeledDataset <SparseVector <double> >();
foreach (Cluster cluster in clusters.Roots)
{
SparseVector <double> centroid = ModelUtils.ComputeCentroid(cluster.Items, dataset, CentroidType.NrmL2);
centroids.Add(centroid);
centroid = Trim(centroid, 1000, 0.8);
cluster.ClusterInfo = 1; // cluster level
}
SparseMatrix <double> simMtx = ModelUtils.GetDotProductSimilarity(centroids, /*thresh=*/ 0, /*fullMatrix=*/ false);
SparseMatrix <double> clustMtxTr = ModelUtils.GetTransposedMatrix(centroids);
int iter = 1;
while (clusters.Roots.Count > 1)
{
Console.WriteLine("Iteration {0} ...", iter++);
int idx1, idx2;
FindMaxSim(simMtx, out idx1, out idx2);
Update(simMtx, clustMtxTr, clusters.Roots.Count, idx1, idx2, clusters.Roots.Inner, dataset, /*damping=*/ 0.9);
Console.WriteLine(simMtx.ToString("E0.00"));
Console.WriteLine();
}
return(clusters);
}
private UnlabeledDataset <SparseVector <double> > GetDatasetSubset(IEnumerable <int> items, IUnlabeledExampleCollection <SparseVector <double> > dataset)
{
UnlabeledDataset <SparseVector <double> > datasetSubset = new UnlabeledDataset <SparseVector <double> >();
foreach (int item in items)
{
datasetSubset.Add(dataset[item]);
}
return(datasetSubset);
}
public static IUnlabeledExampleCollection <ExT> ConvertToUnlabeledDataset <LblT, ExT>(ILabeledExampleCollection <LblT, ExT> dataset)
{
UnlabeledDataset <ExT> unlabeledDataset = new UnlabeledDataset <ExT>();
foreach (LabeledExample <LblT, ExT> labeledExample in dataset)
{
unlabeledDataset.Add(labeledExample.Example);
}
return(unlabeledDataset);
}
public static UnlabeledDataset <ExT> ConvertToUnlabeledDataset <LblT, ExT>(ILabeledExampleCollection <LblT, ExT> dataset)
{
Utils.ThrowException(dataset == null ? new ArgumentNullException("dataset") : null);
UnlabeledDataset <ExT> unlabeledDataset = new UnlabeledDataset <ExT>();
foreach (LabeledExample <LblT, ExT> labeledExample in dataset)
{
unlabeledDataset.Add(labeledExample.Example);
}
return(unlabeledDataset);
}
