/// <summary>
/// Performs a hierarchical clustering on the the given data matrix.
/// </summary>
/// <param name="data">Data matrix that is going to be clustered.</param>
/// <param name="access">Specifies whether rows or columns are to be clustered</param>
/// <param name="distance">Defines the distance between two elements</param>
/// <param name="linkage">Specifies the linkage for the clustering.</param>
/// <param name="preserveOrder"></param>
/// <param name="periodic"></param>
/// <param name="nthreads"></param>
/// <param name="progress"></param>
/// <returns>An array of cluster nodes defining the resulting tree.</returns>
public HierarchicalClusterNode[] TreeCluster(MatrixIndexer data, MatrixAccess access, IDistance distance,
HierarchicalClusterLinkage linkage, bool preserveOrder, bool periodic, int nthreads, Action<int> progress)
{
int nelements = (access == MatrixAccess.Rows) ? data.RowCount : data.ColumnCount;
if (nelements < 2){
return new HierarchicalClusterNode[0];
}
float[,] distMatrix = DistanceMatrix(data, distance, access);
return TreeCluster(distMatrix, linkage, preserveOrder, periodic, nthreads, progress);
}
/// <summary>
/// Create distance matrix from <see cref="IDistance"/>.
/// </summary>
/// <param name="data"></param>
/// <param name="distance"></param>
public GenericDistanceMatrix(MatrixIndexer data, IDistance distance)
{
N = data.RowCount;
_distances = new double[N * (N - 1) / 2];
int k = 0;
for (int i = 0; i < N; i++)
{
var xi = data.GetRow(i);
for (int j = i+1; j < N; j++)
{
_distances[k++] = distance.Get(xi, data.GetRow(j));
}
}
}
private static BaseVector GetVector(MatrixIndexer data, int index, MatrixAccess access)
{
return access == MatrixAccess.Rows ? data.GetRow(index) : data.GetColumn(index);
}
private static float[,] DistanceMatrix(MatrixIndexer data, IDistance distance, MatrixAccess access)
{
int nrows = data.RowCount;
int ncols = data.ColumnCount;
int nelements = (access == MatrixAccess.Rows) ? nrows : ncols;
float[,] result = new float[nelements, nelements];
for (int i = 0; i < nelements; i++){
for (int j = 0; j < i; j++){
result[i, j] = (float) distance.Get(GetVector(data, i, access), GetVector(data, j, access));
}
}
return result;
}
public HierarchicalClusterNode[] TreeClusterKmeans(MatrixIndexer data, MatrixAccess access, IDistance distance,
HierarchicalClusterLinkage linkage, bool preserveOrder, bool periodic, int nthreads, int nmeans, int restarts,
int maxIter, Action<int> progress)
{
int nelements = (access == MatrixAccess.Rows) ? data.RowCount : data.ColumnCount;
if (nelements <= nmeans){
return TreeCluster(data, access, distance, linkage, preserveOrder, periodic, nthreads, progress);
}
float[,] c;
int[] inds;
if (access == MatrixAccess.Rows){
KmeansClustering.GenerateClusters(data, nmeans, maxIter, restarts, progress, out c, out inds);
} else{
KmeansClustering.GenerateClusters(data.Transpose(), nmeans, maxIter, restarts, progress, out c, out inds);
}
float[,] distMatrix = DistanceMatrix(new FloatMatrixIndexer(c), distance, MatrixAccess.Rows);
HierarchicalClusterNode[] nodes = TreeCluster(distMatrix, linkage, preserveOrder, periodic, nthreads, progress);
Dictionary<int, int[]> clusters;
Dictionary<int, int> singletons;
RearrangeClusters(inds, c.GetLength(0), out clusters, out singletons);
HierarchicalClusterNode[] newNodes = new HierarchicalClusterNode[nelements - 1];
int fill = nelements - nmeans;
Array.Copy(nodes, 0, newNodes, fill, nodes.Length);
int pos = 0;
for (int i = fill; i < newNodes.Length; i++){
HierarchicalClusterNode node = newNodes[i];
if (node.left < 0){
node.left -= fill;
} else if (singletons.ContainsKey(node.left)){
node.left = singletons[node.left];
} else{
if (clusters.ContainsKey(node.left)){
HierarchicalClusterNode[] branch = FillTerminalBranch(clusters[node.left], pos);
Array.Copy(branch, 0, newNodes, pos, branch.Length);
pos += branch.Length;
node.left = -pos;
}
}
if (node.right < 0){
node.right -= fill;
} else if (singletons.ContainsKey(node.right)){
node.right = singletons[node.right];
} else{
if (clusters.ContainsKey(node.right)){
HierarchicalClusterNode[] branch = FillTerminalBranch(clusters[node.right], pos);
Array.Copy(branch, 0, newNodes, pos, branch.Length);
pos += branch.Length;
node.right = -pos;
}
}
}
return newNodes;
}