public void SetCentroidsAsMeansHighDimensionality()
{
foreach (Cluster Clust in clusters)
{
Clust.SetCentroidAsMean(true);
}
}
public void SetCentroidsAsMeans()
{
foreach (Cluster Clust in clusters)
{
Clust.SetCentroidAsMean();
}
}
public override void IterateOnce()
{
double AlphaI = 0;
double AlphaJ = 0;
double Beta = 0;
double Gamma = 0;
int Winner;
if (!stopped)
{
if (clusters.Count > 1)
{
DenseMatrix InterimMatrix = new DenseMatrix(currentDistanceMatrix.RowCount);
currentDistanceMatrix.CopyTo(InterimMatrix);
Cluster[] InterimClusters = new Cluster[clusters.Count];
Parallel.For(0, clusters.Count, i => {
InterimClusters[i] = (Cluster)clusters[i].Clone();
});
List <Cluster> InterimClusterList = InterimClusters.ToList <Cluster>();
Tuple <int, int, double> CurrentMinimumDistance = new Tuple <int, int, double>(0, 0, 0);
Parallel.ForEach <Tuple <int, int, double> >(currentDistanceMatrix.EnumerateIndexed(), CurrentTuple =>
{
if (CurrentTuple.Item3 == nextDistance)
{
CurrentMinimumDistance = CurrentTuple;
}
});
switch (style)
//this loops initialises coefficient values for the lance williams algorithm - this is within the iterate once method
//as some styles require iterative recalculation
{
case HACDistanceStyle.Centroid:
AlphaI = calculateMeanAlpha(clusters[CurrentMinimumDistance.Item1], clusters[CurrentMinimumDistance.Item2]);
AlphaJ = calculateMeanAlpha(clusters[CurrentMinimumDistance.Item2], clusters[CurrentMinimumDistance.Item1]);
Beta = calculateCentroidBeta(clusters[CurrentMinimumDistance.Item1], clusters[CurrentMinimumDistance.Item2]);
Gamma = 0;
break;
case HACDistanceStyle.CLink:
AlphaI = 0.5;
AlphaJ = 0.5;
Beta = 0;
Gamma = 0.5;
break;
case HACDistanceStyle.MeanDist:
AlphaI = calculateMeanAlpha(clusters[CurrentMinimumDistance.Item1], clusters[CurrentMinimumDistance.Item2]);
AlphaJ = calculateMeanAlpha(clusters[CurrentMinimumDistance.Item2], clusters[CurrentMinimumDistance.Item1]);
Beta = 0;
Gamma = 0;
break;
case HACDistanceStyle.SLink:
AlphaI = 0.5;
AlphaJ = 0.5;
Beta = 0;
Gamma = -0.5;
break;
case HACDistanceStyle.Ward:
//has to be implemented inside matrix update loop
//as requires values for cluster k
break;
}
//handle cluster merging in list
InterimClusterList[CurrentMinimumDistance.Item1].Merge(InterimClusterList[CurrentMinimumDistance.Item2]);
InterimClusterList.RemoveAt(CurrentMinimumDistance.Item2);
updateClusterIndexes(InterimClusterList);
//handles removal of subsumed cluster's distances from distance matrix
if (CurrentMinimumDistance.Item1 < CurrentMinimumDistance.Item2)
{
Winner = CurrentMinimumDistance.Item1;
}
else
{
//if the item 1 value is further down the distances matrix than the row/column to be removed
Winner = CurrentMinimumDistance.Item1 - 1;
}
InterimMatrix = (DenseMatrix)InterimMatrix.RemoveColumn(CurrentMinimumDistance.Item2).RemoveRow(CurrentMinimumDistance.Item2);
Parallel.For(0, InterimMatrix.RowCount, i =>
{
//recalculate distances from new cluster to all other clusters
if (style == HACDistanceStyle.Ward)
{
AlphaI = calculateWardAlpha(clusters[CurrentMinimumDistance.Item1], clusters[CurrentMinimumDistance.Item2], clusters[i]);
AlphaJ = calculateWardAlpha(clusters[CurrentMinimumDistance.Item2], clusters[CurrentMinimumDistance.Item1], clusters[i]);
Beta = calculateWardBeta(clusters[CurrentMinimumDistance.Item1], clusters[CurrentMinimumDistance.Item2], clusters[i]);
Gamma = 0;
}
double DistanceIJ = nextDistance;
double DistanceIK = currentDistanceMatrix[CurrentMinimumDistance.Item1, i];
double DistanceJK = currentDistanceMatrix[CurrentMinimumDistance.Item2, i];
InterimMatrix[Winner, i] = runLanceWilliamsEquation(DistanceIK, DistanceJK, DistanceIJ, AlphaI, AlphaJ, Beta, Gamma);
InterimMatrix[i, Winner] = InterimMatrix[Winner, i];
InterimMatrix[Winner, Winner] = artificialMax;
});
lastDistance = nextDistance;
nextDistance = InterimMatrix.Values.Min();
if (!stopped)
{
currentDistanceMatrix = (DenseMatrix)InterimMatrix.Clone();
double XValue = InterimClusterList[Winner].XValue;
Tuple <string, string, double, double> ThisDendroEntry = new Tuple <string, string, double, double>(clusters[CurrentMinimumDistance.Item1].ClusterID, clusters[CurrentMinimumDistance.Item2].ClusterID, lastDistance, XValue);
dendrogram.Add(ThisDendroEntry);
clusters = InterimClusterList;
iterator++;
stopped = StoppingConditionMet();
}
else
{
Parallel.ForEach(clusters, Clust => {
Clust.SetCentroidAsMean();
});
stopped = true;
}
}
else
{
stopped = true;
}
}
else
{
Parallel.ForEach(clusters, Clust => {
Clust.SetCentroidAsMean();
});
}
}