/// <summary>
/// Add noise points to the data and classify each noise point with the nearest cluster center.
/// </summary>
/// <param name="noisePointsToAdd">Number of noise points to add.</param>
/// <param name="clusterCenters">Cluster centers for each cluster, where the key is the cluster id.</param>
/// <param name="clusters">The noise points will be added to these clusters.</param>
private void AddNoise(int noisePointsToAdd, Dictionary <string, UnsignedPoint> clusterCenters, Classification <UnsignedPoint, string> clusters)
{
if (noisePointsToAdd <= 0)
{
return;
}
var pccp = new PolyChromaticClosestPoint <string> (clusters);
var closest = new List <Tuple <String, String> > ();
// Find the nearest neighboring cluster to each cluster.
// We will be choosing random noise points positioned in the space between clusters that are near neighbors.
foreach (var clusterId in clusters.ClassLabels())
{
var cp = pccp.FindClusterApproximately(clusterId).Swap(clusterId);
closest.Add(new Tuple <string, string>(cp.Color1, cp.Color2));
}
// We need to pick random points from each cluster, so must convert from Sets to Lists for performance.
var clustersAsLists = new Dictionary <string, List <UnsignedPoint> > ();
foreach (var pair in clusters.LabelToPoints)
{
clustersAsLists [pair.Key] = pair.Value.ToList();
}
// Pick random pairs of clusters that are close neighbors.
// Then pick a random point from each cluster and compute a weighted average of the two points.
// This will construct noise points that tend to form a filament between two clusters.
// Such connecting filaments pose the greatest likelihood of merging two distinct
// clusters into one, the very error that must be compensated for by an improved algorithm.
for (var i = 0; i < noisePointsToAdd; i++)
{
var whereToAdd = closest [r.Next(closest.Count)];
// The weight will range from 0.18 to 0.82 so as to keep most noise points from being inside a cluster,
// which would make them non-noisy.
var weight1 = r.NextDouble() * 0.64 + 0.18;
var weight2 = 1.0 - weight1;
var c1 = clustersAsLists[whereToAdd.Item1];
var c2 = clustersAsLists[whereToAdd.Item2];
var p1 = c1[r.Next(c1.Count)];
var p2 = c2[r.Next(c2.Count)];
var vRandom = new int[Dimensions];
for (var iDim = 0; iDim < vRandom.Length; iDim++)
{
vRandom [iDim] = (int)(weight1 * p1.Coordinates [iDim] + weight2 * p2.Coordinates [iDim]);
}
var pRandom = new UnsignedPoint(vRandom);
var d1 = c1.Select(p => pRandom.Measure(p)).Min();
var d2 = c2.Select(p => pRandom.Measure(p)).Min();
var cRandom = d1 < d2 ? whereToAdd.Item1 : whereToAdd.Item2;
clusters.Add(pRandom, cRandom);
Noise.Add(pRandom);
}
}
