public static IList <IndexFound> SearchMany(IList <HilbertPoint> points, int indexCount, int outlierSize, int noiseSkipBy, int reducedNoiseSkipBy, int maxTrials, int maxIterationsWithoutImprovement = 3, bool useSample = false, bool shouldCompact = false)
{
var parallel = 4;
var optimizer = new OptimalIndex(outlierSize, noiseSkipBy, reducedNoiseSkipBy, ScrambleHalfStrategy)
{
MaxIterations = (maxTrials + (parallel / 2)) / parallel,
MaxIterationsWithoutImprovement = maxIterationsWithoutImprovement,
ParallelTrials = parallel,
UseSample = useSample,
ShouldCompact = shouldCompact
};
return(optimizer.SearchMany(points, indexCount));
}
/// <summary>
/// Perform unassisted classification of points.
/// </summary>
public Classification <UnsignedPoint, string> Classify()
{
// 3) Create multiple HilbertIndexes.
// 4) Find best HilbertIndex and find the one that predicts the lowest number of clusters K (OptimalIndex).
// 5) Set the characteristic merge distance S (MergeSquareDistance).
//TODO: Support formation and use of more than one HilbertIndex, to respect IndexBudget.IndexCount.
var useOptimalPermutation = true;
UnsignedPoint[] hilbertOrderedPoints;
Timer.Start("Find optimum Hilbert ordering");
if (!useOptimalPermutation)
{
var optimum = OptimalIndex.Search(
HilbertPoints,
IndexConfig.OutlierSize,
IndexConfig.NoiseSkipBy,
IndexConfig.ReducedNoiseSkipBy,
IndexConfig.MaxTrials,
IndexConfig.MaxIterationsWithoutImprovement,
IndexConfig.UseSample,
true
);
hilbertOrderedPoints = HilbertOrderedPoints(optimum.SortedPointIndices.ToList());
MergeSquareDistance = optimum.MergeSquareDistance;
}
else
{
var optimum = OptimalPermutation.Search(
Clusters.Points().ToList(),
BitsPerDimension,
IndexConfig.OutlierSize,
IndexConfig.NoiseSkipBy,
IndexConfig.ReducedNoiseSkipBy,
IndexConfig.MaxTrials,
IndexConfig.MaxIterationsWithoutImprovement,
IndexConfig.UseSample,
true
);
hilbertOrderedPoints = optimum.SortedPoints.ToArray();
MergeSquareDistance = optimum.MergeSquareDistance;
}
Timer.Stop("Find optimum Hilbert ordering");
// 6) Pass over the points in Hilbert order. Every consescutive pair closer than the distance S is merged into the
// same cluster.
Timer.Start("Merge by Hilbert index");
MergeByHilbertIndex(hilbertOrderedPoints);
Timer.Stop("Merge by Hilbert index");
// 7) Find the distance from the Centroid of each non-outlier cluster to every other large cluster (ClosestCluster).
// 8) For the closest neighboring large clusters, probe deeper and find the pair of points,
// one drawn from each of two clusters, that is closest and their separation s (square Cartesian distance).
// 9) If a pair of clusters is closer than S (s ≤ S), merge them, transitively.
Timer.Start("Merge neighboring large clusters");
var cc = new ClosestCluster <string>(Clusters);
var closeClusterPairs = cc.FindClosestClusters(MaxNeighborsToCompare, MergeSquareDistance, OutlierSize, UseExactClusterDistance);
var clusterMerges = 0;
foreach (var pair in closeClusterPairs.Where(p => p.SquareDistance <= MergeSquareDistance))
{
pair.Relabel(Clusters);
if (Clusters.Merge(pair.Color1, pair.Color2))
{
clusterMerges++;
}
}
Timer.Stop("Merge neighboring large clusters");
// 10) Merge outliers with neighboring clusters.
// For all the remaining outliers (small clusters), merge them with the nearest large cluster
// unless their distance is too great (MergeSquareDistance * OutlierDistanceMultiplier).
// Do not permit this phase to cause two large clusters to be joined to each other.
Timer.Start("Merge outliers");
var maxOutlierMergeDistance = (long)(MergeSquareDistance * OutlierDistanceMultiplier);
var outlierMerges = MergeOutliers(maxOutlierMergeDistance);
Timer.Stop("Merge outliers");
var msg = $" {clusterMerges} Cluster merges, {outlierMerges} Outlier merges";
Logger.Info(msg);
return(Clusters);
}
