/// <summary>
/// Verifies the exists.
/// </summary>
private void VerifyExists()
{
if (!Classification.Exists(_databasePath, _classificationName, out _errOut))
{
Classification.Add(_databasePath, _classificationName, out _errOut);
}
}
public void AddTest()
{
VerifyDoesntExist();
bool value = Classification.Add(_databasePath, _classificationName, out _errOut);
General.HasTrueValue(value, _errOut);
}
/// <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);
}
}
/// <summary>
/// Generate random points clumped into individual, well-separated, Gaussian clusters with optional uniform noise added.
///
/// </summary>
/// <returns>Points that are grouped into clusters and stored in a Classification.</returns>
public Classification <UnsignedPoint, string> MakeClusters()
{
var clusters = new Classification <UnsignedPoint, string>();
r = new FastRandom();
//var z = new ZigguratGaussianSampler();
var farthestDistanceFromClusterCenter = 0.0;
var minDistance = EllipsoidalGenerator.MinimumSeparation(MaxDistanceStdDev, Dimensions);
var centerGenerator = new DiffuseGenerator(Dimensions, minDistance)
{
// Keep the centers of the clusters away from the edge, so that points do not go out of bounds and have their coordinates truncated.
Minimum = MaxDistanceStdDev,
Maximum = MaxCoordinate - MaxDistanceStdDev
};
var iCluster = 0;
var clusterCenters = new Dictionary <string, UnsignedPoint> ();
foreach (var clusterCenter in centerGenerator.Take(ClusterCount).Where(ctr => ctr != null))
{
var centerPoint = new UnsignedPoint(clusterCenter);
// The cluster size may be random, or come from ClusterSizes.
int clusterSize;
if (ClusterSizes.Length > 0)
{
clusterSize = ClusterSizes[iCluster % ClusterSizes.Length];
}
else
{
clusterSize = r.Next(MinClusterSize, MaxClusterSize);
}
var pointGenerator = new EllipsoidalGenerator(clusterCenter, RandomDoubles(Dimensions, MinDistanceStdDev, MaxDistanceStdDev, r), Dimensions);
var clusterId = iCluster.ToString();
foreach (var iPoint in Enumerable.Range(1, clusterSize))
{
UnsignedPoint p;
clusters.Add(
p = new UnsignedPoint(pointGenerator.Generate(new int[Dimensions])),
clusterId
);
var distance = Math.Sqrt(centerPoint.Measure(p));
farthestDistanceFromClusterCenter = Math.Max(farthestDistanceFromClusterCenter, distance);
}
clusterCenters[clusterId] = centerPoint;
iCluster++;
}
AddNoise((int)Math.Floor(clusters.NumPoints * NoisePercentage / 100), clusterCenters, clusters);
Debug.WriteLine("Test data: Farthest Distance from center = {0:N2}. Minimum Distance Permitted between Clusters = {1:N2}. Max Standard Deviation = {2}",
farthestDistanceFromClusterCenter,
minDistance,
MaxDistanceStdDev
);
return(clusters);
}
/// <summary>
/// Make a Classification of N-Dimensional data where the inputs are arrays of integers and the final element in each matrix
/// is the number of its category.
/// </summary>
/// <param name="pointsPlusClass">Data to classify.</param>
/// <returns>A Classification of the points.</returns>
public static Classification <UnsignedPoint, string> MakeClassification(IList <int[]> pointsPlusClass)
{
var dimensions = pointsPlusClass[0].Length - 1; // The last number for each point is its category.
var c = new Classification <UnsignedPoint, string>();
foreach (var pointPlusClass in pointsPlusClass)
{
var point = new UnsignedPoint(pointPlusClass.Take(dimensions).ToArray());
c.Add(point, pointPlusClass[dimensions].ToString(CultureInfo.InvariantCulture));
}
return(c);
}
/// <summary>
/// Generate random points clumped into individual, well-separated, chains of Gaussian clusters.
/// Each chain consists of individiual Gaussian clusters that overlap.
/// </summary>
/// <returns>Points that are grouped into clusters and stored in a Classification.</returns>
public Classification <UnsignedPoint, string> MakeChains(int chainLength)
{
var clusters = new Classification <UnsignedPoint, string>();
r = new FastRandom();
var minDistance = EllipsoidalGenerator.MinimumSeparation(MaxDistanceStdDev, Dimensions);
var centerGenerator = new ChainGenerator(Dimensions, minDistance)
{
// Keep the centers of the clusters away from the edge, so that points do not go out of bounds and have their coordinates truncated.
Minimum = MaxDistanceStdDev,
Maximum = MaxCoordinate - MaxDistanceStdDev
};
var segmentLength = (int)(MinDistanceStdDev * Math.Sqrt(Dimensions) / 3);
var iCluster = 0;
foreach (var chain in centerGenerator.Chains(chainLength, segmentLength).Take(ClusterCount).Where(chain => chain.Any()))
{
var centerPoints = chain.Select(center => new UnsignedPoint(center)).ToList();
// The cluster size may be random, or come from ClusterSizes.
int clusterSize;
if (ClusterSizes.Length > 0)
{
clusterSize = ClusterSizes[iCluster % ClusterSizes.Length];
}
else
{
clusterSize = r.Next(MinClusterSize, MaxClusterSize);
}
// Having decided on an overall cluster size, each segment gets an even number of points.
var segmentSize = clusterSize / chainLength;
var clusterId = iCluster.ToString();
// Each point generator is for a different segment of a chain.
foreach (var pointGenerator in chain
.Select(segmentCenter =>
new EllipsoidalGenerator(segmentCenter, RandomDoubles(Dimensions, MinDistanceStdDev, MaxDistanceStdDev, r), Dimensions))
)
{
foreach (var iPoint in Enumerable.Range(1, segmentSize))
{
clusters.Add(
new UnsignedPoint(pointGenerator.Generate(new int[Dimensions])),
clusterId
);
}
}
iCluster++;
}
return(clusters);
}
/// <summary>
/// Create two random clusters that may be separated from one another by enough distance
/// that they do not overlap, or be partly overlapping, or fully overlapping.
///
/// NOTE: This type of setup is to test divisive clustering, that divides two partly mixed gaussians.
/// </summary>
/// <param name="overlapPercent">A number from zero to 100.
/// If zero, the clusters do not overlap at all.
/// If fifty, then the clusters partly overlap.
/// If 100, the clusters have the same center, so are indistinguishable.</param>
/// <returns>The two clusters.</returns>
public Classification <UnsignedPoint, string> TwoClusters(double overlapPercent)
{
var clusters = new Classification <UnsignedPoint, string>();
r = new FastRandom();
var farthestDistanceFromClusterCenter = 0.0;
var minDistance = EllipsoidalGenerator.MinimumSeparation(MaxDistanceStdDev, Dimensions);
var centerGenerator = new DiffuseGenerator(Dimensions, minDistance)
{
// Keep the centers of the clusters away from the edge, so that points do not go out of bounds and have their coordinates truncated.
// Keep the maximum coordinate farther away, because we will pick the second point by shifting one coordinate
// in the higher direction.
Minimum = MaxDistanceStdDev,
Maximum = MaxCoordinate - MaxDistanceStdDev - (int)minDistance
};
var iCluster = 0;
var clusterCenter1 = centerGenerator.Take(1).FirstOrDefault();
var clusterCenter2 = (int[])clusterCenter1.Clone();
clusterCenter2[0] += (int)(minDistance * (100.0 - overlapPercent) / 100.0);
var centers = new[] { clusterCenter1, clusterCenter2 };
foreach (var clusterCenter in centers)
{
var centerPoint = new UnsignedPoint(clusterCenter);
var clusterSize = r.Next(MinClusterSize, MaxClusterSize);
var pointGenerator = new EllipsoidalGenerator(clusterCenter, RandomDoubles(Dimensions, MinDistanceStdDev, MaxDistanceStdDev, r), Dimensions);
var clusterId = iCluster.ToString();
foreach (var iPoint in Enumerable.Range(1, clusterSize))
{
UnsignedPoint p;
clusters.Add(
p = new UnsignedPoint(pointGenerator.Generate(new int[Dimensions])),
clusterId
);
var distance = Math.Sqrt(centerPoint.Measure(p));
farthestDistanceFromClusterCenter = Math.Max(farthestDistanceFromClusterCenter, distance);
}
iCluster++;
}
//TODO: Go back and recluster the points. Put each point into the cluster whose centroid
// it is nearest. Thus, if two clusters partly overlap, the points from one will be pushed into the other.
return(clusters);
}
