/// <summary>
/// calculateNearestCluster is a function that determines the nearest cluster and calculates the distance between those two clusters.
/// </summary>
/// <param name="Centroids">the centroids of the clusters</param>
/// <param name="SamplesInClusters">number of samples in each cluster</param>
/// <returns>Tuple of two Items: <br />
/// - Item 1: contains the number of nearest cluster <br />
/// - Item 2: contains the distance to the nearest cluster
/// </returns>
private static Tuple <int[], double[]> calculateNearestCluster(double[][] Centroids, int[] SamplesInClusters)
{
int[] NearestClustersArray = new int[Centroids.Length];
double[] DistanceToNearestClusterArray = new double[Centroids.Length];
int Code;
string Message = "Function <calculateNearestCluster>: ";
try
{
double curDistance;
for (int i = 0; i < Centroids.Length; i++)
{
//in case of empty cluster
if (SamplesInClusters[i] == 0)
{
NearestClustersArray[i] = -1;
DistanceToNearestClusterArray[i] = -1;
continue;
}
DistanceToNearestClusterArray[i] = double.MaxValue;
for (int j = 0; j < Centroids.Length; j++)
{
if (i == j || SamplesInClusters[j] == 0)
{
continue;
}
curDistance = KMeans.calculateDistance(Centroids[i], Centroids[j]);
if (curDistance < DistanceToNearestClusterArray[i])
{
DistanceToNearestClusterArray[i] = curDistance;
NearestClustersArray[i] = j;
}
}
}
return(Tuple.Create(NearestClustersArray, DistanceToNearestClusterArray));
}
catch (Exception Ex)
{
Code = 400;
Message += "Unhandled exception:\t" + Ex.ToString();
throw new KMeansException(Code, Message);
}
}
/// <summary>
/// calculateNoreStatistics is a function that claculates statistics of a cluster. These statistics are dependent on other clusters.
/// </summary>
/// <param name="RawData">data to be clustered</param>
/// <param name="DataToClusterMapping">contains the assigned cluster number for each sample of the RawData</param>
/// <param name="Centroids">the centroids of the clusters</param>
/// <param name="NearestCluster">nearest cluster number</param>
/// <param name="NearestForeignSampleInNearestCluster">nearest sample belonging of the nearest cluster to this cluster's centroid</param>
/// <param name="DistanceToNearestForeignSampleInNearestCluster">distance between the nearest sample of the nearest cluster and this cluster's centroid</param>
/// <param name="NearestForeignSample">nearest sample not belonging to this cluster and this cluster's centroid</param>
/// <param name="DistanceToNearestForeignSample">distance between the nearest foreign sample and this cluster's centroid</param>
/// <param name="ClusterOfNearestForeignSample">the cluster to which the nearest foreign sample belongs</param>
private static void calculateMoreStatistics(double[][] RawData, int[] DataToClusterMapping, double[][] Centroids, int[] NearestCluster, out double[][] NearestForeignSampleInNearestCluster, out double[] DistanceToNearestForeignSampleInNearestCluster, out double[][] NearestForeignSample, out double[] DistanceToNearestForeignSample, out int[] ClusterOfNearestForeignSample)
{
int Code;
string Message = "Function <calculateMoreStatistics>: ";
try
{
NearestForeignSampleInNearestCluster = new double[Centroids.Length][];
DistanceToNearestForeignSampleInNearestCluster = new double[Centroids.Length];
NearestForeignSample = new double[Centroids.Length][];
DistanceToNearestForeignSample = new double[Centroids.Length];
ClusterOfNearestForeignSample = new int[Centroids.Length];
for (int i = 0; i < Centroids.Length; i++)
{
//in case of empty cluster
if (NearestCluster[i] == -1)
{
NearestForeignSampleInNearestCluster[i] = null;
NearestForeignSample[i] = null;
DistanceToNearestForeignSampleInNearestCluster[i] = -1;
DistanceToNearestForeignSample[i] = -1;
ClusterOfNearestForeignSample[i] = -1;
}
else
{
DistanceToNearestForeignSampleInNearestCluster[i] = double.MaxValue;
DistanceToNearestForeignSample[i] = double.MaxValue;
}
}
double curDistance;
for (int i = 0; i < RawData.Length; i++)
{
for (int j = 0; j < Centroids.Length; j++)
{
//skip if sample belong to the cluster itself or the cluster is empty
if (DataToClusterMapping[i] == j || NearestCluster[j] == -1)
{
continue;
}
curDistance = KMeans.calculateDistance(RawData[i], Centroids[j]);
if (curDistance < DistanceToNearestForeignSample[j])
{
DistanceToNearestForeignSample[j] = curDistance;
NearestForeignSample[j] = RawData[i];
ClusterOfNearestForeignSample[j] = DataToClusterMapping[i];
}
if (DataToClusterMapping[i] == NearestCluster[j])
{
if (curDistance < DistanceToNearestForeignSampleInNearestCluster[j])
{
DistanceToNearestForeignSampleInNearestCluster[j] = curDistance;
NearestForeignSampleInNearestCluster[j] = RawData[i];
}
}
}
}
}
catch (Exception Ex)
{
Code = 400;
Message += "Unhandled exception:\t" + Ex.ToString();
throw new KMeansException(Code, Message);
}
}
/// <summary>
/// calculateStatistics is a function that claculates statistics and properties of a cluster. These statistics are independent on other clusters.
/// </summary>
/// <param name="Cluster">a cluster object</param>
private static void calculateStatistics(Cluster cls)
{
int Code;
string Message = "Function <calculateStatistics>: ";
try
{
int NumberOfSamples = cls.ClusterData.Length;
int NumberOfAttributes = cls.Centroid.Length;
cls.ClusterDataDistanceToCentroid = new double[NumberOfSamples];
cls.Mean = new double[NumberOfAttributes];
cls.StandardDeviation = new double[NumberOfAttributes];
cls.InClusterMaxDistance = -1;
//in case of empty cluster
if (NumberOfSamples == 0)
{
cls.InClusterFarthestSampleIndex = 0;
cls.InClusterMaxDistance = 0;
cls.InClusterFarthestSample = new double[NumberOfAttributes];
for (int j = 0; j < NumberOfAttributes; j++)
{
cls.Mean[j] = 0;
cls.Centroid[j] = 0;
cls.InClusterFarthestSample[j] = 0;
}
cls.NearestCluster = -1;
}
else
{
for (int i = 0; i < NumberOfSamples; i++)
{
//calculate distance for each sample
cls.ClusterDataDistanceToCentroid[i] = KMeans.calculateDistance(cls.ClusterData[i], cls.Centroid);
if (cls.ClusterDataDistanceToCentroid[i] > cls.InClusterMaxDistance)
{
//farthest sample
cls.InClusterFarthestSampleIndex = i;
cls.InClusterFarthestSample = cls.ClusterData[i];
cls.InClusterMaxDistance = cls.ClusterDataDistanceToCentroid[i];
}
for (int j = 0; j < NumberOfAttributes; j++)
{
cls.Mean[j] += cls.ClusterData[i][j] / NumberOfSamples;
}
}
double[] ClusterVariance = new double[NumberOfAttributes];
for (int i = 0; i < NumberOfSamples; i++)
{
for (int j = 0; j < NumberOfAttributes; j++)
{
ClusterVariance[j] += Math.Pow((cls.ClusterData[i][j] - cls.Mean[j]), 2) / NumberOfSamples;
}
}
for (int i = 0; i < NumberOfAttributes; i++)
{
cls.StandardDeviation[i] = Math.Sqrt(ClusterVariance[i]);
}
}
}
catch (Exception Ex)
{
Code = 400;
Message += "Unhandled exception:\t" + Ex.ToString();
throw new KMeansException(Code, Message);
}
}