/// <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);
}
}
/// <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>
/// RecommendedNumberOfClusters is a function that gives a recommended number of clusters for the given samples based on some provided methods.
/// </summary>
/// <param name="rawData">The samples to be clustered</param>
/// <param name="kmeansMaxIterations">Maximum allowed number of Kmeans iteration for clustering</param>
/// <param name="kmeansAlgorithm">The desired Kmeans clustering algorithm (1 or 2)
/// <ul style="list-style-type:none">
/// <li> - 1: Centoids are the nearest samples to the means</li>
/// <li> - 2: Centoids are the means</li>
/// </ul></param>
/// <param name="numberOfAttributes">Number of attributes for each sample</param>
/// <param name="maxNumberOfClusters">Maximum desired number of clusters</param>
/// <param name="minNumberOfClusters">Minimum desired number of clusters</param>
/// <param name="method">Integer 0,1,2 or 3 representing the method to be used
/// <ul style = "list-style-type:none" >
/// <li> - Method 0: Radial method in which the farthest sample of each cluster must be closer to the cluster centoid than the nearest foreign sample of the other clusters </li>
/// <li> - Method 1: Standard Deviation method in which the standard deviation in each cluster must be less than the desired standard deviation </li>
/// <li> - Method 2: Both. uses radial and standard deviation methods at the same time </li>
/// <li> - Method 3: Balanced clusters method in which the clusters contain the closest number of samples</li>
/// </ul>
/// </param>
/// <param name="standardDeviation">The desired standard deviation upper limit in each cluster</param>
/// <param name="recommendedNumbersOfCluster">The variable through which the recommended number of clusters is returned</param>
/// <param name="centroids">Initial Centroids</param>
/// <returns>The recommended number of clusters for the given samples based on the specified method.</returns>
public int RecommendedNumberOfClusters(double[][] rawData, int kmeansMaxIterations, int numberOfAttributes, int maxNumberOfClusters, int minNumberOfClusters, int method, double[] standardDeviation, int kmeansAlgorithm = 1, double[][] centroids = null)
{
int recommendedNumbersOfCluster;
int Code;
string Message = "Function <RecommendedNumberOfClusters>: ";
try
{
//some checks
if (maxNumberOfClusters < 2)
{
Code = 104;
Message += "Maximum number of clusters must be at least 2";
throw new KMeansException(Code, Message);
}
int MaxClusters = Math.Min(rawData.Length, maxNumberOfClusters);
if (minNumberOfClusters < 2)
{
minNumberOfClusters = 2;
}
if (method > 3 || method < 0)
{
Code = 122;
Message += "Method must be either 0,1,2 or 3";
throw new KMeansException(Code, Message);
}
if ((method == 1 || method == 2) && standardDeviation == null)
{
Code = 123;
Message += "Parameter StdDev is needed";
throw new KMeansException(Code, Message);
}
if (kmeansMaxIterations < 1)
{
Code = 108;
Message += "Unacceptable number of maximum iterations";
throw new KMeansException(Code, Message);
}
if (rawData == null)
{
Code = 100;
Message += "RawData is null";
throw new KMeansException(Code, Message);
}
if (numberOfAttributes < 1)
{
Code = 107;
Message += "Unacceptable number of attributes. Must be at least 1";
throw new KMeansException(Code, Message);
}
if (kmeansAlgorithm != 2)
{
kmeansAlgorithm = 1;
}
//checks that all the samples have same number of attributes
KMeans.verifyRawDataConsistency(rawData, numberOfAttributes);
double[][] Centroids;
int IterationReached = -1;
int[] kMeansResponse;
Cluster[] cluster;
bool isRadial, isStandardDeviation;
double[] balancedError = new double[MaxClusters - minNumberOfClusters + 1];
for (int i = minNumberOfClusters; i <= MaxClusters; i++)
{
//cluster the data with number of clusters equals to i
kMeansResponse = KMeans.runKMeansAlgorithm(rawData, i, numberOfAttributes, kmeansMaxIterations, kmeansAlgorithm, centroids, out Centroids, out IterationReached);
cluster = ClusteringResults.CreateClusteringResult(rawData, kMeansResponse, Centroids, i);
isRadial = true;
isStandardDeviation = true;
if (method == 0 || method == 2)
{
//radial method check
isRadial = radialClustersCheck(cluster);
}
if (method == 1 || method == 2)
{
//standard deviation check
isStandardDeviation = stdDeviationClustersCheck(cluster, standardDeviation);
}
if (method == 3)
{
//start balanced check
balancedError[i - minNumberOfClusters] = 0;
double[] countSamples = new double[i];
double average = 0;
for (int c = 0; c < i; c++)
{
countSamples[c] = cluster[c].ClusterData.Length;
average = average + countSamples[c] / i;
}
for (int c = 0; c < i; c++)
{
//error calculation
balancedError[i - minNumberOfClusters] = balancedError[i - minNumberOfClusters] + Math.Pow(countSamples[c] - average, 2) / i;
}
}
else if (isRadial && isStandardDeviation)
{
recommendedNumbersOfCluster = i;
//return new AnomalyDetectionResponse(0, "OK");
return(recommendedNumbersOfCluster);
}
}
if (method == 3)
{
// get minimum value (most balanced solution)
int minIndex = 0;
for (int l = 1; l < balancedError.Length; l++)
{
if (balancedError[l] < balancedError[minIndex])
{
minIndex = l;
}
}
recommendedNumbersOfCluster = minIndex + minNumberOfClusters;
//return new AnomalyDetectionResponse(0, "OK");
return(recommendedNumbersOfCluster);
}
///// find a way to throw the response
recommendedNumbersOfCluster = 0;
//return new AnomalyDetectionResponse(1, "Could not find a recommended number of clusters based on the desired constraints");
return(recommendedNumbersOfCluster);
}
catch (Exception Ex)
{
Code = 400;
Message += "Unhandled exception:\t" + Ex.ToString();
throw new KMeansException(Code, Message);
}
}
