/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusters">A collection of data clusters</param>
/// <param name="data">An array containing data to b eclustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(ClusterCollection clusters, IList<IDataList> data)
{
double[] dataPoint;
double[] clusterMean;
double firstClusterDistance = 0.0;
double secondClusterDistance = 0.0;
int rowCount = data.Count;
int fieldCount = data[0].Data.Length;
int position = 0;
// create a new collection of clusters
ClusterCollection newClusters = new ClusterCollection();
for (int count = 0; count < clusters.Count; count++)
{
Cluster newCluster = new Cluster();
newClusters.Add(newCluster);
}
if (clusters.Count <= 0)
{
throw new SystemException("Cluster Count Cannot Be Zero!");
}
//((20+30)/2), ((170+160)/2), ((80+120)/2)
for (int row = 0; row < rowCount; row++)
{
IDataList rowData = data[row];
for (int cluster = 0; cluster < clusters.Count; cluster++)
{
clusterMean = clusters[cluster].ClusterMean;
if (cluster == 0)
{
firstClusterDistance = KMeans.EuclideanDistance(rowData.Data, clusterMean);
position = cluster;
}
else
{
secondClusterDistance = KMeans.EuclideanDistance(rowData.Data, clusterMean);
if (firstClusterDistance > secondClusterDistance)
{
firstClusterDistance = secondClusterDistance;
position = cluster;
}
}
}
newClusters[position].Add(rowData);
}
return newClusters;
}
/// <summary>
/// Seperates a dataset into clusters or groups with similar characteristics
/// </summary>
/// <param name="clusterCount">The number of clusters or groups to form</param>
/// <param name="data">An array containing data that will be clustered</param>
/// <returns>A collection of clusters of data</returns>
public static ClusterCollection ClusterDataSet(int clusterCount, IList<IDataList> data)
{
//bool stableClusterFormation = false;
int clusterNumber = 0;
int rowCount = data.Count;
int fieldCount = data[0].Data.Length;
int stableClustersCount = 0;
int iterationCount = 0;
double[] dataPoint;
Random random = new Random();
Cluster cluster = null;
ClusterCollection clusters = new ClusterCollection();
System.Collections.ArrayList clusterNumbers = new System.Collections.ArrayList(clusterCount);
while (clusterNumbers.Count < clusterCount)
{
clusterNumber = random.Next(0, rowCount - 1);
if (!clusterNumbers.Contains(clusterNumber))
{
cluster = new Cluster();
clusterNumbers.Add(clusterNumber);
cluster.Add(data[clusterNumber]);
clusters.Add(cluster);
}
}
while (stableClustersCount != clusters.Count)
{
stableClustersCount = 0;
ClusterCollection newClusters = KMeans.ClusterDataSet(clusters, data);
for (int clusterIndex = 0; clusterIndex < clusters.Count; clusterIndex++)
{
if ((KMeans.EuclideanDistance(newClusters[clusterIndex].ClusterMean, clusters[clusterIndex].ClusterMean)) == 0)
{
stableClustersCount++;
}
}
iterationCount++;
clusters = newClusters;
}
return clusters;
}