public KMeansClusteringSolution(KMeansClusteringModel model, IClusteringProblemData problemData)
: base(model, problemData) {
double trainingIntraClusterSumOfSquares = KMeansClusteringUtil.CalculateIntraClusterSumOfSquares(model, problemData.Dataset, problemData.TrainingIndices);
double testIntraClusterSumOfSquares = KMeansClusteringUtil.CalculateIntraClusterSumOfSquares(model, problemData.Dataset, problemData.TestIndices);
this.Add(new Result(TrainingIntraClusterSumOfSquaresResultName, "The sum of squared distances of points of the training partition to the cluster center (is minimized by k-Means).", new DoubleValue(trainingIntraClusterSumOfSquares)));
this.Add(new Result(TestIntraClusterSumOfSquaresResultName, "The sum of squared distances of points of the test partition to the cluster center (is minimized by k-Means).", new DoubleValue(testIntraClusterSumOfSquares)));
}
public KMeansClusteringSolution(KMeansClusteringModel model, IClusteringProblemData problemData)
: base(model, problemData)
{
double trainingIntraClusterSumOfSquares = KMeansClusteringUtil.CalculateIntraClusterSumOfSquares(model, problemData.Dataset, problemData.TrainingIndices);
double testIntraClusterSumOfSquares = KMeansClusteringUtil.CalculateIntraClusterSumOfSquares(model, problemData.Dataset, problemData.TestIndices);
this.Add(new Result(TrainingIntraClusterSumOfSquaresResultName, "The sum of squared distances of points of the training partition to the cluster center (is minimized by k-Means).", new DoubleValue(trainingIntraClusterSumOfSquares)));
this.Add(new Result(TestIntraClusterSumOfSquaresResultName, "The sum of squared distances of points of the test partition to the cluster center (is minimized by k-Means).", new DoubleValue(testIntraClusterSumOfSquares)));
}
public static double CalculateIntraClusterSumOfSquares(KMeansClusteringModel model, IDataset dataset, IEnumerable<int> rows) {
List<int> clusterValues = model.GetClusterValues(dataset, rows).ToList();
List<string> allowedInputVariables = model.AllowedInputVariables.ToList();
int nCols = allowedInputVariables.Count;
Dictionary<int, List<double[]>> clusterPoints = new Dictionary<int, List<double[]>>();
Dictionary<int, double[]> clusterMeans = new Dictionary<int, double[]>();
foreach (var clusterValue in clusterValues.Distinct()) {
clusterPoints.Add(clusterValue, new List<double[]>());
}
// collect points of clusters
int clusterValueIndex = 0;
foreach (var row in rows) {
double[] p = new double[allowedInputVariables.Count];
for (int i = 0; i < nCols; i++) {
p[i] = dataset.GetDoubleValue(allowedInputVariables[i], row);
}
clusterPoints[clusterValues[clusterValueIndex++]].Add(p);
}
// calculate cluster means
foreach (var pair in clusterPoints) {
double[] mean = new double[nCols];
foreach (var p in pair.Value) {
for (int i = 0; i < nCols; i++) {
mean[i] += p[i];
}
}
for (int i = 0; i < nCols; i++) {
mean[i] /= pair.Value.Count;
}
clusterMeans[pair.Key] = mean;
}
// calculate distances
double allCenterDistances = 0;
foreach (var pair in clusterMeans) {
double[] mean = pair.Value;
double centerDistances = 0;
foreach (var clusterPoint in clusterPoints[pair.Key]) {
double centerDistance = 0;
for (int i = 0; i < nCols; i++) {
double d = mean[i] - clusterPoint[i];
d = d * d;
centerDistance += d;
}
centerDistances += centerDistance;
}
allCenterDistances += centerDistances;
}
return allCenterDistances;
}
private KMeansClusteringModel(KMeansClusteringModel original, Cloner cloner)
: base(original, cloner)
{
this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
this.centers = new List <double[]>(original.Centers);
}
public static double CalculateIntraClusterSumOfSquares(KMeansClusteringModel model, IDataset dataset, IEnumerable <int> rows)
{
List <int> clusterValues = model.GetClusterValues(dataset, rows).ToList();
List <string> allowedInputVariables = model.AllowedInputVariables.ToList();
int nCols = allowedInputVariables.Count;
Dictionary <int, List <double[]> > clusterPoints = new Dictionary <int, List <double[]> >();
Dictionary <int, double[]> clusterMeans = new Dictionary <int, double[]>();
foreach (var clusterValue in clusterValues.Distinct())
{
clusterPoints.Add(clusterValue, new List <double[]>());
}
// collect points of clusters
int clusterValueIndex = 0;
foreach (var row in rows)
{
double[] p = new double[allowedInputVariables.Count];
for (int i = 0; i < nCols; i++)
{
p[i] = dataset.GetDoubleValue(allowedInputVariables[i], row);
}
clusterPoints[clusterValues[clusterValueIndex++]].Add(p);
}
// calculate cluster means
foreach (var pair in clusterPoints)
{
double[] mean = new double[nCols];
foreach (var p in pair.Value)
{
for (int i = 0; i < nCols; i++)
{
mean[i] += p[i];
}
}
for (int i = 0; i < nCols; i++)
{
mean[i] /= pair.Value.Count;
}
clusterMeans[pair.Key] = mean;
}
// calculate distances
double allCenterDistances = 0;
foreach (var pair in clusterMeans)
{
double[] mean = pair.Value;
double centerDistances = 0;
foreach (var clusterPoint in clusterPoints[pair.Key])
{
double centerDistance = 0;
for (int i = 0; i < nCols; i++)
{
double d = mean[i] - clusterPoint[i];
d = d * d;
centerDistance += d;
}
centerDistances += centerDistance;
}
allCenterDistances += centerDistances;
}
return(allCenterDistances);
}
private KMeansClusteringModel(KMeansClusteringModel original, Cloner cloner)
: base(original, cloner) {
this.allowedInputVariables = (string[])original.allowedInputVariables.Clone();
this.centers = new List<double[]>(original.Centers);
}
