private static Tuple <double[][], double[][]> split(double[][] cluster,
KMeans kmeans, double threshold)
{
kmeans.Randomize(cluster, useSeeding: false);
kmeans.Tolerance = threshold;
kmeans.ComputeInformation = false;
int[] idx = kmeans.Compute(cluster);
List <double[]> a = new List <double[]>();
List <double[]> b = new List <double[]>();
for (int i = 0; i < idx.Length; i++)
{
if (idx[i] == 0)
{
a.Add(cluster[i]);
}
else
{
b.Add(cluster[i]);
}
}
return(Tuple.Create(a.ToArray(), b.ToArray()));
}
/// <summary>
/// Initializes the model with initial values obtained
/// throught a run of the K-Means clustering algorithm.
/// </summary>
///
public double Initialize(double[][] data, double threshold)
{
double error = double.MaxValue;
double errorNew;
KMeans kmeans = new KMeans(clusters.Count);
for (int i = 0; i < 100; ++i)
{
// Create a new K-Means algorithm
KMeans _kmeans = new KMeans(clusters.Count);
// Compute the K-Means
_kmeans.Compute(data, threshold, out errorNew);
// is this the best model so far?
if (errorNew < error || i == 0)
{
error = errorNew;
kmeans = _kmeans;
}
}
// Initialize the model with K-Means
Initialize(kmeans);
return(error);
}
/// <summary>
/// Initializes the model with initial values obtained
/// through a run of the K-Means clustering algorithm.
/// </summary>
///
public double Initialize(double[][] data, double threshold)
{
double error;
// Create a new K-Means algorithm
KMeans kmeans = new KMeans(clusters.Count);
// Compute the K-Means
kmeans.Compute(data, threshold, out error);
// Initialize the model with K-Means
Initialize(kmeans);
return(error);
}
/// <summary>
/// Initializes the model with initial values obtained
/// through a run of the K-Means clustering algorithm.
/// </summary>
///
public double Initialize(double[][] data, double threshold)
{
double error;
// Create a new K-Means algorithm
KMeans kmeans = new KMeans(clusters.Count)
{
ComputeInformation = true,
UseCentroidSeeding = false,
Tolerance = threshold
};
// Compute the K-Means
kmeans.Compute(data, out error);
// Initialize the model with K-Means
Initialize(kmeans);
return(error);
}
private static Tuple <double[][], double[][]> split(double[][] cluster, KMeans kmeans)
{
kmeans.Randomize(cluster);
int[] idx = kmeans.Compute(cluster);
List <double[]> a = new List <double[]>();
List <double[]> b = new List <double[]>();
for (int i = 0; i < idx.Length; i++)
{
if (idx[i] == 0)
{
a.Add(cluster[i]);
}
else
{
b.Add(cluster[i]);
}
}
return(Tuple.Create(a.ToArray(), b.ToArray()));
}