/// <summary>
/// Returns a clone of this estimator.
/// </summary>
/// <returns></returns>
public object Clone()
{
GaussianEstimator result = new GaussianEstimator();
result.SetTo(this);
return(result);
}
/// <summary>
/// Initialises the parameters from data
/// </summary>
/// <param name="X">X data - initialises weight variances</param>
public void InitialiseFromData(IList <Vector> X)
{
int ND = X.Count;
int NL = X[0].Count;
double[] logWeightVariances = new double[NL];
GaussianEstimator[] gex = new GaussianEstimator[NL];
for (int l = 0; l < NL; l++)
{
gex[l] = new GaussianEstimator();
}
for (int d = 0; d < ND; d++)
{
Vector x = X[d];
for (int l = 0; l < NL; l++)
{
gex[l].Add(x[l]);
}
}
double dimMult = System.Math.Sqrt((double)NL);
for (int l = 0; l < NL; l++)
{
Gaussian g = gex[l].GetDistribution(new Gaussian());
double length = 0.5 * dimMult * System.Math.Sqrt(g.GetVariance());
// If the variance is zero, set to some nominal value.
// This is different from the situation where length
// is very small
if (length < 0.000000001)
{
length = 1.0;
}
double wtSDev = 1.0 / length;
logWeightVariances[l] = 2.0 * System.Math.Log(wtSDev);
}
double logBiasWeightVariance = -System.Math.Log((double)NL);
SetupParams(logWeightVariances, logBiasWeightVariance);
}
/// <summary>
/// Sets the state of this estimator from the specified estimator.
/// </summary>
/// <param name="value"></param>
public void SetTo(GaussianEstimator value)
{
mva.SetTo(value.mva);
}