private void btnEstimateSig_Click(object sender, EventArgs e)
{
double[,] sourceMatrix;
double[,] inputs;
int[] labels;
getData(out sourceMatrix, out inputs, out labels);
DoubleRange range;
var g = Sigmoid.Estimate(inputs.ToArray(), labels.Length, out range);
numSigAlpha.Value = (decimal)g.Alpha;
numSigB.Value = (decimal)g.Constant;
}
private void buttonEstimate_Click(object sender, EventArgs e)
{
if (MessageBox.Show(this, "This action will first save the configuration. Do you wish to Continue?", "Save required", MessageBoxButtons.YesNo, MessageBoxIcon.Question) == DialogResult.Yes)
{
if (save())
{
double[,] sourceMatrix = _model.FeatureTable.ToMatrix <double>(_activeFeatures.ToArray());
double[][] inputs = sourceMatrix.ToArray();
DoubleRange range;
if (groupGaussianKernel.Enabled)
{
Gaussian gaussian = Gaussian.Estimate(inputs, inputs.Length, out range);
tbGaussianSigma.Value = (decimal)gaussian.Sigma;
}
if (groupPolyKernel.Enabled)
{
}
if (groupSigmoidKernel.Enabled)
{
Sigmoid sigmoid = Sigmoid.Estimate(inputs, inputs.Length, out range);
if (sigmoid.Alpha < (double)Decimal.MaxValue && sigmoid.Alpha > (double)Decimal.MinValue)
{
tbSigmoidAlpha.Value = (decimal)sigmoid.Alpha;
}
if (sigmoid.Constant < (double)Decimal.MaxValue && sigmoid.Constant > (double)Decimal.MinValue)
{
tbSigmoidConst.Value = (decimal)sigmoid.Constant;
}
}
if (groupLaplacianKernel.Enabled)
{
Laplacian laplacian = Laplacian.Estimate(inputs, inputs.Length, out range);
tbLaplacianSigma.Value = (decimal)laplacian.Sigma;
}
}
else
{
MessageBox.Show("Failed to fully save the configuration.\nTherefore configuration properties can not be estimated.");
}
}
}
private void setKernalType(KernelType k)
{
switch (k)
{
case KernelType.Linear:
kernel = new Linear();
break;
case KernelType.Quadratic:
kernel = new Quadratic();
break;
case KernelType.Sigmoid:
kernel = Sigmoid.Estimate(independentVls);
break;
case KernelType.Spline:
kernel = new Spline();
break;
case KernelType.ChiSquared:
kernel = new ChiSquare();
break;
case KernelType.Gaussian:
kernel = Gaussian.Estimate(independentVls);
break;
case KernelType.Multiquadric:
kernel = new Multiquadric();
break;
case KernelType.InverseMultquadric:
kernel = new InverseMultiquadric();
break;
case KernelType.Laplacian:
kernel = Laplacian.Estimate(independentVls);
break;
default:
kernel = new Polynomial(2);
break;
}
}
private void btnEstimateSig_Click(object sender, EventArgs e)
{
// Get only the input vector values (in the first two columns)
double[][] inputs = ConvertDataTableToMatrix(TrainingData.Tables["InterestedTrainingDataValues"]);
DoubleRange range; // valid range will be returned as an out parameter
var sigmoid = Sigmoid.Estimate(inputs, inputs.Length, out range);
if (sigmoid.Alpha < (double)Decimal.MaxValue && sigmoid.Alpha > (double)Decimal.MinValue)
{
numSigAlpha.Value = (decimal)sigmoid.Alpha;
}
if (sigmoid.Constant < (double)Decimal.MaxValue && sigmoid.Constant > (double)Decimal.MinValue)
{
numSigB.Value = (decimal)sigmoid.Constant;
}
}
private void btnEstimateSigmoid_Click(object sender, EventArgs e)
{
DataTable source = dgvLearningSource.DataSource as DataTable;
// Creates a matrix from the source data table
double[,] sourceMatrix = source.ToMatrix(out columnNames);
// Get only the input vector values (in the first two columns)
double[][] inputs = sourceMatrix.GetColumns(0, 1).ToArray();
DoubleRange range; // valid range will be returned as an out parameter
var sigmoid = Sigmoid.Estimate(inputs, inputs.Length, out range);
if (sigmoid.Alpha < (double)Decimal.MaxValue && sigmoid.Alpha > (double)Decimal.MinValue)
{
numSigAlpha.Value = (decimal)sigmoid.Alpha;
}
if (sigmoid.Constant < (double)Decimal.MaxValue && sigmoid.Constant > (double)Decimal.MinValue)
{
numSigB.Value = (decimal)sigmoid.Constant;
}
}