public double[] CalculateOutput(IChromosome chromosome, IParameters param, bool isTrainingData)
{
var ch = ((Chromosome)chromosome);
var node = ch.expressionTree;
if (TData == null && isTrainingData == false)//there is no test data
{
return(null);
}
var rowCount = isTrainingData ? Data.Length : TData.Length;
var y = new double[rowCount];
//
for (int i = 0; i < rowCount; i++)
{
var rowInputData = isTrainingData ? GetDataInputRow(i) : GetTestDataInputRow(i);
// evaluate the function against each rowData
if (param.IsMultipleOutput && ch.ExtraData != null)
{
var oneHotVector = node.Evaluate2(rowInputData, param);
//calculate Mahanalobis distance for each training sample
double minMD = double.MaxValue;
int predictedCluster = 0;
foreach (var c in ch.ExtraData.Keys)
{
var md = AdvancedStatistics.MD(oneHotVector, ch.ExtraData[c].Item1, ch.ExtraData[c].Item2);
//map result with class
if (minMD > md)
{
predictedCluster = c;
minMD = md;
}
}
//map actual and predicted class value
y[i] = predictedCluster;
}
else// evaluate the function against each rowData
{
y[i] = node.Evaluate(rowInputData, param);
}
}
return(y);
}
public float Evaluate(IChromosome ch, IParameters param, int it)
{
var iData = GetData();
var chr = (Chromosome)ch;
var expTree = chr.expressionTree;
double fitness = 0;
double rowFitness = 0.0;
double[] y;
var evalData = new List <(int, double[])>();
var dic = new Dictionary <int, List <double[]> >();
var preCalcData = new Dictionary <int, (double[], double[][])>();
var result = new List <(int, int)>();
//for each trainign sample
for (int i = 0; i < iData.RowCount; i++)
{
var rowInputData = iData.GetDataInputRow(i);
// evaluate the function against each rowData
y = expTree.Evaluate2(rowInputData, param);
if (y == null)
{
return(float.NaN);
}
//get output Value
var yo = (int)iData.GetRowOutput(i);
//add result in to list
evalData.Add((yo, y));
//map result with class
if (dic.ContainsKey(yo))
{
dic[yo].Add(y);
}
else
{
dic.Add(yo, new List <double[]>()
{
y
});
}
}
//calculate centroids and Covariance matrix for each cluster
for (int i = 0; i < dic.Keys.Count; i++)
{
//class value
var c = dic.Keys.ElementAt(i);
var vals = dic.Values.ElementAt(i).ToArray();
//predicted values for the class
var cData = AdvancedStatistics.ToColumnVector <double>(vals);
//calculated centroid for the cData
var cen = cData.Select(x => x.MeanOf()).ToArray();
//calculate CovarianceMatrix
var cov = BasicStatistics.Covariance(cData);
if (!isValid(cov))
{
return(float.NaN);
}
preCalcData.Add(c, (cen, cov));
}
//for each training sample
//go through all samples
foreach (var item in evalData)
{
//calculate Mahanalobis distance for each training sample
double minMD = double.MaxValue;
int predictedCluster = 0;
foreach (var c in dic.Keys)
{
var md = AdvancedStatistics.MD(item.Item2, preCalcData[c].Item1, preCalcData[c].Item2);
//map result with class
if (minMD > md)
{
predictedCluster = c;
minMD = md;
}
}
//map actual and predicted class value
result.Add((item.Item1, predictedCluster));
}
float corectedPredicted = result.Where(x => x.Item1 == x.Item2).Count();
var rawFitness = corectedPredicted / (float)result.Count;
if (double.IsNaN(rawFitness) || double.IsInfinity(rawFitness))
{
fitness = float.NaN;
}
else//calculate adjusted fitness
{
fitness = (rawFitness * 1000.0);
}
//store extra data into chromosome
chr.ExtraData = preCalcData;
return((float)System.Math.Round(fitness, 2));
}
