/// <summary>
/// Evaluate the provided black box against the function regression task,
/// and return its fitness score.
/// </summary>
/// <param name="box">The black box to evaluate.</param>
/// <returns>A new instance of <see cref="FitnessInfo"/>.</returns>
public FitnessInfo Evaluate(IBlackBox <double> box)
{
// Probe the black box over the full range of the input parameter.
_blackBoxProbe.Probe(box, _yArr);
// Calc gradients.
FuncRegressionUtils.CalcGradients(_paramSamplingInfo, _yArr, _gradientArr);
// Calc y position mean squared error (MSE), and apply weighting.
double yMse = MathSpanUtils.MeanSquaredDelta(_yArr, _yArrTarget);
yMse *= _yMseWeight;
// Calc gradient mean squared error.
double gradientMse = MathSpanUtils.MeanSquaredDelta(_gradientArr, _gradientArrTarget);
gradientMse *= _gradientMseWeight;
// Calc fitness as the inverse of MSE (higher value is fitter).
// Add a constant to avoid divide by zero, and to constrain the fitness range between bad and good solutions;
// this allows the selection strategy to select solutions that are mediocre and therefore helps preserve diversity.
double fitness = 20.0 / (yMse + gradientMse + 0.02);
return(new FitnessInfo(fitness));
}
/// <summary>
/// Calculate a frequency distribution for the provided array of values.
/// 1) The minimum and maximum values are found.
/// 2) The resulting value range is divided into equal sized sub-ranges (categoryCount).
/// 3) The number of values that fall into each category is determined.
/// </summary>
public static HistogramData BuildHistogramData(double[] valArr, int categoryCount)
{
// Determine min/max.
MathSpanUtils.MinMax(valArr, out double min, out double max);
// Note. each bucket's range has interval [low,high), i.e. samples exactly equal to 'high'
// will fall into the next highest bucket. Therefore to prevent the maximum sample vAalue falling into the
// last bucket by itself, we inflate the range by a small proportion so that the max value falls just below
// the max range covered by the distribution.
double range = (max - min) * 1.01;
// Handle special case where the data series contains a single value.
if (0.0 == range)
{
return(new HistogramData(min, max, 0.0, new int[] { valArr.Length }));
}
// Loop values and for each one increment the relevant category's frequency count.
double incr = range / categoryCount;
int[] frequencyArr = new int[categoryCount];
for (int i = 0; i < valArr.Length; i++)
{
frequencyArr[(int)((valArr[i] - min) / incr)]++;
}
return(new HistogramData(min, max, incr, frequencyArr));
}
private static void MinMax_Inner(UniformDistributionSampler sampler, int len)
{
// Alloc arrays and fill with uniform random noise.
double[] a = new double[len];
sampler.Sample(a);
// Calc results and compare.
PointwiseMinMax(a, out double expectedMin, out double expectedMax);
MathSpanUtils.MinMax(a, out double actualMin, out double actualMax);
Assert.Equal(expectedMin, actualMin, 10);
Assert.Equal(expectedMax, actualMax, 10);
}
private static void MeanSquaredDelta_Inner(UniformDistributionSampler sampler, int len)
{
// Alloc arrays and fill with uniform random noise.
double[] a = new double[len];
double[] b = new double[len];
sampler.Sample(a);
sampler.Sample(b);
// Calc results and compare.
double expected = PointwiseSumSquaredDelta(a, b) / a.Length;
double actual = MathSpanUtils.MeanSquaredDelta(a, b);
Assert.Equal(expected, actual, 10);
}
private static void Clamp_Inner(UniformDistributionSampler sampler, int len)
{
// Alloc array and fill with uniform random noise.
double[] x = new double[len];
sampler.Sample(x);
// Clip the elements of the array with the safe routine.
double[] expected = (double[])x.Clone();
PointwiseClip(expected, -1.1, 18.8);
// Clip the elements of the array.
double[] actual = (double[])x.Clone();
MathSpanUtils.Clamp(actual, -1.1, 18.8);
// Compare expected with actual array.
Assert.True(SpanUtils.Equal <double>(expected, actual));
}
/// <summary>
/// Calculate a histogram for the provided span of values.
/// 1) The minimum and maximum values are found.
/// 2) The resulting value range is divided into equal sized sub-ranges or bins.
/// 3) The number of values that fall into each bin is determined.
/// </summary>
/// <param name="vals">The values to calculate a histogram for.</param>
/// <param name="binCount">The number of histogram bins to use.</param>
/// <returns>A new instance of <see cref="HistogramData"/>.</returns>
public static HistogramData BuildHistogramData(Span <double> vals, int binCount)
{
// Determine min/max.
MathSpanUtils.MinMax(vals, out double min, out double max);
// Note. each bin's range has interval [low,high), i.e. samples exactly equal to 'high' will fall
// into the next highest bin. Except for the last bin which has interval [low, high].
double range = max - min;
// Handle special case where the data series contains a single value.
if (range == 0.0)
{
return(new HistogramData(min, max, 0.0, new int[] { vals.Length }));
}
// Loop values, and for each one increment the relevant category's frequency count.
double incr = range / binCount;
int[] frequencyArr = new int[binCount];
for (int i = 0; i < vals.Length; i++)
{
// Determine which bin the value falls within.
int idx = (int)((vals[i] - min) / incr);
// Values that equal max, are placed into the last bin.
if (idx == vals.Length)
{
idx--;
}
frequencyArr[idx]++;
}
return(new HistogramData(min, max, incr, frequencyArr));
}
