/// <summary>
/// Genetic mutation for auxiliary argument data.
/// </summary>
public void MutateAuxArgs(double[] auxArgs, XorShiftRandom rng, ZigguratGaussianSampler gaussianSampler, double connectionWeightRange)
{
// Mutate center.
// Add gaussian ditribution sample and clamp result to +-connectionWeightRange.
double tmp = auxArgs[0] + gaussianSampler.NextSample(0, _auxArgsMutationSigmaCenter);
if (tmp < -connectionWeightRange)
{
auxArgs[0] = -connectionWeightRange;
}
else if (tmp > connectionWeightRange)
{
auxArgs[0] = connectionWeightRange;
}
else
{
auxArgs[0] = tmp;
}
// Mutate radius.
// Add gaussian ditribution sample and clamp result to [0,1]
tmp = auxArgs[1] + gaussianSampler.NextSample(0, _auxArgsMutationSigmaRadius);
if (tmp < 0.0)
{
auxArgs[1] = 0.0;
}
else if (tmp > 1.0)
{
auxArgs[1] = 1.0;
}
else
{
auxArgs[1] = tmp;
}
}
//public static float NextGaussianFloat()
//{
// float U, u, v, S;
// do
// {
// u = 2 * Random.value - 1;
// v = 2 * Random.value - 1;
// S = u * u + v * v;
// } while (S>=1.0);
// float fac = Mathf.Sqrt(-2 * Mathf.Log(S) / S);
// return u * fac;
//}
public static int RandomGaussianIntInRange(int min, int max) //using ZigguratGaussianSampler.cs, for gold and exp
{
int mean = (min + max) / 2;
int sigma = (max - mean) / 3;
int returnValue;
do
{
returnValue = (int)normalSampler.NextSample(mean, sigma);
} while (returnValue < min || returnValue > max);
return(returnValue);
}
public static float GaussRandom()
{
if (!gaussianSamplerInitialized)
{
NewGaussSeed();
}
return((float)gaussianSampler.NextSample());
}
/// <summary>
/// Return a gaussian distributed random integer in the range [min,max]
/// Note: standard deviation will be (max-min/6.0)
/// </summary>
/// <param name="min">Inclusive minimum of range</param>
/// <param name="max">Inclusive maximum of range</param>
/// <returns></returns>
public int Inclusive(int min, int max)
{
var range = max - min;
var mean = (max + min) / 2.0;
var sigma = range / 3.0;
var gaussian = (int)_ziggurt.NextSample(mean, sigma);
if (gaussian > max)
{
return(max);
}
if (gaussian < min)
{
return(min);
}
return(gaussian);
}
public void EstimateMedianOfGaussianDistribution()
{
var gaussianRng = new ZigguratGaussianSampler();
var testData = Enumerable.Range(0, 1000).Select(i => Math.Abs((int)gaussianRng.NextSample(500, 250))).ToList();
var actualMedian = FrugalQuantile.ShuffledEstimate(testData, 1, 2, FrugalQuantile.LinearStepAdjuster);
var msg = $"Estimated median of numbers following a Gaussian distribution is {actualMedian}, should be near 500";
Debug.WriteLine(msg);
Assert.IsTrue(actualMedian >= 450 && actualMedian <= 550, msg);
}
//нормальное распределение(зиккурат-алогритм)
public static double ZigguratNormalDistibution()
{
ZigguratGaussianSampler zig = new ZigguratGaussianSampler();
Random rnd = new Random();
var res = zig.NextSample();
if (Math.Abs(res) > 1)
{
return(rnd.NextDouble());
}
return(Math.Abs(res));
}
/// <summary>
/// Genetic mutation for auxiliary argument data.
/// </summary>
public void MutateAuxArgs(double[] auxArgs, XorShiftRandom rng, ZigguratGaussianSampler gaussianSampler, double connectionWeightRange)
{
// Mutate center.
// Add gaussian ditribution sample and clamp result to +-connectionWeightRange.
double tmp = auxArgs[0] + gaussianSampler.NextSample(0, _auxArgsMutationSigmaCenter);
if(tmp < -connectionWeightRange) {
auxArgs[0] = -connectionWeightRange;
}
else if(tmp > connectionWeightRange) {
auxArgs[0] = connectionWeightRange;
}
else {
auxArgs[0] = tmp;
}
// Mutate radius.
// Add gaussian ditribution sample and clamp result to [0,1]
tmp = auxArgs[1] + gaussianSampler.NextSample(0, _auxArgsMutationSigmaRadius);
if(tmp < 0.0) {
auxArgs[1] = 0.0;
}
else if(tmp > 1.0) {
auxArgs[1] = 1.0;
}
else {
auxArgs[1] = tmp;
}
}
