/// <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.
MathArrayUtils.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(UniformDistributionSampler sampler, int len)
{
// Alloc arrays and fill with uniform random noise.
double[] a = new double[len];
sampler.Sample(a);
// Calc results and compare.
MinMax(a, out double expectedMin, out double expectedMax);
MathArrayUtils.MinMax(a, out double actualMin, out double actualMax);
Assert.AreEqual(expectedMin, actualMin, 1e-10);
Assert.AreEqual(expectedMax, actualMax, 1e-10);
}
