public void TwoSampleKolmogorovSmirnovTestConstructorTest()
{
Accord.Math.Tools.SetupGenerator(0);
// Create a K-S test to verify if two samples have been
// drawn from different populations. In this example, we
// will first generate a number of samples from different
// distributions, and then check if the K-S test can indeed
// see the difference:
// Generate 15 points from a Normal distribution with mean 5 and sigma 2
double[] sample1 = new NormalDistribution(mean: 5, stdDev: 1).Generate(25);
// Generate 15 points from an uniform distribution from 0 to 10
double[] sample2 = new UniformContinuousDistribution(a: 0, b: 10).Generate(25);
// Now we can create a K-S test and test the unequal hypothesis:
var test = new TwoSampleKolmogorovSmirnovTest(sample1, sample2,
TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
bool significant = test.Significant; // outputs true
Assert.IsTrue(test.Significant);
Assert.AreEqual(0.44, test.Statistic, 1e-15);
Assert.IsFalse(Double.IsNaN(test.Statistic));
Assert.AreEqual(0.00826, test.PValue, 1e-5);
}
public void TwoSampleKolmogorovSmirnovTestConstructorTest()
{
Accord.Math.Tools.SetupGenerator(0);
// Create a K-S test to verify if two samples have been
// drawn from different populations. In this example, we
// will first generate a number of samples from different
// distributions, and then check if the K-S test can indeed
// see the difference:
// Generate 15 points from a Normal distribution with mean 5 and sigma 2
double[] sample1 = new NormalDistribution(mean: 5, stdDev: 1).Generate(25);
// Generate 15 points from an uniform distribution from 0 to 10
double[] sample2 = new UniformContinuousDistribution(a: 0, b: 10).Generate(25);
// Now we can create a K-S test and test the unequal hypothesis:
var test = new TwoSampleKolmogorovSmirnovTest(sample1, sample2,
TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
bool significant = test.Significant; // outputs true
Assert.IsTrue(test.Significant);
Assert.AreEqual(0.44, test.Statistic, 1e-15);
Assert.IsFalse(Double.IsNaN(test.Statistic));
Assert.AreEqual(0.00826, test.PValue, 1e-5);
}
public void TwoSampleKolmogorovSmirnovTestConstructorTest3()
{
double[] x = { 1, 2, 3, 4, 5 };
double[] y = { 2.5, 4.5 };
var target = new TwoSampleKolmogorovSmirnovTest(x, y);
Assert.AreEqual(0.4, target.Statistic);
double actual = target.PValue;
Assert.AreEqual(0.952, actual, 1e-3);
}
public void TwoSampleKolmogorovSmirnovTestConstructorTest2()
{
// The following example comes from the stats page of the College
// of Saint Benedict and Saint John's University (Kirkman, 1996).
// http://www.physics.csbsju.edu/stats/
double[] redwell =
{
23.4, 30.9, 18.8, 23.0, 21.4, 1, 24.6, 23.8, 24.1, 18.7, 16.3, 20.3,
14.9, 35.4, 21.6, 21.2, 21.0, 15.0, 15.6, 24.0, 34.6, 40.9, 30.7,
24.5, 16.6, 1, 21.7, 1, 23.6, 1, 25.7, 19.3, 46.9, 23.3, 21.8, 33.3,
24.9, 24.4, 1, 19.8, 17.2, 21.5, 25.5, 23.3, 18.6, 22.0, 29.8, 33.3,
1, 21.3, 18.6, 26.8, 19.4, 21.1, 21.2, 20.5, 19.8, 26.3, 39.3, 21.4,
22.6, 1, 35.3, 7.0, 19.3, 21.3, 10.1, 20.2, 1, 36.2, 16.7, 21.1, 39.1,
19.9, 32.1, 23.1, 21.8, 30.4, 19.62, 15.5
};
double[] whitney =
{
16.5, 1, 22.6, 25.3, 23.7, 1, 23.3, 23.9, 16.2, 23.0, 21.6, 10.8, 12.2,
23.6, 10.1, 24.4, 16.4, 11.7, 17.7, 34.3, 24.3, 18.7, 27.5, 25.8, 22.5,
14.2, 21.7, 1, 31.2, 13.8, 29.7, 23.1, 26.1, 25.1, 23.4, 21.7, 24.4, 13.2,
22.1, 26.7, 22.7, 1, 18.2, 28.7, 29.1, 27.4, 22.3, 13.2, 22.5, 25.0, 1,
6.6, 23.7, 23.5, 17.3, 24.6, 27.8, 29.7, 25.3, 19.9, 18.2, 26.2, 20.4,
23.3, 26.7, 26.0, 1, 25.1, 33.1, 35.0, 25.3, 23.6, 23.2, 20.2, 24.7, 22.6,
39.1, 26.5, 22.7
};
// Create a non-parametric Kolmogorov-Smirnov's test
var twoTail = new TwoSampleKolmogorovSmirnovTest(redwell, whitney,
alternate: TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
var oneTailGreater = new TwoSampleKolmogorovSmirnovTest(redwell, whitney,
alternate: TwoSampleKolmogorovSmirnovTestHypothesis.FirstSampleIsLargerThanSecond);
var oneTailLesser = new TwoSampleKolmogorovSmirnovTest(redwell, whitney,
alternate: TwoSampleKolmogorovSmirnovTestHypothesis.FirstSampleIsSmallerThanSecond);
Assert.AreEqual(0.2204113924050633, twoTail.Statistic, 1e-10);
Assert.AreEqual(0.2204113924050633, oneTailGreater.Statistic, 1e-10);
Assert.AreEqual(0.1242088607594936, oneTailLesser.Statistic, 1e-10);
Assert.AreEqual(0.03463090913864153, twoTail.PValue, 1e-10);
Assert.AreEqual(0.0177488245823226, oneTailGreater.PValue, 1e-10);
Assert.AreEqual(0.270697775095498, oneTailLesser.PValue, 1e-10);
}
protected override void EndProcessing()
{
var hypo = TestingHelper.GetTwoSampleKolmogorovSmirnovTestHypothesis(Alternate);
TwoSampleKolmogorovSmirnovTest test;
if (ParameterSetName == "Pipeline")
{
test = new TwoSampleKolmogorovSmirnovTest(_data[Sample1Name].ToDoubleArray(), _data[Sample2Name].ToDoubleArray(), hypo);
}
else
{
test = new TwoSampleKolmogorovSmirnovTest(Sample1, Sample2, hypo);
}
test.Size = Size;
WriteObject(test);
}
private void buildModel()
{
if (!checkTables())
{
//Console.WriteLine("CheckTables = false");
return;
}
if (!getSampleRatios())
{
//Console.WriteLine("Sample Ratios = false");
return;
}
pca = new dataPrepPrincipleComponents(Sample1, Variables);
cluster = new dataPrepClusterKmean(Sample1, Variables, numberOfBins);
foreach (string s in cntDic.Keys)
{
buildSamples(s);
double[] pValueArr = new double[Variables.Length];
double[] sValueArr = new double[Variables.Length];
//double[] s1Arr = sample1[0];
//double[] s2Arr = sample2[0];
//TwoSampleKolmogorovSmirnovTest test = new TwoSampleKolmogorovSmirnovTest(s1Arr, s2Arr, TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
//getCdfProp(s, 0, test);
//pValue = test.PValue;
//sValue = test.Statistic;
for (int i = 0; i < Variables.Length; i++)
{
double[] s1Arr = sample1[i];
double[] s2Arr = sample2[i];
TwoSampleKolmogorovSmirnovTest test = new TwoSampleKolmogorovSmirnovTest(s1Arr, s2Arr, TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
//Console.WriteLine(test.Significant.ToString());
getCdfProp(s, i, test);
double pValueS = test.PValue;
double sValueS = test.Statistic;
pValueArr[i] = pValueS;
sValueArr[i] = sValueS;
}
pDic.Add(s, pValueArr);
sDic.Add(s, sValueArr);
}
}
/*private void PerformCmv(Distribution variantResult, Distribution scaledVariantTarget, Distribution nsgaFv, Distribution featureTarget, Distribution interacTarget, Distribution interacVals, Solution solution)
* {
* Task<double>[] tasks = {};
* if (Model.Setting.NoVariantCalculation)
* {
* tasks = new Task<double>[Model.Setting.NumberOfInteractions > 0 ? 2 : 1];
* }
* else
* {
* tasks = new Task<double>[Model.Setting.NumberOfInteractions > 0 ? 3 : 2];
* }
*
*
*
* tasks[0] = Task.Factory.StartNew(() =>
* {
* var cmv2 = new CramerVonMises(nsgaFv.Values, featureTarget.Values);
* return Math.Abs(cmv2.Calculate());
* });
*
* if (!Model.Setting.NoVariantCalculation)
* {
* tasks[2] = Task.Factory.StartNew(() =>
* {
* var cmv = new CramerVonMises(variantResult.Values, scaledVariantTarget.Values);
* return Math.Abs(cmv.Calculate());
* });
* }
* if (Model.Setting.NumberOfInteractions > 0)
* {
*
* tasks[1] = Task.Factory.StartNew(() =>
* {
* var cmv3 = new CramerVonMises(interacTarget.Values, interacVals.Values);
* return Math.Abs(cmv3.Calculate());
* });
*
* }
*
* Task.WaitAll(tasks);
*
* solution.Objective[0] = tasks[0].Result;
* solution.Objective[1] = tasks[1].Result;
* if (Model.Setting.NumberOfInteractions > 0) solution.Objective[2] = tasks[2].Result;
* } */
private static void PerfomKs(Distribution variantResult, Distribution scaledVariantTarget, Distribution nsgaFv, Distribution featureTarget, Solution solution)
{
var variant = new TwoSampleKolmogorovSmirnovTest(variantResult.Values, scaledVariantTarget.Values);
if (variant.PValue == 0d)
{
solution.Objective[0] = double.MaxValue;
}
else
{
solution.Objective[0] = -variant.PValue;
}
var feature = new TwoSampleKolmogorovSmirnovTest(nsgaFv.Values, featureTarget.Values);
if (feature.PValue == 0d)
{
solution.Objective[1] = double.MaxValue;
}
else
{
solution.Objective[1] = -feature.PValue;
}
}
private void getCdfProp(string s, int i, TwoSampleKolmogorovSmirnovTest test)
{
//Console.WriteLine("Key to look up = " + s);
double[][] variableBinProps;
double[][] variableBinProps2;
if (binPropDic1.TryGetValue(s, out variableBinProps))
{
}
else
{
variableBinProps = new double[Variables.Length][];
for (int k = 0; k < Variables.Length; k++)
{
variableBinProps[k] = new double[numberOfBins];
}
binPropDic1.Add(s, variableBinProps);
}
if (binPropDic2.TryGetValue(s, out variableBinProps2))
{
}
else
{
variableBinProps2 = new double[Variables.Length][];
for (int k = 0; k < Variables.Length; k++)
{
variableBinProps2[k] = new double[numberOfBins];
}
binPropDic2.Add(s, variableBinProps2);
}
//Console.WriteLine("Upper bound of VariableBinProps" + variableBinProps.GetUpperBound(0));
double[] binProp2 = variableBinProps2[i];
double[] binProp = variableBinProps[i];
double[][] minMax = minMaxDic1[s];
double min = minMax[0][i];
double max = minMax[1][i];
//Console.WriteLine(min);
//Console.WriteLine(max);
double binD = (max - min);
//Console.WriteLine(binD);
double pCdfp = 0;
double pCdfp2 = 0;
//int cnt = 0;
double[][] minMax2 = minMaxDic2[s];
double min2 = minMax2[0][i];
double max2 = minMax2[1][i];
if (min2 < min)
{
min = min2;
}
if (max2 > max)
{
max = max2;
}
binD = (max - min);
double dvid = System.Convert.ToDouble(numberOfBins);
for (int j = 1; j <= numberOfBins; j++)//double d = 0.1; d <= 1; d+=0.1)
{
double dX = min + binD * (j / dvid);
double pCdf = test.EmpiricalDistribution1.DistributionFunction(dX);
double pCdf2 = test.EmpiricalDistribution2.DistributionFunction(dX);
//Console.WriteLine("Count = " + j.ToString());
//Console.WriteLine("Strata = " + s);
binProp[j - 1] = pCdf - pCdfp;
binProp2[j - 1] = pCdf2 - pCdfp2;
pCdfp = pCdf;
pCdfp2 = pCdf2;
//cnt+=1;
}
}
public double Calculate(Distribution first, Distribution second)
{
var t = new TwoSampleKolmogorovSmirnovTest(first.Values, second.Values);
return(t.Statistic);
}
public void TwoSampleKolmogorovSmirnovTestConstructorTest2()
{
// The following example comes from the stats page of the College
// of Saint Benedict and Saint John's University (Kirkman, 1996).
// http://www.physics.csbsju.edu/stats/
double[] redwell =
{
23.4, 30.9, 18.8, 23.0, 21.4, 1, 24.6, 23.8, 24.1, 18.7, 16.3, 20.3,
14.9, 35.4, 21.6, 21.2, 21.0, 15.0, 15.6, 24.0, 34.6, 40.9, 30.7,
24.5, 16.6, 1, 21.7, 1, 23.6, 1, 25.7, 19.3, 46.9, 23.3, 21.8, 33.3,
24.9, 24.4, 1, 19.8, 17.2, 21.5, 25.5, 23.3, 18.6, 22.0, 29.8, 33.3,
1, 21.3, 18.6, 26.8, 19.4, 21.1, 21.2, 20.5, 19.8, 26.3, 39.3, 21.4,
22.6, 1, 35.3, 7.0, 19.3, 21.3, 10.1, 20.2, 1, 36.2, 16.7, 21.1, 39.1,
19.9, 32.1, 23.1, 21.8, 30.4, 19.62, 15.5
};
double[] whitney =
{
16.5, 1, 22.6, 25.3, 23.7, 1, 23.3, 23.9, 16.2, 23.0, 21.6, 10.8, 12.2,
23.6, 10.1, 24.4, 16.4, 11.7, 17.7, 34.3, 24.3, 18.7, 27.5, 25.8, 22.5,
14.2, 21.7, 1, 31.2, 13.8, 29.7, 23.1, 26.1, 25.1, 23.4, 21.7, 24.4, 13.2,
22.1, 26.7, 22.7, 1, 18.2, 28.7, 29.1, 27.4, 22.3, 13.2, 22.5, 25.0, 1,
6.6, 23.7, 23.5, 17.3, 24.6, 27.8, 29.7, 25.3, 19.9, 18.2, 26.2, 20.4,
23.3, 26.7, 26.0, 1, 25.1, 33.1, 35.0, 25.3, 23.6, 23.2, 20.2, 24.7, 22.6,
39.1, 26.5, 22.7
};
// Create a non-parametric Kolmogorov-Smirnov's test
var twoTail = new TwoSampleKolmogorovSmirnovTest(redwell, whitney,
alternate: TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
var oneTailGreater = new TwoSampleKolmogorovSmirnovTest(redwell, whitney,
alternate: TwoSampleKolmogorovSmirnovTestHypothesis.FirstSampleIsLargerThanSecond);
var oneTailLesser = new TwoSampleKolmogorovSmirnovTest(redwell, whitney,
alternate: TwoSampleKolmogorovSmirnovTestHypothesis.FirstSampleIsSmallerThanSecond);
Assert.AreEqual(0.2204113924050633, twoTail.Statistic, 1e-10);
Assert.AreEqual(0.2204113924050633, oneTailGreater.Statistic, 1e-10);
Assert.AreEqual(0.1242088607594936, oneTailLesser.Statistic, 1e-10);
Assert.AreEqual(0.03463090913864153, twoTail.PValue, 1e-10);
Assert.AreEqual(0.0177488245823226, oneTailGreater.PValue, 1e-10);
Assert.AreEqual(0.270697775095498, oneTailLesser.PValue, 1e-10);
}
public void TwoSampleKolmogorovSmirnovTestConstructorTest3()
{
double[] x = { 1, 2, 3, 4, 5 };
double[] y = { 2.5, 4.5 };
var target = new TwoSampleKolmogorovSmirnovTest(x, y);
Assert.AreEqual(0.4, target.Statistic);
double actual = target.PValue;
Assert.AreEqual(0.952, actual, 1e-3);
}
private void getCdfProp(string s, int i, TwoSampleKolmogorovSmirnovTest test)
{
//Console.WriteLine("Key to look up = " + s);
double[][] variableBinProps;
double[][] variableBinProps2;
if(binPropDic1.TryGetValue(s,out variableBinProps))
{
}
else
{
variableBinProps = new double[Variables.Length][];
for (int k = 0; k < Variables.Length; k++)
{
variableBinProps[k] = new double[numberOfBins];
}
binPropDic1.Add(s,variableBinProps);
}
if (binPropDic2.TryGetValue(s, out variableBinProps2))
{
}
else
{
variableBinProps2 = new double[Variables.Length][];
for (int k = 0; k < Variables.Length; k++)
{
variableBinProps2[k] = new double[numberOfBins];
}
binPropDic2.Add(s, variableBinProps2);
}
//Console.WriteLine("Upper bound of VariableBinProps" + variableBinProps.GetUpperBound(0));
double[] binProp2 = variableBinProps2[i];
double[] binProp = variableBinProps[i];
double[][] minMax = minMaxDic1[s];
double min = minMax[0][i];
double max = minMax[1][i];
//Console.WriteLine(min);
//Console.WriteLine(max);
double binD = (max - min);
//Console.WriteLine(binD);
double pCdfp = 0;
double pCdfp2 = 0;
//int cnt = 0;
double[][] minMax2 = minMaxDic2[s];
double min2 = minMax2[0][i];
double max2 = minMax2[1][i];
if (min2 < min) min = min2;
if (max2 > max) max = max2;
binD = (max - min);
double dvid = System.Convert.ToDouble(numberOfBins);
for (int j=1;j<=numberOfBins;j++)//double d = 0.1; d <= 1; d+=0.1)
{
double dX = min + binD * (j/dvid);
double pCdf = test.EmpiricalDistribution1.DistributionFunction(dX);
double pCdf2 = test.EmpiricalDistribution2.DistributionFunction(dX);
//Console.WriteLine("Count = " + j.ToString());
//Console.WriteLine("Strata = " + s);
binProp[j-1] = pCdf-pCdfp;
binProp2[j - 1] = pCdf2 - pCdfp2;
pCdfp = pCdf;
pCdfp2 = pCdf2;
//cnt+=1;
}
}
private void buildModel()
{
if (!checkTables())
{
//Console.WriteLine("CheckTables = false");
return;
}
if (!getSampleRatios())
{
//Console.WriteLine("Sample Ratios = false");
return;
}
pca = new dataPrepPrincipleComponents(Sample1, Variables);
cluster = new dataPrepClusterKmean(Sample1, Variables, numberOfBins);
foreach(string s in cntDic.Keys)
{
buildSamples(s);
double[] pValueArr = new double[Variables.Length];
double[] sValueArr = new double[Variables.Length];
//double[] s1Arr = sample1[0];
//double[] s2Arr = sample2[0];
//TwoSampleKolmogorovSmirnovTest test = new TwoSampleKolmogorovSmirnovTest(s1Arr, s2Arr, TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
//getCdfProp(s, 0, test);
//pValue = test.PValue;
//sValue = test.Statistic;
for (int i = 0; i < Variables.Length; i++)
{
double[] s1Arr = sample1[i];
double[] s2Arr = sample2[i];
TwoSampleKolmogorovSmirnovTest test = new TwoSampleKolmogorovSmirnovTest(s1Arr, s2Arr, TwoSampleKolmogorovSmirnovTestHypothesis.SamplesDistributionsAreUnequal);
//Console.WriteLine(test.Significant.ToString());
getCdfProp(s, i, test);
double pValueS = test.PValue;
double sValueS = test.Statistic;
pValueArr[i] = pValueS;
sValueArr[i] = sValueS;
}
pDic.Add(s, pValueArr);
sDic.Add(s, sValueArr);
}
}
