public void GenerateTest()
{
UniformContinuousDistribution target = new UniformContinuousDistribution(2, 5);
double[] samples = target.Generate(1000000);
var actual = UniformContinuousDistribution.Estimate(samples);
actual.Fit(samples);
Assert.AreEqual(2, actual.Minimum, 1e-4);
Assert.AreEqual(5, actual.Maximum, 1e-4);
}
public void RNGVentura_LillieforsTest_Has_Significant_Deviation_From_Normal_Distribution()
{
double[] sample = GenerateFloatingPointNumberArray();
var distribution = UniformContinuousDistribution.Estimate(sample);
var ndistribution = NormalDistribution.Estimate(sample);
var lillie = new LillieforsTest(sample, distribution);
var nlillie = new LillieforsTest(sample, ndistribution);
// no significant deviation from a uniform continuous distribution estimate
lillie.Significant.Should().BeFalse();
// significant deviation from a normal distribution
nlillie.Significant.Should().BeTrue();
}
public void KolmogorovSmirnovTestConstructorTest_with_reestimation()
{
#region doc_uniform
// Test against a Uniform distribution fitted from the data
// Make this example reproducible
Accord.Math.Random.Generator.Seed = 1;
// Suppose we got a new sample, and we would like to test whether this
// sample seems to have originated from a uniform continuous distribution.
//
double[] sample =
{
0.021, 0.003, 0.203, 0.177, 0.910, 0.881, 0.929, 0.180, 0.854, 0.982
};
// First, we create the distribution we would like to test against:
//
var distribution = UniformContinuousDistribution.Estimate(sample);
// Now we can define our hypothesis. The null hypothesis is that the sample
// comes from a standard uniform distribution, while the alternate is that
// the sample is not from a standard uniform distribution.
//
var lillie = new LillieforsTest(sample, distribution, iterations: 10 * 1000 * 1000);
double statistic = lillie.Statistic; // 0.36925
double pvalue = lillie.PValue; // 0.09057
bool significant = lillie.Significant; // false
// Since the null hypothesis could not be rejected, then the sample
// can perhaps be from a uniform distribution. However, please note
// that this doesn't means that the sample *is* from the uniform, it
// only means that we could not rule out the possibility.
#endregion
Assert.AreEqual(distribution, lillie.TheoreticalDistribution);
Assert.AreEqual(KolmogorovSmirnovTestHypothesis.SampleIsDifferent, lillie.Hypothesis);
Assert.AreEqual(DistributionTail.TwoTail, lillie.Tail);
Assert.AreEqual(0.36925434116445355, statistic, 1e-16);
Assert.AreEqual(0.090571500000000027, pvalue, 5e-3);
Assert.IsFalse(lillie.Significant);
}
public void GenerateTest2()
{
UniformContinuousDistribution target = new UniformContinuousDistribution(-1, 4);
double[] samples = new double[1000000];
for (int i = 0; i < samples.Length; i++)
{
samples[i] = target.Generate();
}
var actual = UniformContinuousDistribution.Estimate(samples);
actual.Fit(samples);
Assert.AreEqual(-1, actual.Minimum, 1e-4);
Assert.AreEqual(4, actual.Maximum, 1e-4);
}
public void tf_random_uniform()
{
using (var K = new TensorFlowBackend())
{
#region doc_random_uniform
var kvar = K.random_uniform(new int[] { 100, 2000 }, minval: -4, maxval: 2, dtype: DataType.Double, seed: 1337, name: "uni");
var a = K.dtype(kvar); // float64 (Double)
var b = kvar.eval();
#endregion
double[,] actual = (double[, ])b;
Assert.AreEqual(100, actual.Rows());
Assert.AreEqual(2000, actual.Columns());
var u = UniformContinuousDistribution.Estimate(actual.Reshape());
Assert.AreEqual(-4, u.Minimum, 1e-3);
Assert.AreEqual(+2, u.Maximum, 1e-3);
Assert.AreEqual(-1, u.Mean, 1e-2);
}
}
