Class SmallMeanPoissonSampler

java.lang.Object

org.apache.commons.rng.sampling.distribution.SmallMeanPoissonSampler

All Implemented Interfaces:

DiscreteSampler, SharedStateDiscreteSampler, SharedStateSampler<SharedStateDiscreteSampler>

public class SmallMeanPoissonSampler
extends Object
implements SharedStateDiscreteSampler

Sampler for the Poisson distribution.

• For small means, a Poisson process is simulated using uniform deviates, as described in

  Knuth (1969). Seminumerical Algorithms. The Art of Computer Programming, Volume 2. Chapter 3.4.1.F.3 Important integer-valued distributions: The Poisson distribution. Addison Wesley.

  The Poisson process (and hence, the returned value) is bounded by 1000 * mean.

This sampler is suitable for mean < 40. For large means, LargeMeanPoissonSampler should be used instead.

Sampling uses UniformRandomProvider.nextDouble() and requires on average mean + 1 deviates per sample.

Since:

1.1

Field Summary

Fields

Modifier and Type	Field	Description
private final int	limit	Pre-compute 1000 * mean as the upper limit of the sample.
private final double	p0	Pre-compute Math.exp(-mean).
private final UniformRandomProvider	rng	Underlying source of randomness.

Constructor Summary

Constructors

Modifier	Constructor	Description
	SmallMeanPoissonSampler(UniformRandomProvider rng, double mean)	Create an instance.
private	SmallMeanPoissonSampler(UniformRandomProvider rng, double mean, double p0)	Instantiates a new small mean poisson sampler.
private	SmallMeanPoissonSampler(UniformRandomProvider rng, SmallMeanPoissonSampler source)

Method Summary

Modifier and Type	Method	Description
private static double	computeP0(double mean)	Compute Math.exp(-mean).
static SharedStateDiscreteSampler	of(UniformRandomProvider rng, double mean)	Creates a new sampler for the Poisson distribution.
int	sample()	Creates an int sample.
String	toString()
SharedStateDiscreteSampler	withUniformRandomProvider(UniformRandomProvider rng)	Create a new instance of the sampler with the same underlying state using the given uniform random provider as the source of randomness.

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface DiscreteSampler

samples, samples

Field Details

p0

private final double p0

Pre-compute Math.exp(-mean). Note: This is the probability of the Poisson sample P(n=0).

limit

private final int limit

Pre-compute 1000 * mean as the upper limit of the sample.

rng

private final UniformRandomProvider rng

Underlying source of randomness.

Constructor Details

SmallMeanPoissonSampler

public SmallMeanPoissonSampler(UniformRandomProvider rng,
 double mean)

Create an instance.

Parameters:

rng - Generator of uniformly distributed random numbers.

mean - Mean.

Throws:

IllegalArgumentException - if mean <= 0 or Math.exp(-mean) == 0

SmallMeanPoissonSampler

private SmallMeanPoissonSampler(UniformRandomProvider rng,
 double mean,
 double p0)

Instantiates a new small mean poisson sampler.

Parameters:

rng - Generator of uniformly distributed random numbers.

mean - Mean.

p0 - Math.exp(-mean).

SmallMeanPoissonSampler

private SmallMeanPoissonSampler(UniformRandomProvider rng,
 SmallMeanPoissonSampler source)

Parameters:

rng - Generator of uniformly distributed random numbers.

source - Source to copy.

Method Details

sample

public int sample()

Creates an int sample.

Specified by:

sample in interface DiscreteSampler

Returns:

a sample.

toString

public String toString()

Overrides:

toString in class Object

withUniformRandomProvider

public SharedStateDiscreteSampler withUniformRandomProvider(UniformRandomProvider rng)

Create a new instance of the sampler with the same underlying state using the given uniform random provider as the source of randomness.

Specified by:

withUniformRandomProvider in interface SharedStateSampler<SharedStateDiscreteSampler>

Parameters:

rng - Generator of uniformly distributed random numbers.

Returns:

the sampler

Since:

1.3

of

public static SharedStateDiscreteSampler of(UniformRandomProvider rng,
 double mean)

Creates a new sampler for the Poisson distribution.

Parameters:

rng - Generator of uniformly distributed random numbers.

mean - Mean of the distribution.

Returns:

the sampler

Throws:

IllegalArgumentException - if mean <= 0 or Math.exp(-mean) == 0.

Since:

1.3

computeP0

private static double computeP0(double mean)

Compute Math.exp(-mean).

This method exists to raise an exception before invocation of the private constructor; this mitigates Finalizer attacks (see SpotBugs CT_CONSTRUCTOR_THROW).

Parameters:

mean - Mean.

Returns:

the mean

Throws:

IllegalArgumentException - if mean <= 0 or Math.exp(-mean) == 0