jsat.distributions.discrete

Class DiscreteDistribution

java.lang.Object

jsat.distributions.Distribution

jsat.distributions.discrete.DiscreteDistribution

All Implemented Interfaces:

Serializable, Cloneable

Direct Known Subclasses:

Binomial, Poisson, UniformDiscrete

public abstract class DiscreteDistribution
extends Distribution

This abstract class defines the contract for a distribution over the integer values.

The cdf(double) method will behave by rounding down and then calling the integer cdf(int) counterpart.

Author:

Edward Raff

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
DiscreteDistribution()

Method Summary

Modifier and Type	Method and Description
double	cdf(double x) Computes the value of the Cumulative Density Function (CDF) at the given point.
abstract double	cdf(int x) Computes the value of the Cumulative Density Function (CDF) at the given point.
abstract DiscreteDistribution	clone()
double	invCdf(double p) Computes the inverse Cumulative Density Function (CDF-1) at the given point.
protected double	invCdf(double p, Function cdf) This method is provided as a quick helper function, as any CDF has a 1 to 1 mapping with an inverse, CDF.-1.
double	logPmf(int x) Computes the log of the Probability Mass Function.
abstract double	pmf(int x)

Methods inherited from class jsat.distributions.Distribution

getFunctionCDF, max, mean, median, min, mode, sample, sampleVec, skewness, standardDeviation, variance

Methods inherited from class java.lang.Object

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

Constructor Detail

DiscreteDistribution

public DiscreteDistribution()

Method Detail

logPmf

public double logPmf(int x)

Computes the log of the Probability Mass Function. Note, that then the probability is zero, Double.NEGATIVE_INFINITY would be the true value. Instead, this method will always return the negative of Double.MAX_VALUE. This is to avoid propagating bad values through computation.

Parameters:

x - the value to get the log(PMF) of

Returns:

the value of log(PMF(x))

pmf

public abstract double pmf(int x)

cdf

public abstract double cdf(int x)

Computes the value of the Cumulative Density Function (CDF) at the given point. The CDF returns a value in the range [0, 1], indicating what portion of values occur at or below that point.

Parameters:

x - the value to get the CDF of

Returns:

the CDF(x)

cdf

public double cdf(double x)

Description copied from class: Distribution

Computes the value of the Cumulative Density Function (CDF) at the given point. The CDF returns a value in the range [0, 1], indicating what portion of values occur at or below that point.

Specified by:

cdf in class Distribution

Parameters:

x - the value to get the CDF of

Returns:

the CDF(x)

invCdf

public double invCdf(double p)

Description copied from class: Distribution

Computes the inverse Cumulative Density Function (CDF^-1) at the given point. It takes in a value in the range of [0, 1] and returns the value x, such that CDF(x) = p

Overrides:

invCdf in class Distribution

Parameters:

p - the probability value

Returns:

the value such that the CDF would return p

invCdf

protected double invCdf(double p,
                        Function cdf)

Description copied from class: Distribution

This method is provided as a quick helper function, as any CDF has a 1 to 1 mapping with an inverse, CDF^.-1. This does a search for that value, and should only be used if the quantile function will be used infrequently or no alternative is available.

Overrides:

invCdf in class Distribution

Parameters:

p - the [0,1] probability value

cdf - a function that provides the CDF we want to emulate the inverse of

Returns:

the quantile function, CDF^-1(p) = x

clone

public abstract DiscreteDistribution clone()

Specified by:

clone in class Distribution