io.improbable.keanu.vertices.generic.probabilistic.discrete

Class SelectVertex<T>

java.lang.Object

io.improbable.keanu.vertices.Vertex<T>

io.improbable.keanu.vertices.generic.probabilistic.Probabilistic<T>

io.improbable.keanu.vertices.generic.probabilistic.discrete.SelectVertex<T>

public class SelectVertex<T>
extends Probabilistic<T>

Field Summary

Fields inherited from class io.improbable.keanu.vertices.Vertex

ID_GENERATOR

Constructor Summary

Constructors

Constructor and Description
SelectVertex(java.util.Map<T,DoubleVertex> selectableValues)

Method Summary

Modifier and Type	Method and Description
java.util.Map<java.lang.Long,DoubleTensor>	dLogProb(T value) The partial derivatives of the natural log prob.
java.util.Map<T,DoubleVertex>	getSelectableValues()
double	logProb(T value) This is the natural log of the probability at the supplied value.
static <T> SelectVertex<T>	of(java.util.Map<T,java.lang.Double> selectableValues)
T	sample(KeanuRandom random)

Methods inherited from class io.improbable.keanu.vertices.generic.probabilistic.Probabilistic

isProbabilistic, updateValue

Methods inherited from class io.improbable.keanu.vertices.Vertex

addChild, addParent, addParents, dLogProbAtValue, equals, eval, getChildren, getConnectedGraph, getId, getParents, getRawValue, getShape, getValue, hashCode, hasValue, isObserved, lazyEval, logProbAtValue, observe, observeOwnValue, sample, setAndCascade, setParents, setParents, setValue, unobserve

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SelectVertex

public SelectVertex(java.util.Map<T,DoubleVertex> selectableValues)

Method Detail

of

public static <T> SelectVertex<T> of(java.util.Map<T,java.lang.Double> selectableValues)

getSelectableValues

public java.util.Map<T,DoubleVertex> getSelectableValues()

sample

public T sample(KeanuRandom random)

Specified by:

sample in class Vertex<T>

Parameters:

random - source of randomness

Returns:

a sample from the vertex's distribution. For non-probabilistic vertices, this will always be the same value.

logProb

public double logProb(T value)

Description copied from class: Vertex

This is the natural log of the probability at the supplied value. In the case of continuous vertices, this is actually the log of the density, which will differ from the probability by a constant.

Specified by:

logProb in class Vertex<T>

Parameters:

value - The supplied value.

Returns:

The natural log of the probability density at the supplied value

dLogProb

public java.util.Map<java.lang.Long,DoubleTensor> dLogProb(T value)

Description copied from class: Vertex

The partial derivatives of the natural log prob.

Specified by:

dLogProb in class Vertex<T>

Parameters:

value - at a given value

Returns:

the partial derivatives of the log density