aima.core.probability.util

Class ProbUtil

java.lang.Object

aima.core.probability.util.ProbUtil

public class ProbUtil
extends java.lang.Object

Constructor Summary

Constructors

Constructor and Description
ProbUtil()

Method Summary

Modifier and Type	Method and Description
static void	checkValidRandomVariableName(java.lang.String name) Check if name provided is valid for use as the name of a RandomVariable.
static Proposition	constructConjunction(Proposition[] props) Convenience method for ensure a conjunction of probabilistic propositions.
static int	expectedSizeOfCategoricalDistribution(RandomVariable... vars) Calculated the expected size of a CategoricalDistribution for the provided random variables.
static int	expectedSizeOfProbabilityTable(RandomVariable... vars) Calculated the expected size of a ProbabilityTable for the provided random variables.
static java.lang.Object[]	getEventValuesForParents(Node Xi, java.util.Map<RandomVariable,java.lang.Object> event) Get the parent values for the Random Variable Xi from the provided event.
static java.lang.Object[]	getEventValuesForXiGivenParents(Node Xi, java.util.Map<RandomVariable,java.lang.Object> event) Get the values for the Random Variable Xi's parents and its own value from the provided event.
static java.lang.Object[]	getEventValuesForXiGivenParents(Node Xi, java.lang.Object xDelta, java.util.Map<RandomVariable,java.lang.Object> event) Get the values for the Random Variable Xi's parents and its own value from the provided event.
static int[]	indexesOfValue(RandomVariable[] X, int idx, java.util.Map<RandomVariable,java.lang.Object> x) Calculate the indexes for X[i] into a vector representing the enumeration of the value assignments for the variables X and their corresponding assignment in x.
static int	indexOf(RandomVariable[] X, java.util.Map<RandomVariable,java.lang.Object> x) Calculate the index into a vector representing the enumeration of the value assignments for the variables X and their corresponding assignment in x.
static double[]	mbDistribution(Node Xi, java.util.Map<RandomVariable,java.lang.Object> event) Calculate the probability distribution for P(Xi | mb(Xi)), where mb(Xi) is the Markov Blanket of Xi.
static java.lang.Object	mbRandomSample(Node Xi, java.util.Map<RandomVariable,java.lang.Object> event, Randomizer r) Get a random sample from P(Xi | mb(Xi)), where mb(Xi) is the Markov Blanket of Xi.
static java.lang.Object	randomSample(Node Xi, java.util.Map<RandomVariable,java.lang.Object> event, Randomizer r) Get a random sample from P(Xi | parents(Xi))
static java.lang.Object	sample(double probabilityChoice, RandomVariable Xi, double[] distribution)

Methods inherited from class java.lang.Object

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

Constructor Detail

ProbUtil

public ProbUtil()

Method Detail

checkValidRandomVariableName

public static void checkValidRandomVariableName(java.lang.String name)
                                         throws java.lang.IllegalArgumentException

Check if name provided is valid for use as the name of a RandomVariable.

Parameters:

name - proposed for the RandomVariable.

Throws:

java.lang.IllegalArgumentException - if not a valid RandomVariable name.

expectedSizeOfProbabilityTable

public static int expectedSizeOfProbabilityTable(RandomVariable... vars)

Calculated the expected size of a ProbabilityTable for the provided random variables.

Parameters:

vars - null, 0 or more random variables that are to be used to construct a CategoricalDistribution.

Returns:

the size (i.e. getValues().length) that the CategoricalDistribution will need to be in order to represent the specified random variables.

See Also:

CategoricalDistribution.getValues()

expectedSizeOfCategoricalDistribution

public static int expectedSizeOfCategoricalDistribution(RandomVariable... vars)

Calculated the expected size of a CategoricalDistribution for the provided random variables.

Parameters:

vars - null, 0 or more random variables that are to be used to construct a CategoricalDistribution.

Returns:

the size (i.e. getValues().length) that the CategoricalDistribution will need to be in order to represent the specified random variables.

See Also:

CategoricalDistribution.getValues()

constructConjunction

public static Proposition constructConjunction(Proposition[] props)

Convenience method for ensure a conjunction of probabilistic propositions.

Parameters:

props - propositions to be combined into a ConjunctiveProposition if necessary.

Returns:

a ConjunctivePropositions if more than 1 proposition in 'props', otherwise props[0].

sample

public static java.lang.Object sample(double probabilityChoice,
                                      RandomVariable Xi,
                                      double[] distribution)

Parameters:

probabilityChoice - a probability choice for the sample

Xi - a Random Variable with a finite domain from which a random sample is to be chosen based on the probability choice.

distribution - Xi's distribution.

Returns:

a Random Sample from Xi's domain.

randomSample

public static java.lang.Object randomSample(Node Xi,
                                            java.util.Map<RandomVariable,java.lang.Object> event,
                                            Randomizer r)

Get a random sample from P(X_i | parents(X_i))

Parameters:

Xi - a Node from a Bayesian network for the Random Variable X_i.

event - comprising assignments for parents(X_i)

r - a Randomizer for generating a probability choice for the sample.

Returns:

a random sample from P(X_i | parents(X_i))

mbRandomSample

public static java.lang.Object mbRandomSample(Node Xi,
                                              java.util.Map<RandomVariable,java.lang.Object> event,
                                              Randomizer r)

Get a random sample from P(X_i | mb(X_i)), where mb(X_i) is the Markov Blanket of X_i. The probability of a variable given its Markov blanket is proportional to the probability of the variable given its parents times the probability of each child given its respective parents (see equation 14.12 pg. 538 AIMA3e):

P(x'_i|mb(Xi)) = αP(x'_i|parents(X_i)) * ∏_{Yj ∈ Children(Xi)} P(y_j|parents(Y_j))

Parameters:

Xi - a Node from a Bayesian network for the Random Variable X_i.

event - comprising assignments for the Markov Blanket X_i.

r - a Randomizer for generating a probability choice for the sample.

Returns:

a random sample from P(X_i | mb(X_i))

mbDistribution

public static double[] mbDistribution(Node Xi,
                                      java.util.Map<RandomVariable,java.lang.Object> event)

Calculate the probability distribution for P(X_i | mb(X_i)), where mb(X_i) is the Markov Blanket of X_i. The probability of a variable given its Markov blanket is proportional to the probability of the variable given its parents times the probability of each child given its respective parents (see equation 14.12 pg. 538 AIMA3e):

P(x'_i|mb(Xi)) = αP(x'_i|parents(X_i)) * ∏_{Yj ∈ Children(Xi)} P(y_j|parents(Y_j))

Parameters:

Xi - a Node from a Bayesian network for the Random Variable X_i.

event - comprising assignments for the Markov Blanket X_i.

Returns:

a random sample from P(X_i | mb(X_i))

getEventValuesForParents

public static java.lang.Object[] getEventValuesForParents(Node Xi,
                                                          java.util.Map<RandomVariable,java.lang.Object> event)

Get the parent values for the Random Variable Xi from the provided event.

Parameters:

Xi - a Node for the Random Variable Xi whose parent values are to be extracted from the provided event in the correct order.

event - an event containing assignments for Xi's parents.

Returns:

an ordered set of values for the parents of Xi from the provided event.

getEventValuesForXiGivenParents

public static java.lang.Object[] getEventValuesForXiGivenParents(Node Xi,
                                                                 java.util.Map<RandomVariable,java.lang.Object> event)

Get the values for the Random Variable Xi's parents and its own value from the provided event.

Parameters:

Xi - a Node for the Random Variable Xi whose parent values and value are to be extracted from the provided event in the correct order.

event - an event containing assignments for Xi's parents and its own value.

Returns:

an ordered set of values for the parents of Xi and its value from the provided event.

getEventValuesForXiGivenParents

public static java.lang.Object[] getEventValuesForXiGivenParents(Node Xi,
                                                                 java.lang.Object xDelta,
                                                                 java.util.Map<RandomVariable,java.lang.Object> event)

Get the values for the Random Variable Xi's parents and its own value from the provided event.

Parameters:

Xi - a Node for the Random Variable Xi whose parent values are to be extracted from the provided event in the correct order.

xDelta - the value for the Random Variable Xi to be assigned to the values returned.

event - an event containing assignments for Xi's parents and its own value.

Returns:

an ordered set of values for the parents of Xi and its value from the provided event.

indexOf

public static int indexOf(RandomVariable[] X,
                          java.util.Map<RandomVariable,java.lang.Object> x)

Calculate the index into a vector representing the enumeration of the value assignments for the variables X and their corresponding assignment in x. For example the Random Variables:
Q::{true, false}, R::{'A', 'B','C'}, and T::{true, false}, would be enumerated in a Vector as follows:

 Index  Q      R  T
 -----  -      -  -
 00:    true,  A, true
 01:    true,  A, false
 02:    true,  B, true
 03:    true,  B, false
 04:    true,  C, true
 05:    true,  C, false
 06:    false, A, true
 07:    false, A, false
 08:    false, B, true
 09:    false, B, false
 10:    false, C, true
 11:    false, C, false
 

if x = {Q=true, R='C', T=false} the index returned would be 5.

Parameters:

X - a list of the Random Variables that would comprise the vector.

x - an assignment for the Random Variables in X.

Returns:

an index into a vector that would represent the enumeration of the values for X.

indexesOfValue

public static int[] indexesOfValue(RandomVariable[] X,
                                   int idx,
                                   java.util.Map<RandomVariable,java.lang.Object> x)

Calculate the indexes for X[i] into a vector representing the enumeration of the value assignments for the variables X and their corresponding assignment in x. For example the Random Variables:
Q::{true, false}, R::{'A', 'B','C'}, and T::{true, false}, would be enumerated in a Vector as follows:

 Index  Q      R  T
 -----  -      -  -
 00:    true,  A, true
 01:    true,  A, false
 02:    true,  B, true
 03:    true,  B, false
 04:    true,  C, true
 05:    true,  C, false
 06:    false, A, true
 07:    false, A, false
 08:    false, B, true
 09:    false, B, false
 10:    false, C, true
 11:    false, C, false
 

if X[i] = R and x = {..., R='C', ...} then the indexes returned would be [4, 5, 10, 11].

Parameters:

X - a list of the Random Variables that would comprise the vector.

idx - the index into X for the Random Variable whose assignment we wish to retrieve its indexes for.

x - an assignment for the Random Variables in X.

Returns:

the indexes into a vector that would represent the enumeration of the values for X[i] in x.