FiniteBayesModel

java.lang.Object
- aima.core.probability.bayes.model.FiniteBayesModel

All Implemented Interfaces:

FiniteProbabilityModel, ProbabilityModel
```
public class FiniteBayesModel
extends java.lang.Object
implements FiniteProbabilityModel
```
Very simple implementation of the FiniteProbabilityModel API using a Bayesian Network, consisting of FiniteNodes, to represent the underlying model.

Note: The implementation currently doesn't take advantage of the use of evidence values when calculating posterior values using the provided Bayesian Inference implementation (e.g enumerationAsk). Instead it simply creates a joint distribution over the scope of the propositions (i.e. using the inference implementation with just query variables corresponding to the scope of the propositions) and then iterates over this to get the appropriate probability values. A smarter version, in the general case, would need to dynamically create deterministic nodes to represent the outcome of logical and derived propositions (e.g. conjuncts and summations over variables) in order to be able to correctly calculate using evidence values.

Author:

Ciaran O'Reilly

Field Summary
- Fields inherited from interface aima.core.probability.ProbabilityModel
  DEFAULT_ROUNDING_THRESHOLD

Constructor Summary

Constructors
Constructor and Description

FiniteBayesModel(BayesianNetwork bn)

FiniteBayesModel(BayesianNetwork bn, BayesInference bi)

Constructors
Constructor and Description
`FiniteBayesModel(BayesianNetwork bn)`
`FiniteBayesModel(BayesianNetwork bn, BayesInference bi)`

Method Summary

All Methods Instance Methods Concrete Methods
Modifier and Type	Method and Description
`BayesInference`	`getBayesInference()`
`java.util.Set<RandomVariable>`	`getRepresentation()`
`boolean`	`isValid()`
`CategoricalDistribution`	`jointDistribution(Proposition... propositions)` Get a distribution on multiple variables.
`double`	`posterior(Proposition phi, Proposition... evidence)` Unlike unconditional or prior probabilities, most of the time we have some information, usually called evidence, that has already been revealed.
`CategoricalDistribution`	`posteriorDistribution(Proposition phi, Proposition... evidence)` Get a conditional distribution.
`double`	`prior(Proposition... phi)` For any proposition φ, P(φ) = ∑_{ω ∈ φ} P(ω).
`CategoricalDistribution`	`priorDistribution(Proposition... phi)` P(X,...)
`void`	`setBayesInference(BayesInference bi)`

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Constructor Detail
  - FiniteBayesModel
```
public FiniteBayesModel(BayesianNetwork bn)
```
  - FiniteBayesModel
```
public FiniteBayesModel(BayesianNetwork bn,
                        BayesInference bi)
```
- Method Detail
  - getBayesInference
```
public BayesInference getBayesInference()
```
  - setBayesInference
```
public void setBayesInference(BayesInference bi)
```
  - isValid
```
public boolean isValid()
```
    Specified by:
    
    isValid in interface ProbabilityModel
    
    Returns:
    
    true, if 0 <= P(ω) <= 1 for every ω and ∑_{ω ∈ Ω} P(ω) = 1 (Equation 13.1 pg. 484 AIMA3e), false otherwise.
  - prior
```
public double prior(Proposition... phi)
```
    Description copied from interface: ProbabilityModel
    
    For any proposition φ, P(φ) = ∑_{ω ∈
    φ} P(ω). Refer to equation 13.2 page 485 of AIMA3e. Probabilities such as P(Total = 11) and P(doubles) are called unconditional or prior probabilities (and sometimes just "priors" for short); they refer to degrees of belief in propositions in the absence of any other information.
    
    Specified by:
    
    prior in interface ProbabilityModel
    
    Parameters:
    
    phi - the propositional terms for which a probability value is to be returned.
    
    Returns:
    
    the probability of the proposition φ.
  - posterior
```
public double posterior(Proposition phi,
                        Proposition... evidence)
```
    Description copied from interface: ProbabilityModel
    
    Unlike unconditional or prior probabilities, most of the time we have some information, usually called evidence, that has already been revealed. This is the conditional or posterior probability (or just "posterior" for short). Mathematically speaking, conditional probabilities are defined in terms of unconditional probabilities as follows, for any propositions a and b, we have:
    
    P(a | b) = P(a AND b)/P(b)
    
    which holds whenever P(b) > 0. Refer to equation 13.3 page 485 of AIMA3e. This can be rewritten in a different form called the product rule:
    
    P(a AND b) = P(a | b)P(b)
    
    and also as:
    
    P(a AND b) = P(b | a)P(a)
    
    whereby, equating the two right-hand sides and dividing by P(a) gives you Bayes' rule:
    
    P(b | a) = (P(a | b)P(b))/P(a) - i.e. (likelihood * prior)/evidence
    
    Specified by:
    
    posterior in interface ProbabilityModel
    
    Parameters:
    
    phi - the proposition for which a probability value is to be returned.
    
    evidence - information we already have.
    
    Returns:
    
    the probability of the proposition φ given evidence.
  - getRepresentation
```
public java.util.Set<RandomVariable> getRepresentation()
```
    Specified by:
    
    getRepresentation in interface ProbabilityModel
    
    Returns:
    
    a consistent ordered Set (e.g. LinkedHashSet) of the random variables describing the atomic variable/value pairs this probability model can take on. Refer to pg. 486 AIMA3e.
  - priorDistribution
```
public CategoricalDistribution priorDistribution(Proposition... phi)
```
    Description copied from interface: FiniteProbabilityModel
    
    P(X,...)
    
    Specified by:
    
    priorDistribution in interface FiniteProbabilityModel
    
    Parameters:
    
    phi - the propositions of interest.
    
    Returns:
    
    all the possible values of the propositions φ. This is a Vector of numbers, where we assume a predefined ordering of the domain of the relevant random variables.
  - posteriorDistribution
```
public CategoricalDistribution posteriorDistribution(Proposition phi,
                                                     Proposition... evidence)
```
    Description copied from interface: FiniteProbabilityModel
    
    Get a conditional distribution. Example:
    
    P(X | Y) gives the values of P(X = x_i | Y = y_j) for each possible i, j pair.
    
    Specified by:
    
    posteriorDistribution in interface FiniteProbabilityModel
    
    Parameters:
    
    phi - the proposition for which a probability distribution is to be returned.
    
    evidence - information we already have.
    
    Returns:
    
    the conditional distribution for P(φ | evidence).
  - jointDistribution
```
public CategoricalDistribution jointDistribution(Proposition... propositions)
```
    Description copied from interface: FiniteProbabilityModel
    
    Get a distribution on multiple variables. Example, the product rule:
    
    P(X, Y) gives the values of P(X = x_i | Y = y_j)P(Y = y_j) for each possible i, j pair.
    
    Specified by:
    
    jointDistribution in interface FiniteProbabilityModel
    
    Parameters:
    
    propositions - the propositions for which a joint probability distribution is to be returned.
    
    Returns:
    
    the joint distribution for P(X, Y, ...).

Class FiniteBayesModel

Field Summary

Fields inherited from interface aima.core.probability.ProbabilityModel

Constructor Summary

Method Summary

Methods inherited from class java.lang.Object

Constructor Detail

FiniteBayesModel

FiniteBayesModel

Method Detail

getBayesInference

setBayesInference

isValid

prior

posterior

getRepresentation

priorDistribution

posteriorDistribution

jointDistribution