Safe Haskell | Safe-Infered |
---|

Algorithms for variable elimination

- priorMarginal :: (Graph g, Factor f, Show f, BayesianDiscreteVariable dva, BayesianDiscreteVariable dvb) => BayesianNetwork g f -> EliminationOrder dva -> EliminationOrder dvb -> f
- posteriorMarginal :: (Graph g, Factor f, Show f, BayesianDiscreteVariable dva, BayesianDiscreteVariable dvb) => BayesianNetwork g f -> EliminationOrder dva -> EliminationOrder dvb -> [DVI] -> f
- interactionGraph :: (FoldableWithVertex g, Factor f, UndirectedGraph g') => BayesianNetwork g f -> g' () DV
- degreeOrder :: (FoldableWithVertex g, Factor f, Graph g) => BayesianNetwork g f -> EliminationOrder DV -> Int
- minDegreeOrder :: (Graph g, Factor f, FoldableWithVertex g) => BayesianNetwork g f -> EliminationOrder DV
- minFillOrder :: (Graph g, Factor f, FoldableWithVertex g) => BayesianNetwork g f -> EliminationOrder DV
- allVariables :: (Graph g, Factor f) => BayesianNetwork g f -> [DV]
- marginal :: Factor f => [f] -> EliminationOrder DV -> EliminationOrder DV -> [DVI] -> f
- mpemarginal :: [CPT] -> EliminationOrder DV -> EliminationOrder DV -> [DVI] -> MAXCPT
- mpe :: (Graph g, BayesianDiscreteVariable dva, BayesianDiscreteVariable dvb) => BayesianNetwork g CPT -> EliminationOrder dva -> EliminationOrder dvb -> [DVI] -> [DVISet]
- type EliminationOrder dv = [dv]

# Inferences

:: (Graph g, Factor f, Show f, BayesianDiscreteVariable dva, BayesianDiscreteVariable dvb) | |

=> BayesianNetwork g f | Bayesian Network |

-> EliminationOrder dva | Ordering of variables to marginalize |

-> EliminationOrder dvb | Ordering of remaining to keep in result |

-> f |

Compute the prior marginal. All the variables in the elimination order are conditionning variables ( p( . | conditionning variables) )

:: (Graph g, Factor f, Show f, BayesianDiscreteVariable dva, BayesianDiscreteVariable dvb) | |

=> BayesianNetwork g f | Bayesian Network |

-> EliminationOrder dva | Ordering of variables to marginzalie |

-> EliminationOrder dvb | Ordering of remaining variables |

-> [DVI] | Assignment for some factors in variables to marginalize |

-> f |

# Interaction graph and elimination order

interactionGraph :: (FoldableWithVertex g, Factor f, UndirectedGraph g') => BayesianNetwork g f -> g' () DVSource

Compute the interaction graph of the BayesianNetwork

degreeOrder :: (FoldableWithVertex g, Factor f, Graph g) => BayesianNetwork g f -> EliminationOrder DV -> IntSource

Compute the degree order of an elimination order

minDegreeOrder :: (Graph g, Factor f, FoldableWithVertex g) => BayesianNetwork g f -> EliminationOrder DVSource

Elimination order minimizing the degree

minFillOrder :: (Graph g, Factor f, FoldableWithVertex g) => BayesianNetwork g f -> EliminationOrder DVSource

Elimination order minimizing the filling

allVariables :: (Graph g, Factor f) => BayesianNetwork g f -> [DV]Source

Get all variables from a Bayesian Network

:: Factor f | |

=> [f] | Bayesian Network |

-> EliminationOrder DV | Ordering of variables to marginalize |

-> EliminationOrder DV | Ordering of remaining variables |

-> [DVI] | Assignment for some factors in variables to marginalize |

-> f |

Compute the prior marginal. All the variables in the elimination order are conditionning variables ( p( . | conditionning variables) )

:: [CPT] | Bayesian Network |

-> EliminationOrder DV | Ordering of variables to marginalize |

-> EliminationOrder DV | Ordering of remaining variables |

-> [DVI] | Assignment for some factors in variables to marginalize |

-> MAXCPT |

Compute the prior marginal. All the variables in the elimination order are conditionning variables ( p( . | conditionning variables) ) First we sum, then we maximize for the remaining variables

:: (Graph g, BayesianDiscreteVariable dva, BayesianDiscreteVariable dvb) | |

=> BayesianNetwork g CPT | Bayesian network defining the factors |

-> EliminationOrder dva | Ordering of variables to sum out (should contain evidence variables) |

-> EliminationOrder dvb | Ordering of remaining variables (to maximize) |

-> [DVI] | Assignment |

-> [DVISet] | MPE or MAP instantiation |

Most Probable Explanation (or Maximum A Posteriori estimator) when restricted to a subest of variables in output

type EliminationOrder dv = [dv]Source

Elimination order