mml

Class R_D.ForestSearch

java.lang.Object

la.la.Value

la.la.Function

la.la.Function.Native

mml.UPModel

mml.ByPdf

mml.R_D

mml.R_D.ForestSearch

All Implemented Interfaces:

java.lang.Comparable<Value>

Enclosing class:

R_D

public static class R_D.ForestSearch
extends R_D

A generalisation of R_D.Forest that is able to estimate the model's structure – the child-parent relations – as well as the parameters of the component distributions. Note that the "estimating" statistics and the "likelihood" statistics differ considerably. The fully parameterised model is R_D.ForestSearch.M.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	R_D.ForestSearch.M The fully parameterised R_D.ForestSearch-model.

Nested classes/interfaces inherited from class mml.R_D

R_D.Forest, R_D.ForestSearch, R_D.Independent, R_D.NrmDir, R_D.Transform

Nested classes/interfaces inherited from class mml.UPModel

UPModel.Est

Nested classes/interfaces inherited from class la.la.Function.Native

Function.Native.WithInverse

Nested classes/interfaces inherited from class la.la.Function

Function.Cts2Cts, Function.Cts2Cts2Cts, Function.CtsD2CtsD, Function.HasInverse, Function.Native, Function.Native2, Function.Native3

Nested classes/interfaces inherited from class la.la.Value

Value.Atomic, Value.Bool, Value.Char, Value.Chars, Value.Cts, Value.Defer, Value.Discrete, Value.Enum, Value.Inc_Or, Value.Int, Value.Lambda, Value.List, Value.Maybe, Value.Option, Value.Real, Value.Scannable, Value.Structured, Value.Triv, Value.Tuple

Field Summary

Fields

Modifier and Type	Field and Description
int	D A datum is a Vector of 'D' Continuous Values.

Fields inherited from class mml.UPModel

dp

Fields inherited from class la.la.Value

C, comparator, CR, E, eight, ffalse, five, fiveR, four, fourR, half, negCR, negOne, negOneR, negTenR, nilVal, nine, None, one, oneR, PI, PIby2, point01, point1, point5, point9, quarter, seven, six, ten, tenR, three, threeR, triv, ttrue, two, twoR, zero, zeroR

Constructor Summary

Constructors

Constructor and Description
ForestSearch(Value dp) 'dp' is the dimension, "width", D.

Method Summary

Modifier and Type	Method and Description
int	D() Return D.
UPModel.Est	estimator(Value ps) Parameter 'ps' is bounds on μ, σ, and b.
R_D.ForestSearch.M	sp2Model(double msg1, double msg2, Value sp) Return a fully parameterised model.
Value	stats(boolean add, Value ss0, Value ss1) Combine statistics ss0 and ss1, either positively (add=true) or negatively (add=false).
Value	stats(Vector ds, int lo, int hi) Sufficient statistics 'ss' are ⟨D× stats for Normals, D×(D-1) stats for Linear1s⟩.

Methods inherited from class mml.R_D

ds2L1stats, ds2NorL1stats, ds2Nstats, transform

Methods inherited from class mml.UPModel

apply, defnParams, main, stats, stats, toString, transform

Methods inherited from class la.la.Function

bOp, fromBop, fromUop, type, uOp

Methods inherited from class la.la.Value

AoM, bOp, compareTo, cons, cts, elt, errMsg, error, force, isTuple, just, n, nElts, nlAoM, pair, print, quad, real, RTE, triple, tuple, UOE, x

Methods inherited from class java.lang.Object

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

Field Detail

D

public final int D

A datum is a Vector of 'D' Continuous Values.

Constructor Detail

ForestSearch

public ForestSearch(Value dp)

'dp' is the dimension, "width", D.

Method Detail

D

public int D()

Return D.

Specified by:

D in class R_D

stats

public Value stats(Vector ds,
                   int lo,
                   int hi)

Sufficient statistics 'ss' are ⟨D× stats for Normals, D×(D-1) stats for Linear1s⟩. This is much more than R_D.ForestSearch.M.stats(Vector,int,int) because the structure is not yet decided. (Uses R_D.ds2Nstats(la.maths.Vector) and R_D.ds2L1stats(la.maths.Vector).)

Specified by:

stats in class UPModel

stats

public Value stats(boolean add,
                   Value ss0,
                   Value ss1)

Combine statistics ss0 and ss1, either positively (add=true) or negatively (add=false).

Specified by:

stats in class UPModel

sp2Model

public R_D.ForestSearch.M sp2Model(double msg1,
                                   double msg2,
                                   Value sp)

Return a fully parameterised model.

Specified by:

sp2Model in class R_D

estimator

public UPModel.Est estimator(Value ps)

Parameter 'ps' is bounds on μ, σ, and b. A greedy search is used to find parent-child relationships and component models. Note that parent[] must represent a Forest. Also see NormalUPM.estimator(la.la.Value) and Linear1.estimator(la.la.Value).

Overrides:

estimator in class UPModel