mml

Class Mixture.M

java.lang.Object

la.la.Value

mml.Model

mml.UPModel.M

mml.Mixture.M

All Implemented Interfaces:

java.lang.Comparable<Value>

Enclosing class:

Mixture

public class Mixture.M
extends UPModel.M

A fully parameterised (non-abstract) Mixture Model with statistical-parameters being the weights and parameters of the classes (clusters, components). Also see the UnParameterised Mixture.

Nested Class Summary

Nested classes/interfaces inherited from class mml.Model

Model.Defaults, Model.Transform

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 inherited from class mml.Model

msg1, msg2, sp

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
M(double msg1, double msg2, Value sp) Given statistical parameter sp = (wts, sps), where 'wts' is the relative abundances and 'sps' the classes' statistical parameters, construct a Mixture Model.

Method Summary

Modifier and Type	Method and Description
Mixture.M	asGiven(double msg2) Calls asGiven(0,msg2).
Mixture.M	asGiven(double msg1, double msg2) Enables setting the first- and second-part message lengths, msg1 and msg2, after having estimated the statistical parameter(s) of a Model, say.
Multivariate.M	asMultivariateM() 'this' Mixture.M is not a Multivariate.M but this.asMultivariateM() is – provided that Mixture.upm is a Multivariate.
MultiState.M	mixer() Return the MultiState that weights the class Models.
Model[]	ms() Return the sub-Models, one per class (cluster).
double	nlLH(Value ss) Assumes that statistics are the data-set itself.
double	nlPr(int i, Value d) The negative log probability of datum 'd' according to class 'i' alone.
double	nlPr(Value d) The negative log probability of datum d under 'this' Mixture is log( ∑{ mixer().pr(i) × ms()[i].pr(d) } ) = logSum{ mixer().nlPr(i) + ms()[i].nlPr(d) } .
Value	random() Produce (sample) a random Value from 'this' Mixture Model.
java.lang.String	toString() Return a short description of the Mixture Model.

Methods inherited from class mml.UPModel.M

stats, stats

Methods inherited from class mml.Model

asEstimator, asUPModel, m1m2sp, msg, msg1, msg1bits, msg2, msg2bits, msgBits, nl2LH, nl2Pr, pr, random, randomSeries, statParams, stats, stats, sumNlPr, transform, type, zeroTriv

Methods inherited from class la.la.Value

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

Methods inherited from class java.lang.Object

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

Constructor Detail

M

public M(double msg1,
         double msg2,
         Value sp)

Given statistical parameter sp = (wts, sps), where 'wts' is the relative abundances and 'sps' the classes' statistical parameters, construct a Mixture Model.

Method Detail

mixer

public MultiState.M mixer()

Return the MultiState that weights the class Models.

ms

public Model[] ms()

Return the sub-Models, one per class (cluster).

nlPr

public double nlPr(Value d)

The negative log probability of datum d under 'this' Mixture is log( ∑{ mixer().pr(i) × ms()[i].pr(d) } ) = logSum{ mixer().nlPr(i) + ms()[i].nlPr(d) } . Also see Maths.logSum(double[]).

Specified by:

nlPr in class Model

nlPr

public double nlPr(int i,
                   Value d)

The negative log probability of datum 'd' according to class 'i' alone. That is, nlPr(i) + nlPr(d|i).

nlLH

public double nlLH(Value ss)

Assumes that statistics are the data-set itself.

Specified by:

nlLH in class Model

random

public Value random()

Produce (sample) a random Value from 'this' Mixture Model. Select a random sub-Model ms()[r] and generate a random Value from it, if possible.

Overrides:

random in class Model

asGiven

public Mixture.M asGiven(double msg2)

Description copied from class: UPModel.M

Calls asGiven(0,msg2).

Overrides:

asGiven in class UPModel.M

asGiven

public Mixture.M asGiven(double msg1,
                         double msg2)

Description copied from class: UPModel.M

Enables setting the first- and second-part message lengths, msg1 and msg2, after having estimated the statistical parameter(s) of a Model, say. Also see asGiven(msg2).

Overrides:

asGiven in class UPModel.M

asMultivariateM

public Multivariate.M asMultivariateM()

'this' Mixture.M is not a Multivariate.M but this.asMultivariateM() is – provided that Mixture.upm is a Multivariate. In particular, this allows such a mixture model access to Multivariate.M.functionModel(int, la.la.Type).

toString

public java.lang.String toString()

Return a short description of the Mixture Model.

Overrides:

toString in class UPModel.M