mml

Class Adaptive

java.lang.Object

la.la.Value

la.la.Function

la.la.Function.Native

mml.UPModel

mml.Discretes

mml.Discretes.Bounded

mml.Adaptive

All Implemented Interfaces:

java.lang.Comparable<Value>

public class Adaptive
extends Discretes.Bounded

The UnParameterised Adapative Model of Bounded Discrete data; also see M. The model (idea) is that a data-set is homogeneous, and the data are independent, but M does not care what the probabilities of the various Values actually are. It offers no opinion about the probabilities so M has no statistical parameters. Note, it is debatable whether 'Adaptive' should be a Model of Bounded Discretes, as here, or rather a Model of Vector of Bounded Discretes. These are not necessarily exclusive, and we do want the present form as a comparison to Discretes.Bounded. Note, for a data-set 'ds', nlLH(stats(ds)) and ∑_i nlPr(ds_i) may give very different results. Adapative should not be used in structured Models, such as Mixture, that require nlPr(d).

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	Adaptive.M Model Mdl should be enough for most purposes but here is its class, fully (trivially) parameterised (M).

Nested classes/interfaces inherited from class mml.Discretes

Discretes.Bounded, Discretes.Shifted, Discretes.Uniform

Nested classes/interfaces inherited from class mml.UPModel

UPModel.Est, UPModel.Transform

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
Adaptive.M	Mdl Adaptive fully (trivially) parameterised.

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
Adaptive(Value dp) Definition parameters dp = (bounds, α) where bounds = (lwb, upb) on 'this' Model's data-space, and αk > 0 is the "offset" to be added to the frequency of value vk by nlLH(ss).

Method Summary

Modifier and Type	Method and Description
Vector	alpha() The "offsets" to be the initial values of the frequency counters of data Values by nlLH(ss).
Value.Tuple	bounds() The bounds, [lwb(), upb()], on 'this' Model's dataspace.
Estimator	estimator(Value t) Return the trivial Estimator, Mdl.asEstimator(t), of Mdl.
static void	main(java.lang.String[] argv) See Test.
Adaptive.M	sp2Model(double msg1, double msg2, Value sp) Return a Model with 2-part message lengths, msg1=0 and msg2, and statistical parameter sp=(), triv.
Vector	stats(boolean add, Value ss0, Value ss1) For sufficient statisticses 'ss0' and 'ss1', either combine ss0 and ss1 (add=true), or remove ss1 from ss0 (add=false).
Vector	stats(Vector ds, int lo, int hi) Return sufficient statistics, that is frequency counts, for elements [lo, hi) of data-set 'ds'.

Methods inherited from class mml.Discretes.Bounded

freqs, freqs, freqs, lwb_n, lwb, upb_n, upb

Methods inherited from class mml.Discretes

apply, NandSum, NandSum, shifted, shifted

Methods inherited from class mml.UPModel

defnParams, 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

Mdl

public final Adaptive.M Mdl

Adaptive fully (trivially) parameterised.

Constructor Detail

Adaptive

public Adaptive(Value dp)

Definition parameters dp = (bounds, α) where bounds = (lwb, upb) on 'this' Model's data-space, and α_k > 0 is the "offset" to be added to the frequency of value v_k by nlLH(ss). Setting all α_k = 1 gives the uniform "prior" distribution over probabilities (frequencies), while α_k > 1 raises probabilities in the interior of the Simplex, and α_k < 1 has the opposite effect. Note, α cannot be sensibly estimated from a data-set because the next data-set may be very different.

Method Detail

bounds

public Value.Tuple bounds()

Description copied from class: Discretes.Bounded

The bounds, [lwb(), upb()], on 'this' Model's dataspace.

Specified by:

bounds in class Discretes.Bounded

alpha

public Vector alpha()

The "offsets" to be the initial values of the frequency counters of data Values by nlLH(ss).

stats

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

Return sufficient statistics, that is frequency counts, for elements [lo, hi) of data-set 'ds'. More on stats here.

Specified by:

stats in class UPModel

stats

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

For sufficient statisticses 'ss0' and 'ss1', either combine ss0 and ss1 (add=true), or remove ss1 from ss0 (add=false). Note, it is only valid to remove from ss0 the contribution of elements previously counted in ss0. Also see stats(ds,lo,hi).

Specified by:

stats in class UPModel

sp2Model

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

Return a Model with 2-part message lengths, msg1=0 and msg2, and statistical parameter sp=(), triv.

Specified by:

sp2Model in class Discretes

estimator

public Estimator estimator(Value t)

Return the trivial Estimator, Mdl.asEstimator(t), of Mdl.

Overrides:

estimator in class UPModel

main

public static void main(java.lang.String[] argv)

See Test.