Package org.biojava.bio.dist

Interface DistributionTrainerContext

All Known Subinterfaces:

ModelTrainer

All Known Implementing Classes:

SimpleDistributionTrainerContext, SimpleModelTrainer

public interface DistributionTrainerContext

A context within a group of DistributionTrainers can be trained together.

Since:

1.0

Author:

Matthew Pocock

Method Summary

Modifier and Type	Method	Description
void	addCount(Distribution dist, Symbol sym, double times)	Registers that sym was counted in this state.
void	clearCounts()	Clears all of the counts to zero.
double	getCount(Distribution dist, Symbol sym)	Return the number of counts of a particular symbol which will be used to train the specified distribution.
double	getNullModelWeight()	Return the number of pseudocounts added to the distribution when training.
DistributionTrainer	getTrainer(Distribution dist)	Return the Distribution trainer object from the current context.
void	registerDistribution(Distribution dist)	Register a distribution object with this context.
void	registerTrainer(Distribution dist, DistributionTrainer trainer)	Register a Distribution and an associated DistributionTrainer object.
void	setNullModelWeight(double weight)	Set the number of pseudocounts to add when training the distribution.
void	train()	Trains the Distribution, given a null model.

Method Detail

getNullModelWeight

double getNullModelWeight()

Return the number of pseudocounts added to the distribution when training.

Returns:

the null model weight

setNullModelWeight

void setNullModelWeight(double weight)

Set the number of pseudocounts to add when training the distribution. These counts are added in proportion to the null model of the distribution being trained.

Parameters:

weight - the new null model weight

registerDistribution

void registerDistribution(Distribution dist)

Register a distribution object with this context.

This method is a request to the context to register dist. If dist is already registered then this method should do nothing. If it is not registered, then it should invoke dist.registerWithTrainer

Parameters:

dist - the Distribution to register

registerTrainer

void registerTrainer(Distribution dist,
                     DistributionTrainer trainer)

Register a Distribution and an associated DistributionTrainer object.

In the registerWithTrainer method of a Distribution, it should associate itself with a trainer using this method.

Parameters:

dist - the distribution to be registered.

trainer - the distribution's trainer object to be registered.

getTrainer

DistributionTrainer getTrainer(Distribution dist)

Return the Distribution trainer object from the current context.

Parameters:

dist - the Distribution whose trainer is required

Returns:

the DistributionTrainer for the distribution

addCount

void addCount(Distribution dist,
              Symbol sym,
              double times)
       throws IllegalSymbolException

Registers that sym was counted in this state.

This method may be called multiple times with the same symbol. In this case, the times should be summed.

Parameters:

dist - the Distribution that the symbol was associated with

sym - the Symbol seen

times - the number of times to add

Throws:

IllegalSymbolException - if sym is not recognised by dist

getCount

double getCount(Distribution dist,
                Symbol sym)
         throws IllegalSymbolException

Return the number of counts of a particular symbol which will be used to train the specified distribution.

Parameters:

dist - the Distribution to return counts for

sym - the symbol to get the count for

Returns:

the number of counts

Throws:

IllegalSymbolException - if the symbol is not accepted by the distribution

train

void train()
    throws ChangeVetoException

Trains the Distribution, given a null model.

This will use the information collected with multiple addCount calls, and the null model to generate the new weights.

Throws:

ChangeVetoException - if any of the distributions can't be trained

clearCounts

void clearCounts()

Clears all of the counts to zero.