com.mockturtlesolutions.snifflib.invprobs

Class GaussianProposal

java.lang.Object

com.mockturtlesolutions.snifflib.functions.AbstractFunction

com.mockturtlesolutions.snifflib.invprobs.StatisticalModel

com.mockturtlesolutions.snifflib.invprobs.AbstractProposalDistribution

com.mockturtlesolutions.snifflib.invprobs.GaussianProposal

All Implemented Interfaces:

Nameable, FigureReportable, Reportable, DeclaredParameters, DeclaredVariables, Likelihood, NamedParameters, ObjectSampler, ObjectSamplerClient, OptimizableScalar, ProposalDistribution

public class GaussianProposal
extends AbstractProposalDistribution

A convenience class for setting up a proposal distribution which is Gaussian for all parameters in a companion StatisticalModel.

Field Summary

Fields inherited from class com.mockturtlesolutions.snifflib.invprobs.AbstractProposalDistribution

mixingParameter, newParams, oldParams

Fields inherited from class com.mockturtlesolutions.snifflib.invprobs.StatisticalModel

adapter, FigureReporters, invertParameterDeclarations, LIKELIHOOD, NEG_LOG_LIKELIHOOD, paramListeners, Params, PosteriorParams, PREDICTION, priorParamListeners, PriorParams, SUM_NEG_LOG_LIKELIHOOD, usingDataSet

Fields inherited from class com.mockturtlesolutions.snifflib.functions.AbstractFunction

domainDimension, rangeDimension

Constructor Summary

Constructors

Constructor and Description
GaussianProposal(StatisticalModel model) The means of the Gaussians will be assumed to be the current values in

Method Summary

Methods

Modifier and Type	Method and Description
java.lang.String	about() Return a string giving some descriptive information about the model.
java.lang.String	getLeftParameter(java.lang.String name)
int	getOrderStatistic(java.lang.String name)
DblMatrix	getPredictionAt(DblMatrix[] X)
boolean	isLogNormal(java.lang.String param) Returns true if the proposal distribution for the named parameter is lognormal.
boolean	isOrderRestricted(java.lang.String param)
DblParamSet	negLogPrior() Returns the negative log of the prior probability of the current parameter set.
DblParamSet	samplePosterior(java.lang.String[] subset) Samples parameters from a Gaussian distribution centered about the current old values.
void	setLogNormal(java.lang.String param) Sets up the given parameter to be sampled from a Log-Normal distribution.
void	setLogNormal(java.lang.String param, DblMatrix mixing) Sets up the given parameter to be sampled from a Log-Normal distribution with the given standard deviation.
void	setOrderRestriction(java.lang.String[] ord_params)
void	setOrderRestriction(java.lang.String[] ord_params, DblMatrix mixing)

Methods inherited from class com.mockturtlesolutions.snifflib.invprobs.AbstractProposalDistribution

getMixingParam, getMixingParams, negLogLikeNewGivenOld, negLogLikeOldGivenNew, replaceMixingParams, sample, sample, samplePosterior, setMixingParam, setMixingParams, updateNewParams, updateOldParams

Methods inherited from class com.mockturtlesolutions.snifflib.invprobs.StatisticalModel

addFigureReporter, addObjectToSample, addParameterChangeListener, declareIfNotParameter, declareIfNotPriorParameter, declareParameter, declareParameter, declarePriorParameter, declarePriorParameter, declareVariable, fireParameterAdded, fireParameterRemoved, fireParameterValueChanged, fireParameterValuesChanged, firePriorParameterAdded, firePriorParameterRemoved, firePriorParameterValueChanged, firePriorParameterValuesChanged, getDataAugment, getDataSet, getDataSetAdapter, getDeclaredParameters, getDeclaredPriorParameters, getDeclaredVariables, getFigureReporter, getFigureReporters, getIgnoreNaN, getMSE, getName, getNewObjectSample, getNewObjectSamples, getObjectSamplingOffered, getObjectsToSample, getParam, getParams, getPosteriorParam, getPosteriorParams, getPriorParam, getPriorParams, getValueAt, getValueAt, getValueAt, getValueToMinimize, getX, getY, hasParameter, hasPriorParameter, invertParameterDeclarations, isSamplingObject, isVectorBased, likelihood, mapName, negLogLikelihood, numParams, offerObjectSamplingFor, offersObjectSamplingFor, parameterSet, putNewObjectSample, removeAllParameterChangeListener, removeFigureReporter, removeObjectToSample, removeParameterChangeListener, replaceParams, replacePosteriorParams, replacePriorParams, residuals, revokeObjectSamplingFor, revokeParameter, revokePriorParameter, revokeVariable, setDataAugment, setDataSet, setIgnoreNaN, setName, setObjectsToSample, setParam, setParams, setPosteriorParam, setPosteriorParams, setPriorParam, setPriorParams, setValueToGet, setX, setY, sumNegLogLikelihood, unMapName, variableSet

Methods inherited from class com.mockturtlesolutions.snifflib.functions.AbstractFunction

domainDimension, plotOver, plotOver, rangeDimension

Methods inherited from class java.lang.Object

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

Constructor Detail

GaussianProposal

public GaussianProposal(StatisticalModel model)

The means of the Gaussians will be assumed to be the current values in

Method Detail

setLogNormal

public void setLogNormal(java.lang.String param)

Sets up the given parameter to be sampled from a Log-Normal distribution. The mixing standard deviation is automatically overwritten to be 0.1.

setLogNormal

public void setLogNormal(java.lang.String param,
                DblMatrix mixing)

Sets up the given parameter to be sampled from a Log-Normal distribution with the given standard deviation.

setOrderRestriction

public void setOrderRestriction(java.lang.String[] ord_params)

setOrderRestriction

public void setOrderRestriction(java.lang.String[] ord_params,
                       DblMatrix mixing)

getOrderStatistic

public int getOrderStatistic(java.lang.String name)

getLeftParameter

public java.lang.String getLeftParameter(java.lang.String name)

isLogNormal

public boolean isLogNormal(java.lang.String param)

Returns true if the proposal distribution for the named parameter is lognormal.

isOrderRestricted

public boolean isOrderRestricted(java.lang.String param)

getPredictionAt

public DblMatrix getPredictionAt(DblMatrix[] X)

Specified by:

getPredictionAt in class StatisticalModel

negLogPrior

public DblParamSet negLogPrior()

Description copied from class: StatisticalModel

Returns the negative log of the prior probability of the current parameter set. This default implementation assumes a prior probability of 1 for each parameter resulting in a return value of zero. Method should be over-riden for other priors.

Specified by:

negLogPrior in class AbstractProposalDistribution

samplePosterior

public DblParamSet samplePosterior(java.lang.String[] subset)

Samples parameters from a Gaussian distribution centered about the current old values.

Specified by:

samplePosterior in class AbstractProposalDistribution

about

public java.lang.String about()

Description copied from class: StatisticalModel

Return a string giving some descriptive information about the model.

Specified by:

about in class StatisticalModel