Uses of Interface
gov.sandia.cognition.statistics.ComputableDistribution

Packages that use ComputableDistribution

Package	Description
gov.sandia.cognition.learning.algorithm.hmm	Provides hidden Markov model (HMM) algorithms.
gov.sandia.cognition.learning.function.categorization	Provides functions that output a discrete set of categories.
gov.sandia.cognition.learning.function.cost	Provides cost functions.
gov.sandia.cognition.statistics	Provides the inheritance hierarchy for general statistical methods and distributions.
gov.sandia.cognition.statistics.bayesian	Provides algorithms for computing Bayesian estimates of parameters.
gov.sandia.cognition.statistics.distribution	Provides statistical distributions.

Uses of ComputableDistribution in gov.sandia.cognition.learning.algorithm.hmm

Fields in gov.sandia.cognition.learning.algorithm.hmm with type parameters of type ComputableDistribution

Modifier and Type	Field and Description
protected BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>>	AbstractBaumWelchAlgorithm.distributionLearner Learner for the Distribution Functions of the HMM.
protected BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>>	ParallelBaumWelchAlgorithm.DistributionEstimatorTask.distributionLearner My copy of the PDF estimator.
protected java.util.Collection<? extends ComputableDistribution<ObservationType>>	HiddenMarkovModel.emissionFunctions The PDFs that emit symbols from each state.

Methods in gov.sandia.cognition.learning.algorithm.hmm that return types with arguments of type ComputableDistribution

Modifier and Type	Method and Description
BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>>	AbstractBaumWelchAlgorithm.getDistributionLearner() Getter for distributionLearner
java.util.Collection<? extends ComputableDistribution<ObservationType>>	HiddenMarkovModel.getEmissionFunctions() Getter for emissionFunctions

Methods in gov.sandia.cognition.learning.algorithm.hmm with parameters of type ComputableDistribution

Modifier and Type	Method and Description
static <ObservationType> HiddenMarkovModel<ObservationType>	HiddenMarkovModel.createRandom(int numStates, ComputableDistribution<ObservationType> distribution, java.util.Random random) Creates a Hidden Markov Model with the same PMF/PDF for each state, but sampling the columns of the transition matrix and the initial probability distributions from a diffuse Dirichlet.

Method parameters in gov.sandia.cognition.learning.algorithm.hmm with type arguments of type ComputableDistribution

Modifier and Type	Method and Description
static <ObservationType> HiddenMarkovModel<ObservationType>	HiddenMarkovModel.createRandom(int numStates, BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>> learner, java.util.Collection<? extends ObservationType> data, java.util.Random random) Creates a Hidden Markov Model with the same PMF/PDF for each state, but sampling the columns of the transition matrix and the initial probability distributions from a diffuse Dirichlet.
void	AbstractBaumWelchAlgorithm.setDistributionLearner(BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>> distributionLearner) Setter for distributionLearner
void	HiddenMarkovModel.setEmissionFunctions(java.util.Collection<? extends ComputableDistribution<ObservationType>> emissionFunctions) Setter for emissionFunctions.

Constructor parameters in gov.sandia.cognition.learning.algorithm.hmm with type arguments of type ComputableDistribution

Constructor and Description
AbstractBaumWelchAlgorithm(HiddenMarkovModel<ObservationType> initialGuess, BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>> distributionLearner, boolean reestimateInitialProbabilities) Creates a new instance of AbstractBaumWelchAlgorithm
BaumWelchAlgorithm(HiddenMarkovModel<ObservationType> initialGuess, BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>> distributionLearner, boolean reestimateInitialProbabilities) Creates a new instance of BaumWelchAlgorithm
DistributionEstimatorTask(java.util.Collection<? extends ObservationType> data, BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>> distributionLearner, int index) Creates an instance of DistributionEstimatorTask
HiddenMarkovModel(Vector initialProbability, Matrix transitionProbability, java.util.Collection<? extends ComputableDistribution<ObservationType>> emissionFunctions) Creates a new instance of ContinuousDensityHiddenMarkovModel
ParallelBaumWelchAlgorithm(HiddenMarkovModel<ObservationType> initialGuess, BatchLearner<java.util.Collection<? extends WeightedValue<? extends ObservationType>>,? extends ComputableDistribution<ObservationType>> distributionLearner, boolean reestimateInitialProbabilities) Creates a new instance of ParallelBaumWelchAlgorithm
ParallelHiddenMarkovModel(Vector initialProbability, Matrix transitionProbability, java.util.Collection<? extends ComputableDistribution<ObservationType>> emissionFunctions) Creates a new instance of ParallelHiddenMarkovModel

Uses of ComputableDistribution in gov.sandia.cognition.learning.function.categorization

Methods in gov.sandia.cognition.learning.function.categorization that return types with arguments of type ComputableDistribution

Modifier and Type	Method and Description
BatchLearner<java.util.Collection<? extends ObservationType>,? extends ComputableDistribution<ObservationType>>	MaximumAPosterioriCategorizer.Learner.getConditionalLearner() Getter for conditionalLearner

Method parameters in gov.sandia.cognition.learning.function.categorization with type arguments of type ComputableDistribution

Modifier and Type	Method and Description
void	MaximumAPosterioriCategorizer.Learner.setConditionalLearner(BatchLearner<java.util.Collection<? extends ObservationType>,? extends ComputableDistribution<ObservationType>> conditionalLearner) Setter for conditionalLearner

Constructor parameters in gov.sandia.cognition.learning.function.categorization with type arguments of type ComputableDistribution

Constructor and Description
Learner(BatchLearner<java.util.Collection<? extends ObservationType>,? extends ComputableDistribution<ObservationType>> conditionalLearner) Creates a new instance of Learner

Uses of ComputableDistribution in gov.sandia.cognition.learning.function.cost

Methods in gov.sandia.cognition.learning.function.cost with parameters of type ComputableDistribution

Modifier and Type	Method and Description
java.lang.Double	NegativeLogLikelihood.evaluate(ComputableDistribution<DataType> target)
java.lang.Double	ParallelNegativeLogLikelihood.evaluate(ComputableDistribution<DataType> target)

Uses of ComputableDistribution in gov.sandia.cognition.statistics

Subinterfaces of ComputableDistribution in gov.sandia.cognition.statistics

Modifier and Type	Interface and Description
interface	ClosedFormComputableDiscreteDistribution<DataType> A discrete, closed-form Distribution with a PMF.
interface	ClosedFormComputableDistribution<DataType> A closed-form Distribution that also has an associated distribution function.
interface	ClosedFormDiscreteUnivariateDistribution<DomainType extends java.lang.Number> A ClosedFormUnivariateDistribution that is also a DiscreteDistribution
interface	DataDistribution<DataType> A distribution of data from which we can sample and perform Ring operations.
static interface	DataDistribution.PMF<KeyType> Interface for the probability mass function (PMF) of a data distribution.
interface	DiscreteDistribution<DataType> A Distribution with a countable domain (input) set.
interface	IntegerDistribution Defines a distribution over natural numbers.
interface	ProbabilityDensityFunction<DataType> Defines a probability density function.
interface	ProbabilityFunction<DataType> A Distribution that has an evaluate method that indicates p(x), such as a probability density function or a probability mass function (but NOT a cumulative distribution function).
interface	ProbabilityMassFunction<DataType> The ProbabilityMassFunction interface defines the functionality of a probability mass function.
interface	SmoothCumulativeDistributionFunction This defines a CDF that has an associated derivative, which is its PDF.
interface	SmoothUnivariateDistribution A closed-form scalar distribution that is also smooth.
interface	UnivariateProbabilityDensityFunction A PDF that takes doubles as input.

Classes in gov.sandia.cognition.statistics that implement ComputableDistribution

Modifier and Type	Class and Description
class	AbstractClosedFormIntegerDistribution An abstract class for closed-form integer distributions.
class	AbstractClosedFormSmoothUnivariateDistribution Partial implementation of SmoothUnivariateDistribution
class	AbstractDataDistribution<KeyType> An abstract implementation of the DataDistribution interface.

Uses of ComputableDistribution in gov.sandia.cognition.statistics.bayesian

Classes in gov.sandia.cognition.statistics.bayesian that implement ComputableDistribution

Modifier and Type	Class and Description
class	AdaptiveRejectionSampling.UpperEnvelope Constructs the upper envelope for sampling.

Methods in gov.sandia.cognition.statistics.bayesian that return ComputableDistribution

Modifier and Type	Method and Description
ComputableDistribution<ObservationType>	BayesianEstimatorPredictor.createPredictiveDistribution(PosteriorType posterior) Creates the predictive distribution of new data given the posterior.

Methods in gov.sandia.cognition.statistics.bayesian with parameters of type ComputableDistribution

Modifier and Type	Method and Description
double	ConditionalProbability.computeConditionalProbability(java.util.Collection<DataType> prior, DataType posterior, ComputableDistribution<java.util.Collection<DataType>> priorDistribution, ComputableDistribution<java.util.Collection<DataType>> posteriorDistribution) Computes the conditional probability between a collection of objects and a new object.
double	ConditionalProbability.computeConditionalProbability(java.util.Collection<DataType> prior, DataType posterior, ComputableDistribution<java.util.Collection<DataType>> priorDistribution, ComputableDistribution<java.util.Collection<DataType>> posteriorDistribution) Computes the conditional probability between a collection of objects and a new object.
double	ConditionalProbability.computeConditionalProbability(DataType prior, DataType posterior, ComputableDistribution<DataType> priorDistribution, ComputableDistribution<java.util.Collection<DataType>> posteriorDistribution) Computes the conditional probability between two objects.
double	ConditionalProbability.computeConditionalProbability(DataType prior, DataType posterior, ComputableDistribution<DataType> priorDistribution, ComputableDistribution<java.util.Collection<DataType>> posteriorDistribution) Computes the conditional probability between two objects.
double	ConditionalProbability.computeConditionalProbabilityWhenDataTypeHasHistoricalData(DataType prior, DataType posterior, ComputableDistribution<DataType> priorDistribution, ComputableDistribution<DataType> posteriorDistribution) Computes the conditional probability between two objects.
double	ConditionalProbability.computeConditionalProbabilityWhenDataTypeHasHistoricalData(DataType prior, DataType posterior, ComputableDistribution<DataType> priorDistribution, ComputableDistribution<DataType> posteriorDistribution) Computes the conditional probability between two objects.
static <ObservationType> double	BayesianUtil.deviance(ComputableDistribution<ObservationType> conditional, java.lang.Iterable<? extends ObservationType> observations) Computes the deviance of the model, which is -2log(p(observations|parameter)).
static <ObservationType> double	BayesianUtil.logLikelihood(ComputableDistribution<? super ObservationType> distribution, java.lang.Iterable<? extends ObservationType> observations) Computes the log likelihood of the i.i.d.

Method parameters in gov.sandia.cognition.statistics.bayesian with type arguments of type ComputableDistribution

Modifier and Type	Method and Description
static <ObservationType,ParameterType> UnivariateGaussian	BayesianUtil.expectedDeviance(BayesianParameter<ParameterType,? extends ComputableDistribution<ObservationType>,?> predictiveDistribution, java.lang.Iterable<? extends ObservationType> observations, java.util.Random random, int numSamples) Computes the expected deviance of the model by sampling parameters from the posterior and then computing the deviance using the conditional distribution.

Uses of ComputableDistribution in gov.sandia.cognition.statistics.distribution

Classes in gov.sandia.cognition.statistics.distribution that implement ComputableDistribution

Modifier and Type	Class and Description
class	BernoulliDistribution A Bernoulli distribution, which takes a value of "1" with probability "p" and value of "0" with probability "1-p".
static class	BernoulliDistribution.CDF CDF of a Bernoulli distribution.
static class	BernoulliDistribution.PMF PMF of the Bernoulli distribution.
class	BetaBinomialDistribution A Binomial distribution where the binomial parameter, p, is set according to a Beta distribution instead of a single value.
static class	BetaBinomialDistribution.CDF CDF of BetaBinomialDistribution
static class	BetaBinomialDistribution.PMF PMF of the BetaBinomialDistribution
class	BetaDistribution Computes the Beta-family of probability distributions.
static class	BetaDistribution.CDF CDF of the Beta-family distribution
static class	BetaDistribution.PDF Beta distribution probability density function
class	BinomialDistribution Binomial distribution, which is a collection of Bernoulli trials
static class	BinomialDistribution.CDF CDF of the Binomial distribution, which is the probability of getting up to "x" successes in "N" trials with a Bernoulli probability of "p"
static class	BinomialDistribution.PMF The Probability Mass Function of a binomial distribution.
class	CategoricalDistribution The Categorical Distribution is the multivariate generalization of the Bernoulli distribution, where the outcome of an experiment is a one-of-N output, where the output is a selector Vector.
static class	CategoricalDistribution.PMF PMF of the Categorical Distribution
class	CauchyDistribution A Cauchy Distribution is the ratio of two Gaussian Distributions, sometimes known as the Lorentz distribution.
static class	CauchyDistribution.CDF CDF of the CauchyDistribution.
static class	CauchyDistribution.PDF PDF of the CauchyDistribution.
class	ChineseRestaurantProcess A Chinese Restaurant Process is a discrete stochastic processes that partitions data points to clusters.
static class	ChineseRestaurantProcess.PMF PMF of the Chinese Restaurant Process
class	ChiSquareDistribution Describes a Chi-Square Distribution.
static class	ChiSquareDistribution.CDF Cumulative Distribution Function (CDF) of a Chi-Square Distribution
static class	ChiSquareDistribution.PDF PDF of the Chi-Square distribution
class	DataCountTreeSetBinnedMapHistogram<ValueType extends java.lang.Comparable<? super ValueType>> The DataCountTreeSetBinnedMapHistogram class extends a DefaultDataDistribution by mapping values to user defined bins using a TreeSetBinner.
class	DefaultDataDistribution<KeyType> A default implementation of ScalarDataDistribution that uses a backing map.
static class	DefaultDataDistribution.PMF<KeyType> PMF of the DefaultDataDistribution
class	DeterministicDistribution A deterministic distribution that returns samples at a single point.
static class	DeterministicDistribution.CDF CDF of the deterministic distribution.
static class	DeterministicDistribution.PMF PMF of the deterministic distribution.
class	DirichletDistribution The Dirichlet distribution is the multivariate generalization of the beta distribution.
static class	DirichletDistribution.PDF PDF of the Dirichlet distribution.
class	ExponentialDistribution An Exponential distribution describes the time between events in a poisson process, resulting in a memoryless distribution.
static class	ExponentialDistribution.CDF CDF of the ExponentialDistribution.
static class	ExponentialDistribution.PDF PDF of the ExponentialDistribution.
class	GammaDistribution Class representing the Gamma distribution.
static class	GammaDistribution.CDF CDF of the Gamma distribution
static class	GammaDistribution.PDF Closed-form PDF of the Gamma distribution
class	GeometricDistribution The geometric distribution models the number of successes before the first failure occurs under an independent succession of Bernoulli tests.
static class	GeometricDistribution.CDF CDF of the Geometric distribution
static class	GeometricDistribution.PMF PMF of the Geometric distribution
class	InverseGammaDistribution Defines an inverse-gamma distribution.
static class	InverseGammaDistribution.CDF CDF of the inverseRootFinder-gamma distribution.
static class	InverseGammaDistribution.PDF PDF of the inverseRootFinder-Gamma distribution.
class	InverseWishartDistribution The Inverse-Wishart distribution is the multivariate generalization of the inverse-gamma distribution.
static class	InverseWishartDistribution.PDF PDF of the Inverse-Wishart distribution, though I have absolutely no idea why anybody would evaluate the PDF of an Inverse-Wishart...
class	LaplaceDistribution A Laplace distribution, sometimes called a double exponential distribution.
static class	LaplaceDistribution.CDF CDF of the Laplace distribution.
static class	LaplaceDistribution.PDF The PDF of a Laplace Distribution.
class	LogisticDistribution A implementation of the scalar logistic distribution, which measures the log-odds of a binary event.
static class	LogisticDistribution.CDF CDF of the LogisticDistribution
static class	LogisticDistribution.PDF PDF of the LogisticDistribution
class	LogNormalDistribution Log-Normal distribution PDF and CDF implementations.
static class	LogNormalDistribution.CDF CDF of the Log-Normal Distribution
static class	LogNormalDistribution.PDF PDF of a Log-normal distribution
static class	MixtureOfGaussians.PDF PDF of the MixtureOfGaussians
class	MultinomialDistribution A multinomial distribution is the multivariate/multiclass generalization of the Binomial distribution.
static class	MultinomialDistribution.PMF Probability Mass Function of the Multinomial Distribution.
class	MultivariateGaussian The MultivariateGaussian class implements a multidimensional Gaussian distribution that contains a mean vector and a covariance matrix.
static class	MultivariateGaussian.PDF PDF of a multivariate Gaussian
class	MultivariateMixtureDensityModel<DistributionType extends ClosedFormComputableDistribution<Vector>> A LinearMixtureModel of multivariate distributions with associated PDFs.
static class	MultivariateMixtureDensityModel.PDF<DistributionType extends ClosedFormComputableDistribution<Vector>> PDF of the MultivariateMixtureDensityModel
class	MultivariatePolyaDistribution A multivariate Polya Distribution, also known as a Dirichlet-Multinomial model, is a compound distribution where the parameters of a multinomial are drawn from a Dirichlet distribution with fixed parameters and a constant number of trials and then the observations are generated by this multinomial.
static class	MultivariatePolyaDistribution.PMF PMF of the MultivariatePolyaDistribution
class	MultivariateStudentTDistribution Multivariate generalization of the noncentral Student's t-distribution.
static class	MultivariateStudentTDistribution.PDF PDF of the MultivariateStudentTDistribution
class	NegativeBinomialDistribution Negative binomial distribution, also known as the Polya distribution, gives the number of successes of a series of Bernoulli trials before recording a given number of failures.
static class	NegativeBinomialDistribution.CDF CDF of the NegativeBinomialDistribution
static class	NegativeBinomialDistribution.PMF PMF of the NegativeBinomialDistribution.
class	NormalInverseGammaDistribution The normal inverse-gamma distribution is the product of a univariate Gaussian distribution with an inverse-gamma distribution.
static class	NormalInverseGammaDistribution.PDF PDF of the NormalInverseGammaDistribution
class	NormalInverseWishartDistribution The normal inverse Wishart distribution
static class	NormalInverseWishartDistribution.PDF PDF of the normal inverse-Wishart distribution.
class	ParetoDistribution This class describes the Pareto distribution, sometimes called the Bradford Distribution.
static class	ParetoDistribution.CDF CDF of the Pareto Distribution.
static class	ParetoDistribution.PDF PDF of the ParetoDistribution
class	PoissonDistribution A Poisson distribution is the limits of what happens when a Bernoulli trial with "rare" events are sampled on a continuous basis and then binned into discrete time intervals.
static class	PoissonDistribution.CDF CDF of the PoissonDistribution
static class	PoissonDistribution.PMF PMF of the PoissonDistribution.
class	ScalarDataDistribution A Data Distribution that uses Doubles as its keys, making it a univariate distribution
static class	ScalarDataDistribution.CDF CDF of the ScalarDataDistribution, maintains the keys/domain in sorted order (TreeMap), so it's slower than it's peers.
static class	ScalarDataDistribution.PMF PMF of the ScalarDataDistribution
class	ScalarMixtureDensityModel ScalarMixtureDensityModel (SMDM) implements just that: a scalar mixture density model.
static class	ScalarMixtureDensityModel.CDF CDFof the SMDM
static class	ScalarMixtureDensityModel.PDF PDF of the SMDM
class	StudentTDistribution Defines a noncentral Student-t Distribution.
static class	StudentTDistribution.CDF Evaluator that computes the Cumulative Distribution Function (CDF) of a Student-t distribution with a fixed number of degrees of freedom
static class	StudentTDistribution.PDF Evaluator that computes the Probability Density Function (CDF) of a Student-t distribution with a fixed number of degrees of freedom
class	UniformDistribution Contains the (very simple) definition of a continuous Uniform distribution, parameterized between the minimum and maximum bounds.
static class	UniformDistribution.CDF Cumulative Distribution Function of a uniform
static class	UniformDistribution.PDF Probability density function of a Uniform Distribution
class	UniformIntegerDistribution Contains the (very simple) definition of a continuous Uniform distribution, parameterized between the minimum and maximum bounds.
static class	UniformIntegerDistribution.CDF Implements the cumulative distribution function for the discrete uniform distribution.
static class	UniformIntegerDistribution.PMF Probability mass function of a discrete uniform distribution.
class	UnivariateGaussian This class contains internal classes that implement useful functions based on the Gaussian distribution.
static class	UnivariateGaussian.CDF CDF of the underlying Gaussian.
static class	UnivariateGaussian.CDF.Inverse Inverts the CumulativeDistribution function.
static class	UnivariateGaussian.PDF PDF of the underlying Gaussian.
class	WeibullDistribution Describes a Weibull distribution, which is often used to describe the mortality, lifespan, or size distribution of objects.
static class	WeibullDistribution.CDF CDF of the Weibull distribution
static class	WeibullDistribution.PDF PDF of the Weibull distribution
class	YuleSimonDistribution The Yule-Simon distribution is a model of preferential attachment, such as a model of the number of groups follows a power-law distribution (Zipf's Law).
static class	YuleSimonDistribution.CDF CDF of the Yule-Simon Distribution
static class	YuleSimonDistribution.PMF PMF of the Yule-Simon Distribution