A typeclass representing a Collection with a few additional features required for implementing the particle filter
Credible intervals from a set of samples in a distribution
Credible intervals from a set of samples in a distribution
the lower interval
the upper interval
A single observation of a time series
Read a csv file in, where the first column corresponds to the Time, represented as a Double and the second column represents the observation.
Read a csv file in, where the first column corresponds to the Time, represented as a Double and the second column represents the observation.
a java.nio.file.Path to a file
Read a JSON file
Marshalling from JSON and to JSON for Simulated Data and MCMC data from the Composed Models Package
A particle filter which can represent particle clouds as a Collection, Collection is a typeclass which can currently has concrete methods for Vector and ParVector
A particle filter which takes a sample from the joint-posterior of the parameters and state p(x, theta | y)
Forecast data
Forecast data
the time of the observation
an observation of the process
the upper and lower credible intervals of the observation
the untransformed latent state
the intervals of the latent state
The state of the metropolis-hastings algorithms
The state of the metropolis-hastings algorithms
the log-likelihood of the observations given the latent state and the current parameters
the current set of parameters
the total number of accepted moves in the metropolis hastings algorithm
Simulate from a multivariate normal using Eigenvalue decomposition Y = Q * Z + mean, where Q = L^0.5 * M
A single observation of a time series, containing a realisation of the filtering state
A single observation of a time series, containing a realisation of the filtering state
This class represents the state of a a filter starting with a draw from the joint posterior p(x, theta | y) as the filter is applied, the value of the state changes with time, but the parameters, theta, are static
This class represents the state of a a filter starting with a draw from the joint posterior p(x, theta | y) as the filter is applied, the value of the state changes with time, but the parameters, theta, are static
the time of the draw from the joint posterior
the measurement taken at time t
a tuple containing the parameter and state drawn from the joint posterior
The state of the metropolis-hastings algorithms
The state of the metropolis-hastings algorithms
the log-likelihood of the observations given the latent state and the current parameters
the current set of parameters
the total number of accepted moves in the metropolis hastings algorithm
Implementation of the particle metropolis algorithm
Implementation of the particle metropolis algorithm
a function from parameters to LogLikelihood
the starting parameters for the metropolis algorithm
a SYMMETRIC proposal distribution for the metropolis algorithm (eg. Gaussian)
Implementation of the particle metropolis algorithm
Implementation of the particle metropolis algorithm
a function from parameters to LogLikelihood
the starting parameters for the metropolis algorithm
Implementation of the particle metropolis hastings algorithm specified prior distribution
Implementation of the particle metropolis hastings algorithm specified prior distribution
a function from parameters to LogLikelihood
a generic proposal distribution for the metropolis algorithm (eg. Gaussian)
the starting parameters for the metropolis algorithm
Implementation of the particle metropolis algorithm
Implementation of the particle metropolis algorithm
a function from parameters to LogLikelihood
the starting parameters for the metropolis algorithm
a SYMMETRIC proposal distribution for the metropolis algorithm (eg. Gaussian)
Particle Metropolis hastings which also samples the final value of the state
A class representing a return type for the particle filter, containing the state and associated credible intervals
A class representing a return type for the particle filter, containing the state and associated credible intervals
the time of the process
an optional observation, note discretely observed processes cannot be seen at all time points continuously
the mean of the empirical filtering distribution at time 'time'
Representation of the state of the particle filter, where the particles are in a Collection typeclass defined in package.scala
Representation of the state of the particle filter, where the particles are in a Collection typeclass defined in package.scala
the time of the current observation
the current observation at time t
a collection containing an approximate sample from the filtering distribution p(x(t) | y(t0:t))
the estimated log-likelihood of the path given the observations so far
the effective sample size
Representing a realisation from a stochastic differential equation
A single observation of a time series
A single observation of a time series
A binary tree implementation, to be used when combining models Hopefully this simplifies "zooming" into values and changing them
Set the taskSupport for Parallel collections globally for the session using reflection Source: stackoverflow.com/questions/17865823/how-do-i-set-the-default-number-of-threads-for-scala-2-10-parallel-collections
Set the taskSupport for Parallel collections globally for the session using reflection Source: stackoverflow.com/questions/17865823/how-do-i-set-the-default-number-of-threads-for-scala-2-10-parallel-collections
the number of threads to use for a parallel collection