probnum.filtsmooth¶
Bayesian Filtering and Smoothing.
This package provides different kinds of Bayesian filters and smoothers which estimate the distribution over observed and hidden variables in a sequential model. The two operations differ by what information they use. Filtering considers all observations up to a given point, while smoothing takes the entire set of observations into account.
Functions¶
|
Samples true states and observations at pre-determined timesteps “times” for a state space model. |
|
Matrix fraction decomposition. |
|
Computes mean and covariance of SDE solution. |
Classes¶
|
Gaussian filtering and smoothing, i.e. Kalman-like filters and smoothers. |
|
Iterated filter/smoother based on posterior linearisation. |
|
Continuous extended Kalman filter transition. |
|
Continuous unscented Kalman filter transition. |
|
Discrete extended Kalman filter transition. |
|
Discrete extended Kalman filter transition. |
|
Used for unscented Kalman filter. |
Markov transition rules in discrete or continuous time. |
|
|
Stochastic differential equation. |
|
Linear stochastic differential equation (SDE), |
|
Linear time-invariant continuous Markov models of the form dx = [F x(t) + u] dt + L dBt. |
|
Random variable transitions with additive Gaussian noise. |
|
Discrete, linear Gaussian transition models of the form. |
|
Discrete, linear, time-invariant Gaussian transition models of the form. |
Posterior Distribution over States after Filtering/Smoothing. |
|
|
Posterior Distribution after (Extended/Unscented) Kalman Filtering/Smoothing. |
|
Stopping criteria for iterated filters/smoothers. |
|
Keep updating until the filter recursion arrives at a fixed-point. |