Models¶

class stonesoup.models.base.Model[source]¶

Bases: stonesoup.base.Base

Model type

Base/Abstract class for all models.

abstract property ndim¶: Number of dimensions of model

abstract function(state, noise=False)[source]¶: Model function

abstract rvs(num_samples=1)[source]¶: Model noise/sample generation method

abstract pdf(state1, state2)[source]¶: Model pdf/likelihood evaluator method

class stonesoup.models.base.LinearModel[source]¶

Bases: stonesoup.models.base.Model

LinearModel class

Base/Abstract class for all linear models

abstract matrix()[source]¶: Model matrix

function(state, noise=False, **kwargs)[source]¶

Model linear function \(f_k(x(k),w(k)) = F_k(x_k) + w_k\)

Parameters

state (State) – An input state
noise (numpy.ndarray or bool) – An externally generated random process noise sample (the default is False, in which case no noise will be added if ‘True’, the output of rvs() is added)

Returns

The updated State with the model function evaluated.

Return type

State

class stonesoup.models.base.NonLinearModel[source]¶

Bases: stonesoup.models.base.Model

NonLinearModel class

Base/Abstract class for all non-linear models

jacobian(state, **kwargs)[source]¶

Model jacobian matrix \(H_{jac}\)

Parameters: state (State) – An input state
Returns: The model jacobian matrix evaluated around the given state vector.
Return type: numpy.ndarray of shape (ndim_meas, ndim_state)

abstract function(state, noise=False, **kwargs)[source]¶

Model function \(f(t,x(t),w(t))\)

Parameters

state (State) – An input state
noise (numpy.ndarray or bool) – An externally generated random process noise sample (the default is False, in which case no noise will be added if ‘True’, the output of rvs() is added)

Returns

The model function evaluated.

Return type

numpy.ndarray

class stonesoup.models.base.ReversibleModel[source]¶

Bases: stonesoup.models.base.NonLinearModel

Non-linear model containing sufficient co-ordinate information such that the linear co-ordinate conversions can be calculated from the non-linear counterparts.

Contains an inverse function which computes the reverse of the relevant linear-to-non-linear function

abstract inverse_function(detection, **kwargs)[source]¶

Takes in the result of the function and computes the inverse function, returning the initial input of the function.

Parameters: detection (Detection) – Input state (non-linear format)
Returns: The linear co-ordinates
Return type: numpy.ndarray

class stonesoup.models.base.TimeVariantModel[source]¶

Bases: stonesoup.models.base.Model

TimeVariantModel class

Base/Abstract class for all time-variant models

class stonesoup.models.base.TimeInvariantModel[source]¶

Bases: stonesoup.models.base.Model

TimeInvariantModel class

Base/Abstract class for all time-invariant models

class stonesoup.models.base.GaussianModel[source]¶

Bases: stonesoup.models.base.Model

GaussianModel class

Base/Abstract class for all Gaussian models

rvs(num_samples=1, **kwargs)[source]¶

Model noise/sample generation function

Generates noise samples from the model.

In mathematical terms, this can be written as:

\[v_t \sim \mathcal{N}(0,Q)\]

where \(v_t =\) noise and \(Q\) = covar.

Parameters: num_samples (scalar, optional) – The number of samples to be generated (the default is 1)
Returns: noise – A set of Np samples, generated from the model’s noise distribution.
Return type: 2-D array of shape (ndim, num_samples)

pdf(state1, state2, **kwargs)[source]¶

Model pdf/likelihood evaluation function

Evaluates the pdf/likelihood of state1, given the state state2 which is passed to function().

In mathematical terms, this can be written as:

\[p = p(y_t | x_t) = \mathcal{N}(y_t; x_t, Q)\]

where \(y_t\) = state_vector1, \(x_t\) = state_vector2 and \(Q\) = covar.

Parameters

state1 (State) –
state2 (State) –

Returns

The likelihood of state1, given state2

Return type

Probability

abstract covar()[source]¶: Model covariance