class KoopmanWeightingModel

class deeptime.covariance.KoopmanWeightingModel(u, u_const, koopman_operator, whitening_transformation=None, covariances=None)

A model which contains the Koopman operator in a modified basis (PC|1) and can transform data into Koopman weights.

Weights are computed according to [1].

Parameters:
  • u (ndarray) – Reweighting vector in input basis

  • u_const (float) – Constant offset for reweighting in input basis.

  • koopman_operator (ndarray) – Koopman operator in modified basis.

  • whitening_transformation (ndarray, optional, default=None) – Whitening transformation.

  • covariances (CovarianceModel, optional, default=None) – Estimated covariances.

References

Attributes

const_weight_input

Yields the constant offset for reweighting in input basis.

covariances

Covariance model which was used to compute the Koopman model.

koopman_operator

The Koopman operator in modified basis (PC|1).

weights_input

Yields the reweighting vector in input basis.

whitening_transformation

Estimated whitening transformation for data

Methods

copy()

Makes a deep copy of this model.

get_params([deep])

Get the parameters.

set_params(**params)

Set the parameters of this estimator.

transform(data, **kw)

Same as weights().

weights(X)

Applies reweighting vectors to data, yielding corresponding weights.

__call__(*args, **kwargs)

Call self as a function.

copy() Model

Makes a deep copy of this model.

Returns:

A new copy of this model.

Return type:

copy

get_params(deep=False)

Get the parameters.

Returns:

params – Parameter names mapped to their values.

Return type:

mapping of string to any

set_params(**params)

Set the parameters of this estimator.

The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form <component>__<parameter> so that it’s possible to update each component of a nested object.

Parameters:

**params (dict) – Estimator parameters.

Returns:

self – Estimator instance.

Return type:

object

transform(data, **kw)

Same as weights().

weights(X)

Applies reweighting vectors to data, yielding corresponding weights.

Parameters:

X ((T, d) ndarray) – The input data.

Returns:

weights – Weights for input data.

Return type:

(T, 1) ndarray

property const_weight_input: float

Yields the constant offset for reweighting in input basis.

Type:

float

property covariances: CovarianceModel

Covariance model which was used to compute the Koopman model.

Type:

CovarianceModel or None

property koopman_operator: ndarray

The Koopman operator in modified basis (PC|1).

Type:

ndarray

property weights_input: ndarray

Yields the reweighting vector in input basis.

Type:

(T, d) ndarray

property whitening_transformation: ndarray

Estimated whitening transformation for data

Type:

ndarray or None