ncrf.NCRF¶
- class ncrf.NCRF(forward, theta, design)¶
Fitted NCRF model that can be applied to compatible datasets.
Holds the estimated weights together with the forward model and stimulus design needed to reconstruct response functions, predict whitened sensor data, and evaluate predictions. Reusable and picklable; produced by
NCRFEstimator.fit()and exposed asNCRFFit.model.- forward¶
The internal forward-model state (lead field, whitening filter, and source, sensor, and orientation dimensions).
- theta¶
Fitted NCRF coefficients over the Gaussian basis, shape
(source, stimulus * lag): rows are the source dipoles in lead-field order (orientation varying fastest), columns are the predictors ofdesignconcatenated, each ordered by stimulus with lag varying fastest.
- design¶
Stimulus, basis, and normalization metadata of the data the model was fit on, including the TRF timing (
design.tstart,design.tstep,design.tstop) and the Gaussian-basis width (design.basis_std). Pass it tonormalize()to bring another dataset onto the same scale.
Methods
|
Score predictions on |
|
Predict sensor-space data for each segment. |
Compute each source's contribution to explained variance. |
Attributes
The spatio-temporal response function as (list of) |
|
|