API reference¶
The public ncrf API provides a convenience function as well as composable
data, estimator, solver, model, and fit objects.
High-level interface¶
|
One shot function for cortical TRF localization. |
Fitting pipeline¶
|
Dataset for NCRF fitting: M/EEG segments, their predictors, and the design. |
|
Estimator for neuro-current response functions (NCRFs). |
|
Fit one fixed solver configuration on whitened data. |
|
Configuration for selecting among solver candidates. |
|
Cross-validation scores for one solver candidate. |
|
Perform cross-validation over a set of solver candidates. |
Models and fits¶
|
Fitted NCRF model that can be applied to compatible datasets. |
|
Report produced by |
|
Context in which an |
Solvers¶
|
Configuration contract for an algorithm that estimates NCRF weights. |
|
Fitted state from one solver execution. |
|
Alternating FASTA/Champagne solver for NCRF estimation. |
|
Fitted state produced by |
Metrics¶
|
Mean sensor-by-segment explained variance in whitened sensor space. |
|
Mean unweighted squared prediction error in whitened sensor space. |
Model components¶
|
Forward model and noise covariance with derived whitened quantities. |
|
Stimulus and basis metadata defining the coefficient space. |