dreye.ReceptorEstimator.fit_underdetermined#

ReceptorEstimator.fit_underdetermined(B=None, underdetermined_opt=None, l2_eps=0.0001, batch_size=1, verbose=0, **opt_kwargs)[source]#

Fit capture values that are within the system’s hull and where the system is underdetermined (i.e. multiple solutions exist).

Parameters:
Bndarray of shape (n_samples, n_filters)

Relative total capture points. If None, the registered B is used. Defaults to None.

underdetermined_optstr, float, ndarray of shape (n_sources), optional
The underdetermined objective:

  • None : The L2-norm of the independent variables is minimized

  • floatThe objective becomes to get the

    overall source intensities as close as possible to the given value.

  • ndarrayThe objective becomes to get each source intensity as close

    as possible to the given value

  • ‘min’ : Minimize the overall intensity as much as possible

  • ‘max’ : Maximize the overall intensity as much as possible

  • ‘var’ : Reduce the variance between source intensities

By default None.

l2_epsfloat, optional

Allowable error in the l2-norm of the difference between target and fitted capture values. By default 1e-5.

batch_sizeint, optional

Batch size used to simultaneously fit multiple samples, by default 1. This is currently not implemented for this method.

verboseint, optional

Verbosity of the fitting procedure, by default 0.

Returns:
selfobject

The ReceptorEstimator object. This is the only thing returned if B is None.

Xndarray of shape (n_samples, n_sources)

Fitted intensity values. Returned if B is not None.

Bndarray of shape (n_samples, n_filters)

Capture values calculated using the fitted intensity values. Returned if B is not None.