brainspace.gradient.alignment.ProcrustesAlignment

class brainspace.gradient.alignment.ProcrustesAlignment(n_iter=10, tol=1e-05, verbose=False)

Iterative alignment using generalized procrustes analysis.

Parameters:

• n_iter (int, optional) – Number of iterations. Default is 10.
• tol (float, optional) – Tolerance for stopping criteria. Default is 1e-5.
• verbose (bool, optional) – Verbosity. Default is False.

Variables:

• aligned (list of ndarray, shape = (n_samples, n_feat)) – Aligned datsets.
• mean (ndarray, shape = (n_samples, n_feat)) – Reference dataset built in the last iteration.

__init__(n_iter=10, tol=1e-05, verbose=False)

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([n_iter, tol, verbose])	Initialize self.
fit(data[, reference])	Align data.
get_params([deep])	Get parameters for this estimator.
set_params(**params)	Set the parameters of this estimator.

fit(data, reference=None)

Align data.

Parameters:

• data (list of ndarrays, shape = (n_samples, n_feat)) – List of datasets to align.
• reference (ndarray, shape = (n_samples, n_feat), optional) – Dataset to use as reference in the first iteration. If None, the first dataset in data is used as reference. Default is None.

Returns:

self (object) – Returns self.