Note

This page is a reference documentation. It only explains the class signature, and not how to use it. Please refer to the user guide for the big picture.

3.3.3. fmralign.alignment_methods.ScaledOrthogonalAlignment

class fmralign.alignment_methods.ScaledOrthogonalAlignment(scaling=True)[source]

Compute a orthogonal mixing matrix R and a scaling sc. These are calculated such that Frobenius norm ||sc RX - Y||^2 is minimized.

Parameters:
scalingboolean, optional

Determines whether a scaling parameter is applied to improve transform.

Attributes:
Rndarray (n_features, n_features)

Optimal orthogonal transform

__init__(scaling=True)[source]
fit(X, Y)[source]

Fit orthogonal R s.t. ||sc XR - Y||^2

Parameters:
X: (n_samples, n_features) nd array

source data

Y: (n_samples, n_features) nd array

target data

transform(X)[source]

Transform X using optimal transform computed during fit.