3. Reference documentation

This is the class and function reference of fmralign. Please refer to the full user guide for further details, as the class and function raw specifications may not be enough to give full guidelines on their uses.

3.1. fmralign.alignment.pairwise_alignment: Pairwise Alignment

Classes:

PairwiseAlignment([method, labels, n_jobs, ...])

Performs pairwise alignment between two subjects.

3.2. fmralign.alignment.group_alignment: Group Alignment

Classes:

GroupAlignment([method, labels, n_jobs, ...])

Performs group-level alignment of various subject data.

3.3. fmralign.methods: Alignment Methods

Classes:

Identity()

Compute no alignment, used as baseline for benchmarks : RX = X.

DetSRM([n_components])

Compute the alignment from one subjects to the shared latent response.

Procrustes([scaling])

Compute a orthogonal mixing matrix R and a scaling sc.

RidgeAlignment([alphas, cv])

Compute a scikit-estimator R using a mixing matrix M s.t Frobenius norm || XM - Y ||^2 + alpha * ||M||^2 is minimized.

OptimalTransport([solver, metric, reg, ...])

Compute the optimal coupling between X and Y with entropic regularization, using the pure Python POT (https://pythonot.github.io/) package.

3.4. fmralign.embeddings: Embedding Methods

Functions:

connectivity.get_connectivity_features(data, ...)

Compute connectivity features for a single subject.

parcellation.get_labels(imgs, masker[, ...])

Generate an array of labels for each voxel in the data.

whole_brain.get_adjacency_from_mask(...)

Creates a sparse adjacency matrix from a mask image where each voxel is connected to its neighbors within a specified radius.