xcp_d.interfaces.nilearn

Machine Learning module for NeuroImaging in python

Documentation is available in the docstrings and online at http://nilearn.github.io.

Contents

Nilearn aims at simplifying the use of the scikit-learn package in the context of neuroimaging. It provides specific input/output functions, algorithms and visualization tools.

Submodules

datasets — Utilities to download NeuroImaging datasets decoding — Decoding tools and algorithms decomposition — Includes a subject level variant of the ICA

algorithm called Canonical ICA

connectome — Set of tools for computing functional connectivity matrices

and for sparse multi-subjects learning of Gaussian graphical models

image — Set of functions defining mathematical operations

working on Niimg-like objects

maskers — Includes scikit-learn transformers. masking — Utilities to compute and operate on brain masks interfaces — Includes tools to preprocess neuro-imaging data

from various common interfaces like fMRIPrep.

mass_univariate — Defines a Massively Univariate Linear Model

estimated with OLS and permutation test

plotting — Plotting code for nilearn region — Set of functions for extracting region-defined

signals, clustering methods, connected regions extraction

signal — Set of preprocessing functions for time series