Representational Similarity Analysis

unit_tests build_docs

This is a Python package for performing representational similarity analysis (RSA) using MNE-Python data structures. The RSA is computed using a “searchlight” approach.

Read more on RSA in the paper that introduced the technique:

Nikolaus Kriegeskorte, Marieke Mur and Peter Bandettini (2008). Representational similarity analysis - connecting the branches of systems neuroscience. Frontiers in Systems Neuroscience, 2(4).


The package can be installed either through PIP: pip install mne-rsa or through conda using the conda-forge channel: conda install -c conda-forge mne-rsa

Use cases

This is what the package can do for you:

Supported metrics for comparing DSMs:

Juicy bits of the API

def compute_dsm(data, metric='correlation', **kwargs)

def rsa_stcs(stcs, dsm_model, src, spatial_radius=0.04, temporal_radius=0.1,
             stc_dsm_metric='correlation', stc_dsm_params=dict(),
             rsa_metric='spearman', y=None, n_folds=1, sel_vertices=None,
             tmin=None, tmax=None, n_jobs=1, verbose=False):

def rsa_evokeds(evokeds, dsm_model, noise_cov=None, spatial_radius=0.04,
                temporal_radius=0.1, evoked_dsm_metric='correlation',
                evoked_dsm_params=dict(), rsa_metric='spearman', y=None,
                n_folds=1, picks=None, tmin=None, tmax=None, n_jobs=1,

def rsa_epochs(epochs, dsm_model, noise_cov=None, spatial_radius=0.04,
               temporal_radius=0.1, epochs_dsm_metric='correlation',
               epochs_dsm_params=dict(), rsa_metric='spearman', y=None,
               n_folds=1, picks=None, tmin=None, tmax=None, n_jobs=1,

def rsa_nifti(image, dsm_model, spatial_radius=0.01,
              image_dsm_metric='correlation', image_dsm_params=dict(),
              rsa_metric='spearman', y=None, n_folds=1, roi_mask=None,
              brain_mask=None, n_jobs=1, verbose=False):

Example usage

Basic example on the EEG “kiloword” data:

import mne
import rsa
data_path = mne.datasets.kiloword.data_path(verbose=True)
epochs = mne.read_epochs(data_path + '/kword_metadata-epo.fif')
# Compute the model DSM using all word properties
dsm_model = rsa.compute_dsm(epochs.metadata.iloc[:, 1:].values)
evoked_rsa = rsa.rsa_epochs(epochs, dsm_model,
                            spatial_radius=0.04, temporal_radius=0.01,


For quick guides on how to do specific things, see the examples.

Finally, there is the API reference documentation.

Integration with other packages

I mainly wrote this package to perform RSA analysis on MEG data. Hence, integration functions with MNE-Python are provided. There is also some integration with nipy for fMRI.


This package aims to be fast and memory efficient. An important design feature is that under the hood, everything operates on generators. The searchlight routines produce a generator of DSMs which are consumed by a generator of RSA values. Parallel processing is also supported, so you can use all of your CPU cores.


Here is how to set up the package as a developer:

git clone
cd mne-rsa
python develop --user