tjiagom/interpreting-cognition-paper-2019

A machine learning tool for interpreting differences in cognition using brain features

This repository stores the code used in the following preprint: https://www.biorxiv.org/content/10.1101/558403v1 (accepted in AIAI 2019).

We cannot share the original data used in the paper so we provide example files in example_data/ folder so the code in this repository can be executed.

Dependencies to execute the code are listed in environment_paper.yml. One can easily install all the dependencias by using an Anaconda environment, and running the following commands:

# Creating the environment with the file we provided
$ conda env create --force --file environment_paper.yml

# Activating the environment
$ conda activate env-paper

The main packages and respective versions that were used in this work (and defined in environment_paper.yml) are:

• jupyterlab 0.35.4
• matplotlib 3.0.2
• numpy 1.15.4
• pandas 0.24.1
• python 3.6.8
• scikit-learn 0.20.2
• scipy 1.2.0
• shap 0.27.0
• xgboost 0.81

All the descriptions are in the folder notebooks/, which you can see by executing, for example, Jupyter Lab:

(env-paper) $ jupyter lab

If you have any questions please just open an issue.