Skip to content
/ enc Public

Reproducing encoding models published by Lebel et al. 2023

License

Notifications You must be signed in to change notification settings

GabrielKP/enc

Folders and files

NameName
Last commit message
Last commit date
Mar 10, 2025
Mar 20, 2025
Mar 4, 2025
Mar 20, 2025
Mar 21, 2025
Mar 3, 2025
Mar 20, 2025
Mar 4, 2025
Mar 20, 2025
Feb 9, 2025
Mar 20, 2025
Mar 4, 2025
Mar 10, 2025
Mar 10, 2025
Jan 28, 2025

Repository files navigation

Encoding Models

A project reproducing endocing models published by LeBel et al. 2023.

We documented our results in this Report.

code documentation documentation ML framework Code style: Ruff packaging framwork: Poetry tool: pre-commit


Setup

# setup up conda environment
conda create -n enc python=3.9
conda activate enc

# install package
pip install .

# install git-annex
https://handbook.datalad.org/en/latest/intro/installation.html

# download the data (one of the below)
python src/encoders/download_data.py # subject 2 & few stories
python src/encoders/download_data.py --stories all # subject 2 & all stories
python src/encoders/download_data.py --stories all --subjects all # all subjects & all stories

# you can also install the path into a custom dir
python src/encoders/download_data.py --data_dir /path/to/custom/dir


# Setup the config with the editor of your choice
nano config.yaml
# If you want to generate plots, make sure to install inkscape
# and set its path in INKSCAPE_DIR (see below)

Setup pycortex (for visualization)

  1. Find out the location of the pycortex config: In the ipython terminal:
import cortex
cortex.options.usercfg
  1. Open the config file (should be a */options.cfg)

  2. Modify the filestore entry to point towards ds003020/derivative/pycortex-db

  3. To use quickshow install inkscape: https://inkscape.org/release/inkscape-1.3.2/

  4. Make sure inkscape is available in the terminal. Instructions Mac

Development setup

  1. Install poetry
  2. Run following commands:
# setup up conda environment (optional)
conda create -n enc python=3.9
conda activate enc

# install dependencies
poetry install

# install pre-commit
pre-commit install

# run pre-commit against all files once
pre-commit run --all-files

# download the data (one of the below)
python src/encoders/download_data.py # subject 2 & few stories

# Setup the config with the editor of your choice
nano config.yaml

Team

License