chrisferreyra13 / hoi Goto Github PK

HOI (Higher Order Interactions) is a Python package to go beyond pairwise interactions by quantifying the statistical dependencies between 2 or more units using information-theoretical metrics. The package is built on top of Jax allowing computations on CPU or GPU.

HOI requires :

• Python (>= 3.8)
• numpy(>=1.22)
• scipy (>=1.9)
• jax
• pandas
• scikit-learn
• tqdm

To install Jax on GPU or CPU-only, please refer to Jax's documentation : https://jax.readthedocs.io/en/latest/installation.html

If you already have a working installation of NumPy, SciPy and Jax, the easiest way to install hoi is using pip:

pip install -U hoi

You can also install the latest version of the software directly from Github :

pip install git+https://github.com/brainets/hoi.git

For developers, you can install it in develop mode with the following commands :

git clone https://github.com/brainets/hoi.git
cd hoi
pip install -e .['full']

The full installation of HOI includes additional packages to test the software and build the documentation :

• pytest
• pytest-cov
• codecov
• xarray
• sphinx!=4.1.0
• sphinx-gallery
• pydata-sphinx-theme
• sphinxcontrib-bibtex
• numpydoc
• matplotlib
• flake8
• pep8-naming
• black

• Link to the documentation: https://brainets.github.io/hoi/
• Overview of the mathematical background : https://brainets.github.io/hoi/overview/ovw_theory.html
• List of implemented HOI metrics : https://brainets.github.io/hoi/api/modules.html
• Examples : https://brainets.github.io/hoi/auto_examples/index.html

For questions, please use the following link : https://github.com/brainets/hoi/discussions

HOI was mainly developed during the Google Summer of Code 2023 (https://summerofcode.withgoogle.com/archive/2023/projects/z6hGpvLS)