RecList
Project description
RecList
RecList
Free software: MIT license
Documentation: https://reclist.readthedocs.io.
Overview
RecList is an open source library providing behavioral, “black-box” testing for recommender systems. Inspired by the pioneering work of [Ribeiro et al. 2020](https://aclanthology.org/2020.acl-main.442.pdf) in NLP, we introduce a general plug-and-play procedure to scale up behavioral testing, with an easy-to-extend interface for custom use cases.
RecList ships with some popular datasets and ready-made behavioral tests: check the paper (forthcoming) for more details on the relevant literature and the philosophical motivations behind the project.
If you are not familiar with the library, we suggest first taking our small [tour](#a-guided-tour) to get acquainted with the main abstractions through ready-made models and public datasets.
Project updates
_Nov. 2021: the library is currently in alpha. We welcome contributions (see below) and feedback, but please be advised that the package may change substantially in the upcoming months. A pre-print of the companion paper is planned to be released before Dec. 2021
As the project is in active development, come back often for updates.
Summary
This doc is structured as follows:
Quick Start
TBC
A Guided Tour
TBC
Available Datasets
TBC
Ready-made Tests
TBC
Roadmap
TBC
Contributing
TBC
Acknowledgments
The main contributors are:
If you have questions or feedback, please reach out to: jacopo dot tagliabue at tooso dot ai
.
License and Citation
All the code is released under an open MIT license. If you found RecList useful, or you are using it to benchmark/debug your model, please cite our pre-print (forhtcoming):
@article{recListPre2021,
title={Beyond NDCG: behavioral testing of recommender systems with RecList},
author={Patrick John Chia and Jacopo Tagliabue and Federico Bianchi and Chloe He and Brian Ko},
journal={ArXiv},
year={forthcoming}
}
Credits
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.
History
0.1.0 (2021-11-16)
First release on PyPI.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for reclist-0.2.0-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | acc69911e9c230cf9256e24c206d6d92a0ea8619bcab6738da262606073afc2e |
|
MD5 | 86f38a2bcb92456c28c2a8498bc4def5 |
|
BLAKE2b-256 | 5d9781036fc68ad70b47c07733ce3a49fd20cbf747c8e89f6c5e8655546c5b6a |