FairRecKitLib is a library that functions as a combinatory interface between a set of existing recommender libraries, such as LensKit, Implicit, and Surprise. It was made to accompany the FairRecKit application (FairRecKitApp).
This software has been developed by students within the Software Project course of the bachelor program Computer Science at Utrecht University, commissioned by Christine Bauer.
Development team: Lennard Chung, Aleksej Cornelissen, Isabelle van Driessel, Diede van der Hoorn, Yme de Jong, Lan Le, Sanaz Najiyan Tabriz, Roderick Spaans, Casper Thijsen, Robert Verbeeten, Vos Wesseling, Fern Wieland
© Copyright Utrecht University (Department of Information and Computing Sciences)
If you use FairRecKit in research, please cite:
Christine Bauer, Lennard Chung, Aleksej Cornelissen, Isabelle van Driessel, Diede van der Hoorn, Yme de Jong, Lan Le, Sanaz Najiyan Tabriz, Roderick Spaans, Casper Thijsen, Robert Verbeeten, Vos Wesseling, & Fern Wieland (2023). FairRecKit: A Web-based analysis software for recommender evaluations. Proceedings of the 8th ACM SIGIR Conference on Human Information Interaction and Retrieval (CHIIR 2023), Austin, TX, USA, 19–23 March, pp 438-443. DOI: 10.1145/3576840.3578274
FairRecKitLib utilises the scikit-surprise package, which relies on having a suitable C/C++ compiler present on the system to be able to install itself. For this purpose, make sure you have Cython installed before attempting to install FairRecKitLib. If your system lacks a compiler, install the 'Desktop development with C++' build tools through the Visual Studio installer.
Meeting these requirements, you can install FairRecKitLib like any PyPI package, using e.g. pip or conda.
pip:
pip install fairreckitlib
conda
conda install fairreckitlib
Please check out the FairRecKitLib Wiki and FairRecKitLib API for instructions and guides on how to utilise the library or add new functionality.