A Haskell wrapper around the Microsoft LightGBM library for machine learning uses. The emphasis here is on using Haskell types to help ensure that the hyperparameter settings chosen by the user are coherent and in-bounds at all times.
This software is not on Hackage yet - in the meantime you can find Haddock API documentation here and a tutorial blog post here.
N.B. This package is still under heavy development including API changes and should not be used in production code. Contributions, suggestions, and PRs are welcome.
- Install the LightGBM library
- Add the location of the 'lightgbm' executable to you PATH
- Install the Haskell 'stack' build tool
- Clone the HaskellGBM source code:
$ git clone https://github.com/dpkatz/HaskellGBM.git- Build HaskellGBM
$ stack setup
$ stack build
$ stack test