whitebeam is a python module for decision trees without the use of sklearn and SciPy
| docs | |
| test |   |
| package |      |
The project was started in 2020 by Kieran Molloy as a coursework component for SCC461 at Lancaster University
whitebeam requires:
- Python (>= 3.6)
- NumPy (>= 1.14)
- Cython (>= 0.29.21)
- joblib (>= 1.0.0)
If you already have a working directory, the easiest installation is via pip
pip install whitebeam
However it is advisable to install within a virtual environment
virtualenv venv
venv/bin/activate
pip install whitebeam
There will soon be more detailed installation instructions in the docs.
See the changelog for a history of notable changes to whitebeam
Development is planned to be ongoing however this may change due to university requirements.
Installing from source requires python-dev which can be installed using
sudo apt-get install python3-dev
then cloning this repo, installing requirements and building which is handled by poetry
git clone https://github.com/K-Molloy/whitebeam
pip install -r requirements.txt
python setup.py build_ext --inplace
again, it is advisable to use a virtual environment.
After installation, the test suite can be launched from outside the source directory ( although pytest >= 5.01 must be installed)
pytest whitebeam