Metadata-Version: 2.1
Name: clique-ml
Version: 0.0.2
Summary: A selective ensemble for predictive models that tests new additions to prevent downgrades in performance.
Project-URL: Source, https://github.com/whitgroves/ensemble
Keywords: selective,ensemble,tensorflow,maching learning,cuda
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: joblib>=1.4.2
Requires-Dist: psutil>=6.1.0
Requires-Dist: pandas>=2.2.2
Requires-Dist: numpy>=1.26.4
Requires-Dist: scikit-learn>=1.5.2
Requires-Dist: typing_extensions>=4.12.2
Requires-Dist: tensorflow>=2.18.0

# ensemble
While working on the Kaggle competition, [Optiver - Trading at the Close](https://github.com/whitgroves/optiver-trading-at-the-close), I developed some code that I want to repackage here.

This code was written against CUDA 12.2 and not tested on other versions. Compatability was a hassle, so run `cuda-venv.sh` to setup the virtual environment instead of using `conda` or `pip`.
