mlte: Machine Learning Test and Evaluation

mlte (pronounced "melt") is a framework and infrastructure for machine learning evaluation.

Getting Started

mlte is available on PyPI. Install the latest version with:

$ pip install mlte-python

You can go to our getting started page to see details on setting up and running MLTE. After that, you can head to our guide on using MLTE for next steps. If you just want to know how to use the package in an existing project, check out our MLTE Mechanics guide. If you're interested in reading about the project more generally, see our documentation.

Citing This Work

If you're interested in learning more about this work, you can read our paper. While not required, it is highly encouraged and greatly appreciated if you cite our paper when you use MLTE for academic research.

@INPROCEEDINGS{10173876,
  author={Maffey, Katherine R. and Dotterrer, Kyle and Niemann, Jennifer and Cruickshank, Iain and Lewis, Grace A. and Kästner, Christian},
  booktitle={2023 IEEE/ACM 45th International Conference on Software Engineering: New Ideas and Emerging Results (ICSE-NIER)}, 
  title={MLTEing Models: Negotiating, Evaluating, and Documenting Model and System Qualities}, 
  year={2023},
  volume={},
  number={},
  pages={31-36},
  keywords={Measurement;Machine learning;Production;Organizations;Software;Stakeholders;Software engineering;machine learning;test and evaluation;machine learning evaluation;responsible AI},
  doi={10.1109/ICSE-NIER58687.2023.00012}
}