model-metrics

Pre-release

This release is a pre-release and may not be stable for production use.

Welcome to Model Metrics! Model Metrics is a versatile Python library designed to streamline the evaluation and interpretation of machine learning models. It provides a robust framework for generating predictions, computing model metrics, analyzing feature importance, and visualizing results. Whether you're working with SHAP values, model coefficients, confusion matrices, ROC curves, precision-recall plots, and other key performance indicators.

Prerequisites

Before you install model_metrics, ensure your system meets the following requirements:

Python: Version 3.8 or higher.

Additionally, model_metrics depends on the following packages, which will be automatically installed when you install model_metrics:

matplotlib: version 3.5.3 or higher, but capped below 3.11
matplotlib-venn: version 1.0.0 or higher, but capped at 1.1.2
numpy: version 1.21.6 or higher, but capped below 2.2
pandas: version 1.3.5 or higher, but capped below 2.3
plotly: version 5.18.0 or higher, but capped below 5.25
scikit-learn: version 1.0.2 or higher
scipy: version 1.7.3 or higher
statsmodels: version 0.13 or higher, but capped below 0.15
shap: version 0.41.0 or higher, but capped below 0.53
tqdm: version 4.66.4 or higher

💾 Installation

To install model_metrics, simply run the following command in your terminal:

pip install model_metrics

📄 Official Documentation

https://lshpaner.github.io/model_metrics_docs

🌐 Authors' Website(s)

Leon Shpaner

🙏 Acknowledgements

Gratitude goes to Dr. Ebrahim Tarshizi for his mentorship during the University of San Diego M.S. Applied Data Science Program, as well as the Shiley-Marcos School of Engineering for its support.

Special thanks to Dr. Alex Bui, and to Panayiotis Petousis, PhD, and Arthur Funnell for their invaluable guidance and their exceptional teamwork in maintaining a strong data science infrastructure at UCLA CTSI. Their leadership and support have helped foster the kind of collaborative environment that makes work like this possible. Additional thanks to all who offered guidance and encouragement throughout the development of this library. This project reflects a shared commitment to knowledge sharing, teamwork, and advancing model evaluation practices.

⚖️ License

model_metrics is distributed under the MIT License. See LICENSE for more information.

⚓ Support

If you have any questions or issues with model_metrics, please open an issue on this GitHub repository.

📚 Citing `model_metrics`

If you use model_metrics in your research or projects, please consider citing it.

@software{shpaner_2025_14879819,
  author       = {Shpaner, Leonid and Funnell, Arthur},
  title        = {Model Metrics},
  month        = feb,
  year         = 2025,
  publisher    = {Zenodo},
  version      = {0.0.6a6},
  doi          = {10.5281/zenodo.14879819},
  url          = {https://doi.org/10.5281/zenodo.14879819}
}

Release files for model-metrics 0.0.6a6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for model-metrics 0.0.6a6
File	Size	Uploaded
model_metrics-0.0.6a6.tar.gz	117.5 kB	Sep 14, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for model-metrics 0.0.6a6
File	Interpreter	ABI	Platform	Reset
model_metrics-0.0.6a6-py3-none-any.whl 119.0 kB Sep 14, 2026	Python 3	none	any	Details

Total release size: 236.5 kB

Release files / model_metrics-0.0.6a6.tar.gz

Download URL	model_metrics-0.0.6a6.tar.gz
Size	117.5 kB
Tags	Source
SHA-256 checksum How to use checksums	`28f21fd63604bde9c44b69ec6ebf104a8f0d0370cffbdbf80cce7110426e4c3e`
BLAKE2b-256 checksum How to use checksums	`06ed6c20bbd7ab7e72e1e5196962b89f3563db13d3fd4d7bacedc6f612f63687`
Upload date	Sep 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.14.7`

Release files / model_metrics-0.0.6a6-py3-none-any.whl

Download URL	model_metrics-0.0.6a6-py3-none-any.whl
Size	119.0 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`6adac2d1c33eecf735266b63230c9bb78cc9c011cbfd2d6e7de256d7fa4558a7`
BLAKE2b-256 checksum How to use checksums	`f9ea9c96f0aeb22e6a94e41897806be3644408cf7bd1a68a1f5d8130c7f12095`
Upload date	Sep 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.14.7`