Metadata-Version: 2.4
Name: vv4ml
Version: 1.0.5
Summary: A solid verification and validation python library for ml models
Author-email: Cristiano Epifania <c.epifania5@studenti.uniba.it>
Classifier: Programming Language :: Python :: 3.14
Classifier: Operating System :: OS Independent
Requires-Python: >=3.12
Description-Content-Type: text/markdown
Requires-Dist: catboost>=1.2.10
Requires-Dist: ipykernel>=7.3.0
Requires-Dist: mlflow-skinny>=3.12.0
Requires-Dist: numpy>=2.4.4
Requires-Dist: pandas>=3.0.2
Requires-Dist: pydantic>=2.13.3
Requires-Dist: pydantic-yaml>=1.6.0
Requires-Dist: scikit-learn>=1.8.0
Requires-Dist: xgboost>=3.2.0

<h1 align="center">
    <img src="https://raw.githubusercontent.com/collab-uniba/vv4ml/refs/heads/main/logo/vv4ml-logo-icon.png" width="350" alt="logo">
</h1><br>

![Python Version](https://img.shields.io/badge/dynamic/toml?url=https%3A%2F%2Fraw.githubusercontent.com%2Fcollab-uniba%2Fvv4ml%2Fmain%2Fpyproject.toml&query=%24.project.requires-python&style=for-the-badge&label=py_ver)
![Project Version](https://img.shields.io/badge/dynamic/toml?url=https%3A%2F%2Fraw.githubusercontent.com%2Fcollab-uniba%2Fvv4ml%2Fmain%2Fpyproject.toml&query=%24.project.version&style=for-the-badge&label=COLLAB&labelColor=yellow&color=%23284169)

**vv4ml** is the verification and validation library for your machine learning models and
simulations. vv4ml is particular useful for predictors in medical systems.

It offers tools for performing tests that assess credibility.

In particular:

- Fundamental verification tests: that's to say `convergence`, `smoothness` and `numerical error` test) which handle the credibility of your model
- A useful Latin hypercube sampling method: it has available a `base` and `maximin` optimization method
- Different metrics: `MeanRelativeError`, `MeanAbsoluteError`, `MaximumRelativeError`, `MaximumAbsoluteError`
- YAML parser and loader: a convenient configuration file parser and loader for your model card document
- `Pydantic` models: most of the project is Pydantic structured whose models are validated at runtime

## Get started

Refer to the [Read the Docs guide here](https://vv4ml.readthedocs.io/en/latest/) where you will find everything you need.

For a general overlook check the [index](https://github.com/collab-uniba/vv4ml/blob/main/docs/index.md).

For a quick try look at the [Jupyter notebook](https://github.com/collab-uniba/vv4ml/blob/main/vv4ml_quickstart.ipynb).

## Install

See the [installation page](https://github.com/collab-uniba/vv4ml/blob/main/docs/install.md) for further information.

You can quickly install vv4ml with:
```bash
pip install vv4ml
```

## Contributing

TBA

## License

TBA
