Skip to main content

Symbolic audit engine for divergence detection and structural analysis

Project description

Digamma Prime (digamma-ep)

Sistema simbólico para auditoria de modelos com métricas de divergência estrutural, temporal e algébrica.

Symbolic audit framework for comparing models, tracking divergence, and teaching algebraic structure.


📦 Instalação / Installation

pip install digamma-ep


#Basic Usage

from epe_maria import phi, delta_phi, phi_star

f = lambda x: x**2 + 2*x + 1
g = lambda x: x**2 + x + 1

print(phi(f, g))        # Divergência estrutural
print(delta_phi(f, g))  # Divergência de taxa
print(phi_star(f, g))   # Métrica de fusão

#Tests

pytest test_benchmark.py
pytest test_monitor.py

#Documentation
See examples and explanations in docs/ep_documentacao

#About
Created by Cerene Rúbio
License: MIT


# 🔮 Digamma Prime — Symbolic Model Auditing Framework

Digamma Prime is a symbolic framework for comparing machine learning models by their **behavior**, not just their outputs.

It introduces interpretable metrics like:

- **φ**  structural divergence  
- **Δφ**  rate divergence  
- **φ***  fusion metric  
- **drift**  directional bias  
- **curvature**  shape sensitivity

---

## 🚀 Features

- Symbolic comparison of models  
- CLI for drift detection and audits  
- Visual modules for φ and Δφ  
- Tutorials and case studies  
- Ready for CI/CD and dashboards

---

## 📚 Documentation

See the full docs in the `docs/` folder or at [GitHub Pages link once published].

---

## 🧪 Quickstart

```python
from epe_maria import phi, delta_phi
phi_val = phi(model_a.predict(X), model_b.predict(X))
🤝 Contributing
We welcome contributions in tutorials, metrics, automation, and visualizations. See docs/roadmap.md and docs/style_guide.md to get started.

🧠 Vision
Digamma Prime aims to become a universal symbolic standard for model auditing, drift detection, and interpretability.

![GitHub last commit](https://img.shields.io/github/last-commit/Cerene-Salt/Digamma-Prime-Framework)
![GitHub tag](https://img.shields.io/github/v/tag/Cerene-Salt/Digamma-Prime-Framework)
![License](https://img.shields.io/github/license/Cerene-Salt/Digamma-Prime-Framework)

![Python version](https://img.shields.io/badge/python-3.11+-blue)
![Build status](https://img.shields.io/github/actions/workflow/status/Cerene-Salt/Digamma-Prime-Framework/test.yml)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

digamma_prime-0.2.0.tar.gz (8.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

digamma_prime-0.2.0-py3-none-any.whl (10.4 kB view details)

Uploaded Python 3

File details

Details for the file digamma_prime-0.2.0.tar.gz.

File metadata

  • Download URL: digamma_prime-0.2.0.tar.gz
  • Upload date:
  • Size: 8.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for digamma_prime-0.2.0.tar.gz
Algorithm Hash digest
SHA256 a0a9da777267715c7c584eebd1b85e600ab86f56c53444712d70cb77454f2484
MD5 ecf6dcf15583cda45d6f9175ac1b3116
BLAKE2b-256 49e4897e0eeab2b91e1e440f2555b50ca1ce0c05f0d1b1ebc7b6414079113de1

See more details on using hashes here.

File details

Details for the file digamma_prime-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: digamma_prime-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 10.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for digamma_prime-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1e3df58ea6ee31010cc78b9fcade59b41fb1c09003919e447f07adccd5650fd6
MD5 ef0b397d0792a884f75851e5a7a4d354
BLAKE2b-256 95b583cac54506d0f4efbd7859663bfe71c7e0db70a171568809dd29f3ee06d2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page