Metadata-Version: 2.4
Name: pyruleanalyzer
Version: 1.1.0
Author: GrupoCybersegurancaVirtus
License-Expression: MIT
Project-URL: Homepage, https://github.com/GrupoCybersegurancaVirtus/pyruleanalyzer
Project-URL: Documentation, https://grupocybersegurancavirtus.github.io/pyruleanalyzer/
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn
Requires-Dist: matplotlib
Provides-Extra: docs
Requires-Dist: sphinx; extra == "docs"
Requires-Dist: sphinx-autobuild; extra == "docs"
Requires-Dist: sphinx_rtd_theme; extra == "docs"
Requires-Dist: sphinxcontrib-bibtex; extra == "docs"
Dynamic: license-file

# PyRuleAnalyzer

PyRuleAnalyzer is a Python-based tool designed to support rule extraction, analysis, and simplification from decision tree and random forest models. It provides a comprehensive pipeline to generate interpretable models, remove redundancies, and evaluate model accuracy and interpretability.

Key functionalities include:

- Extracting decision rules from Random Forests and Decision Trees.

- Identifying and removing redundant and duplicate rules.

- Evaluating initial and simplified models through classification accuracy, confusion matrices, and interpretability metrics.

- Computing sparsity and interpretability scores to assess model complexity and understandability.

For guides on installation and usage refer to the documentation on https://grupocybersegurancavirtus.github.io/pyruleanalyzer/
