Metadata-Version: 2.4
Name: scikit-bayes
Version: 1.3.0
Summary: Bayesian network classifiers (AnDE, AnJE, ALR, TAN, KDB, mixed Naive Bayes) for scikit-learn.
Author-email: Pablo Torrijos <pablo.torrijos@uclm.es>
Project-URL: Homepage, https://github.com/ptorrijos99/scikit-bayes
Project-URL: Documentation, https://ptorrijos99.github.io/scikit-bayes/
Project-URL: Changelog, https://github.com/ptorrijos99/scikit-bayes/blob/main/CHANGELOG.md
Project-URL: Issues, https://github.com/ptorrijos99/scikit-bayes/issues
Keywords: bayesian network classifiers,naive bayes,aode,ande,tan,kdb,scikit-learn,machine learning
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: License :: OSI Approved :: BSD License
Classifier: Operating System :: POSIX
Classifier: Operating System :: Unix
Classifier: Operating System :: MacOS
Classifier: Operating System :: Microsoft :: Windows
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy>=1.23.5
Requires-Dist: scipy>=1.9.3
Requires-Dist: scikit-learn>=1.6
Requires-Dist: joblib>=1.2.0
Requires-Dist: numba>=0.58.1
Provides-Extra: experiments
Requires-Dist: pyyaml>=6.0; extra == "experiments"
Requires-Dist: liac-arff>=2.5; extra == "experiments"
Requires-Dist: xgboost>=2.0.0; extra == "experiments"
Requires-Dist: lightgbm>=4.0.0; extra == "experiments"
Requires-Dist: py-cpuinfo>=9.0.0; extra == "experiments"
Dynamic: license-file

# scikit-bayes

[![tests](https://github.com/ptorrijos99/scikit-bayes/actions/workflows/python-app.yml/badge.svg)](https://github.com/ptorrijos99/scikit-bayes/actions/workflows/python-app.yml)
[![codecov](https://codecov.io/gh/ptorrijos99/scikit-bayes/graph/badge.svg)](https://codecov.io/gh/ptorrijos99/scikit-bayes)
[![doc](https://github.com/ptorrijos99/scikit-bayes/actions/workflows/deploy-gh-pages.yml/badge.svg)](https://ptorrijos99.github.io/scikit-bayes/)
[![Python](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
[![License](https://img.shields.io/badge/license-BSD--3--Clause-green.svg)](LICENSE)

**scikit-bayes** is a Python package that extends `scikit-learn` with a suite of Bayesian Network Classifiers.

The primary goal of this package is to provide robust, `scikit-learn`-compatible implementations of advanced Bayesian classifiers that are not available in the core library.

## Key Features

- **MixedNB**: Naive Bayes for mixed data types (Gaussian + Categorical + Bernoulli) in a single model
- **AnDE**: Averaged n-Dependence Estimators (AODE, A2DE) that relax the independence assumption, pooled with the arithmetic or the geometric mean
- **WeightedAnDE**: AnDE with discriminative weights, one per component or one per factor of each component (weighted CCBN), at four levels of granularity, fitted jointly or one component at a time (the AnDE<sup>w</sup> of FedAnDE)
- **AnJE and ALR**: Averaged n-Join Estimators and Accelerated Logistic Regression, as defined by Zaidi et al. (2016), with the training protocol of the paper by default
- **GaussianAnJE and GaussianALR**: AnJE and ALR built on the factors of the SPnDEs, so that continuous attributes keep Gaussian conditionals as in HAODE
- **TAN**: Tree Augmented Naive Bayes, a tree of attribute dependencies learned with the Chow-Liu procedure
- **KDB**: K-Dependence Bayesian classifier, in which every attribute has at most k attribute parents chosen by conditional mutual information
- **Full scikit-learn API**: Compatible with pipelines, cross-validation, and grid search

## Quick Start

```python
import numpy as np
from skbn import MixedNB, AnDE

# MixedNB: Handle mixed data types automatically
X = np.array([[1.5, 0, 2], [-0.5, 1, 0], [2.1, 1, 1], [-1.2, 0, 2]])
y = np.array([0, 1, 1, 0])

clf = MixedNB()
clf.fit(X, y)
print(clf.predict([[0.5, 1, 1]]))  # Automatically handles Gaussian, Bernoulli, Categorical

# AnDE: Solve problems Naive Bayes cannot (XOR)
X_xor = np.array([[-1, -1], [-1, 1], [1, -1], [1, 1]])
y_xor = np.array([0, 1, 1, 0])

clf = AnDE(n_dependence=1, n_bins=2)
clf.fit(X_xor, y_xor)
print(clf.predict(X_xor))  # [0, 1, 1, 0] ✓
```

## Installation

```bash
pip install scikit-bayes
```

Or install from source:

```bash
pip install git+https://github.com/ptorrijos99/scikit-bayes.git
```

## Documentation

- 📖 [User Guide](https://ptorrijos99.github.io/scikit-bayes/user_guide.html) - Detailed documentation
- 📚 [API Reference](https://ptorrijos99.github.io/scikit-bayes/api.html) - Complete API docs
- 🎨 [Examples Gallery](https://ptorrijos99.github.io/scikit-bayes/auto_examples/index.html) - Visual examples

## Development

This project uses [pixi](https://pixi.sh) for environment management.

```bash
# Run tests
pixi run test

# Run linter
pixi run lint

# Build documentation
pixi run build-doc

# Activate development environment
pixi shell -e dev
```

## Citation

If you use scikit-bayes in a scientific publication, please cite:

```bibtex
@software{scikit_bayes,
  author = {Torrijos, Pablo and Alcarria Laserna, {\'O}scar and G{\'a}mez, Jos{\'e} A. and Puerta, Jos{\'e} M.},
  title = {scikit-bayes: Bayesian Network Classifiers for Python},
  year = {2026},
  url = {https://github.com/ptorrijos99/scikit-bayes}
}
```

The same information is in [`CITATION.cff`](CITATION.cff), which GitHub shows as "Cite this repository".

## References

- Webb, G. I., Boughton, J., & Wang, Z. (2005). *Not so naive Bayes: Aggregating one-dependence estimators*. Machine Learning, 58(1), 5-24.
- Flores, M. J., Gámez, J. A., Martínez, A. M., & Puerta, J. M. (2009). *GAODE and HAODE: Two proposals based on AODE to deal with continuous variables*. ICML '09, 313-320.
- Zaidi, N. A., Webb, G. I., Carman, M. J., Petitjean, F., & Cerquides, J. (2016). *ALR^n: Accelerated higher-order logistic regression*. Machine Learning, 104(2-3), 151-194.
- Zaidi, N. A., Webb, G. I., Carman, M. J., Petitjean, F., Buntine, W., Hynes, M., & De Sterck, H. (2017). *Efficient parameter learning of Bayesian network classifiers*. Machine Learning, 106(9-10), 1289-1329.

## License

BSD-3-Clause. See [LICENSE](LICENSE) for details.
