Metadata-Version: 2.4
Name: ayurvaidya
Version: 0.1.0
Summary: Multi-system medical treatment recommendation using XGBoost — bridges traditional and modern medicine
Author-email: Sahil Kundu <sahil03kundu@gmail.com>
License: MIT
Project-URL: Homepage, https://github.com/sahil03kundu-code/AyurVaidya
Project-URL: Repository, https://github.com/sahil03kundu-code/AyurVaidya
Project-URL: Bug Tracker, https://github.com/sahil03kundu-code/AyurVaidya/issues
Project-URL: Model Card, https://huggingface.co/sahil03kundu/ayurvaidya-xgboost
Project-URL: Dataset, https://www.kaggle.com/datasets/sahil03kundu/ayurvaidya-medical-treatment-dataset
Keywords: ayurveda,medicine,healthcare,xgboost,treatment-recommendation,traditional-medicine,machine-learning,classification
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: Intended Audience :: Healthcare Industry
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.8
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: xgboost>=1.7.0
Requires-Dist: numpy>=1.21.0
Requires-Dist: pandas>=1.3.0
Requires-Dist: huggingface-hub>=0.14.0
Dynamic: license-file

# AyurVaidya

**Multi-system medical treatment recommendation using XGBoost.**

Recommends treatments across 10 medical traditions — Allopathic, Ayurveda, TCM, Siddha, Unani, Kampo, Korean TM, African TM, Naturopathic, and Integrative medicine — using a 66-feature clinical profile.

## Installation

```bash
pip install ayurvaidya
```

## Quick Start

```python
from ayurvaidya import AyurVaidya

# Loads the model from Hugging Face Hub automatically
model = AyurVaidya()

# Predict with a 66-feature vector
result = model.predict(your_features)
print(result)  # e.g. "Ayurveda"

# Get probabilities for all 10 systems
probs = model.predict_proba(your_features)
print(probs)  # {"African TM": 0.02, "Allopathic": 0.15, "Ayurveda": 0.45, ...}
```

## Performance

| Metric | Score |
|--------|-------|
| Accuracy | 88.47% |
| Weighted F1 | 0.88 |
| Weighted Precision | 0.89 |
| Weighted Recall | 0.88 |

## Links

- [GitHub](https://github.com/sahil03kundu-code/AyurVaidya)
- [Model Card (Hugging Face)](https://huggingface.co/sahil03kundu/ayurvaidya-xgboost)
- [Dataset (Kaggle)](https://www.kaggle.com/datasets/sahil03kundu/ayurvaidya-medical-treatment-dataset)

## Important

This is a **research tool** trained on synthetic data. It is **NOT** intended for clinical decision-making without proper validation and regulatory approval.

## License

MIT
