Metadata-Version: 2.1
Name: elusight
Version: 1.0.0
Summary: EluSight - Chromatographic Decision Intelligence Framework
Author-email: SubhraC-prog <subhrac@example.com>
License: MIT
Project-URL: Homepage, https://github.com/SubhraC-prog/EluSight
Project-URL: Repository, https://github.com/SubhraC-prog/EluSight.git
Project-URL: Issues, https://github.com/SubhraC-prog/EluSight/issues
Keywords: chromatography,hplc,optimization,machine-learning,decision-intelligence,aqbd
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Operating System :: OS Independent
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy<2.0.0,>=1.24.0
Requires-Dist: scipy<2.0.0,>=1.10.0
Requires-Dist: pandas<3.0.0,>=2.0.0
Requires-Dist: pydantic<3.0.0,>=2.0.0
Requires-Dist: scikit-learn<2.0.0,>=1.3.0
Requires-Dist: shap<1.0.0,>=0.42.0
Requires-Dist: matplotlib<4.0.0,>=3.7.0
Requires-Dist: seaborn<1.0.0,>=0.12.0
Requires-Dist: plotly<6.0.0,>=5.17.0
Requires-Dist: streamlit<2.0.0,>=1.25.0
Requires-Dist: fastapi<1.0.0,>=0.100.0
Requires-Dist: uvicorn<1.0.0,>=0.23.0
Requires-Dist: requests<3.0.0,>=2.31.0
Requires-Dist: sqlalchemy<3.0.0,>=2.0.0
Requires-Dist: pyarrow<15.0.0,>=12.0.0
Requires-Dist: tqdm<5.0.0,>=4.65.0
Requires-Dist: pyyaml<7.0,>=6.0
Requires-Dist: python-dotenv<2.0.0,>=1.0.0
Provides-Extra: dev
Requires-Dist: pytest<8.0.0,>=7.4.0; extra == "dev"
Requires-Dist: pytest-cov<5.0.0,>=4.1.0; extra == "dev"
Requires-Dist: black<24.0.0,>=23.0.0; extra == "dev"
Requires-Dist: ruff<1.0.0,>=0.0.280; extra == "dev"
Requires-Dist: mypy<2.0.0,>=1.4.0; extra == "dev"

# 🔬 EluSight – Chromatographic Decision Intelligence Framework

[![Python](https://img.shields.io/badge/python-3.11+-blue.svg)](https://python.org)
[![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
[![Tests](https://img.shields.io/badge/tests-passing-brightgreen.svg)]()

**EluSight** converts chromatographic optimization outputs into **explainable, trustworthy, and visual decision intelligence**.

> Not just *what works* — but **why it works, how reliable it is, and what risks exist**.

---

## 🎯 What EluSight Does

Traditional tools → *“Best method = X”*
EluSight → *“X is best because…”*

* ✅ Scientific reasoning
* ✅ Trust score (0–100)
* ✅ Risk & robustness analysis
* ✅ Tradeoff insights (Pareto)
* ✅ Feature importance (SHAP)
* ✅ Automatic visualizations

---

## 📊 Key Outputs

### 🔹 Trust Score

```json
{
  "overall_score": 87.3,
  "recommendation": "Strongly Recommend"
}
```

### 🔹 Scientific Reasoning

* Constraint satisfaction with margins
* Robustness probability
* Risk (co-elution, failure)
* Expert alignment

### 🔹 Visualizations (Auto-generated)

* Correlation heatmap
* Feature importance
* SHAP summary
* Partial dependence
* Parallel coordinates
* Radar chart

---

## ⚙️ Core Engines

| Engine                | Purpose              |
| --------------------- | -------------------- |
| Constraint Engine     | AQbD evaluation      |
| Robustness Engine     | Sensitivity analysis |
| Risk Engine           | Failure probability  |
| Tradeoff Engine       | Pareto analysis      |
| Explainability Engine | SHAP insights        |
| Trust Engine          | Final scoring        |
| Visualization Engine  | Auto plots           |

---

## 🔌 Supported Inputs

* Bayesian Optimization
* NSGA-II / Genetic Algorithms
* Optuna / ML pipelines
* DryLab / AQbD DoE
* Any CSV / JSON dataset

---

## 🚀 Installation

```bash
pip install elusight
```

---

## 📦 Quick Example

```python
from elusight import Ingestor, TrustEngine
from elusight.constraints import ConstraintEngine

methods = Ingestor.from_csv("results.csv")

constraints = {
    "resolution": {"type": "minimum", "value": 2.0}
}

report = ConstraintEngine(constraints).evaluate(methods[0])
trust = TrustEngine().compute_trust(
    method_id=methods[0].method_id,
    constraint_report=report
)

print(trust.overall_score)
```

---

## 📁 Output Structure

```
elusight_outputs/
├── correlation_heatmap.png
├── feature_importance.png
├── shap_summary.png
├── parallel_coordinates.png
├── radar_chart.png
├── report.md
├── report.html
└── report.json
```

---

## 💡 Use Cases

* Pharmaceutical method development (ICH Q14)
* QC validation & transfer
* Regulatory submissions
* High-throughput screening

---

## 🧪 Testing

```bash
pytest tests/ -v
```

---

## 📚 Scientific Basis

* ICH Q14 – Method Development
* ICH Q9 – Risk Management
* AQbD principles
* Multi-objective optimization

---

## 📞 Support

* GitHub: https://github.com/SubhraC-prog/EluSight
* Issues: Bug reports & features

---

## 📄 License

MIT License

---

### 🔬 Philosophy

> Scientists need **confidence, evidence, and reasoning** — not just results.
