Metadata-Version: 2.4
Name: modnn
Version: 2.0.1
Summary: Physics-Informed Modularized Neural Network for Building Energy Modeling
Author-email: Zixin Jiang <zjiang19@syr.edu>
License-Expression: MIT
Requires-Python: >=3.7
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: torch
Requires-Dist: pandas
Requires-Dist: matplotlib
Requires-Dist: seaborn
Requires-Dist: scikit-learn
Requires-Dist: tqdm
Dynamic: license-file

# ModNN

**ModNN** is a Modularized Physics-Informed Neural Network for building energy modeling.

It incorporates with physics-informed model structure, loss function, and model constraints.

---

## 🚀 Installation

You can install the package using pip:

pip install modnn



## 🧠 Example
Please find the online Jupyter notebook for a step-by-step instruction:
https://colab.research.google.com/drive/1A2jt1q53RtxGuaoym6N1PmlKELDPpYFX?usp=sharing


## 🧠 Update log
To further improve physics consistency, 
I replaced heattransfer module by energy balance equations, start from version 2.0.0


## 🧪 Requirements

    Python 3.7+

    PyTorch

    NumPy

    Pandas

    Matplotlib

    Seaborn

    scikit-learn

    tqdm

---
📬 License

MIT License

🙋‍♂️ Author

Zixin Jiang: 
zjiang19@syr.edu
