vlachosgroup / nextorch Goto Github PK

View Code? Open in Web Editor NEW

44.0 6.0 10.0 49.23 MB

Experimental design and Bayesian optimization library in Python/PyTorch

Home Page: https://nextorch.readthedocs.io/en/latest/

License: MIT License

Python 100.00%

bayesian-optimization design-of-experiments experimental-design pytorch

nextorch's Introduction

NEXTorch

NEXTorch is an open-source software package in Python/PyTorch to faciliate experimental design using Bayesian Optimization (BO).

NEXTorch stands for Next EXperiment toolkit in PyTorch/BoTorch. It is also a library for learning the theory and implementation of Bayesian Optimization.

Documentation

See our documentation page for examples, equations used, and docstrings.

Developers

Yifan Wang ([email protected])
Tai-Ying (Chris) Chen

Dependencies

Python >= 3.7
PyTorch >= 1.8: Used for tensor operations with GPU and autograd support
GPyTorch >= 1.4: Used for training Gaussian Processes
BoTorch = 0.4.0: Used for providing Bayesian Optimization framework
Matplotlib: Used for generating plots
PyDOE2: Used for constructing experimental designs
Numpy: Used for vector and matrix operations
Scipy: Used for curve fitting
Pandas: Used to import data from Excel or CSV files
openpyxl: Used by Pandas to import Excel files
pytest: Used for unit tests

Getting Started

Install using pip (see documentation for full instructions):
```
pip install nextorch
```
Run the unit tests.
Read the documentation for tutorials and examples.

License

This project is licensed under the MIT License - see the LICENSE.md. file for details.

Contributing

If you have a suggestion or find a bug, please post to our Issues page on GitHub.

Questions

If you are having issues, please post to our Issues page on GitHub.

Funding

This material is based upon work supported by the Department of Energy's Office of Energy Efficient and Renewable Energy's Advanced Manufacturing Office under Award Number DE-EE0007888-9.5.

Acknowledgements

Jaynell Keely (Logo design)

Publications

Y. Wang, T.-Y. Chen, and D.G. Vlachos, NEXTorch: A Design and Bayesian Optimization Toolkit for Chemical Sciences and Engineering, J. Chem. Inf. Model. 2021, 61, 11, 5312–5319.

nextorch's People

Contributors

Stargazers

Watchers

Forkers

kirbybroderick brucelai yingli2009 passion4energy mehdishishehbor skip2mylou1 shigeyuki-matsunami hehalrow eric-verret trumanw

nextorch's Issues

I cannot import PFR_yield

Once I want to run your example in the supporting information of your paper, I cannot import PFR_yield. I also cannot install this package.

Time to upgrade to keep up with Ax

I tried to create a conda environment where Ax and nextorch could play together, but I am not so lucky.
I installed ax-platform first.

nextorch 0.4.0 requires botorch<=0.4.0, but you have botorch 0.9.5 which is incompatible.
nextorch 0.4.0 requires gpytorch<=1.4, but you have gpytorch 1.11 which is incompatible.

Please update nextorch to make that possible.

Heatmap and surface plots no longer working

Thank you for a great tool and this is probably something that is non-urgent as the core code still seems to work.

When trying to produce heat map and surface plots using the template I end up with a uniform value across all values:

I initially thought that there was a problem with my code, but when running one of your notebooks (10_PFR_mixed_type_inputs.ipynb) I see the exact same behaviour:

My assumption is that this is probably just a dependency issue. The optimal values still seem to be correct and so it doesn't seem to be a problem that affects the underlying data processing.

Does NEXTorch support inequality constraints?

Nice work on NEXTorch! Seems like a compelling idea, and some difficulty with implementing human-in-the-loop optimization via Ax is what led me here.

Something very important for my use-case is inequality constraints for composition-based Bayesian optimization (also prevalence-based, fractional-based, etc., i.e. everything needs to sum to 1). For example:

A + B + C <= 1

where A, B, and C are parameters to be optimized.

For me, there would technically also be D, the final parameter is determined automatically outside of the optimization loop via:

D = 1 - sum([A, B, C])

In other words, safe to ignore D, but relevant for the context of a composition-based optimization.

Is it possible to specify an inequality constraint within the current implementation of NEXTorch?