Glyph: Symbolic Regression Tools

Markus Quade; Julien Gout; Markus Abel

doi:10.5334/jors.192

Abstract

We present Glyph – a Python package for genetic programming based symbolic regression. Glyph is designed for usage in numerical simulations as well as real world experiments. For experimentalists, glyph-remote provides a separation of tasks: a ZeroMQ interface splits the genetic programming optimization task from the evaluation of an experimental (or numerical) run. Glyph can be accessed at https://github.com/Ambrosys/glyph. Domain experts are able to employ symbolic regression in their experiments with ease, even if they are not expert programmers. The reuse potential is kept high by a generic interface design. Glyph is available on PyPI and Github.

Funding statement: This work has been partially supported by the German Science Foundation via SFB 880. MQ was supported by a fellowship within the FITweltweit program of the German Academic Exchange Service (DAAD).

References

Schmidt, M and Lipson, H “Distilling Free-Form Natural Laws from Experimental Data”. In: Science, 324(5923): 81–85. Apr. 2009. DOI: 10.1126/science.1165893
Open DOI Search in Google Scholar Back to article
Koza, J R Genetic programming: On the programming of computers by means of natural selection, 1. MIT press, 1992.
Search in Google Scholar Back to article
Vladislavleva, E, et al. “Predicting the energy output of wind farms based on weather data: Important variables and their correlation”. In: Re-newable Energy, 50: 236–243. Feb. 2013. DOI: 10.1016/j.renene.2012.06.036
Open DOI Search in Google Scholar Back to article
Quade, M, et al. “Prediction of dynamical systems by symbolic regression”. In: Physical Review E, 94(1). July 2016. DOI: 10.1103/PhysRevE.94.012214
Open DOI Search in Google Scholar Back to article
Gout, J, et al. “Synchronization control of oscillator networks using symbolic regression”. In: Nonlinear Dyn, 91(2): 1001–1021. Nov. 2017. DOI: 10.1007/s11071-017-3925-z
Open DOI Search in Google Scholar Back to article
Duriez, T, Brunton, S L and Noack, B R Machine Learning Control – Taming Nonlinear Dynamics and Turbulence. Springer International Publishing, 2017. DOI: 10.1007/978-3-319-40624-4
Open DOI Search in Google Scholar Back to article
Schmidt, M D, et al. “Automated refinement and inference of analytical models for metabolic networks”. In: Physical Biology, 8(5). Aug. 2011. DOI: 10.1088/1478-3975/8/5/055011
Open DOI Search in Google Scholar Back to article
Schmidt, M and Lipson, H “Age-Fitness Pareto Optimization”. In: Genetic Programming Theory and Practice VIII, 129–146. New York: Springer, Oct. 2010. DOI: 10.1007/978-1-4419-7747-2_8
Open DOI Search in Google Scholar Back to article
La Cava, W, Danai, K and Spector, L “Inference of compact nonlinear dynamic models by epigenetic local search”. In: Engineering Applications of Artificial Intelligence, 55: 292–306. Oct. 2016. DOI: 10.1016/j.engappai.2016.07.004
Open DOI Search in Google Scholar Back to article
Galvan-Lopez, E “Efficient graph-based genetic programming representation with multiple outputs”. In: International Journal of Automation and Computing, 5(1): 81–89. Jan. 2008. DOI: 10.1007/s11633-008-0081-4
Open DOI Search in Google Scholar Back to article
Akgul, F ZeroMQ. Packt Publishing, 2013.
Search in Google Scholar Back to article
Ecma International. “The JSON Data Interchange Format”. In: Standard ECMA-404, 9(2013).
Search in Google Scholar Back to article
Jorke, G, Lampe, B and Wengel, N Arithmetische Algorithmen der Mikrorechentechnik. Verlag Technik, 1989.
Search in Google Scholar Back to article
Lorenz, E N “Deterministic Nonperiodic Flow”. In: Journal of the At-mospheric Sciences, 20(2): 130–141. 1963. DOI: 10.1175/1520-0469(1963)020<;0130:DNF>2.0.CO;2
Open DOI Search in Google Scholar Back to article
MachineLearningControl. OpenMLC-Python. Aug. 2017. URL: https://github.com/MachineLearningControl/OpenMLC-Python.
Search in Google Scholar Back to article
De Rainville, F-M, et al. “DEAP”. In: ACM SIGEVOlution, 6(2): 17–26. (Feb. 2014). DOI: 10.1145/2597453.2597455
Open DOI Search in Google Scholar Back to article

Glyph: Symbolic Regression Tools

Abstract

Paradigm

My account