Differential equation modeling in Pymc

[matsuo_basho]

I’m up to chapter 16 of McElreath’s Statistical Rethinking. I’m on the last example that models hare and lynx populations using differential equations. I haven’t been able to find a Python version of the code:

pymc-devs/pymc-resources/blob/main/Rethinking_2/Chp_16.ipynb

The above stops at problems that come earlier in the chapter.

I do see R versions that replicate what he does:

16 Generalized Linear Madness | Statistical rethinking with brms, ggplot2,...

I’ve found a tutorial and notebook here so that may be the answer:

Including Partial Differential Equations in Your PyMC3 Model by Ivan Yashchuk

Talk Abstract This tutorial will demonstrate use of PyMC3 for PDE-based inverse problems. We will infer parameters of a simple continuum mechanics model but the demonstrated tools can be readily applied to other complex PDE-based models. Talk [Including Partial Differential Equations in Your PyMC Model (Ivan Yashchuk)] Ivan Yashchuk Ivan Yashchuk has 3 years’ experience in computational mechanics and scientific computing with occasional contributions to OSS projects. He received…

https://ivanyashchuk.github.io/fenics_pymccon2020/

However, the above is even more complex than what I’m trying to understand. I’m trying to take it one step at a time and want to just understand if there is a straightforward way in PyMC to build the hare-link differential equation population models as per the book?

Thanks

[aseyboldt]

That’s for Partial Differential Equations. If all you have is an ODE, you might want to look here: GitHub - pymc-devs/sunode: Solve ODEs fast, with support for PyMC