Skip to content

Latest commit

 

History

History
103 lines (50 loc) · 4.29 KB

README.md

File metadata and controls

103 lines (50 loc) · 4.29 KB
Raw

Playing with Runge-Kutta methods and SageMath.

To use the code, you must install SageMath.

The goal of this code is to verify different properties of a given Runge--Kutta method, defined by it's Butcher array (all the notions used here are defined in the Bible, see below).

  • With SageMath, it is possible to make exact computations in somme usefull sets of numbers, and thus we make the hypothesis that the coefficients of the methods live in the set of (real) algebraic numbers (called AA in SageMath); this is not a really restrictive hypothesis. But then, the result obtained are proofs (if my codes and SageMath are both correct!).

  • To compute the order of a Runge-Kutta method, one use the so called rooted trees for which we have a SageMath implementation, coded by Florent Hivert.

  • We also provide a function to compute the Butcher array of a method defined by collocation. A classical application is the set of Gaussian Runge-Kutta methods.

Some sage/jupyter notebooks are provided: they probably provide the best way to learn and to test this code (even, you can run the notebooks on binder, see below).

References:

  • To learn about Ordinary Differential Equations solvers, you should read the Bible:
  1. Solving Ordinary Differential Equations I, by Hairer, Nørsett,, Wanner (HNW),
  2. Solving Ordinary Differential Equations II Stiff and Differential-Algebraic Problems by Hairer and Wanner (HW),
  3. Geometric Numerical Integration by Hairer, Lubich and Wanner (HLW).

If you want to learn and to understand rooted trees and B-series, I recommend to start first by reading reference 3.. Being the latest book, things have become much easier to understand than in reference 1.

  • If you want to learn SageMath, you can read the book Mathematical Computation with Sage (which now is available in French, English and German), and for which freely available pdf files can be downloaded here and there.

Using the code

  • First, you must define a Runge--Kutta method. To do this you must write a (simple) python class: have a look at one of the "*.sage" files in methods/.

This class must derive from "RungeKutta" class and include a constructor.

The constructor must:

  • Define the arrays A and B of the Butcher array (the C part is not necessary).

  • Give a title.

  • Call the base RungeKutta class contructor.

Remember that the "*.sage" files in methods/ give examples of such classes.

Be carefull: The coefficients of A and B must be algebraic numbers (AA or QQbar) or rational numbers (QQ).

  • Then, the best is to look at the notebook Example1.ipynb. For this, launch sage like this:

>sage -n jupyter

and launch the notebook Exemple1.ipynb.

Gaussian formulas (and other methods obtained be collocation)

Gausian formulae with n steps are obtained by collocation at the roots of the Legendre P polynomials of degree n, shifted from [-1,1] to [0,1].

RKcolloc.colloc computes the Butcher arrays, given collocation points in [0,1] and returns a Runge-Kutta method class (note that collocation points are not necessary Gaussian points).

See the notebook Gaussian.ipynb.

Notebooks

All are Sage/Jupyter notebooks. Launch Sage by typing:

sage -n jupyter

  1. Example.ipynb : a tour of the system.

  2. Gaussian.ipynb: construct and test some of the Gauss methods.

  3. AllProperties.ipynb: show how to compute all possible properties of a method.

  4. Test.ipynb : just testing that everything works fine on a set of formulas.

  5. RadauByCollocation.ipynb : Radau methods are collocation methods. Play with this.

Runing the notebooks on Binder

Just Click me.

otherwise, if it does not work, read "Dockerfile".

Implementation:

  • The code uses a decorator @_persistance to avoid recomputing known properties (which is often expensive).

A precedent version was using Sage's @lazy_attribute decorator, which could be disturbing.