SymINDy
SymINDy copied to clipboard
andreikitaitsev
Symbolic Identification of Non-linear Dynamics. The method generalizes the SINDy algorithm by combining sparse and genetic-programming-based symbolic regression.
Instead of feeding in equations, can I feed in a set of raw data to pysindy so it can return estimate equations to me? I tested the following system: >...
The user shall be able to input istimedependent=True, so that the regression is performed also using the time measurements as part of the regression. Strogatz docet.
As done in Miles Cranmer's library: [SymbolicRegression.jl](https://github.com/MilesCranmer/SymbolicRegression.jl) At that point, reconstruct something like: xdot = - k x + A sin(omega sqrt(x))
To make the package more accessible to the user, we want to publish a simple user guide article showing standard use cases of the package.
See [here](https://github.com/TezRomacH/python-package-template). Regardless of this choice, GitHub actions checking the unit tests and the pre-commit, among other things, are needed.
Using Scoop in a manner described at DEAP page does not work. Error message: *ImportError: cannot import name 'Iterable' from 'collections' (C:\Users\AndreiKitaitsev\AppData\Local\Programs\Python\Python310\lib\collections\__init__.py) toolbox, creator, history = _create_toolbox(pset, ntrees, max_depth=self.max_depth) File...
Can we also do something with divergence? Gradient? Do we need measurements in space as well to compute the partials with finite difference? In this way we can have a...
It could be nice to show the evolution of the value of the linear coefficients as a function of the number of observations, now associated to the sampling rate, I...
https://github.com/ahmedfgad/GeneticAlgorithmPython
Metadata
Owner
Metadata
Symbolic Identification of Non-linear Dynamics. The method generalizes the SINDy algorithm by combining sparse and genetic-programming-based symbolic regression.