-
This is a problem with both SymbolicRegression.jl and PySR - parameters are mixed in terms of using snake_case vs camelCase (vs PascalCase, for some symbols). In 0.9.0, this will be fixed: types/const…
-
Please consider updating the compatibility requirement for the `SymbolicUtils` package, to v0.19, given the current one is really out of date.
-
cc @AlCap23
I've noticed many times during training that equations are overly complex, so I think simplification isn't working for some reason. I narrowed it down to this:
https://github.com/Mile…
-
The default settings as used in PySR should also be used in SymbolicRegression, so that pure-Julia users can access the same defaults as the Python users.
Also see the discussion here: https://gith…
-
Thought of a couple of improvements to the loss function.
1. The complexity frequencies should be a moving count, rather than summed over the entire search. This is because a new expression may be …
-
Cross post with https://github.com/MilesCranmer/PySR/issues/116
It seems like there are some very rare edge cases where a domain error will occur. For the vast majority of instances, an Inf or Nan …
-
I am posting this here since I am encountering the same issue myself. Here are the issues in FromFile.jl and Documenter.jl
https://github.com/Roger-luo/FromFile.jl/issues/41
https://github.com/Jul…
-
It seems like there are still some domain errors in very rare edge cases (~one in a billion!). This is the traceback:
```julia
nested task error: TaskFailedException
Stacktrace:
[1] w…
-
I'd like to benchmark this library against other ones, and one of the natural metrics would be the total number of evaluations (summing ovet iterations, cores, etc.) . Is there a flag (combination) th…
-
I was wondering if there is a way to turn off automatic simplification? Perhaps there is something like #340 set up, also discussed in #327? cc @shashi @ChrisRackauckas @AlCap23
For example:
```ju…