Miles Cranmer

(`options.complexity_mapping.constant_complexity` is by default 1, but you could re-define it with `complexity_of_constants=...` passed to PySR)

Hi @nice-mon, My recommendation for this, if you do know a common functional form, is to define this as a new feature. e.g., set x4=x0*exp(sin(x2)) before passing it. The other...

Do you have git installed? Also, note that your Julia version is not available for M1 so there will likely be other issues. You should install the 1.8 version here:...

Maybe try running this: ```bash export JULIA_SSL_CA_ROOTS_PATH="" ``` before running the install?

One other thing you could try to get it working directly on your M1 is to manually clone the SymbolicRegression.jl github repository: https://github.com/MilesCranmer/SymbolicRegression.jl, and then specify the folder it is...

What specific part of their paper are you referring to? [for reference, their paper is my favorite all-time :) ]

Good idea. I was thinking about adding this but haven't yet. Would be really interesting to try. The fact that the backend of PySR is written in Julia makes this...

Great question. Two notes: - For loading external Julia libraries, you need to manually call a few Julia functions. See example below. - `besselj` actually assumes non-negative inputs. PySR assumes...

besselj seems to be really slow for large inputs (I guess that's a property of bessel functions?). Therefore, you could instead clip the inputs to the range [0, 5] so...

As a side note, I think I should just make all the `SpecialFunctions.jl` functions available by default in PySR, since it has a lot of useful functions. What do you...