evaluation tuning - where to start?

[maksimKorzh]

The problem with Python is, the regression will have to implement your evaluation function, so unless your engine is in Python, you'd have to call your code from Python. Therefore you might consider a C++ library such as mlpack (https://mlpack.org/), although implementing something yourself is not too hard, see for example: https://github.com/jdart1/arasan-chess/ ... /tuner.cpp (methods learn and adjust_params in particular).

I use Julia rather than Python (the popularity of Python has always been a mystery to me). Calling C++ code from Julia is completely trivial. Can't Python be used the same way? I thought one of Python's selling points was to be a nice high-level frontend for C and C++ code.

Of course it can the same way, that's why I consider it. Another reason is because python is the language I'm freelancing with.
Btw here are some reasons why python is so popular:
1. Probably the easiest language to pick up from scratch
2. An ability to do applied programming only jobs like web scraping
3. Implements numerous APIs to interact with business related stuff, e.g. CRLs
4. Probably the easiest web development ever possible (Flask)
5. Countless automation applications

[mar]

the popularity of Python has always been a mystery to me.
I thought one of Python's selling points was to be a nice high-level frontend for C and C++ code.

exactly my thoughts, probably the #1 most overrated scripting language of all time

[mar]

What would you suggest?

I've had great success with Texel tuning in the past with positions extracted solely from a self-play pgn (=no external factors involved)