Gabriel Araujo
Gabriel Araujo
Nice docs! A contributor made the changes here to adequate the main GA to the new api. I'll be looking further at the docs for new features or secondary details....
Cool bro, make a pull request if you wish or I change it later myself, no problem. cheers!
@jackngai Hey, sorry for the delay. Can you (or @nimasTT ) provide your Settings.py? Did you try another strategy, and did you check datasets chosen at Settings? cheers!
Nevermind, I got the same error with PPO strat. The error is on the strategy itself... I'm checking it later.
Candles can be fed via the http listener, or just wrote up in `candles` file, which is expected to by a 3d python array (batch, small number of sequential candles,...
Hey @sakirun, this project is extremely WIP and I don't reccomend it unless you're a hardcore researcher xD The gekko strat `neuraloader.js` and the indicator `nncandle.js` were really missing, added....
Thanks, I'll update in a while. Feel free to make PRs with this and/or more ideas, if you manage to understand the workings of this... I will tell in advance...
Each locale has its own population and its own slice of 30 days (with deltadays=30) of the evolution dataset. This is a multipopulation GA, here is some info: http://www.pohlheim.com/Papers/mpga_gal95/gal2_2.html
Oh yeah, that seems to be a bug on bayesian methods. `-b` is surely unstable because I never use it myself XD, might update a fix later.
Haa I see, at `settings/backtest.toml` we can change that, under `deltaDays`.