@multi_byte-wildebeest Hi. Without an example, it's unclear what the problem might be.

If you use a state and a function that returns the prediction for one day, you will not get correct results with precheck.

This was discussed here: https://quantiacs.com/community/topic/555/access-previous-weights/18

@sun-73 it should be ok

@captain-nidoran Hello, please try to add in a cell at the beginning:

pip install 'sklearn==0.0.post1'

or in the init file:

! apt update && apt install -y libgomp1 && rm -rf /var/lib/apt/lists/*

Best regards

@commanderangle Dear commanderangle,

If you use ML in your strategy but not select that option we can't guarantee for how your strategy will be evaluated and it could be filtered out.

Regards

@alphastar Sorry for the issue, it has been fixed.

@support It's working now, thanks!

@support Ohh, I understand. Thank you for your support.

@magenta-kabuto We support only Python 3.7 right now. But it can coexist with Python 3.9:

https://quantiacs.com/documentation/en/user_guide/local_development.html

Basically you can use Python 3.7 inside a conda environment.

@antinomy

I got it !
Thanks a lot !!

@alexeigor Hello. Version 0.0.501 of the qnt library works correctly in Colab. Python version support has been extended from 3.10 to 3.13. The basic functionality of the library should work without issues.

To install, use the following command:

Note: Installing ta-lib in Colab is not working for me at the moment.

@vyacheslav_b perfect. It wasnt obvious to me that single pass was meant by that. Thank you

@vyacheslav_b Thank you so much

@antinomy thanks!

@wool-dewgong Hello! We added one template which should address your issue and allow you to perform a rolling fast ML training with retraining. It is available in your user space in the Examples section and you can read it here also in the public docs:

https://quantiacs.com/documentation/en/examples/machine_learning_with_a_voting_classifier.html

@vyacheslav_b Thank you so much

@support
oh I see now what you mean.
15 strategies PER USER are selected.
At first, I thought you were only going to select 15 strategies total for all users.
Thanks.

@vyacheslav_b Thank you so much

@support Yes, I can load now the stocks data. Thank you once again!

@support I have done that twice before my post, but now F_RY looks fine. There are several directories with scripts and notebooks I use with qnt, so maybe I deleted the wrong data-cache before...
Thanks for fixing the data!

@xiaolan That is correct, but the logic can be easily re-used. The only novel element will be the introduction of the liquidity filter at intermediate stages/at the final stage for the selection of the weights.