backtest_ml()

Sun-73

Hi there,

The new function backtest_ml() implemented in the example: "Machine Learning with a Voting Classifier" is a great way of getting a fast feedback from a given model.

Is it possible to use it with multiple datasets (for example, using "futures" and "commodity" data, as done in the template: "Futures - IMF Commodity") ?

Thank you!

support

@sun-73 thanks, sure, please let us a little bit of time to prepare an example with these specifications!

Sun-73

@support Many thanks! An example would be very much appreciated!

cortezkwan

@support Hi,
I tried to replicate the "Machine Learning with a Voting Classifier" example on strategy notebook, but I got the error message: "AttributeError: module 'qnt.backtester' has no attribute 'backtest_ml'".

support

@cortezkwan

Just update the library, it will be enough.

Conda:
You can see the latest version of library here: https://anaconda.org/quantiacs-source/qnt/files
This command will update the package in the current environment.

conda install 'quantiacs-source::qnt>=0.0.255'

Pip:
If you use pip, just reinstall the package from github:

pip install --force-reinstall git+git://github.com/quantiacs/toolbox.git

support

@sun-73 Hello, finally it is here:

https://github.com/quantiacs/strategy-ml-predict-BTC-use-IMF/blob/master/strategy.ipynb

Soon in the templates once we add some more text

Sun-73

@support Great! This route opens new possibilities in terms of model design. Thanks a lot!