Too few features are selected

[ql257]

Hi, I tried to run controlburn.classifier on a dataset that has 62301 rows, and 1208 features, but it only outputs 2 features when I set alpha = 0.05. When I tried smaller alpha values like 0.005 or 0.0005, it raised an error "SolverError: Solver 'ECOS_BB' failed. Try another solver, or solve with verbose=True for more information.".

Thank you for reviewing the issue!

[brianliu12437]

Hi, try re-installing an updated version of ControlBurn from https://pypi.org/project/ControlBurn/0.1.2/ with an improved solver.
Also please check how many features are used by the original forests, either by accessing cb.forest or by running the lasso step with alpha = 0. If a few features are highly informative, the ensemble building step in ControlBurn may terminate after very few iterations.

Thanks,
Brian