Nikolay Nikitin

We refactored the requirements in the current master version to make it compatible Python 3.9. Is it works for you now? The release with this updates is coming soon.

"Importance Cut off" feature selection effectiventess also can be analysed

@https://github.com/graceyangfan We did not plan to design the features by GA itself. However, we use existing feature generators like poly_features and tune it's hyperparameters during evolution and tuning.

Ok, it's yours :-) Feel free to ask questions.

>Progress bar is for GPComposer.compose_pipeline() Yes, it is. However, you can also try to implement it in the lower level - GPOptimizer, if necessary. See https://github.com/nccr-itmo/FEDOT/blob/master/fedot/core/optimisers/gp_comp/gp_optimiser.py and https://github.com/nccr-itmo/FEDOT/blob/master/fedot/core/optimisers/gp_comp/param_free_gp_optimiser.py This optimizer...

Several changed were proposed in https://github.com/nccr-itmo/FEDOT/pull/481, so the issue is still can be considered as actual.

Сейчас для работы с графами используется библиотека networkx, мб в ней есть готовая функция для этого.

@andreygetmanov pls check is it still actual

6. ~Необходимость явного deepcopy для моделей и нод, чтобы обеспечить актуальность кэша~ 7. ~Неочевидные флаги обучения и кэширования в нодах и стратегиях.~

10. Рефакторинг CRUD-операций над цепочками