Consider extending the GridSearchCV class in order to include warm start (when available) and preprocessing?

Question

Consider extending the GridSearchCV class in order to include warm start (when available) and preprocessing?

Closed this issue 8 years ago · 2 comments

This could solve the 'RangeScaler' issue and the fact that no warm-start strategy is implemented.

Answer 1 · 2017-02-16T13:22:50.000Z

I found a main issue of sklearn scikit-learn/scikit-learn#1674
in which they discuss the possibility to add a warm-start strategy to GridSearchCV.

It doesn't seem to be clear on how structure a GridSearchCV with warm-start strategy, mainly because of how GridSearchCV is implemented, its parallel jobs and so on.

Answer 2 · 2017-03-15T08:15:58.000Z

See also this scikit-learn/scikit-learn#1626
It is not clear on how to implement it.

I close this since this is not an issue of PALLADIO, which is independent on the estimator used.