Skip to content
This repository has been archived by the owner on Oct 12, 2021. It is now read-only.

Train with and without unbiasing procedure for unbalanced datasets #470

Closed
paxcema opened this issue Mar 24, 2021 · 1 comment
Closed

Train with and without unbiasing procedure for unbalanced datasets #470

paxcema opened this issue Mar 24, 2021 · 1 comment
Assignees
@paxcema
Labels
enhancement New feature or request

Comments

@paxcema
Copy link
Member

paxcema commented Mar 24, 2021

Long story short, all OpenML suite datasets where we perform worse than a constant predictor (i.e. always output the most popular class) are significantly improved if we set the equal_accuracy_for_all_output_categories to False.

As this option is still highly dependent on each particular use case, we might want to enable a grid search of sorts where we test both options in a single predictor, even if only for benchmarking/competition purposes. On the other hand, we could try adding an auto mode for the flag to enable and disable the unbiasing procedure automatically.
@paxcema paxcema added the enhancement New feature or request label Mar 24, 2021
@paxcema paxcema self-assigned this Mar 24, 2021
@paxcema
Copy link
Member Author

paxcema commented May 3, 2021

Closed by #501

@paxcema paxcema closed this as completed May 3, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees

@paxcema paxcema

Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@paxcema