New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Bug: Kfold partitioning agreement #57

Open

andykrause opened this issue Sep 30, 2019 · 0 comments

Assignees

Labels

bug

Milestone

Owner

andykrause commented Sep 30, 2019

Currently, when using RT data as validation set, the KFold process for non-RT data (hedonic, for example) does not properly sample.

This is because for each RT observation, there are two observations in the Hed data.

Possible solution: Just hold out the second transaction in the RT pair?

Does that bias toward beginning of the observations

Possible solution: Serially holdout observations such that each KFold is valid?

Needs some thought

andykrause self-assigned this

andykrause added the bug label

andykrause added this to the Version 0.4.0 milestone

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment