Question about Methodology

[pford221]

Thanks for making your code available and for the interesting paper. I have a quick question about the experimental design in the paper. When adding the four-type feature (e.g. rare, safe, etc.), was that done for each training set in the cross-validation procedure separately or done once for the full dataset? Thank you!

[FayKong]

Dear Patrick,

Thanks for reaching out and sorry for the late reply. I recently found there is a mistake in our code (I have used the label in the test set as known information, which is not correct) and I will update the code later this month or early next month. In the new version I am working on, the four-type feature (e.g. rare, safe, etc.), was that done for each training set in the cross-validation procedure separately.

Best wishes,

Fay

On Sun, 27 Feb 2022 at 01:15, Patrick Ford @.***> wrote:

Thanks for making your code available and for the interesting paper. I have a quick question about the experimental design in the paper. When adding the four-type feature (e.g. rare, safe, etc.), was that done for each training set in the cross-validation procedure separately or done once for the full dataset? Thank you!

— Reply to this email directly, view it on GitHub https://github.com/FayKong/PPSN2020/issues/1, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQA55RDDYHJ55ESP5NDT6PLU5FUJ3ANCNFSM5PN4OBCA . Triage notifications on the go with GitHub Mobile for iOS https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675 or Android https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub.

You are receiving this because you are subscribed to this thread.Message ID: @.***>

[FayKong]

Dear Mark,

Thanks for reaching out. Sorry for making this unclear, you need to first run "chess_resampling.py", the train and test are from the validation procedure. I will update the code early next month and will make this clear...

Best wishes,

Fay

On Tue, 14 Jun 2022 at 08:24, Mark Caple @.***> wrote:

I like the idea of your work. One question, you have changed chess_LOF_plot.py in February to now reference "train" and "test" but I cannot see how you calculate these. Is there another file that needs to be updated? Thanks

— Reply to this email directly, view it on GitHub https://github.com/FayKong/PPSN2020/issues/1#issuecomment-1154766294, or unsubscribe https://github.com/notifications/unsubscribe-auth/AQA55RBPJM25FNL5YULN2O3VPAQQFANCNFSM5PN4OBCA . You are receiving this because you are subscribed to this thread.Message ID: @.***>