-
-
Notifications
You must be signed in to change notification settings - Fork 90
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.
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
default_target_attribute missing in data 40992 #669
Comments
And: Do we really want to allow uploading of tasks if the target is not specified? If yes, I have to make a fix in the R package. |
In my perception, default target attribute has always been a mandatory field. (Apparently I am wrong on this: But I wouldn't mind making it mandatory, let's discuss (there are some complications due to multi-target tasks) |
+1 for making it mandatory, @mfeurer , @joaquinvanschoren do you guys see any disadvantages here? |
What would you do for completely unsupervised data? Besides that, I do not really have an opinion on this. |
Ok, for specific tasks where a target is required (classification, regression) etc. it should be mandatory. For unsupervised stuff it could be left out? |
No, clustering datasets do not have a target feature...
On Mon, 19 Mar 2018 at 16:00 Giuseppe Casalicchio ***@***.***> wrote:
Ok, for specific tasks where a target is required (classification,
regression) etc. it should be mandatory. For unsupervised stuff it could be
left out.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#669 (comment)>, or mute
the thread
<https://github.com/notifications/unsubscribe-auth/ABpQVzeLCSRx-2kR14ZM6P9v9GaTrpmqks5tf8gdgaJpZM4Sv2sn>
.
--
Thank you,
Joaquin
|
Hi,
according to openml/openml-r#412 the target feature was not specified for data set here https://www.openml.org/d/40992 . We deactivated the V1 but V2 now does not provide the target. Could this be fixed in V2 or do we have to upload V3?
The text was updated successfully, but these errors were encountered: