You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem? Please describe.
In my dataset, certain columns of certain rows (as opposed to the entire column) have invalid values. Currently I'm not sure how to solve it.
Describe the solution you'd like
We can pass in an optional mask dataframe with a similar format to how pytorch's own transformers handle masking tokens such as padding.
Describe alternatives you've considered
I considered just removing the rows or replacing them with a fixed value. It's probably not ideal but it somewhat works.
Additional context
I don't know if this is possible yet, so I'm mostly asking a question here. If it's not planned I might be able to help out on this. I imagine the implementation might be relatively easy for the transformer- / attention-based models.
The text was updated successfully, but these errors were encountered:
@Aceticia Sorry for the late response. Been tied up with many other engagements.. So, currently there is no way to use a mask in attention based models. At least not with the current API in PyTorch Tabular.
But out of curiosity, why isn't it ideal to just drop the invalid rows? is it because of some temporal nature of the data?
I understand. The reason I'm interested in this function is that I have a small table where most of the rows contain a small number of invalid values. Simply dropping the rows results in an approximately 75% fewer rows. If you think it's something that can be included in the official API, I'll be happy to discuss ways I can contribute to make this feature available.
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
Is your feature request related to a problem? Please describe.
In my dataset, certain columns of certain rows (as opposed to the entire column) have invalid values. Currently I'm not sure how to solve it.
Describe the solution you'd like
We can pass in an optional mask dataframe with a similar format to how pytorch's own transformers handle masking tokens such as padding.
Describe alternatives you've considered
I considered just removing the rows or replacing them with a fixed value. It's probably not ideal but it somewhat works.
Additional context
I don't know if this is possible yet, so I'm mostly asking a question here. If it's not planned I might be able to help out on this. I imagine the implementation might be relatively easy for the transformer- / attention-based models.
The text was updated successfully, but these errors were encountered: