optimizations across many columns #28091
celestinoxp
started this conversation in
Ideas
Replies: 1 comment 1 reply
-
There is field in which modeling have ill-posed problem where the number of features is much larger than the number of columns: neuroimaging, EEG and MEG data, bioinformatics with gene data. You might want to have a look how people are handling this the issue (I think that they use simple model with regularization on the top). |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
With some data engineering my dataset was a little out of the "normal"... 3000 columns and 2500 rows!
While we are waiting for the final version of scikit-learn 1.4, I would like to know if anyone can take a look at this scenario, taking into account that if you remove a column the accuracy may drop, in other words, scikit-learn was good be "prepared" for datasets like mine... the idea is to explore new "scenarios"... large datasets (with many columns not rows)! I hope this makes sense to someone...
Beta Was this translation helpful? Give feedback.
All reactions