DOC Better UG for calibration #16175
Conversation
|
Now ready for reviews @adrinjalali @qinhanmin2014 @thomasjpfan @glemaitre (when reviewing, checking the rendered UG docs might be easier than looking at the diff) |
Co-Authored-By: Guillaume Lemaitre <[email protected]>
|
The failure is due to the fact that the reference added is not present in the text. I think this is better as you did now but you could reference the article at the right position this could be great. |
|
|
||
| .. topic:: References: | ||
|
|
||
| * Obtaining calibrated probability estimates from decision trees | ||
| and naive Bayesian classifiers, B. Zadrozny & C. Elkan, ICML 2001 |
There was a problem hiding this comment.
I removed it because I didn't see any relevant place where to link to this ref. I don't think we use the techniques described in this paper anywhere in the code, so adding it is just noise.
side note, @glemaitre suggested to unify the refs using the .. [X] blahblah format, and when using this format, all refs need to be linked to, otherwise our CI complains.
Co-Authored-By: Roman Yurchak <[email protected]>
|
Thanks for the reviews @glemaitre @rth , is this good to go? (I'd like to get it merged so I can review #16167 more easily) CI failure is unrelated |
|
Merging thanks @NicolasHug ! |
This PR updates the UG to: