[docs] clarify that custom eval functions are not only used on training data #5011
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Continues #5002.
Fixes #4759.
The intent of changes proposed in #4759 was to clarify that in
lgb.train()
andlgb.cv()
, theDataset
passed to custom evaluation functions isn't always "the training data", but that instead it can be either the training data or a validation set.This PR clarifies that in a few additional places. I found those places like this:
git grep 'Customized evaluation function'
As of this PR, the documentation on custom evaluation functions would be identical and not say "the training data" for
cv()
,train()
, andBooster.eval()
.I think that it's ok for
Booster.eval_train()
to say "the training dataset" and forBooster.eval_valid()
to say "the validation dataset", since those are specific to those contexts.