[breaking] Remove the predictor param, allow fallback to prediction using DMatrix.
#9129
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
trivialfis
force-pushed
the
inplace-predict-dmatrix
branch
from
60b8a75
to
edba724
Compare
const. Allow inplace predict in skl. remove configuration. Revert "remove configuration." This reverts commit 3b47048. Dispatch create DMatrix. Device name. Dispatch based on booster context. cleanup. Document. Restart removing predictor param. Fix cpu compilation. Use context. Remove workaround. Remove test. Lint. Remove old test. Add note. Add test. fix cuda inplace predict checks. Fix test pickling. Revert changes.
trivialfis
force-pushed
the
inplace-predict-dmatrix
branch
from
d2ce7b1
to
a93b80d
Compare
trivialfis
changed the title
predictor param, allow fallback to prediction using DMatrix.predictor param, allow fallback to prediction using DMatrix.
RAMitchell
approved these changes
Jul 3, 2023
1 task
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
This lowers the fallback from the sklearn interface directly to C++ gbtree. The fallback logic is clearer: when devices don't match. Along with this, the
predictorparameter will be removed, and the predictor used inside xgboost will be decided solely by the booster context.DeviceOrdstruct is implemented to indicate the device. It will eventually replace thegpu_idparameter.predictorparameter is removed.DMatrixwheninplace_predictis not available.Some of the code hasn't been updated yet, including the jupyter notebook for GPU SHAP and the benchmarking code in GPUTreesshap. I will update them once the
deviceparameter is in place.