Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[dask] Add shap tests. #6575

Merged
merged 9 commits into from
Jan 8, 2021
Merged

[dask] Add shap tests. #6575

merged 9 commits into from
Jan 8, 2021

Conversation

trivialfis
Copy link
Member

@trivialfis trivialfis commented Jan 6, 2021

  • Add tests for contribution and interaction.
    * Add test for IO. Moved to Support _estimator_type. #6582
  • Move mypy from github action file to makefile for easier local testing.

Related: #6568 .

I haven't been able to reproduce the particular error on referenced issue with cleanly trained model. Will keep it open for now.

@trivialfis trivialfis requested a review from hcho3 January 6, 2021 09:23
@codecov-io
Copy link

codecov-io commented Jan 6, 2021

Codecov Report

Merging #6575 (9e5a72d) into master (f5ff90c) will increase coverage by 0.02%.
The diff coverage is n/a.

Impacted file tree graph

@@            Coverage Diff             @@
##           master    #6575      +/-   ##
==========================================
+ Coverage   80.21%   80.23%   +0.02%     
==========================================
  Files          13       13              
  Lines        3609     3613       +4     
==========================================
+ Hits         2895     2899       +4     
  Misses        714      714              
Impacted Files Coverage Δ
python-package/xgboost/training.py 95.32% <0.00%> (-0.39%) ⬇️
python-package/xgboost/core.py 81.28% <0.00%> (+0.12%) ⬆️

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update f5ff90c...9e5a72d. Read the comment docs.

@hcho3
Copy link
Collaborator

hcho3 commented Jan 6, 2021

I'm assuming that Dask sklearn doesn't support pred_contribs?

@trivialfis
Copy link
Member Author

The skl API doesn't support contrib. Dask interface is just aligning with it.

@pseudotensor
Copy link
Contributor

pseudotensor commented Jan 6, 2021

The skl API doesn't support contrib. Dask interface is just aligning with it.

Ya, but it's super trivial to add support, it's a bug in my view that it's not supported. It's literally just about adding arguments to predict and predict_proba and just passing that along in the existing lean wrapper.

@trivialfis
Copy link
Member Author

Ya, but it's super trivial to add support, it's a bug in my view that it's not supported. It's literally just about adding arguments to predict and predict_proba and just passing that along in the existing lean wrapper.

We are making good progress I think.

@trivialfis trivialfis merged commit 96d3d32 into dmlc:master Jan 8, 2021
@trivialfis trivialfis deleted the dask-shap branch January 8, 2021 06:59
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants