Christoph Molnar

This is indeed an issue in the Metrics package then. Did you open an issue there?

Do you mean FeatureEffect or FeatureEffects? For FeatureEffects there should be an option ncol

I can't reproduce the problem. When I run your example, the importance is zero.

Could you try if you still have this problem with the latest iml version from github? `remotes:::install_github("christophM/iml")`

What would you use as a prediction in the case of survival analysis? Do you have a quick proof of concept using a custom predict.fun for Predictor$new()?

Thanks for this pull request. The tests don't run through, it seems that now the Shapley values don't add up to the difference in the test, as the should.

It does add up, but only in expectation, meaning that when you increase the sample.size in Shapley$new, you will get closer to the difference. The test for Shapley to add...

This line ```r mod

Thanks for reporting this. Error message is: ``` Error in estimate_feature_imp(feature, data.sample = data.sample, y = y, : task 1 failed - "no applicable method for 'predict' applied to an...

This is a bigger decision to make and would mean bigger changes to the iml package. Would love to discuss it with you. If we would decide to go down...