Add support for white-box explainers to alibi-explain runtime

[ascillitoe]

Summary

This PR adds support for the sklearn API white-box explainers (TreeShap, TreePartialDependence, PartialDependenceVariance) to the AlibiExplainRuntime.

Implementation details

• New runtime: Support is implemented via the new AlibiExplainSKLearnAPIRuntime subclass. For the remaining white-box explainers two further subclassed runtimes will be required (one being the IntegratedGradientsWrapper). See the notion doc for more details.

• Tests: Some explainer's have various "nitty-gritty" details wrt to serving, for example the target kwarg for IntegratedGradients, calling fit with no data for TreeShap, and black-box/white-box mode of PartialDependenceVariance being determined by type(predictor). Therefore, the PR is proposing to perform an E2E test (test_end_2_end) on every explainer (with relevant parametrisation such as testing uri vs init_param's based loading). This would provide more confidence that all explainers can actually be served. However, it will increase the number of tests being run somewhat, so needs discussion...

TODO

• Linting etc
• Docs (leave until all white box explainers supported...)
• Add tests to check loading of all supported tree models e.g. lightgbm models etc - done in afae1e6

[adriangonz]

This is a great PR @ascillitoe !!

I love the test thoroughness - the more tests the better IMO (as long as they are not massively slow!). Added a few comments here-and-there, but they are mainly questions and suggestions - nothing biggie.

[adriangonz]

Nice one @ascillitoe! Thanks for making those changes.

Once the linter passes, this looks good to go from my side! Conscious it's still marked as a draft though, so happy to re-review once you think it's ready.

[ascillitoe]

Thanks @adriangonz, I'll make the linter changes now and turn off draft once done!