Remove remaining usages of the boston dataset.

dsgibbons / shap

A game theoretic approach to explain the output of any machine learning model.

https://shap-community.readthedocs.io/en/latest/

MIT License

25 stars 5 forks source link

Remove remaining usages of the boston dataset. #20

Closed simonangerbauer closed 1 year ago

simonangerbauer commented 1 year ago

There are a few remaining usages of the boston dataset in the tests that are not covered by #19.

As the california dataset is much bigger (20k samples) than the boston dataset (500 samples), I only used 500 samples of the california dataset to not increase test runtime too much (same as slundberg#2501).

Related to #4 and #8

dsgibbons commented 1 year ago

LGTM - thank you for your contribution!