search

Ekeany / Boruta-Shap

A Tree based feature selection tool which combines both the Boruta feature selection algorithm with shapley values.
MIT License
559 stars 86 forks source link

Handle missing values in histgradboost trees #123

Open cvraut opened 9 months ago

cvraut commented 9 months ago

What does this PR do?

Should address https://github.com/Ekeany/Boruta-Shap/issues/122

References

Testing performed

also fixed the actions workflow so that the tests run and can pass accounting for the HistogramGradientBoostingRegressor and HistogramGradientBoostingClassifier. I have also tested the changes against the code from the issue to verify that it works.

Known issues

HistogramGradientBoosting trees are not available in Python 3.6 so I had to include logic not to test them in that Python version.