Calculation of feature relative importance from XG Boost Regression Tree


Is there any way to calculate the feature relative importance from the XG Boost Learner (Regression) in knime?


Hi @Astha,

we currently only have a component to calculate the feature importance for classifications (not for regressions): Global Feature Importance Component
You can find an example workflow how to use the component here: Compute and Visualize Global Feature Importance Metrics
You could try to adapt it to regression yourself or you could wait a little bit as we are also planning to create such a component for regression soon.

Kind regards,


This topic was automatically closed 182 days after the last reply. New replies are no longer allowed.