Feature Importance by Tree Ensemble Learner

Sometimes you want to see which factors are influencing the most. One very typical way is to use random forest and feature extract so lets see that in KNIME.

I first got to know how to use this Tree Ensemble learner to extract feature importance from this KNIME forum.

https://forum.knime.com/t/how-to-get-the-variable-importance-from-the-random-forest-model/8613/3

and I been using the Math Formula from the example in the forum. I really like how the KNIME community is helping each other do the KNIME things.

So, after the Math formula you get a result like this with importance score.

You can weight the score according to the depth level if you wish to. Just modify the math formula from the example to fit your needs.

I tend to do this but also see if PLS works and if it does, see if the features are contributing in positively or negatively.