Hi Adrien, thanks for reading the article. What I know is that the first graph shows the relative importance of features relative to y. The second graphs show the relative importance of the features of the DecisionTreeClassifier model.

If we take a look at the first graph, the relative importance of different features are not much different from one another. That might explain why the influence of the model can flip the relative ranks of these features.

But I am not exactly sure why the relative importance of features relative to y is different from the relative importance of the features of the DecisionTreeClassifier model.

Written by

Data scientist. I share a little bit of goodness every day through articles and daily data science tips: https://mathdatasimplified.com/

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store