christophM / interpretable-ml-book

Book about interpretable machine learning
https://christophm.github.io/interpretable-ml-book/
Other
4.73k stars 1.05k forks source link

Typo in advantages for decision trees #297

Closed AllegraChen closed 2 years ago

AllegraChen commented 2 years ago

I think that it should be minimum instead of maximum in the following line, right?

https://github.com/christophM/interpretable-ml-book/blob/a2efaca7032477e336162a2b3ae5b6af41564560/manuscript/04.5-interpretable-tree.Rmd#L139

A (binary) tree with a depth of three can take seven features at maximum.

christophM commented 2 years ago

Minimum would be one feature, as the same feature could have been chosen by the tree 3 times. And the maximum is 3 features if in the path to the terminal node 3 times a different feature was selected