0
$\begingroup$

data set

I have to decide for which value of "Klasse"

How do i do it?

I know that I have to decide on maximum information gain

So first off I've calculated the entropy of "Klasse"

That is E(Klasse)= -(3/11*log(3/11)+3/11*log(3/11)+5/11*log(5/11)) = 1.067

So how do I proceed from that?

I now need to find the first decision node, yes?

And how do I proceed if I've found a decision node ?

Thanks

$\endgroup$
  • $\begingroup$ What's your optimization goal? Minimal depth, minimal size or something else? There are many decision trees which produce the same result. A trivial tree has "Animiert" at the root node, "Einfach" as both child nodes of the root node, etcetera. $\endgroup$ – MSalters Jan 20 at 11:28
  • $\begingroup$ Had to do it with maximum inforrmation gain so Entropies Now I have calculated each entropy for the next decision and decided for the one with the least entrrropy $\endgroup$ – Rapiz Jan 20 at 18:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.