Decision Tree

funnyhat

Hi, there.

I am a beginner of RM 5, I met a very strange thing in decision tree. my data have 468 examples, 5 regular attributes (gender, weight , length etc),2 special (one for id , one for label (true, false)), around 70 of them are true, when i try to use decision tree ,  only a false label shows, nothing else,  but the log said successfully, however if i test the golf or iris data, the results are correct.  I have no missing value.  anyone have any idea about it? is it possible related to impossible to make a cutoff?

Thanks

land

Hi,
this might be true, yes. The RapidMiner Decision tree performs two ways of pruning the tree: Before and after making splits. Might be it stops to early or prunes the tree back to the root. You should deactivate the pruning to test if the tree grows
If yes, you could play around with the pruning related parameters to prevent pruning from cutting the hole tree.

Greetings,
  Sebastian