Building models with SAS Enterprise Miner, SAS Factory Miner, SAS Visual Data Mining and Machine Learning or just with programming

random forest

Reply
Occasional Contributor
Posts: 6

random forest

Hi,

 


Is it possible to know which variables are most important at Random Forest  and how they are selected ?

 

thanks

 

moshe

 

 

 

Super User
Posts: 9,681

Re: random forest

Use Decision Tree PROC HPSPLIT . and Check the documentation, there is already an example to do this .

Example 61.5: Assessing Variable Importance


proc hpsplit data=MBE_Data maxdepth=6;
class Usable Dopant;
model Usable = gTemp aTemp Rot Dopant;
prune none;
run;


Occasional Contributor
Posts: 6

Re: random forest

Thanks ,

Is there a mathematical description of how the explanatory variables selected,

 

Moshe

Super User
Posts: 9,681

Re: random forest

Yes. Check documentation. Like entropy .....
SAS Employee
Posts: 122

Re: random forest

[ Edited ]
Hi, Here is sample code to turn on VI in HPFOREST (please see attached .sas code) There is a section "Measure variable importance" that covers the details on the subject including all the math details. VI is sensitive to split method selected. Hope this helps. Jason Xin
Attachment
SAS Employee
Posts: 122

Re: random forest

Sorry, my previous post had the format of the sample code messed up. Attached is the sample .sas program for the variable importance option. Thanks. Jason Xin
Attachment
Ask a Question
Discussion stats
  • 5 replies
  • 435 views
  • 0 likes
  • 3 in conversation