BookmarkSubscribeRSS Feed
Pritish
Quartz | Level 8

Hi All, 

I wanted to get some idea on how I can force eminer decision tree to iteratively try variables (300+) in a dataset and recommend / find the most optimal split based on user specified criteria. 

1 REPLY 1
M_Maldonado
Barite | Level 11

Hi Pritish,

Are you using SAS Enterprise Miner?

If I understand well, you don't want to create a decision tree model, but rather to determine the optimal split on each of your 300+ variables?

 

If the end goal is optimal binning using a decision tree, you can do that using the Transform node with option set to optimal binning.

 

If you are doing something else, you need to create a macro that calls proc arbor passing one variable at a time.

Give it a try creating your macro, happy to help if you have questions.

 

Arbor doc in case it helps:    http://support.sas.com/documentation/onlinedoc/miner/em43/allproc.pdf

 

Good luck,

M

Ready to join fellow brilliant minds for the SAS Hackathon?

Build your skills. Make connections. Enjoy creative freedom. Maybe change the world. Registration is now open through August 30th. Visit the SAS Hackathon homepage.

Register today!
How to choose a machine learning algorithm

Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 847 views
  • 0 likes
  • 2 in conversation