BookmarkSubscribeRSS Feed
frupaul
Quartz | Level 8

Hi everyone,

I successfully created a score code (by writing out codes) in SAS enterprise Guide to help me cluster the levels of a variable - Region.

 

I have used the code editor in SAS Enterprise miner to score Region. It has been scored successfully as shown in attachment.

 

When I connect another node to the SAS code node, the new variable created from scoring isnt part of the output from the SAS code node. Can someone please look at the attachment and advise me on any necessary adjustment that will make the new scored variable visible to preceeding nodes?

Thanks,

 

Paul


cap1.JPG
3 REPLIES 3
DavidPope
SAS Employee

The new variable should be available to nodes attached after the scode node not to nodes attached proceeding to node.

Q: Why are you taking clustering code from Enterprise Guide and using it within a code node in SAS EM instead of using the clustering node within EM?

frupaul
Quartz | Level 8

Hi David,

I have checked attacked a statexplore node to the sas code node and after running it, obtained the output attached below. The new variable is not in it. I have also checked if the new variable was created by clicking the ellipse button of the export data property of the sas code node. Still this just confirms the new variable wasnt created

 

As for your second question, I have read your documentations and asked experts on this forum and concluded that SAS Enterprise Miner's cluster node does not have a property to enable it cluster the levels of categorical variables using the Greenacre's methods. Hence why I used Greenacre's clustering algorithm on SAS enterprise Guide, built my score codes and scored the categorical variables on Enterprise miner.

 


show1.JPG
DavidPope
SAS Employee

Figured you had a reason for doing the clustering outside of EM.

Have you looked into the export variables and import variables as part of the EM node's properties? 

 

sas-innovate-2024.png

Join us for SAS Innovate April 16-19 at the Aria in Las Vegas. Bring the team and save big with our group pricing for a limited time only.

Pre-conference courses and tutorials are filling up fast and are always a sellout. Register today to reserve your seat.

 

Register now!

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
  • 3 replies
  • 1511 views
  • 0 likes
  • 2 in conversation