Processing by Group in Enterprise Miner

[JeffN]

I have a proc reg that I run in EG. In that proc reg, I use a BY statement to generate coefficient estimates that are used to score additional data.  That proc reg runs very quickly either in EM (in a code node) or EG. I want to replicate that functionality in EM so I can compare that model to other models in EM. When I try and replicate that process using Start Groups & End Groups, the amount of time required to loop through my Stratas is prohibitive (read as ridiculously slowwwww). Is there another way to run by processing in EM?

Thanks,

Jeff 

[WendyCzika]

I'm sorry to hear the group processing is so slow - not sure why that would be.  But you should be able to fairly easily compare your PROC REG model using a SAS Code node in EM and feed that into a Model Comparison node to compare with your other EM models.

Just be sure to include this line in your PROC REG call so it generates the needed flow score code to enable the assessment:

code file="&EM_FILE_EMFLOWSCORECODE";

And set the Tool Type property for the SAS Code node to "Model".  Then you can connect that to a Model Comparison node along with your other EM models.

This is some sample code I used in SAS Code node (assuming you have an interval target):

proc sort data=&em_import_data out=temp;
   by <Your-by-var>;
run;

proc reg data=temp;
   model %em_target = %em_interval_input;
   by <Your-by-var>;
   code file="&EM_FILE_EMFLOWSCORECODE";
run;