Hi,
I have used "options validvarname=any;" in my EM project start up code, and everything works okay until I get to the reject inference node which is giving "not valid SAS name" error messages in the log.
Please can someone confirm if validvarname=any is not compatible with the reject inference node? If it is compatible, is there another way that you are supposed to set the option?
I have a very large number of variables with hyphens in the name and don't want to have to rename them all.
Thanks
EM version = 14.3
Edit:
Error message (I've tried completely dropping and renaming the variables from the data node but still get the error):
NOTE: CALL EXECUTE generated line.
1 + data EMWS1.RejInf_SCOREREJECTS;
2 + set EMWS1.Ids_DATA;
3 + %include _F1;
NOTE: %INCLUDE (level 1) file _F1 is file [......]\PATHFLOWCODE.sas.
18111 +*------------------------------------------------------------*;
18112 +* TOOL: Input Data Source;
18113 +* TYPE: SAMPLE;
18114 +* NODE: Ids2;
18115 +*------------------------------------------------------------*;
18116 +drop Day;
18117 +drop 'Example-1-External-Variable'n;
-----------------------
24
ERROR 24-322: Variable name is not valid.
I'd suggest contacting SAS Technical Support for this: https://support.sas.com/en/technical-support.html
Thanks, I have done.
I've not heard back yet but in case anyone else has the same issue, after using a macro to replace all of the non SAS compliant variable names the reject inference node started working.
It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.
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.