Hello everyone,
I would like to initialize the values of my parameters of my proc nlp, by picking them from a table. My table nr has two variables x1 and x2, with one value for each. My objective function is a function that I have defined in a previous proc fcmp.
I have tried to run this code, but it can't seem to work, I have the following error message: Missing variable TYPE on the INEST= input data set.
proc nlp tech=NEWRAP invar=two(type=PARMS) gradcheck=detail gconv2=1e-12 ;
min f;
decvar x1 x2;
f = (1-x1)*2+100(x2-x1*2)*2;
run;
Thanks a lot for your help!
Hello,
I have moved your question to this board:
I see now it's a duplicate of another question that is already posted in this board.
Cheers,
Koen
Hello,
I have moved your question to this board:
I see now it's a duplicate of another question that is already posted in this board.
Cheers,
Koen
@sarrabeny and @CerditoSalvaje
You both posted the same question. Could you please let us know if you are taking a course? If so, what is the topic of the course?
If you post a homework question or a question about a school project, please let us know. That way we can give hints that lead you towards discovering the answers on your own. This is more valuable than telling you an answer.
Hello,
Thanks for clarifying.
PSO ... do you mean particle swarm optimization?
Why are you using the legacy procedure PROC NLP by the way?
I think you should shift to our more modern procedures and solvers (PROC OPTMODEL, PROC OPTLSO, ...).
OPTMODEL also has a great algebraic modelling language (AML) to formulate your mathematical program.
Thanks,
Koen
Yes. The request to use the ancient PROC NLP was one reason I thought the question was related to a course. Sometimes professors reuse old assignments from 20 years ago.
I agree with Koen: If you are doing new work in SAS, use the most modern techniques. Instead of PROC NLP, use PROC OPTMODEL.
Join us for SAS Innovate 2025, our biggest and most exciting global event of the year, in Orlando, FL, from May 6-9.
Early bird rate extended! Save $200 when you sign up by March 31.