@umarigan wrote: input data are same, in model data there are some columns that I rejected for model and those columns are not presenting in prediction data. I think this requires some delineated steps to uncover the root cause. SAS Technical Support is best placed to guide you in this effort. Can you contact SAS Technical Support in your country?   Remark that (as from August 21, 2023) there's a new customer portal that you need to access in order to open a case (= open a ticket). On Aug. 21, the SAS Customer Service Portal (customer portal) was made externally available to customers. https://service.sas.com/csm You need a SAS Profile to use the customer portal. If you do not have a SAS Profile, you can create it here. The new customer experience is here By Kimberly May on SAS Users August 21, 2023 https://blogs.sas.com/content/sgf/2023/08/21/the-new-customer-experience-is-here/ The new customer experience is here https://communities.sas.com/t5/All-Things-Community/The-new-customer-experience-is-here/m-p/890237 If you are used to support.sas.com ... you can still open a TS-ticket from there : After signing in on the SAS Support home page (support.sas.com), you may access links to open a case or manage your cases from the My Profile dropdown in the top right of the navigation menu.   Good luck, Koen ... View more

Hello,    I don't have Viya. I do have Jupyter notebook.  Just run Pd. read_parquet to read in your parquest file. Write out to CSV and then use SAS proc import. to read it back in. I run batch to  process many GB size. CSV is your best bridge between SAS and open source data files.  It has a distinctive speed edge over SAS Hadoop Access. I once tested Viya and felt it still has too many layers in the background like 'old SAS'.  It may be optimizing something, but for 195 MB? you don't need that elaboration. You just need straight shot, simple and fast.    Jia ... View more