BookmarkSubscribeRSS Feed
znhnm
Quartz | Level 8

Hello, 

 

I have a pipeline on Model Studio to create a segmentation model. Here is how it looks like:

znhnm_0-1726470911987.png

 


I would like to do scoring in Model Manger, so I would need to register my model. However, under Pipeline Comparison tab in Model Studio, I see this notification: 

"There are no pipelines to compare.

In order to view Pipeline Comparison, successfully run a pipeline that contains a modeling node."

Is there a way to register it through Model Studio interface or should I save the output and make the registration to Model Manager using SAS Code? I'd appreciate any suggestions! Thank you! 

2 REPLIES 2
sbxkoenk
SAS Super FREQ

I think you should do like this :

 

See :

Home > SAS Communities Library > Scoring Clustering Models in SAS Viya
https://communities.sas.com/t5/SAS-Communities-Library/Scoring-Clustering-Models-in-SAS-Viya/ta-p/90...

 

Look at section "Scoring data outside of Model Studio"
Look therein at "Option 1".

 

You need to work with a "SAS Code node" (after Clustering node) , ... you need to create a pseudo-target , ...
and move your SAS Code node to the "Supervised Learning"-group of nodes.

 

You now can deploy your score code in various ways (register, publish, download from the Pipeline Comparison tab), just as you would for a supervised model.

 

Koen

sbxkoenk
SAS Super FREQ

Also ... I moved this topic to "Data Science" - / "Data Mining" - board.
You will get more and better responses here.

 

BR, Koen

SAS Innovate 2025: Call for Content

Are you ready for the spotlight? We're accepting content ideas for SAS Innovate 2025 to be held May 6-9 in Orlando, FL. The call is open until September 25. Read more here about why you should contribute and what is in it for you!

Submit your idea!

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
  • 2 replies
  • 346 views
  • 0 likes
  • 2 in conversation