SAS Data Science

Building models with SAS Enterprise Miner, SAS Factory Miner, SAS Viya (Machine Learning), SAS Visual Text Analytics, with point-and-click interfaces or programming
BookmarkSubscribeRSS Feed
🔒 This topic is solved and locked. Need further help from the community? Please sign in and ask a new question.
JPI_UY
Calcite | Level 5

Hello everyone

I need to make a graph of the residuals of a model in SAS Miner. Is this possible?

Thanks!

1 ACCEPTED SOLUTION

Accepted Solutions
WendyCzika
SAS Employee

Most of the plots and tables displayed in the Enterprise Miner node results are based on a summary of the data, not the full training data since it can be large.  But one way to get a residual plot is as follows:

1) With your modeling node selected, click on the ellipsis for Exported Data from the properties panel:

ExportedData.PNG

2) Select the TRAIN data, then click the Explore... button

3) Select Actions>Plot

4) Select Scatter to create a scatter plot of residuals

5) Click on R_target (where target represents your target name) and set Y for the Role

6) Select the predicted values, P_target, or an input variable, or any other variable, and set X for the Role

7) Click on Finish to create your scatter plot

View solution in original post

5 REPLIES 5
ShelleySessoms
Community Manager

Hi, I'm a community manager for SAS. Based on udo@sas's comment, I've moved this thread to the data mining community. Thanks for using our communities.

Thanks,

Shelley

WendyCzika
SAS Employee

Most of the plots and tables displayed in the Enterprise Miner node results are based on a summary of the data, not the full training data since it can be large.  But one way to get a residual plot is as follows:

1) With your modeling node selected, click on the ellipsis for Exported Data from the properties panel:

ExportedData.PNG

2) Select the TRAIN data, then click the Explore... button

3) Select Actions>Plot

4) Select Scatter to create a scatter plot of residuals

5) Click on R_target (where target represents your target name) and set Y for the Role

6) Select the predicted values, P_target, or an input variable, or any other variable, and set X for the Role

7) Click on Finish to create your scatter plot

JPI_UY
Calcite | Level 5

Thank you!

jan_seidel
Calcite | Level 5

Hi,

 

this solution also works for residual plots that should base on the validation data set (this is what I'd like to do Smiley Happy ) .

 

However, I'm wondering whether it's also possible to generate these plots based on validation data using the SAS EM graphical nodes. But as far as I can see the MultiPlot node for instance only processes the training data. Is that correct? Or is there a workaround?

 

Thanks for any hint,

Jan

sas-innovate-white.png

Our biggest data and AI event of the year.

Don’t miss the livestream kicking off May 7. It’s free. It’s easy. And it’s the best seat in the house.

Join us virtually with our complimentary SAS Innovate Digital Pass. Watch live or on-demand in multiple languages, with translations available to help you get the most out of every session.

 

Register now!

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
  • 5 replies
  • 5468 views
  • 7 likes
  • 5 in conversation