I have built a diagram in SAS Enterprise Miner with logistic regression model, I have score node connected to score code export node - the output score.sas was created. However, when I try to use it in SAS enterprise guides got missing values of em_probabilty. What can cause such a problem?
Grateful for any help!
Enterprise Miner uses SAS data sets. There's one with your original data. There's one with the imputed data. There's one with the predicted values from the logistic regression. Those are the ones you need to look at. You can click on the Explorer icon in Enterprise Miner to see the data sets that are being used by Enterprise Miner.
If you are using the Impute node, you need to make sure it actually did the imputing. If all (or most) observations are missing for a certain variable, then Impute node cannot turn those missings into non-missings.
One thing that can cause missing values is there are missing values in the predictor variables in the logistic regression.
I think you need to go back to your Enterprise Miner project and look at the input data set and look at the output data set to see what is happening.
Thank you! I am a new user of Enterprise Miner))) There is some data in input table that is missing, but I thought that the impute node should handle this... What kind of output dataset do you mean? The one that score code export produces?
Enterprise Miner uses SAS data sets. There's one with your original data. There's one with the imputed data. There's one with the predicted values from the logistic regression. Those are the ones you need to look at. You can click on the Explorer icon in Enterprise Miner to see the data sets that are being used by Enterprise Miner.
If you are using the Impute node, you need to make sure it actually did the imputing. If all (or most) observations are missing for a certain variable, then Impute node cannot turn those missings into non-missings.
Thank you! It solved the problem!
Registration is open! SAS is returning to Vegas for an AI and analytics experience like no other! Whether you're an executive, manager, end user or SAS partner, SAS Innovate is designed for everyone on your team. Register for just $495 by 12/31/2023.
If you are interested in speaking, there is still time to submit a session idea. More details are posted on the website.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.