Building models with SAS Enterprise Miner, SAS Factory Miner, SAS Visual Data Mining and Machine Learning or just with programming

SAS Enterprise Miner importation problem

Accepted Solution Solved
Reply
New Contributor
Posts: 3
Accepted Solution

SAS Enterprise Miner importation problem

Hello, I'm trying to import a .csv file (click here to download) in SAS EM 14.1. There are 4 continous variables, with missing values marked by ?, and 1 nominal variable, but the program sets them as nominals and it let me change their levels to anything but continuos. Probably is ?'s fault. What can I do to fix this problem? Thank you in advance.

 

P.S.: I had to set the delimiter character to ; before importing


Accepted Solutions
Solution
‎06-01-2016 04:56 PM
SAS Super FREQ
Posts: 272

Re: SAS Enterprise Miner importation problem

Yes, I think you need to change the '?'s to '.'s for the missing values.  The '?' makes it think those columns are character instead of numeric, so that's why it will only allow the level to be nominal.  Hope that helps (and let me know if that doesn't work).

 

View solution in original post


All Replies
Solution
‎06-01-2016 04:56 PM
SAS Super FREQ
Posts: 272

Re: SAS Enterprise Miner importation problem

Yes, I think you need to change the '?'s to '.'s for the missing values.  The '?' makes it think those columns are character instead of numeric, so that's why it will only allow the level to be nominal.  Hope that helps (and let me know if that doesn't work).

 

New Contributor
Posts: 3

Re: SAS Enterprise Miner importation problem


WendyCzika wrote:

Yes, I think you need to change the '?'s to '.'s for the missing values.  The '?' makes it think those columns are character instead of numeric, so that's why it will only allow the level to be nominal.  Hope that helps (and let me know if that doesn't work).

 


Thank you very much for the tip, it worked! I had to edit the file manually entry-by-entry, because in Excel when I tried to make the replace function (the one next to search) substitute the "?"s with "."s, the program replaced every character of every cell with ".". I was lucky the missing values were just ~20 and the dataset was small, so there was only a little manual work, but I wonder how to replace automatically in .csv files with Excel.

SAS Super FREQ
Posts: 272

Re: SAS Enterprise Miner importation problem

It looks like you need to escape the ? with a tilde when you do the Replace in Excel, so enter

~?

in the Find what field.

New Contributor
Posts: 3

Re: SAS Enterprise Miner importation problem


WendyCzika wrote:

It looks like you need to escape the ? with a tilde when you do the Replace in Excel, so enter

~?

in the Find what field.


Thank you very much again for the support!

☑ This topic is SOLVED.

Need further help from the community? Please ask a new question.

Discussion stats
  • 4 replies
  • 373 views
  • 2 likes
  • 2 in conversation