Problem Note 57329: Using trimmed data in SAS® Factory Miner causes missing values in the score code
 |  |  |  |  |
In SAS Factory Miner, using the Trimmed option in the Interval default method for the Filter section of a model template might generate missing values. The missing values occur in the lower limits of the output score code when any model template is run.
Here is an example:
*------------------------------------------------------------*;
* Node: Filter;
*------------------------------------------------------------*;
Length M_Filter 8;
if (CLAGE eq . or (CLAGE>= . and CLAGE<=360.64005406)) and
(CLNO eq . or (CLNO>= . and CLNO<= 33)) and
(DEBTINC eq . or (DEBTINC>= . and DEBTINC<=40.105029842)) and
(LOAN eq . or (LOAN>= . and LOAN<= 26100)) and
(MORTDUE eq . or (MORTDUE>= . and MORTDUE<= 145000)) and
(VALUE eq . or (VALUE>= . and VALUE<= 184360)) and
(YOJ eq . or (YOJ>= . and YOJ<= 29))
*------------------------------------------------------------*;
There is no workaround.
Click the Hot Fix tab in this note to access the hot fix for this issue.
Operating System and Release Information
| Product Family | Product | System | Product Release | SAS Release | ||
| Reported | Fixed* | Reported | Fixed* | |||
| SAS System | SAS Factory Miner | Microsoft® Windows® for x64 | 14.1 | 14.2 | 9.4 TS1M3 | 9.4 TS1M4 |
| Linux for x64 | 14.1 | 14.2 | 9.4 TS1M3 | 9.4 TS1M4 | ||
A fix for this issue for SAS Enterprise Miner 14.1 is available at:
https://tshf.sas.com/techsup/download/hotfix/HF2/W52.html#57329
Using trimmed data in SAS Factory Miner returns missing values in score code
| Type: | Problem Note |
| Priority: | high |
| Topic: | Analytics ==> Data Mining |
| Date Modified: | 2016-11-04 10:56:32 |
| Date Created: | 2015-12-23 13:42:09 |