Problem Note 46934: The Variable Clustering node might use too many variables when computing the number of global clusters
The Variable Clustering node in SAS® Enterprise Miner™ should compute the number of global clusters in Two Stage Variable Clustering using this formula:
Number of clusters = INT ((number of input variables / 100) + 2)
However, the node incorrectly uses the total number of variables (instead of the number of input variables). The number of global clusters computed might be incorrect, and as a result, the final clustering results are not correct.
There are no errors or warnings to indicate a problem.
To work around the problem, remove all variables except the input variables. An easy way to automatically remove non-input variables is to insert a SAS Code node immediately before your Variable Clustering node. In the SAS Code node, select the Code Editor property, and enter this SAS code:
data &EM_EXPORT_TRAIN;
set &EM_IMPORT_DATA;
keep %em_input;
run;
The the SAS Code node keeps only input variables. When you run the Variable Clustering node, only input variables are used to compute the number of global clusters.
Operating System and Release Information
SAS System | SAS Enterprise Miner | z/OS | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft® Windows® for 64-Bit Itanium-based Systems | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows Server 2003 Datacenter 64-bit Edition | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows Server 2003 Enterprise 64-bit Edition | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows XP 64-bit Edition | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows 2000 Advanced Server | 5.3 | | 9.1 TS1M3 SP4 | |
Microsoft Windows 2000 Datacenter Server | 5.3 | | 9.1 TS1M3 SP4 | |
Microsoft Windows 2000 Server | 5.3 | | 9.1 TS1M3 SP4 | |
Microsoft Windows 2000 Professional | 5.3 | | 9.1 TS1M3 SP4 | |
Microsoft Windows NT Workstation | 5.3 | | 9.1 TS1M3 SP4 | |
Microsoft Windows Server 2003 Datacenter Edition | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows Server 2003 Enterprise Edition | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows Server 2003 Standard Edition | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Microsoft Windows XP Professional | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Windows Vista | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Windows Vista for x64 | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
64-bit Enabled AIX | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
64-bit Enabled HP-UX | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
64-bit Enabled Solaris | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
HP-UX IPF | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Linux | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Linux on Itanium | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Solaris for x64 | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
Tru64 UNIX | 5.3 | 12.1 | 9.1 TS1M3 SP4 | 9.3 TS1M2 |
*
For software releases that are not yet generally available, the Fixed
Release is the software release in which the problem is planned to be
fixed.
Type: | Problem Note |
Priority: | alert |
Date Modified: | 2012-07-06 08:42:57 |
Date Created: | 2012-07-06 08:07:24 |