Orange Forum • View topic - SOM: orange.ContDistribution: cannot compute average

SOM: orange.ContDistribution: cannot compute average

Report bugs (or imagined bugs).
(Archived/read-only, please use our ticketing system for reporting bugs and their discussion.)
Forum rules
Archived/read-only, please use our ticketing system for reporting bugs and their discussion.

SOM: orange.ContDistribution: cannot compute average

Postby ppl » Mon May 10, 2010 14:39

Hi,

I'm trying to run SOM on a dataset, 40 dimensions, ~2k datums. However, I get the following error:

Unhandled exception of type KernelException occured at 10:22:26:
Traceback:
File: OWSOM.py, line 102 in ApplySettings
Code: self.classifier = self.learner(self.data, progressCallback=self.progressBarSet)
File: orngSOM.py, line 338 in __call__
Code: return SOMMap(map, examples)
File: orngSOM.py, line 380 in __init__
Code: node.classifier = orange.MajorityLearner(node.examples)
KernelException: 'orange.ContDistribution': cannot compute average ('Group' has no defined values)


I'm connecting the ExampleFile and SOM. This is on Win7 64bits.

Any help is appreciated.

Postby Guest » Mon May 10, 2010 14:44

Err, this should be in questions and not bugs. :-(

Postby ppl » Mon May 10, 2010 15:26

Found my problem. The file extension was .txt instead of .tab, which would make the attributes to be loaded as meta-attributes.

Problem solved for now. :-)


Return to Bugs



cron