Re: Problem with J48 Decision Tree

 Hi Jens,
To answer your question, this is psychological study data with 113 subjects and about 83 numeric attributes, generally in a range of 1-5 with a classification of Low, Medium or High. The output as you saw just seemed to ignore the attributes and went for High by default, which was a majority of instances. 
    On Wednesday, July 14, 2021, 09:11:30 PM EDT, Potschadtke, Jens <[email protected]> wrote:  
 
 #yiv7112329119 #yiv7112329119 -- _filtered {} _filtered {} _filtered {}#yiv7112329119 #yiv7112329119 p.yiv7112329119MsoNormal, #yiv7112329119 li.yiv7112329119MsoNormal, #yiv7112329119 div.yiv7112329119MsoNormal {margin:0cm;margin-bottom:.0001pt;font-size:12.0pt;font-family:New serif;}#yiv7112329119 a:link, #yiv7112329119 span.yiv7112329119MsoHyperlink {color:blue;text-decoration:underline;}#yiv7112329119 a:visited, #yiv7112329119 span.yiv7112329119MsoHyperlinkFollowed {color:purple;text-decoration:underline;}#yiv7112329119 p.yiv7112329119msonormal0, #yiv7112329119 li.yiv7112329119msonormal0, #yiv7112329119 div.yiv7112329119msonormal0 {margin-right:0cm;margin-left:0cm;font-size:12.0pt;font-family:New serif;}#yiv7112329119 span.yiv7112329119ydp91a286eapple-tab-span {}#yiv7112329119 span.yiv7112329119E-MailFormatvorlage19 {font-family:sans-serif;color:#1F497D;}#yiv7112329119 .yiv7112329119MsoChpDefault {font-size:10.0pt;} _filtered {}#yiv7112329119 div.yiv7112329119WordSection1 {}#yiv7112329119 
Hello,
 
  
 
it would be helpful if you shared with us the configuration of your J48 tree, the context (Weka explorer?) and the kind of input data.
 
Is it some default data set from Weka itself or your own data? If the latter please describe what kind of attributes and what kind of classes, better yet: try to reproduce the behavior with any Weka default data set.
 
Without that information you may need to wait for some superhuman mind reader to channel the solution directly into your brain ;-)
 
  
 
Greetings
 
Jens
 
  
 
Von: [email protected] <[email protected]>
Gesendet: Dienstag, 13. Juli 2021 15:52
An: Weka Machine Learning Workbench List. <[email protected]>
Betreff: [Wekalist] Problem with J48 Decision Tree
 
  
 
I keep running the data through and it makes a binary decision, and only appears to use one attribute, which it doesn't specify. What am I missing in configuring the tree? Output is:
 
  
 
J48 pruned tree
 
------------------
 
: High (113.0/57.0)
 
  
 
Number of Leaves  : 1
 
  
 
Size of the tree : 1
 
  
 
  
 
Time taken to build model: 0 seconds
 
  
 
=== Stratified cross-validation ===
 
=== Summary ===
 
  
 
Correctly Classified Instances          56               49.5575 %
 
Incorrectly Classified Instances        57               50.4425 %
 
Kappa statistic                          0     
 
Mean absolute error                      0.4178
 
Root mean squared error                  0.4572
 
Relative absolute error                 99.8172 %
 
Root relative squared error             99.9995 %
 
Total Number of Instances              113     
 
  
 _______________________________________________
Wekalist mailing list -- [email protected]
Send posts to [email protected]
To unsubscribe send an email to [email protected]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list -- [email protected]
Send posts to [email protected]
To unsubscribe send an email to [email protected]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html