? in the detailed accuracy by class

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

? in the detailed accuracy by class

spezs1
Hello,
I am using SMO classifier.
For the training set it works well:
Correctly Classified Instances 5469 91.6234 %
Incorrectly Classified Instances 500 8.3766 %
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0.949 0.116 0.890 0.949 0.919 0.834 0.916 0.870 walking
0.884 0.051 0.946 0.884 0.914 0.834 0.916 0.894 sitting
Weighted Avg. 0.916 0.084 0.918 0.916 0.916 0.834 0.916 0.882
=== Confusion Matrix ===
a b <-- classified as
2823 152 | a = walking
348 2646 | b = sitting

But for the supplied test set there is a problem
Correctly Classified Instances 1120 94.7547 %
Incorrectly Classified Instances 62 5.2453 %
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class
0.948 ? 1.000 0.948 0.973 ? ? 1.000 walking
? 0.052 0.000 ? ? ? ? ? sitting
Weighted Avg. 0.948 ? 1.000 0.948 0.973 ? ? 1.000
=== Confusion Matrix ===
a b <-- classified as
1120 62 | a = walking
0 0 | b = sitting
Any idea why?
I used the same data with other classifier, but it works. Only the problem
with SMO.
Thank you



--
Sent from: https://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to: To unsubscribe send an email to [hidden email]
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
Reply | Threaded
Open this post in threaded view
|

Re: ? in the detailed accuracy by class

Eibe Frank-2
Administrator

That means the corresponding value is undefined. For example, precision is defined as TP / PP, where TP Is the number of true positives and PP is the number of instances that are predicted to be positive (for whichever class is currently considered the “positive” class). If PP is zero, there will be a division by zero, which yields a “?” in the output.

 

Cheers,

Eibe

 

From: [hidden email]
Sent: Tuesday, 29 October 2019 7:44 AM
To: [hidden email]
Subject: [Wekalist] ? in the detailed accuracy by class

 

Hello,

I am using SMO classifier.

For the training set it works well:

Correctly Classified Instances 5469 91.6234 %

Incorrectly Classified Instances 500 8.3766 %

=== Detailed Accuracy By Class ===

TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class

0.949 0.116 0.890 0.949 0.919 0.834 0.916 0.870 walking

0.884 0.051 0.946 0.884 0.914 0.834 0.916 0.894 sitting

Weighted Avg. 0.916 0.084 0.918 0.916 0.916 0.834 0.916 0.882

=== Confusion Matrix ===

a b <-- classified as

2823 152 | a = walking

348 2646 | b = sitting

 

But for the supplied test set there is a problem

Correctly Classified Instances 1120 94.7547 %

Incorrectly Classified Instances 62 5.2453 %

=== Detailed Accuracy By Class ===

TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class

0.948 ? 1.000 0.948 0.973 ? ? 1.000 walking

? 0.052 0.000 ? ? ? ? ? sitting

Weighted Avg. 0.948 ? 1.000 0.948 0.973 ? ? 1.000

=== Confusion Matrix ===

a b <-- classified as

1120 62 | a = walking

0 0 | b = sitting

Any idea why?

I used the same data with other classifier, but it works. Only the problem

with SMO.

Thank you

 

 

 

--

Sent from: https://weka.8497.n7.nabble.com/

_______________________________________________

Wekalist mailing list -- [hidden email]

Send posts to: To unsubscribe send an email to [hidden email]

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 -- [hidden email]
Send posts to: To unsubscribe send an email to [hidden email]
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