A question about 0% accuracy

[林荻]

Some parts of this message have been removed. Learn more about Nabble's security policy.

Hi everyone:

Yesterday I used weka to analyze an artificial binary datasets, which has only 6 attributes and the sample space is 64. I assigned these 64 observations to either positive or negative and I use "Kstar" (LAZY->kstar) to classify them,  the test option is set as default,  and the outcome is 0% accuracy.

 
I do not know why there is a 0% accuracy, which means weka must know exactly which category they belong and deliberately make the wrong choice.

I attach the dataset at the bottom of this email, can some one kindly classify it and tell me the reason?  I am totally confused, since I give the weka all the space and I except it can at least do some correct guesses.
 

Thanks

 

Di Lin

 
 
 
@relation Dataset1
@attribute 1 {1,0}
@attribute 2 {1,0}
@attribute 3 {1,0}
@attribute 4 {1,0}
@attribute 5 {1,0}
@attribute 6 {1,0}
@attribute classification {yes,no}
@data
1,1,1,1,1,1,yes
1,1,1,1,1,0,no
1,1,1,1,0,1,no
1,1,1,0,1,1,no
1,1,0,1,1,1,no
1,0,1,1,1,1,no
0,1,1,1,1,1,no
1,1,1,1,0,0,yes
1,1,1,0,0,1,yes
1,1,1,0,1,0,yes
1,1,0,0,1,1,yes
1,1,0,1,0,1,yes
1,1,0,1,1,0,yes
1,0,1,1,1,0,yes
1,0,1,1,0,1,yes
1,0,1,0,1,1,yes
1,0,0,1,1,1,yes
0,0,1,1,1,1,yes
0,1,0,1,1,1,yes
0,1,1,0,1,1,yes
0,1,1,1,0,1,yes
0,1,1,1,1,0,yes
1,1,1,0,0,0,no
1,1,0,1,0,0,no
1,1,0,0,1,0,no
1,1,0,0,0,1,no
1,0,0,0,1,1,no
1,0,0,1,0,1,no
1,0,0,1,1,0,no
1,0,1,0,0,1,no
1,0,1,0,1,0,no
1,0,1,1,0,0,no
0,0,0,1,1,1,no
0,0,1,0,1,1,no
0,0,1,1,0,1,no
0,0,1,1,1,0,no
0,1,1,1,0,0,no
0,1,1,0,1,0,no
0,1,1,0,0,1,no
0,1,0,1,1,0,no
0,1,0,1,0,1,no
0,1,0,0,1,1,no
1,1,0,0,0,0,yes
1,0,1,0,0,0,yes
1,0,0,1,0,0,yes
1,0,0,0,1,0,yes
1,0,0,0,0,1,yes
0,1,1,0,0,0,yes
0,1,0,1,0,0,yes
0,1,0,0,1,0,yes
0,1,0,0,0,1,yes
0,0,1,0,0,1,yes
0,0,1,0,1,0,yes
0,0,1,1,0,0,yes
0,0,0,1,0,1,yes
0,0,0,1,1,0,yes
0,0,0,0,1,1,yes
1,0,0,0,0,0,no
0,1,0,0,0,0,no
0,0,1,0,0,0,no
0,0,0,1,0,0,no
0,0,0,0,1,0,no
0,0,0,0,0,1,no
0,0,0,0,0,0,yes

---

更多热辣资讯尽在新版MSN首页！ 立刻访问！
_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@...
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

[Peter Reutemann-3]

> Yesterday I used weka to analyze an artificial binary datasets, which has
> only 6 attributes and the sample space is 64. I assigned these 64
> observations to either positive or negative and I use "Kstar" (LAZY->kstar)
> to classify them,  the test option is set as default,  and the outcome is 0%
> accuracy.
>
>
> I do not know why there is a 0% accuracy, which means weka must know exactly
> which category they belong and deliberately make the wrong choice.

It's not that easy... Running J48 with 10-fold CV results in ~17% and
SMO with ~15%.

> I attach the dataset at the bottom of this email,

[What about attaching it as a proper attachment instead of inserting
it in the email?]

> can some
> one kindly classify it and tell me the reason?  I am totally confused, since
> I give the weka all the space and I except it can at least do some correct
> guesses.

Based on the classifier performance, there doesn't seem to be much
useful information in the dataset to build a model (the large errors
support this).

[...]

Cheers, Peter
--
Peter Reutemann, Dept. of Computer Science, University of Waikato, NZ
http://www.cs.waikato.ac.nz/~fracpete/           Ph. [phone]

_______________________________________________
Wekalist mailing list
Send posts to: Wekalist@...
List info and subscription status: https://list.scms.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html