Problem filtering instances: null using Weka 3.6.11

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

Problem filtering instances: null using Weka 3.6.11

Ashish

Dear all,


I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output


=== Run information ===

 

Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"

Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42

Instances:    345446

Attributes:   11

              Anon Student Id

              Student Response Type

              Student Response Subtype

              Tutor Response Type

              Level (Module)

              Level (Group)

              Problem Name

              Problem View

              Attempt At Step

              Outcome

              Total Num Hints

Test mode:evaluate on training data


My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”


The parameters of the clustering algorithm are given below;


Hierarchical clustering class

debug= False

disanceFunction = EuclideanDistance -R first-last

distanceIsBranchLength= False

linkType = SINGLE

numClusters=2

preintNewick=True

 

Any help in this reference would be greatly appreciated.

 

Regards,

Ashish

 


_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Eibe Frank-2
Administrator
Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?

HierarchicalClusterer doesn’t actually use a filter.

Cheers,
Eibe

On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:

> Dear all,
>
>
>
> I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
>
>
>
> === Run information ===
>
>  
> Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
>
> Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
>
> Instances:    345446
>
> Attributes:   11
>
>               Anon Student Id
>
>               Student Response Type
>
>               Student Response Subtype
>
>               Tutor Response Type
>
>               Level (Module)
>
>               Level (Group)
>
>               Problem Name
>
>               Problem View
>
>               Attempt At Step
>
>               Outcome
>
>               Total Num Hints
>
> Test mode:evaluate on training data
>
>
>
> My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
>
>
>
> The parameters of the clustering algorithm are given below;
>
>
>
> Hierarchical clustering class
>
> debug= False
>
>
> disanceFunction = EuclideanDistance -R first-last
>
> distanceIsBranchLength= False
>
> linkType = SINGLE
>
> numClusters=2
>
> preintNewick=True
>
>  
> Any help in this reference would be greatly appreciated.
>
>  
> Regards,
>
> Ashish
>
>  
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"

Thank you,
Ashish



On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?

HierarchicalClusterer doesn’t actually use a filter.

Cheers,
Eibe

On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:

> Dear all,
>
>
>
> I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
>
>
>
> === Run information ===
>
>
> Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
>
> Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
>
> Instances:    345446
>
> Attributes:   11
>
>               Anon Student Id
>
>               Student Response Type
>
>               Student Response Subtype
>
>               Tutor Response Type
>
>               Level (Module)
>
>               Level (Group)
>
>               Problem Name
>
>               Problem View
>
>               Attempt At Step
>
>               Outcome
>
>               Total Num Hints
>
> Test mode:evaluate on training data
>
>
>
> My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
>
>
>
> The parameters of the clustering algorithm are given below;
>
>
>
> Hierarchical clustering class
>
> debug= False
>
>
> disanceFunction = EuclideanDistance -R first-last
>
> distanceIsBranchLength= False
>
> linkType = SINGLE
>
> numClusters=2
>
> preintNewick=True
>
>
> Any help in this reference would be greatly appreciated.
>
>
> Regards,
>
> Ashish
>
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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


_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
Hi,
I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
Please help what should I do next to solve it.

Thank you,
Ashish


On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"

Thank you,
Ashish



On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?

HierarchicalClusterer doesn’t actually use a filter.

Cheers,
Eibe

On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:

> Dear all,
>
>
>
> I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
>
>
>
> === Run information ===
>
>
> Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
>
> Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
>
> Instances:    345446
>
> Attributes:   11
>
>               Anon Student Id
>
>               Student Response Type
>
>               Student Response Subtype
>
>               Tutor Response Type
>
>               Level (Module)
>
>               Level (Group)
>
>               Problem Name
>
>               Problem View
>
>               Attempt At Step
>
>               Outcome
>
>               Total Num Hints
>
> Test mode:evaluate on training data
>
>
>
> My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
>
>
>
> The parameters of the clustering algorithm are given below;
>
>
>
> Hierarchical clustering class
>
> debug= False
>
>
> disanceFunction = EuclideanDistance -R first-last
>
> distanceIsBranchLength= False
>
> linkType = SINGLE
>
> numClusters=2
>
> preintNewick=True
>
>
> Any help in this reference would be greatly appreciated.
>
>
> Regards,
>
> Ashish
>
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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



_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
Hi, 
I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
Any help would be appreciated.

Thank you,
Ashish 


On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
Hi,
I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
Please help what should I do next to solve it.

Thank you,
Ashish


On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"

Thank you,
Ashish



On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?

HierarchicalClusterer doesn’t actually use a filter.

Cheers,
Eibe

On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:

> Dear all,
>
>
>
> I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
>
>
>
> === Run information ===
>
>
> Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
>
> Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
>
> Instances:    345446
>
> Attributes:   11
>
>               Anon Student Id
>
>               Student Response Type
>
>               Student Response Subtype
>
>               Tutor Response Type
>
>               Level (Module)
>
>               Level (Group)
>
>               Problem Name
>
>               Problem View
>
>               Attempt At Step
>
>               Outcome
>
>               Total Num Hints
>
> Test mode:evaluate on training data
>
>
>
> My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
>
>
>
> The parameters of the clustering algorithm are given below;
>
>
>
> Hierarchical clustering class
>
> debug= False
>
>
> disanceFunction = EuclideanDistance -R first-last
>
> distanceIsBranchLength= False
>
> linkType = SINGLE
>
> numClusters=2
>
> preintNewick=True
>
>
> Any help in this reference would be greatly appreciated.
>
>
> Regards,
>
> Ashish
>
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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




_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Eibe Frank-2
Administrator
Can you post the stack trace for the exception? It should be in the weka.log file.

Cheers,
Eibe

On 12 Aug 2014, at 20:18, Ashish Dutt <[hidden email]> wrote:

> Hi,
> I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
> Any help would be appreciated.
>
> Thank you,
> Ashish
>
>
> On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
> Hi,
> I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
> Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
> Please help what should I do next to solve it.
>
> Thank you,
> Ashish
>
>
> On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
> Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"
>
> Thank you,
> Ashish
>
>
>
> On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
> Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?
>
> HierarchicalClusterer doesn’t actually use a filter.
>
> Cheers,
> Eibe
>
> On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:
>
> > Dear all,
> >
> >
> >
> > I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
> >
> >
> >
> > === Run information ===
> >
> >
> > Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> >
> > Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
> >
> > Instances:    345446
> >
> > Attributes:   11
> >
> >               Anon Student Id
> >
> >               Student Response Type
> >
> >               Student Response Subtype
> >
> >               Tutor Response Type
> >
> >               Level (Module)
> >
> >               Level (Group)
> >
> >               Problem Name
> >
> >               Problem View
> >
> >               Attempt At Step
> >
> >               Outcome
> >
> >               Total Num Hints
> >
> > Test mode:evaluate on training data
> >
> >
> >
> > My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
> >
> >
> >
> > The parameters of the clustering algorithm are given below;
> >
> >
> >
> > Hierarchical clustering class
> >
> > debug= False
> >
> >
> > disanceFunction = EuclideanDistance -R first-last
> >
> > distanceIsBranchLength= False
> >
> > linkType = SINGLE
> >
> > numClusters=2
> >
> > preintNewick=True
> >
> >
> > Any help in this reference would be greatly appreciated.
> >
> >
> > Regards,
> >
> > Ashish
> >
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
Hi,
Thank you for your response.
Given below is the stack trace for the exception. (I'm sorry, I just copied the whole content and pasting it here)
---------------------------------------------------------------------------------------------------------------------------------------------------------------------
2014-08-12 16:05:42 weka.gui.GUIChooser main
INFO: Logging started
[Weka] associationRulesVisualizer can't be loaded because com.sun.j3d.utils.universe.SimpleUniverse can't be instantiated.
[Weka] associationRulesViewer can't be loaded because Java3D does not seem to be installed. Download and install Java3D from https://java3d.dev.java.net/binary-builds.html before restarting Weka.
Refreshing GOE props...
2014-08-12 16:05:49 weka.gui.GenericObjectEditor registerEditors
INFO: ---Registering Weka Editors---
2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
WARNING: Trying to add database driver (JDBC): RmiJdbc.RJDriver - Warning, not in CLASSPATH?
2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
WARNING: Trying to add database driver (JDBC): jdbc.idbDriver - Warning, not in CLASSPATH?
2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
WARNING: Trying to add database driver (JDBC): org.gjt.mm.mysql.Driver - Warning, not in CLASSPATH?
2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
WARNING: Trying to add database driver (JDBC): com.mckoi.JDBCDriver - Warning, not in CLASSPATH?
2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
WARNING: Trying to add database driver (JDBC): org.hsqldb.jdbcDriver - Warning, not in CLASSPATH?
[KnowledgeFlow] Loading properties and plugins...
[KnowledgeFlow] Initializing KF...
2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
INFO: Weka Explorer
2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
INFO: Started on Tuesday, 12 August 2014
2014-08-12 16:06:30 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
2014-08-12 16:07:14 weka.gui.explorer.PreprocessPanel$15 run
INFO: Command: weka.filters.unsupervised.attribute.Remove -R 2,12
2014-08-12 16:07:15 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.Remove-R2,12 (345446 instances)
2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
INFO: Weka Explorer
2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
INFO: Started on Tuesday, 12 August 2014
2014-08-12 16:08:08 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData (345446 instances)
2014-08-12 16:09:07 weka.gui.explorer.PreprocessPanel$15 run
INFO: Command: weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant -A first-last -N NULL -R 0 -D 0 -F yyyy-MM-dd'T'HH:mm:ss
2014-08-12 16:09:08 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
2014-08-12 16:10:01 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
2014-08-12 16:12:15 weka.gui.explorer.PreprocessPanel$15 run
INFO: Command: weka.filters.unsupervised.attribute.AddCluster -W "weka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A \"weka.core.EuclideanDistance -R first-last\" -I 500 -num-slots 1 -S 10" -I 2,4,7,10
2014-08-12 16:12:22 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10 (345446 instances)
2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
INFO: Started weka.clusterers.HierarchicalClusterer
2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
java.lang.IllegalArgumentException
java.util.PriorityQueue.<init>(Unknown Source)
weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)

at java.util.PriorityQueue.<init>(Unknown Source)
at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
INFO: null
2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
INFO: Started weka.clusterers.HierarchicalClusterer
2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
java.lang.IllegalArgumentException
java.util.PriorityQueue.<init>(Unknown Source)
weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)

at java.util.PriorityQueue.<init>(Unknown Source)
at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
INFO: null
2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
INFO: Started weka.clusterers.HierarchicalClusterer
2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
java.lang.IllegalArgumentException
java.util.PriorityQueue.<init>(Unknown Source)
weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)

at java.util.PriorityQueue.<init>(Unknown Source)
at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
INFO: null
2014-08-12 16:21:11 weka.gui.explorer.PreprocessPanel$15 run
INFO: Command: weka.filters.unsupervised.attribute.Remove -R 14
2014-08-12 16:21:12 weka.gui.explorer.PreprocessPanel$14 run
INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10-weka.filters.unsupervised.attribute.Remove-R14 (345446 instances)
2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
INFO: Started weka.clusterers.HierarchicalClusterer
2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
java.lang.IllegalArgumentException
java.util.PriorityQueue.<init>(Unknown Source)
weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)

at java.util.PriorityQueue.<init>(Unknown Source)
at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
INFO: null
2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
INFO: Started weka.clusterers.HierarchicalClusterer
2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
java.lang.IllegalArgumentException
java.util.PriorityQueue.<init>(Unknown Source)
weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)

at java.util.PriorityQueue.<init>(Unknown Source)
at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
INFO: null
2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
INFO: Started weka.clusterers.HierarchicalClusterer
2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
java.lang.IllegalArgumentException
java.util.PriorityQueue.<init>(Unknown Source)
weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)

at java.util.PriorityQueue.<init>(Unknown Source)
at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
INFO: null

Thank you for your help.
Ashish



On Tue, Aug 12, 2014 at 4:32 PM, Eibe Frank <[hidden email]> wrote:
Can you post the stack trace for the exception? It should be in the weka.log file.

Cheers,
Eibe

On 12 Aug 2014, at 20:18, Ashish Dutt <[hidden email]> wrote:

> Hi,
> I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
> Any help would be appreciated.
>
> Thank you,
> Ashish
>
>
> On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
> Hi,
> I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
> Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
> Please help what should I do next to solve it.
>
> Thank you,
> Ashish
>
>
> On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
> Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"
>
> Thank you,
> Ashish
>
>
>
> On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
> Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?
>
> HierarchicalClusterer doesn’t actually use a filter.
>
> Cheers,
> Eibe
>
> On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:
>
> > Dear all,
> >
> >
> >
> > I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
> >
> >
> >
> > === Run information ===
> >
> >
> > Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> >
> > Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
> >
> > Instances:    345446
> >
> > Attributes:   11
> >
> >               Anon Student Id
> >
> >               Student Response Type
> >
> >               Student Response Subtype
> >
> >               Tutor Response Type
> >
> >               Level (Module)
> >
> >               Level (Group)
> >
> >               Problem Name
> >
> >               Problem View
> >
> >               Attempt At Step
> >
> >               Outcome
> >
> >               Total Num Hints
> >
> > Test mode:evaluate on training data
> >
> >
> >
> > My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
> >
> >
> >
> > The parameters of the clustering algorithm are given below;
> >
> >
> >
> > Hierarchical clustering class
> >
> > debug= False
> >
> >
> > disanceFunction = EuclideanDistance -R first-last
> >
> > distanceIsBranchLength= False
> >
> > linkType = SINGLE
> >
> > numClusters=2
> >
> > preintNewick=True
> >
> >
> > Any help in this reference would be greatly appreciated.
> >
> >
> > Regards,
> >
> > Ashish
> >
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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


_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Eibe Frank-2
Administrator
It looks like this is due to an integer overflow.

HierarchicalClusterer tries to create a PriorityQueue of size

 345,446 * 345,446 / 2

where 345,446 is the size of your data. This is

 5,966,646,945

which is larger than the largest value an int can attain in Java, i.e.

 2,147,483,647

The constructor of PriorityQueue takes an int argument to set the initial capacity.

Cheers,
Eibe

On 12 Aug 2014, at 20:37, Ashish Dutt <[hidden email]> wrote:

> Hi,
> Thank you for your response.
> Given below is the stack trace for the exception. (I'm sorry, I just copied the whole content and pasting it here)
> ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
> 2014-08-12 16:05:42 weka.gui.GUIChooser main
> INFO: Logging started
> [Weka] associationRulesVisualizer can't be loaded because com.sun.j3d.utils.universe.SimpleUniverse can't be instantiated.
> [Weka] associationRulesViewer can't be loaded because Java3D does not seem to be installed. Download and install Java3D from https://java3d.dev.java.net/binary-builds.html before restarting Weka.
> Refreshing GOE props...
> 2014-08-12 16:05:49 weka.gui.GenericObjectEditor registerEditors
> INFO: ---Registering Weka Editors---
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): RmiJdbc.RJDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): jdbc.idbDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.gjt.mm.mysql.Driver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): com.mckoi.JDBCDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.hsqldb.jdbcDriver - Warning, not in CLASSPATH?
> [KnowledgeFlow] Loading properties and plugins...
> [KnowledgeFlow] Initializing KF...
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:06:30 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:07:14 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 2,12
> 2014-08-12 16:07:15 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.Remove-R2,12 (345446 instances)
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:08:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData (345446 instances)
> 2014-08-12 16:09:07 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant -A first-last -N NULL -R 0 -D 0 -F yyyy-MM-dd'T'HH:mm:ss
> 2014-08-12 16:09:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:10:01 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:12:15 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.AddCluster -W "weka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A \"weka.core.EuclideanDistance -R first-last\" -I 500 -num-slots 1 -S 10" -I 2,4,7,10
> 2014-08-12 16:12:22 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10 (345446 instances)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
> java.util.PriorityQueue.<init>(Unknown Source)
> weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
> at java.util.PriorityQueue.<init>(Unknown Source)
> at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
> java.util.PriorityQueue.<init>(Unknown Source)
> weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
> at java.util.PriorityQueue.<init>(Unknown Source)
> at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
> java.util.PriorityQueue.<init>(Unknown Source)
> weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
> at java.util.PriorityQueue.<init>(Unknown Source)
> at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:21:11 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 14
> 2014-08-12 16:21:12 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10-weka.filters.unsupervised.attribute.Remove-R14 (345446 instances)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
> java.util.PriorityQueue.<init>(Unknown Source)
> weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
> at java.util.PriorityQueue.<init>(Unknown Source)
> at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
> java.util.PriorityQueue.<init>(Unknown Source)
> weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
> at java.util.PriorityQueue.<init>(Unknown Source)
> at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
> java.util.PriorityQueue.<init>(Unknown Source)
> weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
> at java.util.PriorityQueue.<init>(Unknown Source)
> at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
> at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
> at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
>
> Thank you for your help.
> Ashish
>
>
>
> On Tue, Aug 12, 2014 at 4:32 PM, Eibe Frank <[hidden email]> wrote:
> Can you post the stack trace for the exception? It should be in the weka.log file.
>
> Cheers,
> Eibe
>
> On 12 Aug 2014, at 20:18, Ashish Dutt <[hidden email]> wrote:
>
> > Hi,
> > I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
> > Any help would be appreciated.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
> > Hi,
> > I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
> > Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
> > Please help what should I do next to solve it.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
> > Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"
> >
> > Thank you,
> > Ashish
> >
> >
> >
> > On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
> > Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?
> >
> > HierarchicalClusterer doesn’t actually use a filter.
> >
> > Cheers,
> > Eibe
> >
> > On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:
> >
> > > Dear all,
> > >
> > >
> > >
> > > I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
> > >
> > >
> > >
> > > === Run information ===
> > >
> > >
> > > Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> > >
> > > Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
> > >
> > > Instances:    345446
> > >
> > > Attributes:   11
> > >
> > >               Anon Student Id
> > >
> > >               Student Response Type
> > >
> > >               Student Response Subtype
> > >
> > >               Tutor Response Type
> > >
> > >               Level (Module)
> > >
> > >               Level (Group)
> > >
> > >               Problem Name
> > >
> > >               Problem View
> > >
> > >               Attempt At Step
> > >
> > >               Outcome
> > >
> > >               Total Num Hints
> > >
> > > Test mode:evaluate on training data
> > >
> > >
> > >
> > > My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
> > >
> > >
> > >
> > > The parameters of the clustering algorithm are given below;
> > >
> > >
> > >
> > > Hierarchical clustering class
> > >
> > > debug= False
> > >
> > >
> > > disanceFunction = EuclideanDistance -R first-last
> > >
> > > distanceIsBranchLength= False
> > >
> > > linkType = SINGLE
> > >
> > > numClusters=2
> > >
> > > preintNewick=True
> > >
> > >
> > > Any help in this reference would be greatly appreciated.
> > >
> > >
> > > Regards,
> > >
> > > Ashish
> > >
> > >
> > > _______________________________________________
> > > Wekalist mailing list
> > > Send posts to: [hidden email]
> > > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> >
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
Alright, so how do I fix it. Do I reduce the datasize? But reducing the datasize will impact the clustering...so what do I do?

Thanks, 
Ashish



On Tue, Aug 12, 2014 at 4:48 PM, Eibe Frank <[hidden email]> wrote:
It looks like this is due to an integer overflow.

HierarchicalClusterer tries to create a PriorityQueue of size

 345,446 * 345,446 / 2

where 345,446 is the size of your data. This is

 5,966,646,945

which is larger than the largest value an int can attain in Java, i.e.

 2,147,483,647

The constructor of PriorityQueue takes an int argument to set the initial capacity.

Cheers,
Eibe

On 12 Aug 2014, at 20:37, Ashish Dutt <[hidden email]> wrote:

> Hi,
> Thank you for your response.
> Given below is the stack trace for the exception. (I'm sorry, I just copied the whole content and pasting it here)
> ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
> 2014-08-12 16:05:42 weka.gui.GUIChooser main
> INFO: Logging started
> [Weka] associationRulesVisualizer can't be loaded because com.sun.j3d.utils.universe.SimpleUniverse can't be instantiated.
> [Weka] associationRulesViewer can't be loaded because Java3D does not seem to be installed. Download and install Java3D from https://java3d.dev.java.net/binary-builds.html before restarting Weka.
> Refreshing GOE props...
> 2014-08-12 16:05:49 weka.gui.GenericObjectEditor registerEditors
> INFO: ---Registering Weka Editors---
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): RmiJdbc.RJDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): jdbc.idbDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.gjt.mm.mysql.Driver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): com.mckoi.JDBCDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.hsqldb.jdbcDriver - Warning, not in CLASSPATH?
> [KnowledgeFlow] Loading properties and plugins...
> [KnowledgeFlow] Initializing KF...
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:06:30 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:07:14 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 2,12
> 2014-08-12 16:07:15 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.Remove-R2,12 (345446 instances)
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:08:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData (345446 instances)
> 2014-08-12 16:09:07 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant -A first-last -N NULL -R 0 -D 0 -F yyyy-MM-dd'T'HH:mm:ss
> 2014-08-12 16:09:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:10:01 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:12:15 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.AddCluster -W "weka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A \"weka.core.EuclideanDistance -R first-last\" -I 500 -num-slots 1 -S 10" -I 2,4,7,10
> 2014-08-12 16:12:22 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10 (345446 instances)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:21:11 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 14
> 2014-08-12 16:21:12 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10-weka.filters.unsupervised.attribute.Remove-R14 (345446 instances)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
>
> Thank you for your help.
> Ashish
>
>
>
> On Tue, Aug 12, 2014 at 4:32 PM, Eibe Frank <[hidden email]> wrote:
> Can you post the stack trace for the exception? It should be in the weka.log file.
>
> Cheers,
> Eibe
>
> On 12 Aug 2014, at 20:18, Ashish Dutt <[hidden email]> wrote:
>
> > Hi,
> > I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
> > Any help would be appreciated.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
> > Hi,
> > I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
> > Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
> > Please help what should I do next to solve it.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
> > Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"
> >
> > Thank you,
> > Ashish
> >
> >
> >
> > On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
> > Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?
> >
> > HierarchicalClusterer doesn’t actually use a filter.
> >
> > Cheers,
> > Eibe
> >
> > On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:
> >
> > > Dear all,
> > >
> > >
> > >
> > > I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
> > >
> > >
> > >
> > > === Run information ===
> > >
> > >
> > > Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> > >
> > > Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
> > >
> > > Instances:    345446
> > >
> > > Attributes:   11
> > >
> > >               Anon Student Id
> > >
> > >               Student Response Type
> > >
> > >               Student Response Subtype
> > >
> > >               Tutor Response Type
> > >
> > >               Level (Module)
> > >
> > >               Level (Group)
> > >
> > >               Problem Name
> > >
> > >               Problem View
> > >
> > >               Attempt At Step
> > >
> > >               Outcome
> > >
> > >               Total Num Hints
> > >
> > > Test mode:evaluate on training data
> > >
> > >
> > >
> > > My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
> > >
> > >
> > >
> > > The parameters of the clustering algorithm are given below;
> > >
> > >
> > >
> > > Hierarchical clustering class
> > >
> > > debug= False
> > >
> > >
> > > disanceFunction = EuclideanDistance -R first-last
> > >
> > > distanceIsBranchLength= False
> > >
> > > linkType = SINGLE
> > >
> > > numClusters=2
> > >
> > > preintNewick=True
> > >
> > >
> > > Any help in this reference would be greatly appreciated.
> > >
> > >
> > > Regards,
> > >
> > > Ashish
> > >
> > >
> > > _______________________________________________
> > > Wekalist mailing list
> > > Send posts to: [hidden email]
> > > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> >
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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


_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
As an afterthought, I applied resample filter to the dataset and chose 50% of the original data. Preprocessing completed sucessfully. I now have 172723 instances. When applied Hierarchical clustering, I again get the same error, "Problem evaluating clusterer: null" Then i further applied resample filter to 35.00% reducing the dataset to 60453 instances but still the same error on clustering.

Any help in this reference will be appreciated.

Thank you
Ashish


On Tue, Aug 12, 2014 at 4:51 PM, Ashish Dutt <[hidden email]> wrote:
Alright, so how do I fix it. Do I reduce the datasize? But reducing the datasize will impact the clustering...so what do I do?

Thanks, 
Ashish



On Tue, Aug 12, 2014 at 4:48 PM, Eibe Frank <[hidden email]> wrote:
It looks like this is due to an integer overflow.

HierarchicalClusterer tries to create a PriorityQueue of size

 345,446 * 345,446 / 2

where 345,446 is the size of your data. This is

 5,966,646,945

which is larger than the largest value an int can attain in Java, i.e.

 2,147,483,647

The constructor of PriorityQueue takes an int argument to set the initial capacity.

Cheers,
Eibe

On 12 Aug 2014, at 20:37, Ashish Dutt <[hidden email]> wrote:

> Hi,
> Thank you for your response.
> Given below is the stack trace for the exception. (I'm sorry, I just copied the whole content and pasting it here)
> ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
> 2014-08-12 16:05:42 weka.gui.GUIChooser main
> INFO: Logging started
> [Weka] associationRulesVisualizer can't be loaded because com.sun.j3d.utils.universe.SimpleUniverse can't be instantiated.
> [Weka] associationRulesViewer can't be loaded because Java3D does not seem to be installed. Download and install Java3D from https://java3d.dev.java.net/binary-builds.html before restarting Weka.
> Refreshing GOE props...
> 2014-08-12 16:05:49 weka.gui.GenericObjectEditor registerEditors
> INFO: ---Registering Weka Editors---
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): RmiJdbc.RJDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): jdbc.idbDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.gjt.mm.mysql.Driver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): com.mckoi.JDBCDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.hsqldb.jdbcDriver - Warning, not in CLASSPATH?
> [KnowledgeFlow] Loading properties and plugins...
> [KnowledgeFlow] Initializing KF...
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:06:30 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:07:14 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 2,12
> 2014-08-12 16:07:15 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.Remove-R2,12 (345446 instances)
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:08:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData (345446 instances)
> 2014-08-12 16:09:07 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant -A first-last -N NULL -R 0 -D 0 -F yyyy-MM-dd'T'HH:mm:ss
> 2014-08-12 16:09:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:10:01 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:12:15 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.AddCluster -W "weka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A \"weka.core.EuclideanDistance -R first-last\" -I 500 -num-slots 1 -S 10" -I 2,4,7,10
> 2014-08-12 16:12:22 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10 (345446 instances)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:21:11 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 14
> 2014-08-12 16:21:12 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10-weka.filters.unsupervised.attribute.Remove-R14 (345446 instances)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
>
> Thank you for your help.
> Ashish
>
>
>
> On Tue, Aug 12, 2014 at 4:32 PM, Eibe Frank <[hidden email]> wrote:
> Can you post the stack trace for the exception? It should be in the weka.log file.
>
> Cheers,
> Eibe
>
> On 12 Aug 2014, at 20:18, Ashish Dutt <[hidden email]> wrote:
>
> > Hi,
> > I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
> > Any help would be appreciated.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
> > Hi,
> > I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
> > Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
> > Please help what should I do next to solve it.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
> > Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"
> >
> > Thank you,
> > Ashish
> >
> >
> >
> > On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
> > Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?
> >
> > HierarchicalClusterer doesn’t actually use a filter.
> >
> > Cheers,
> > Eibe
> >
> > On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:
> >
> > > Dear all,
> > >
> > >
> > >
> > > I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
> > >
> > >
> > >
> > > === Run information ===
> > >
> > >
> > > Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> > >
> > > Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
> > >
> > > Instances:    345446
> > >
> > > Attributes:   11
> > >
> > >               Anon Student Id
> > >
> > >               Student Response Type
> > >
> > >               Student Response Subtype
> > >
> > >               Tutor Response Type
> > >
> > >               Level (Module)
> > >
> > >               Level (Group)
> > >
> > >               Problem Name
> > >
> > >               Problem View
> > >
> > >               Attempt At Step
> > >
> > >               Outcome
> > >
> > >               Total Num Hints
> > >
> > > Test mode:evaluate on training data
> > >
> > >
> > >
> > > My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
> > >
> > >
> > >
> > > The parameters of the clustering algorithm are given below;
> > >
> > >
> > >
> > > Hierarchical clustering class
> > >
> > > debug= False
> > >
> > >
> > > disanceFunction = EuclideanDistance -R first-last
> > >
> > > distanceIsBranchLength= False
> > >
> > > linkType = SINGLE
> > >
> > > numClusters=2
> > >
> > > preintNewick=True
> > >
> > >
> > > Any help in this reference would be greatly appreciated.
> > >
> > >
> > > Regards,
> > >
> > > Ashish
> > >
> > >
> > > _______________________________________________
> > > Wekalist mailing list
> > > Send posts to: [hidden email]
> > > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> >
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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



_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Ashish
Hi,
I continued to play with it and when I had sampled the data by applying Resample filter to 20.0% reducing the number of instances to 2418, I was able to do the clustering.
Thank you so much, Eibe. Words are scarce for me to convey the gratitude for helping me solve this problem and also explaining the root cause of it.
Thanks a lot.

Cheers.
Ashish


On Tue, Aug 12, 2014 at 5:02 PM, Ashish Dutt <[hidden email]> wrote:
As an afterthought, I applied resample filter to the dataset and chose 50% of the original data. Preprocessing completed sucessfully. I now have 172723 instances. When applied Hierarchical clustering, I again get the same error, "Problem evaluating clusterer: null" Then i further applied resample filter to 35.00% reducing the dataset to 60453 instances but still the same error on clustering.

Any help in this reference will be appreciated.

Thank you
Ashish


On Tue, Aug 12, 2014 at 4:51 PM, Ashish Dutt <[hidden email]> wrote:
Alright, so how do I fix it. Do I reduce the datasize? But reducing the datasize will impact the clustering...so what do I do?

Thanks, 
Ashish



On Tue, Aug 12, 2014 at 4:48 PM, Eibe Frank <[hidden email]> wrote:
It looks like this is due to an integer overflow.

HierarchicalClusterer tries to create a PriorityQueue of size

 345,446 * 345,446 / 2

where 345,446 is the size of your data. This is

 5,966,646,945

which is larger than the largest value an int can attain in Java, i.e.

 2,147,483,647

The constructor of PriorityQueue takes an int argument to set the initial capacity.

Cheers,
Eibe

On 12 Aug 2014, at 20:37, Ashish Dutt <[hidden email]> wrote:

> Hi,
> Thank you for your response.
> Given below is the stack trace for the exception. (I'm sorry, I just copied the whole content and pasting it here)
> ---------------------------------------------------------------------------------------------------------------------------------------------------------------------
> 2014-08-12 16:05:42 weka.gui.GUIChooser main
> INFO: Logging started
> [Weka] associationRulesVisualizer can't be loaded because com.sun.j3d.utils.universe.SimpleUniverse can't be instantiated.
> [Weka] associationRulesViewer can't be loaded because Java3D does not seem to be installed. Download and install Java3D from https://java3d.dev.java.net/binary-builds.html before restarting Weka.
> Refreshing GOE props...
> 2014-08-12 16:05:49 weka.gui.GenericObjectEditor registerEditors
> INFO: ---Registering Weka Editors---
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): RmiJdbc.RJDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): jdbc.idbDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.gjt.mm.mysql.Driver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): com.mckoi.JDBCDriver - Warning, not in CLASSPATH?
> 2014-08-12 16:05:50 weka.experiment.DatabaseUtils initialize
> WARNING: Trying to add database driver (JDBC): org.hsqldb.jdbcDriver - Warning, not in CLASSPATH?
> [KnowledgeFlow] Loading properties and plugins...
> [KnowledgeFlow] Initializing KF...
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:05:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:06:30 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:07:14 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 2,12
> 2014-08-12 16:07:15 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-N0-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.Remove-R2,12 (345446 instances)
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Weka Explorer
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: (c) 1999-2014 The University of Waikato, Hamilton, New Zealand
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 2014-08-12 16:07:55 weka.gui.explorer.Explorer <init>
> INFO: Started on Tuesday, 12 August 2014
> 2014-08-12 16:08:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData (345446 instances)
> 2014-08-12 16:09:07 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant -A first-last -N NULL -R 0 -D 0 -F yyyy-MM-dd'T'HH:mm:ss
> 2014-08-12 16:09:08 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:10:01 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss (345446 instances)
> 2014-08-12 16:12:15 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.AddCluster -W "weka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A \"weka.core.EuclideanDistance -R first-last\" -I 500 -num-slots 1 -S 10" -I 2,4,7,10
> 2014-08-12 16:12:22 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10 (345446 instances)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:12:55 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:14:42 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:20:57 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:21:11 weka.gui.explorer.PreprocessPanel$15 run
> INFO: Command: weka.filters.unsupervised.attribute.Remove -R 14
> 2014-08-12 16:21:12 weka.gui.explorer.PreprocessPanel$14 run
> INFO: Base relation is now SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingWithUserConstant-Afirst-last-NNULL-R0-D0-Fyyyy-MM-dd'T'HH:mm:ss-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -init 0 -max-candidates 100 -periodic-pruning 10000 -min-density 2.0 -t1 -1.25 -t2 -1.0 -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -num-slots 1 -S 10-I2,4,7,10-weka.filters.unsupervised.attribute.Remove-R14 (345446 instances)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:21:18 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:33:47 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Started weka.clusterers.HierarchicalClusterer
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: Command: weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> java.lang.IllegalArgumentException
>       java.util.PriorityQueue.<init>(Unknown Source)
>       weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
>
>       at java.util.PriorityQueue.<init>(Unknown Source)
>       at weka.clusterers.HierarchicalClusterer.doLinkClustering(HierarchicalClusterer.java:509)
>       at weka.clusterers.HierarchicalClusterer.buildClusterer(HierarchicalClusterer.java:332)
>       at weka.gui.explorer.ClustererPanel$15.run(ClustererPanel.java:922)
> 2014-08-12 16:34:11 weka.gui.explorer.ClustererPanel$15 run
> INFO: null
>
> Thank you for your help.
> Ashish
>
>
>
> On Tue, Aug 12, 2014 at 4:32 PM, Eibe Frank <[hidden email]> wrote:
> Can you post the stack trace for the exception? It should be in the weka.log file.
>
> Cheers,
> Eibe
>
> On 12 Aug 2014, at 20:18, Ashish Dutt <[hidden email]> wrote:
>
> > Hi,
> > I tried it again. I was able to fix the replaceMissing....problem now but I again get stuck in the Hierarchical clusterer . The error message now is "Evaluate Clusterer- problem evaluating clusterer:null"
> > Any help would be appreciated.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt <[hidden email]> wrote:
> > Hi,
> > I tried to pre-process the dataset again. Since the data contains many missing values. So I tried cleaning it using the option "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and date format. My data has no date in it. On applying the filter, I now get this error "problem setting base instances: java.lang.reflect.InvocationTargetException "
> > Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No errors but errors came while doing hierarchical clustering. So i think you are correct. The problem is at Preprocessing stage.
> > Please help what should I do next to solve it.
> >
> > Thank you,
> > Ashish
> >
> >
> > On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt <[hidden email]> wrote:
> > Thank you for responding. I did not get this error message during preprocessing. As I said earlier, I got this error message when i chose Hierarchical clustering from the cluster tab. Cluster mode is set to "use training set"
> >
> > Thank you,
> > Ashish
> >
> >
> >
> > On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank <[hidden email]> wrote:
> > Strange. As far as I can tell, this error message only gets output by the Preprocess panel of the Explorer. Are you sure you didn’t get this problem when you applied a filter in the Preprocess panel?
> >
> > HierarchicalClusterer doesn’t actually use a filter.
> >
> > Cheers,
> > Eibe
> >
> > On 12 Aug 2014, at 17:39, Ashish Dutt <[hidden email]> wrote:
> >
> > > Dear all,
> > >
> > >
> > >
> > > I am mining a dataset that contains the logs of student interaction with an ITS. Most of the attributes are nominal in nature. I’m using Weka 3.6.11. Following is the run output
> > >
> > >
> > >
> > > === Run information ===
> > >
> > >
> > > Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A "weka.core.EuclideanDistance -R first-last"
> > >
> > > Relation:     SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
> > >
> > > Instances:    345446
> > >
> > > Attributes:   11
> > >
> > >               Anon Student Id
> > >
> > >               Student Response Type
> > >
> > >               Student Response Subtype
> > >
> > >               Tutor Response Type
> > >
> > >               Level (Module)
> > >
> > >               Level (Group)
> > >
> > >               Problem Name
> > >
> > >               Problem View
> > >
> > >               Attempt At Step
> > >
> > >               Outcome
> > >
> > >               Total Num Hints
> > >
> > > Test mode:evaluate on training data
> > >
> > >
> > >
> > > My problem is when I apply Hierarchical clustering to my data, I receive an error “Problem filtering instances: null”
> > >
> > >
> > >
> > > The parameters of the clustering algorithm are given below;
> > >
> > >
> > >
> > > Hierarchical clustering class
> > >
> > > debug= False
> > >
> > >
> > > disanceFunction = EuclideanDistance -R first-last
> > >
> > > distanceIsBranchLength= False
> > >
> > > linkType = SINGLE
> > >
> > > numClusters=2
> > >
> > > preintNewick=True
> > >
> > >
> > > Any help in this reference would be greatly appreciated.
> > >
> > >
> > > Regards,
> > >
> > > Ashish
> > >
> > >
> > > _______________________________________________
> > > Wekalist mailing list
> > > Send posts to: [hidden email]
> > > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
> >
> >
> >
> > _______________________________________________
> > Wekalist mailing list
> > Send posts to: [hidden email]
> > List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> > List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

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




_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
List info and subscription status: http://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Ashish Dutt, PhD graduate student,
Dept. of Computer Science, University of Malaya (UM), Malaysia
Blog- http://edumine.wordpress.com/
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Rita
In reply to this post by Eibe Frank-2
CONTENTS DELETED
The author has deleted this message.
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Eibe Frank-2
Administrator
That looks like a bug that needs fixing. I cannot get Optics to work either at the moment.

Cheers,
Eibe

> On 10/03/2019, at 8:10 PM, Rita <[hidden email]> wrote:
>
> Hello Eibe,
>
>
> I  have read the post below and dialogs about errors dealing but i still
> stuck in the problem.Really need help.
>
> I have a data set whcih contains two attribute,and 150 instances.That is
> irisril.arff exactaly.
> and i  went to clustering page and chose OPTICE and set e=0.2 , minP=5
> ues training set,ignore 'class' attribute
> and start
>
> it shows the error:problem evaluating clusterer:null
>
>
> SO..............................I try to ruduce the number of the instances
> i import the data set of iris.arff
> and filter using unsupervised.instance.resample andset the
> percentage=20%,apply it then instances'number  is 30
> and i again  went to clustering page and chose OPTICE and set e=0.2 , minP=5
> ues training set,ignore 'class' attribute
> and start
>
> it shows the error:problem evaluating clusterer:null!!!!
>
> How can i do to deal  with this problem,many thanks!
>
>
> Here is the history of log,Thank you for your time!
> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
>
> 15:00:00: Weka Explorer
> 15:00:00: (c) 1999-2018 The University of Waikato, Hamilton, New Zealand
> 15:00:00: web: http://www.cs.waikato.ac.nz/~ml/weka/
> 15:00:00: Started on 星期日, 10 三月 2019
> 15:00:07: Base relation is now iris (150 instances)
> 15:00:23: Started weka.clusterers.OPTICS
> 15:00:23: Command: weka.clusterers.OPTICS -E 0.2 -M 5 -A
> "weka.core.EuclideanDistance -R first-last" -db-output .
> 15:00:24: null
> 15:00:36: Command: weka.filters.unsupervised.instance.Resample -S 1 -Z 100.0
> 15:00:36: Base relation is now
> iris-weka.filters.unsupervised.instance.Resample-S1-Z100.0 (150 instances)
> 15:00:54: Command: weka.filters.unsupervised.instance.Resample -S 1 -Z 20.0
> 15:00:54: Base relation is now
> iris-weka.filters.unsupervised.instance.Resample-S1-Z100.0-weka.filters.unsupervised.instance.Resample-S1-Z20.0
> (30 instances)
> 15:03:29: Started weka.clusterers.OPTICS
> 15:03:29: Command: weka.clusterers.OPTICS -E 0.2 -M 5 -A
> "weka.core.EuclideanDistance -R first-last" -db-output .
> 15:03:29: null
> %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
>
>
>
>
>
>
>
>> Any help would be appreciated.
>
> Eibe Frank-2 wrote
>> Can you post the stack trace for the exception? It should be in the
>> weka.log file.
>>
>> Cheers,
>> Eibe
>>
>> On 12 Aug 2014, at 20:18, Ashish Dutt &lt;
>
>> ashish.dutt8@
>
>> &gt; wrote:
>>
>>> Hi,
>>> I tried it again. I was able to fix the replaceMissing....problem now but
>>> I again get stuck in the Hierarchical clusterer . The error message now
>>> is "Evaluate Clusterer- problem evaluating clusterer:null"
>>> Any help would be appreciated.
>>>
>>> Thank you,
>>> Ashish
>>>
>>>
>>> On Tue, Aug 12, 2014 at 3:55 PM, Ashish Dutt &lt;
>
>> ashish.dutt8@
>
>> &gt; wrote:
>>> Hi,
>>> I tried to pre-process the dataset again. Since the data contains many
>>> missing values. So I tried cleaning it using the option
>>> "ReplaceMissingValueWithUserConstant" and put 0 for string, numerical and
>>> date format. My data has no date in it. On applying the filter, I now get
>>> this error "problem setting base instances:
>>> java.lang.reflect.InvocationTargetException "
>>> Earlier, I had used the filter, "ReplaceMissingValues" and it passed. No
>>> errors but errors came while doing hierarchical clustering. So i think
>>> you are correct. The problem is at Preprocessing stage.
>>> Please help what should I do next to solve it.
>>>
>>> Thank you,
>>> Ashish
>>>
>>>
>>> On Tue, Aug 12, 2014 at 3:33 PM, Ashish Dutt &lt;
>
>> ashish.dutt8@
>
>> &gt; wrote:
>>> Thank you for responding. I did not get this error message during
>>> preprocessing. As I said earlier, I got this error message when i chose
>>> Hierarchical clustering from the cluster tab. Cluster mode is set to "use
>>> training set"
>>>
>>> Thank you,
>>> Ashish
>>>
>>>
>>>
>>> On Tue, Aug 12, 2014 at 3:24 PM, Eibe Frank &lt;
>
>> eibe@.ac
>
>> &gt; wrote:
>>> Strange. As far as I can tell, this error message only gets output by the
>>> Preprocess panel of the Explorer. Are you sure you didn’t get this
>>> problem when you applied a filter in the Preprocess panel?
>>>
>>> HierarchicalClusterer doesn’t actually use a filter.
>>>
>>> Cheers,
>>> Eibe
>>>
>>> On 12 Aug 2014, at 17:39, Ashish Dutt &lt;
>
>> ashish.dutt8@
>
>> &gt; wrote:
>>>
>>>> Dear all,
>>>>
>>>>
>>>>
>>>> I am mining a dataset that contains the logs of student interaction
>>> with an ITS. Most of the attributes are nominal in nature. I’m using Weka
>>> 3.6.11. Following is the run output
>>>>
>>>>
>>>>
>>>> === Run information ===
>>>>
>>>>
>>>> Scheme:weka.clusterers.HierarchicalClusterer -N 2 -L SINGLE -P -A
>>> "weka.core.EuclideanDistance -R first-last"
>>>>
>>>> Relation:    
>>> SampleTestData-weka.filters.unsupervised.attribute.ReplaceMissingValues-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans
>>> -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S
>>> 10-weka.filters.unsupervised.attribute.Remove-R14-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans
>>> -N 2 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S
>>> 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R2-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.attribute.AddCluster-Wweka.clusterers.SimpleKMeans
>>> -N 5 -A "weka.core.EuclideanDistance -R first-last" -I 500 -S
>>> 10-Ifirst-2,4,7,5,10-weka.filters.unsupervised.attribute.Remove-R12-weka.filters.unsupervised.instance.Randomize-S42
>>>>
>>>> Instances:    345446
>>>>
>>>> Attributes:   11
>>>>
>>>>              Anon Student Id
>>>>
>>>>              Student Response Type
>>>>
>>>>              Student Response Subtype
>>>>
>>>>              Tutor Response Type
>>>>
>>>>              Level (Module)
>>>>
>>>>              Level (Group)
>>>>
>>>>              Problem Name
>>>>
>>>>              Problem View
>>>>
>>>>              Attempt At Step
>>>>
>>>>              Outcome
>>>>
>>>>              Total Num Hints
>>>>
>>>> Test mode:evaluate on training data
>>>>
>>>>
>>>>
>>>> My problem is when I apply Hierarchical clustering to my data, I
>>> receive an error “Problem filtering instances: null”
>>>>
>>>>
>>>>
>>>> The parameters of the clustering algorithm are given below;
>>>>
>>>>
>>>>
>>>> Hierarchical clustering class
>>>>
>>>> debug= False
>>>>
>>>>
>>>> disanceFunction = EuclideanDistance -R first-last
>>>>
>>>> distanceIsBranchLength= False
>>>>
>>>> linkType = SINGLE
>>>>
>>>> numClusters=2
>>>>
>>>> preintNewick=True
>>>>
>>>>
>>>> Any help in this reference would be greatly appreciated.
>>>>
>>>>
>>>> Regards,
>>>>
>>>> Ashish
>>>>
>>>>
>>>> _______________________________________________
>>>> Wekalist mailing list
>>>> Send posts to:
>
>> Wekalist@.ac
>
>>>> List info and subscription status:
>>> http://list.waikato.ac.nz/mailman/listinfo/wekalist
>>>> List etiquette:
>>> http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>>>
>>> _______________________________________________
>>> Wekalist mailing list
>>> Send posts to:
>
>> Wekalist@.ac
>
>>> List info and subscription status:
>>> http://list.waikato.ac.nz/mailman/listinfo/wekalist
>>> List etiquette:
>>> http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>>>
>>>
>>>
>>> _______________________________________________
>>> Wekalist mailing list
>>> Send posts to:
>
>> Wekalist@.ac
>
>>> List info and subscription status:
>>> http://list.waikato.ac.nz/mailman/listinfo/wekalist
>>> List etiquette:
>>> http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>>
>> _______________________________________________
>> Wekalist mailing list
>> Send posts to:
>
>> Wekalist@.ac
>
>> List info and subscription status:
>> http://list.waikato.ac.nz/mailman/listinfo/wekalist
>> List etiquette:
>> http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
>
>
>
>
>
> --
> Sent from: http://weka.8497.n7.nabble.com/
> _______________________________________________
> Wekalist mailing list
> Send posts to: [hidden email]
> To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/mailman/listinfo/wekalist
> List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html

_______________________________________________
Wekalist mailing list
Send posts to: [hidden email]
To subscribe, unsubscribe, etc., visit https://list.waikato.ac.nz/mailman/listinfo/wekalist
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: Problem filtering instances: null using Weka 3.6.11

Alex Cronin
HI Eibe Frank-2,

I was wondering if you managed to get optics working again?

It was working for me <6 months ago. But no longer working.

In the mean time I upgraded to MaxOS Catalina Version 10.15 which might have
been the cause, but it no longer works for a range of Windows users either.

I tried a wide range of combinations I got it working once or twice but not
in a predictable fashion:
- optics distributions from 1.0.0 to 1.05
- Weka distributions both OSX and JAR between versions 3.6 and 3.9

Any insight would be welcome. I am emailing the authors to see if they have
anything to contribute.

Thanks,

Alex



--
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: Problem filtering instances: null using Weka 3.6.11

Eibe Frank-3
The latest release of the WEKA package containing OPTICS fixes the problem.

Cheers,
Eibe

On Sun, Nov 10, 2019 at 1:26 PM Alex Cronin <[hidden email]> wrote:
HI Eibe Frank-2,

I was wondering if you managed to get optics working again?

It was working for me <6 months ago. But no longer working.

In the mean time I upgraded to MaxOS Catalina Version 10.15 which might have
been the cause, but it no longer works for a range of Windows users either.

I tried a wide range of combinations I got it working once or twice but not
in a predictable fashion:
- optics distributions from 1.0.0 to 1.05
- Weka distributions both OSX and JAR between versions 3.6 and 3.9

Any insight would be welcome. I am emailing the authors to see if they have
anything to contribute.

Thanks,

Alex



--
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