Using both weka and r language

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

Using both weka and r language

asadbtk
Hi

Is it a good idea if we use some preprocessing steps like feature selection, class balancing using smot in weka and save the datasets. Then load it into r language and evaluate it with some machine learning techniques such as random forest? Because r language is more generous in tuning the parameters of the algorithm before we evaluate it? 

Best regards 

_______________________________________________
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: Using both weka and r language

Eibe Frank-2
Administrator
Using supervised preprocessing techniques in one framework (e.g., WEKA) and then switching to another framework (e.g., R) in order to be able to more easily “forget” that these techniques have been applied is obviously a bad idea.

Cheers,
Eibe

> On 14/11/2019, at 11:45 PM, javed khan <[hidden email]> wrote:
>
> Hi
>
> Is it a good idea if we use some preprocessing steps like feature selection, class balancing using smot in weka and save the datasets. Then load it into r language and evaluate it with some machine learning techniques such as random forest? Because r language is more generous in tuning the parameters of the algorithm before we evaluate it?
>
> Best regards
> _______________________________________________
> 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
Reply | Threaded
Open this post in threaded view
|

Re: Using both weka and r language

asadbtk
Hi Eibe, I understand but I intend to use the meta heuristic algorithms for feature selection in weka which is either not possible or difficult and time consuming using r language. On the other hand, hyperparameter tuning in weka (I use explorer) is limited to grid and random searches. I am planning to clean the datasets using weka and upload it somewhere so that other people can use it regardless of the development tools. 

On Thursday, November 14, 2019, Eibe Frank <[hidden email]> wrote:
Using supervised preprocessing techniques in one framework (e.g., WEKA) and then switching to another framework (e.g., R) in order to be able to more easily “forget” that these techniques have been applied is obviously a bad idea.

Cheers,
Eibe

> On 14/11/2019, at 11:45 PM, javed khan <[hidden email]> wrote:
>
> Hi
>
> Is it a good idea if we use some preprocessing steps like feature selection, class balancing using smot in weka and save the datasets. Then load it into r language and evaluate it with some machine learning techniques such as random forest? Because r language is more generous in tuning the parameters of the algorithm before we evaluate it?
>
> Best regards
> _______________________________________________
> 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

_______________________________________________
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