WEKA forecasting for Crop Yield

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

WEKA forecasting for Crop Yield

Shital Bhojani
I am using the district rainfall data for yield prediction for a specific
crop.  I want to use the same dataset with the variable number of columns.
First I used the average rainfall and apply the forecast algorithm of weka
(only 2 column in the dataset). Then I have used the weekly (17 weeks) data
and tried to forecast the yield (17 columns of weekly data and one column of
crop yield). I have now two files but still, it's showing me the same result
as an output. Please help me in this regard. How can Proceed for better
predictions?



--
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 %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
List etiquette: http://www.cs.waikato.ac.nz/~ml/weka/mailinglist_etiquette.html
Reply | Threaded
Open this post in threaded view
|

Re: WEKA forecasting for Crop Yield

Eibe Frank-2
Administrator
That sounds interesting, but I don’t quite understand the format of your data.

Normally, for the time series forecasting panel to be applicable, there should be a date attribute (i.e., a date column in your data) and one target attribute value for each date (+ potential values of “overlay” attributes).

There are some example datasets in

<HOME>/wekafiles/packages/timeseriesForecasting/sample-data

where HOME is normally your user home.

Cheers,
Eibe

> On 17/09/2019, at 5:45 PM, Shital Bhojani <[hidden email]> wrote:
>
> I am using the district rainfall data for yield prediction for a specific
> crop.  I want to use the same dataset with the variable number of columns.
> First I used the average rainfall and apply the forecast algorithm of weka
> (only 2 column in the dataset). Then I have used the weekly (17 weeks) data
> and tried to forecast the yield (17 columns of weekly data and one column of
> crop yield). I have now two files but still, it's showing me the same result
> as an output. Please help me in this regard. How can Proceed for better
> predictions?
>
>
>
> --
> 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 %(web_page_url)slistinfo%(cgiext)s/%(_internal_name)s
> 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: WEKA forecasting for Crop Yield

Shital Bhojani
Thank you, sir!

My dataset is not daily. So the date filed is not available in the dataset.
But I have rendered through the WEKA and found the Overlay attribute can
help me in this regard.

Thanks!




--
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