millisecond running precision

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

millisecond running precision

falete
Hi,

I'm running regression models using the forecast tab (Explorer) and I can
get an approximate processing time checking on the log.

00:52:18: Started LinearRegression -S 0 -R 1.0E-8 -num-decimal-places 4
00:52:19: Finished LinearRegression -S 0 -R 1.0E-8 -num-decimal-places 4

However, the accuracy is of seconds, however, it may loss much precision. Is
it possible to get a millisecond accuracy?

Please, if you know another way to measure the process time is welcomed.





--
Sent from: https://weka.8497.n7.nabble.com/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
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: millisecond running precision

Peter Reutemann
> I'm running regression models using the forecast tab (Explorer) and I can
> get an approximate processing time checking on the log.
>
> 00:52:18: Started LinearRegression -S 0 -R 1.0E-8 -num-decimal-places 4
> 00:52:19: Finished LinearRegression -S 0 -R 1.0E-8 -num-decimal-places 4
>
> However, the accuracy is of seconds, however, it may loss much precision. Is
> it possible to get a millisecond accuracy?
>
> Please, if you know another way to measure the process time is welcomed.

If you're after *exact* time measurements, then you will have to code
this yourself (check out the source code of the forecast package).

The Experimenter uses the CPU time that was used by an algorithm,
using the java.lang.management.ThreadMXBean class.
Here it is used in the RegressionSplitEvaluator class:
https://github.com/Waikato/weka-trunk/blob/b0ed0886a092c1786d37083171a422ffbe8c6c98/weka/src/main/java/weka/experiment/RegressionSplitEvaluator.java#L560

See also:
https://stackoverflow.com/a/22894871/4698227

Cheers, Peter
--
Peter Reutemann
Dept. of Computer Science
University of Waikato, NZ
+64 (7) 577-5304
http://www.cms.waikato.ac.nz/~fracpete/
http://www.data-mining.co.nz/
_______________________________________________
Wekalist mailing list -- [hidden email]
Send posts to [hidden email]
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