[R] slowness of auto.arima() from package forecast (was Execution time very high in linux)

[Joao Santos]

Hello Bernardo,

Thanks for replying but I think that you miss a small detail, my frequency
isn't 1 but 168 and it looks like this is the bottleneck.

João Santos
  


Bernardo Rangel tura wrote:
> 
> 
> On Fri, 2007-11-09 at 06:58 -0800, Joao Santos wrote:
>> Hello,
>> 
>> EXAMPLE
>> ##Create time series
>> bb_500 = scan("my_file.dat")
>> ts <- ts(bb_500, frequency=168)
>> 
>> ts
>> Time Series:
>> Start = c(1, 1) 
>> End = c(3, 164) 
>> Frequency = 168 
>>   [1] 61 60 60 59 58 58 58 58 58 61 64 65 65 64 64 64 63 63 62 61 60 60
>> 60
> (...)
> 
>> ##Find the best model using auto.arima() from package forecast 
>> 
>> system.time(fit.500<-auto.arima(ts, d = NA, D = NA, max.p = 2, max.q = 2,
>>             max.P = 1, max.Q = 1, max.order = 5,
>>             start.p=0, start.q=0, start.P=0, start.Q=0,
>>                         stationary = FALSE, ic = c("aic","aicc", "bic"), 
>>             stepwise=FALSE, trace=TRUE))
>> (...)
> 
>>  ARIMA(2,0,2)(1,1,0)[168]          : 1e+20 *
>>  ARIMA(2,0,2)(1,1,0)[168] with drift         : 1e+20 *
>> 
>> ##    user   system  elapsed 
>> ##19041.573  3806.364 22849.199 -> ~6 hours 
> 
> Hi João !
> 
> In my computer (using ubuntu 7.10)  my output with stepwise=F is
> 
>  ARIMA(0,0,0) with zero mean     : 5593.194
>  ARIMA(0,0,0) with zero mean     : 3590.859
>  ARIMA(0,0,1) with zero mean     : 4913.543
>  ARIMA(0,0,1) with zero mean     : 2970.582
>  ARIMA(0,0,2) with zero mean     : 4303.206
>  ARIMA(0,0,2) with zero mean     : 2591.151
>  ARIMA(1,0,0) with zero mean     : 1e+20
>  ARIMA(1,0,0) with zero mean     : 2395.506
>  ARIMA(1,0,1) with zero mean     : 2161.814
>  ARIMA(1,0,1) with zero mean     : 2140.694
>  ARIMA(1,0,2) with zero mean     : 2116.413
>  ARIMA(1,0,2) with zero mean     : 2087.563
>  ARIMA(2,0,0) with zero mean     : 2127.992
>  ARIMA(2,0,0) with zero mean     : 2065.447
>  ARIMA(2,0,1) with zero mean     : 2108.049
>  ARIMA(2,0,1) with zero mean     : 2059.157
>  ARIMA(2,0,2) with zero mean     : 2108.159
>  ARIMA(2,0,2) with zero mean     : 2057.5
> 
>    user  system elapsed 
>   1.016   0.012   2.011 
> 
> with stepwise=T the output is:
> 
>  ARIMA(0,0,0) with zero mean     : 3590.859
>  ARIMA(0,0,0) with zero mean     : 3590.859
>  ARIMA(1,0,0) with zero mean     : 2395.506
>  ARIMA(0,0,1) with zero mean     : 2970.582
>  ARIMA(2,0,0) with zero mean     : 2065.447
>  ARIMA(2,0,1) with zero mean     : 2059.157
>  ARIMA(2,0,1) with zero mean     : 2108.049
>  ARIMA(1,0,1) with zero mean     : 2140.694
>  ARIMA(2,0,2) with zero mean     : 2057.5
>  ARIMA(2,0,2) with zero mean     : 2108.159
>  ARIMA(1,0,2) with zero mean     : 2087.563
> 
>  Best model: ARIMA(2,0,2) with zero mean     
> 
>    user  system elapsed 
>   0.752   0.004   0.796 
> 
> I using a AMD SEMPRO 2800+ with 1 Gb RAM so I think the slow output is
> because other cause.
> 
> 
> 
> -- 
> []s
> Tura
> 
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
> 
> 

-- 
View this message in context: http://www.nabble.com/Help-me-please...Large-execution-time-in-auto.arima%28%29-function-tf4771610.html#a13704121
Sent from the R help mailing list archive at Nabble.com.