dear members,
I am using pbmclapply in pbmcapply package, to do
parallel processing in my R function. Below is the line that is malfunctioning:
> LYG1b <- pbmclapply(lygh171, FUN = auto.arima, mc.cores = detectCores())
auto.arima is a function from the "forecast" package. The length of
lygh171 is 2435.
NOW:
> LYG1b[[1]]
[1] "Error in ts(x) : 'ts' object must have one or more
observations\n"
attr(,"class")
[1] "try-error"
attr(,"condition")
<simpleError in ts(x): 'ts' object must have one or more
observations>
AND:
> auto.arima(lygh171[[1]])
Series: lygh171[[1]]
ARIMA(0,1,0)
sigma^2 estimated as 2.303: log likelihood=-66.1
AIC=134.2 AICc=134.31 BIC=135.78
AND:
> LYG1ba <- pbmclapply(lygh171[1:9], FUN = auto.arima, mc.cores =
detectCores())
> LYG1ba[[1]]
Series: X[[i]]
ARIMA(0,1,0)
sigma^2 estimated as 2.303: log likelihood=-66.1
AIC=134.2 AICc=134.31 BIC=135.78
Why is LYG1b[[1]] not welldefined but LYG1ba[[1]] is eventhough the
function(auto.arima) is the same in both cases? And why is the direct
application of auto.arima on lygh171[[1]] successful, but not when auto.arima is
iterated through pbmclapply on lygh171?
here is the output of dput:
lygh171[1:9] <- list(c(0.699999999999999, 0.399999999999999,
0.300000000000001,
0.149999999999999, 0.25, 0.949999999999999, 1, 0.300000000000001,
0.65, 0.199999999999999, 0.6, 0.0999999999999996, 0.00141287284144427,
1.55, 0.15, 0.300000000000001, 0.449999999999999, 0.350000000000001,
0.149999999999999, 2.35, 0.25, 0.100000000000001, 3.7, 3.95,
3.05, 0.899999999999999, 0.399999999999999, 1.05, 1.1, 1.95,
2, 0.649999999999999, 0.699999999999999, 0.25, 5.25, 0.800000000000001,
0.00141287284144427), c(0, 0.199999999999999, 1.3, 2, 1.9, 1.6
), c(0.699999999999999, 0.399999999999999, 0.300000000000001,
0.149999999999999, 0.25, 1, 0.300000000000001, 0.65, 0.199999999999999,
0.0999999999999996, 0.300000000000001, 0.15, 0.25, 0.15, 0.300000000000001,
0.449999999999999, 0.800000000000001, 0.25, 0.350000000000001,
0.149999999999999, 2.35, 0.25, 0.100000000000001, 3.7, 3.95,
3.05, 0.899999999999999, 0.399999999999999, 1.05, 1.1, 1.95,
2, 0.649999999999999, 0.699999999999999, 0.25, 5.25, 0.800000000000001,
0.699999999999999, 0.449999999999999, 0.800000000000001, 0.800000000000001
), c(0.0500000000000007, 0.25, 0.100000000000001, 1.25, 1, 0.65,
0.65, 0.9, 0.4, 0.0500000000000007, 0.0500000000000007, 0.450000000000001,
1.2, 0.5, 0.15, 0.35, 0.0500000000000007, 0.300000000000001,
1.1, 0.0999999999999996, 0.950000000000001, 0.25, 0.75, 0.199999999999999,
0.5, 0.5, 0.25, 2, 0.699999999999999, 2.75, 1.65, 0.149999999999999,
0.200000000000003, 2, 1.25, 4.3, 0.600000000000001, 0.75, 0.549999999999997,
0.5, 3.6, 4.1, 0.899999999999999, 0.100000000000001, 1, 0.25,
0.100000000000001, 0.399999999999999, 0.149999999999999, 1.7,
0.949999999999999, 0.150000000000002), c(0.0500000000000007,
0.25, 0.15, 0.0999999999999996, 0.5, 0.15, 0.600000000000001,
1, 0.149999999999999, 0.600000000000001, 3.05, 0.100000000000001,
0.199999999999999, 1.3), c(0.5, 0.5, 0.0999999999999996, 1.2,
3.75, 1.9), c(0.000770416024653313, 0.550000000000001, 1.2, 3
), 1, 0.25)
very many thanks for your time and effort....
yours sincerely,
AKSHAY M KULKARNI
[[alternative HTML version deleted]]