parallel doesnt work on custom functions

earowang / hts

Hierarchical and Grouped Time Series

http://pkg.earo.me/hts

110 stars 36 forks source link

Closed brunocarlin closed 4 years ago

brunocarlin commented 5 years ago

forecast.gts( htseg1, h = 10, method = "comb", algorithms = "lu",weights = "mint", FUN = function(x) snaive(x), parallel = T,num.cores = 2 )

yasineahmed commented 4 years ago

any updates on this? trying to use BaggedETS

yasineahmed commented 4 years ago

work around solution would be to add needed libraries using clusterEvalQ. trace(forecast.gts, edit = TRUE) clusterEvalQ(cl, {library(forecast)})