valentinitnelav · August 29, 2017 12:38
diff --git a/closest_geodesic_distance_parallel_foreach_example.R b/closest_geodesic_distance_parallel_foreach_example.R
 # Example of using foreach parallel loop
 # This should work both on Linux and Windows without any modifications.

 # for an interesting intro, check:
 # http://bgc.yale.edu/sites/default/files/ParallelR.html

 library(foreach)
 library(doParallel)

 # Prepare cluster
 FractionCores=0.7 # fraction of cores to use
 numCores <- round(FractCores * parallel::detectCores())
 cl <- parallel::makeCluster(numCores)
 doParallel::registerDoParallel(cl)

 system.time({
    res <- 
        foreach(
            i = 1:length(PLdt_SPdf_NA),
            .combine      = rbind, # how to combine results (the default is a list)
            .multicombine = TRUE,  # if .combine = rbind (above) then .multicombine defaults to TRUE anyway (so redundant here)
            .packages     = c("geosphere"), # packages to load during parallel execution. This should be done even if you call geosphere::dist2Line below
            .options.multicore = list(preschedule=FALSE) # load balancing (only if needed, default is TRUE)
        ) %dopar% 
        {
            geosphere::dist2Line(p       = PLdt_SPdf_NA[i,],
                                 line    = poly.sp.rich,
                                 distfun = distHaversine)
            # if you have multiple operations here, it will return only the last assigned variable
        }
 })
 stopCluster(cl)

 # Note the fact that the foreach() loop returns object(s), so assign the foreach to a variable name like res <- foreach(...), 
 # otherwise you'll lost the results
	# Example of using foreach parallel loop
	# This should work both on Linux and Windows without any modifications.

	# for an interesting intro, check:
	# http://bgc.yale.edu/sites/default/files/ParallelR.html

	library(foreach)
	library(doParallel)

	# Prepare cluster
	FractionCores=0.7 # fraction of cores to use
	numCores <- round(FractCores * parallel::detectCores())
	cl <- parallel::makeCluster(numCores)
	doParallel::registerDoParallel(cl)

	system.time({
	res <-
	foreach(
	i = 1:length(PLdt_SPdf_NA),
	.combine = rbind, # how to combine results (the default is a list)
	.multicombine = TRUE, # if .combine = rbind (above) then .multicombine defaults to TRUE anyway (so redundant here)
	.packages = c("geosphere"), # packages to load during parallel execution. This should be done even if you call geosphere::dist2Line below
	.options.multicore = list(preschedule=FALSE) # load balancing (only if needed, default is TRUE)
	) %dopar%
	{
	geosphere::dist2Line(p = PLdt_SPdf_NA[i,],
	line = poly.sp.rich,
	distfun = distHaversine)
	# if you have multiple operations here, it will return only the last assigned variable
	}
	})
	stopCluster(cl)

	# Note the fact that the foreach() loop returns object(s), so assign the foreach to a variable name like res <- foreach(...),
	# otherwise you'll lost the results