# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(K1, K2, WER, nb_series_per_chunk, indices_tasks, ncores_clust)
+clusteringTask = function(indices_clust)
{
cl_clust = parallel::makeCluster(ncores_clust)
- #parallel::clusterExport(cl=cl_clust, varlist=c("fonctions_du_package"), envir=environment())
- indices_clust = indices_task[[i]]
+ parallel::clusterExport(cl_clust,
+ varlist=c("K1","K2","WER"),
+ envir=environment())
repeat
{
nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
- indices_workers = list()
- for (i in 1:nb_workers)
- {
+ indices_workers = lapply(seq_len(nb_workers), function(i) {
upper_bound = ifelse( i<nb_workers,
min(nb_series_per_chunk*i,length(indices_clust)), length(indices_clust) )
- indices_workers[[i]] = indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
- }
- indices_clust = parallel::parLapply(cl, indices_workers, clusterChunk, K1, K2*(WER=="mix"))
+ indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
+ })
+ indices_clust = parallel::parLapply(cl, indices_workers, clusterChunk)
# TODO: soft condition between K2 and K1, before applying final WER step
if ((WER=="end" && length(indices_clust)==K1) || (WER=="mix" && length(indices_clust)==K2))
break
}
# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-clusterChunk = function(indices, K1, K2)
+clusterChunk = function(indices_chunk)
{
- coeffs = getCoeffs(indices)
+ coeffs = readCoeffs(indices_chunk)
cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE)
- if (K2 > 0)
+ if (WER=="mix" > 0)
{
curves = computeSynchrones(cl)
dists = computeWerDists(curves)
cl = computeClusters(dists, K2, diss=TRUE)
}
- indices[cl]
+ indices_chunk[cl]
}
# Apply the clustering algorithm (PAM) on a coeffs or distances matrix