renaming, refactoring

[epclust.git] / epclust / R / main.R

diff --git a/epclust/R/main.R b/epclust/R/main.R
index e794351..f45c945 100644 (file)
--- a/epclust/R/main.R
+++ b/epclust/R/main.R
@@ -40,7 +40,7 @@
 epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1,
        wf="haar", WER="end", ncores_tasks=1, ncores_clust=4, random=TRUE)
 {
-       #0) check arguments
+       # Check arguments
        if (!is.data.frame(data) && !is.function(data))
        {
                tryCatch(
@@ -66,7 +66,7 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
        if (WER!="end" && WER!="mix")
                stop("WER takes values in {'end','mix'}")
 
-       #1) Serialize all wavelets coefficients (+ IDs) onto a file
+       # Serialize all wavelets coefficients (+ IDs) onto a file
        coeffs_file = ".coeffs"
        index = 1
        nb_curves = 0
@@ -84,20 +84,15 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
                        nb_coeffs = ncol(coeffs_chunk)-1
        }
 
-#      finalizeSerialization(coeffs_file) ........, nb_curves, )
-#TODO: is it really useful ?! we will always have these informations (nb_curves, nb_coeffs)
-
        if (nb_curves < min_series_per_chunk)
                stop("Not enough data: less rows than min_series_per_chunk!")
        nb_series_per_task = round(nb_curves / ntasks)
        if (nb_series_per_task < min_series_per_chunk)
                stop("Too many tasks: less series in one task than min_series_per_chunk!")
 
-       #2) Cluster coefficients in parallel (by nb_series_per_chunk)
-       # All indices, relative to complete dataset
-       indices = if (random) sample(nb_curves) else seq_len(nb_curves)
-       # Indices to be processed in each task
-       indices_tasks = list()
+       # Cluster coefficients in parallel (by nb_series_per_chunk)
+       indices = if (random) sample(nb_curves) else seq_len(nb_curves) #all indices
+       indices_tasks = list() #indices to be processed in each task
        for (i in seq_len(ntasks))
        {
                upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
@@ -105,12 +100,13 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
        }
        library(parallel, quietly=TRUE)
        cl_tasks = parallel::makeCluster(ncores_tasks)
-       parallel::clusterExport(cl_tasks, ..........ncores_clust, indices_tasks, nb_series_per_chunk, processChunk, K1,
-                                                                        K2, WER, )
-       ranks = parallel::parSapply(cl_tasks, seq_along(indices_tasks), oneIteration)
+       #parallel::clusterExport(cl=cl_tasks, varlist=c("ncores_clust", ...), envir=environment())
+       indices = parallel::parLapply(cl_tasks, indices_tasks, clusteringStep12, )
        parallel::stopCluster(cl_tasks)
 
-       #3) Run step1+2 step on resulting ranks
-       ranks = oneIteration(.........)
+##TODO: passer data ?!
+
+       # Run step1+2 step on resulting ranks
+       ranks = clusteringStep12()
        return (list("ranks"=ranks, "medoids"=getSeries(data, ranks)))
 }