X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=75041a4c6a5cea2bebaccf847c01a41d283d3222;hp=f45c9450dab724258047c4161439f3adafc83718;hb=48108c3999d28d973443fa5e78f73a0a9f2bfc07;hpb=7b13d0c28da62d91684a29ced50c740120e2b7a9

diff --git a/epclust/R/main.R b/epclust/R/main.R
index f45c945..75041a4 100644
--- a/epclust/R/main.R
+++ b/epclust/R/main.R
@@ -7,8 +7,8 @@
 #' \itemize{
 #'   \item data.frame: each line contains its ID in the first cell, and all values after
 #'   \item connection: any R connection object (e.g. a file) providing lines as described above
-#'   \item function: a custom way to retrieve the curves; it has two arguments: the start index
-#'     (start) and number of curves (n); see example in package vignette.
+#'   \item function: a custom way to retrieve the curves; it has two arguments: the ranks to be
+#'     retrieved, and the IDs - at least one of them must be present (priority: ranks).
 #' }
 #' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
 #' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
@@ -58,7 +58,7 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
 	}
 	K1 = toInteger(K1, function(x) x>=2)
 	K2 = toInteger(K2, function(x) x>=2)
-	ntasks = toInteger(ntasks)
+	ntasks = toInteger(ntasks, function(x) x>=1)
 	nb_series_per_chunk = toInteger(nb_series_per_chunk, function(x) x>=K1)
 	min_series_per_chunk = toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk)
 	ncores_tasks = toInteger(ncores_tasks, function(x) x>=1)
@@ -67,7 +67,7 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
 		stop("WER takes values in {'end','mix'}")
 
 	# Serialize all wavelets coefficients (+ IDs) onto a file
-	coeffs_file = ".coeffs"
+	unlink(".coeffs")
 	index = 1
 	nb_curves = 0
 	nb_coeffs = NA
@@ -76,8 +76,7 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
 		coeffs_chunk = computeCoeffs(data, index, nb_series_per_chunk, wf)
 		if (is.null(coeffs_chunk))
 			break
-		serialized_coeffs = serialize(coeffs_chunk)
-		appendBinary(coeffs_file, serialized_coeffs)
+		writeCoeffs(coeffs_chunk)
 		index = index + nb_series_per_chunk
 		nb_curves = nb_curves + nrow(coeffs_chunk)
 		if (is.na(nb_coeffs))
@@ -91,22 +90,21 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series
 		stop("Too many tasks: less series in one task than min_series_per_chunk!")
 
 	# 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))
-	{
+	indices = if (random) sample(nb_curves) else seq_len(nb_curves)
+	indices_tasks = lapply(seq_len(ntasks), function(i) {
 		upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
-		indices_task[[i]] = indices[((i-1)*nb_series_per_task+1):upper_bound]
-	}
+		indices[((i-1)*nb_series_per_task+1):upper_bound]
+	})
 	library(parallel, quietly=TRUE)
 	cl_tasks = parallel::makeCluster(ncores_tasks)
-	#parallel::clusterExport(cl=cl_tasks, varlist=c("ncores_clust", ...), envir=environment())
-	indices = parallel::parLapply(cl_tasks, indices_tasks, clusteringStep12, )
+	parallel::clusterExport(cl_tasks,
+		varlist=c("K1","K2","WER","nb_series_per_chunk","ncores_clust"),#TODO: pass also
+						#nb_coeffs...and filename (in a list... ?)
+		envir=environment())
+	indices = parallel::parLapply(cl_tasks, indices_tasks, clusteringTask)
 	parallel::stopCluster(cl_tasks)
 
-##TODO: passer data ?!
-
 	# Run step1+2 step on resulting ranks
-	ranks = clusteringStep12()
-	return (list("ranks"=ranks, "medoids"=getSeries(data, ranks)))
+	indices = clusterChunk(indices, K1, K2)
+	return (list("indices"=indices, "medoids"=getSeries(data, indices)))
 }