X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=36b476987452e84e2978e2093957d2f9d25c25e0;hb=37c82bbafbffc19e8b47a521952bac58f189e9ea;hp=a4c273a7ce8dbc91ba3480fac4a83d61d0b70ae6;hpb=a174b8ea1f322992068ab42810df017a2b9620ee;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index a4c273a..36b4769 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,6 +1,6 @@
 #' @name clustering
 #' @rdname clustering
-#' @aliases clusteringTask1 computeClusters1 computeClusters2
+#' @aliases clusteringTask1 clusteringTask2 computeClusters1 computeClusters2
 #'
 #' @title Two-stage clustering, withing one task (see \code{claws()})
 #'
@@ -11,8 +11,8 @@
 #'   and then WER distances computations, before applying the clustering algorithm.
 #'   \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic
 #'   clustering procedures respectively for stage 1 and 2. The former applies the
-#'   clustering algorithm (PAM) on a contributions matrix, while the latter clusters
-#'   a chunk of series inside one task (~max nb_series_per_chunk)
+#'   first clustering algorithm on a contributions matrix, while the latter clusters
+#'   a set of series inside one task (~nb_items_clust)
 #'
 #' @param indices Range of series indices to cluster in parallel (initial data)
 #' @param getContribs Function to retrieve contributions from initial series indices:
@@ -30,20 +30,20 @@ NULL
 
 #' @rdname clustering
 #' @export
-clusteringTask1 = function(
-	indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
+clusteringTask1 = function(indices, getContribs, K1, nb_items_clust1,
+	ncores_clust=1, verbose=FALSE, parll=TRUE)
 {
 	if (verbose)
 		cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
 
 	if (parll)
 	{
-		cl = parallel::makeCluster(ncores_clust)
+		cl = parallel::makeCluster(ncores_clust, outfile = "")
 		parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
 	}
 	while (length(indices) > K1)
 	{
-		indices_workers = .spreadIndices(indices, nb_series_per_chunk)
+		indices_workers = .spreadIndices(indices, nb_items_clust1, K1+1)
 		indices <-
 			if (parll)
 			{
@@ -87,7 +87,7 @@ computeClusters1 = function(contribs, K1, verbose=FALSE)
 {
 	if (verbose)
 		cat(paste("   computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
-	cluster::pam(contribs, K1, diss=FALSE)$id.med
+	cluster::pam(        t(contribs)       , K1, diss=FALSE)$id.med
 }
 
 #' @rdname clustering
@@ -96,7 +96,7 @@ computeClusters2 = function(distances, K2, verbose=FALSE)
 {
 	if (verbose)
 		cat(paste("   computeClusters2() on ",nrow(distances)," lines\n", sep=""))
-	cluster::pam(distances, K2, diss=TRUE)$id.med
+	cluster::pam(       distances        , K2, diss=TRUE)$id.med
 }
 
 #' computeSynchrones
@@ -110,7 +110,7 @@ computeClusters2 = function(distances, K2, verbose=FALSE)
 #' @param nb_ref_curves How many reference series? (This number is known at this stage)
 #' @inheritParams claws
 #'
-#' @return A big.matrix of size K1 x L where L = data_length
+#' @return A big.matrix of size L x K1 where L = length of a serie
 #'
 #' @export
 computeSynchrones = function(medoids, getRefSeries,
@@ -142,8 +142,8 @@ computeSynchrones = function(medoids, getRefSeries,
 		{
 			if (parll)
 				synchronicity::lock(m)
-			synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,]
-			counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts?
+			synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i]
+			counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? ...or as arg?!
 			if (parll)
 				synchronicity::unlock(m)
 		}
@@ -152,7 +152,7 @@ computeSynchrones = function(medoids, getRefSeries,
 	K = nrow(medoids) ; L = ncol(medoids)
 	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
 	# TODO: if size > RAM (not our case), use file-backed big.matrix
-	synchrones = bigmemory::big.matrix(nrow=K, ncol=L, type="double", init=0.)
+	synchrones = bigmemory::big.matrix(nrow=L, ncol=K, type="double", init=0.)
 	counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
 	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
 	parll = (requireNamespace("synchronicity",quietly=TRUE)
@@ -181,14 +181,14 @@ computeSynchrones = function(medoids, getRefSeries,
 
 	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
 	for (i in seq_len(K))
-		synchrones[i,] = synchrones[i,] / counts[i,1]
+		synchrones[,i] = synchrones[,i] / counts[i]
 	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
 	#      ...maybe; but let's hope resulting K1' be still quite bigger than K2
-	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
+	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[,i])))
 	if (all(noNA_rows))
 		return (synchrones)
 	# Else: some clusters are empty, need to slice synchrones
-	synchrones[noNA_rows,]
+	bigmemory::as.big.matrix(synchrones[,noNA_rows])
 }
 
 #' computeWerDists
@@ -272,7 +272,7 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS
 	{
 		#from cwt_file ...
 		res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian)
-	###############TODO:	
+	###############TODO:
 	}
 
 	# Distance between rows i and j
@@ -317,20 +317,31 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS
 }
 
 # Helper function to divide indices into balanced sets
-.spreadIndices = function(indices, nb_per_chunk)
+.spreadIndices = function(indices, max_per_set, min_nb_per_set = 1)
 {
 	L = length(indices)
-	nb_workers = floor( L / nb_per_chunk )
-	if (nb_workers == 0)
+	min_nb_workers = floor( L / max_per_set )
+	rem = L %% max_per_set
+	if (nb_workers == 0 || (nb_workers==1 && rem==0))
 	{
-		# L < nb_series_per_chunk, simple case
+		# L <= max_nb_per_set, simple case
 		indices_workers = list(indices)
 	}
 	else
 	{
 		indices_workers = lapply( seq_len(nb_workers), function(i)
-			indices[(nb_per_chunk*(i-1)+1):(nb_per_chunk*i)] )
-		# Spread the remaining load among the workers
+			indices[(max_nb_per_set*(i-1)+1):(max_per_set*i)] )
+		# Two cases: remainder is >= min_per_set (easy)...
+		if (rem >= min_nb_per_set)
+			indices_workers = c( indices_workers, list(tail(indices,rem)) )
+		#...or < min_per_set: harder, need to remove indices from current sets to feed
+		# the too-small remainder. It may fail: then fallback to "slightly bigger sets"
+		else
+		{
+			save_indices_workers = indices_workers
+			small_set = tail(indices,rem)
+			# Try feeding small_set until it reaches min_per_set, whle keeping the others big enough
+			# Spread the remaining load among the workers
 		rem = L %% nb_per_chunk
 		while (rem > 0)
 		{