X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=493f90f31c1c20d0cfb591d4acc043ff32505a8a;hp=fce1b1c695f4b6094580375e28a6cd5cd0f1e805;hb=8702eb86906bd6d59e07bb887e690a20f29be63f;hpb=86223e279a954d946ae641888f5107ed9feb6217

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index fce1b1c..493f90f 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -2,16 +2,24 @@
 clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores)
 {
 	cl = parallel::makeCluster(ncores)
+	parallel::clusterExport(cl, varlist=c("getCoefs","K1"), envir=environment())
 	repeat
 	{
-		nb_workers = max( 1, round( length(indices) / nb_series_per_chunk ) )
-		indices_workers = lapply(seq_len(nb_workers), function(i) {
-			upper_bound = ifelse( i<nb_workers,
-				min(nb_series_per_chunk*i,length(indices)), length(indices) )
-			indices[(nb_series_per_chunk*(i-1)+1):upper_bound]
-		})
-		indices = unlist( parallel::parLapply(cl, indices_workers, function(inds)
-			computeClusters1(getCoefs(inds), K1)) )
+		nb_workers = max( 1, floor( length(indices) / nb_series_per_chunk ) )
+		indices_workers = lapply( seq_len(nb_workers), function(i)
+			indices[(nb_series_per_chunk*(i-1)+1):(nb_series_per_chunk*i)] )
+		# Spread the remaining load among the workers
+		rem = length(indices) %% nb_series_per_chunk
+		while (rem > 0)
+		{
+			index = rem%%nb_workers + 1
+			indices_workers[[index]] = c(indices_workers[[index]], tail(indices,rem))
+			rem = rem - 1
+		}
+		indices = unlist( parallel::parLapply( cl, indices_workers, function(inds) {
+			require("epclust", quietly=TRUE)
+			inds[ computeClusters1(getCoefs(inds), K1) ]
+		} ) )
 		if (length(indices) == K1)
 			break
 	}
@@ -21,20 +29,18 @@ clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores)
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
 computeClusters1 = function(coefs, K1)
-	indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
+	cluster::pam(coefs, K1, diss=FALSE)$id.med
 
 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
 computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
 {
 	synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
-	cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids
+	medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ]
 }
 
 # Compute the synchrones curves (sum of clusters elements) from a clustering result
 computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
 {
-	#les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les
-	#courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ?
 	K = nrow(medoids)
 	synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
 	counts = rep(0,K)
@@ -48,18 +54,20 @@ computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
 		#get medoids indices for this chunk of series
 		for (i in seq_len(nrow(ref_series)))
 		{
-			j = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) )
-			synchrones[j,] = synchrones[j,] + series[i,]
+			j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
+			synchrones[j,] = synchrones[j,] + ref_series[i,]
 			counts[j] = counts[j] + 1
 		}
 		index = index + nb_series_per_chunk
 	}
 	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
-	sweep(synchrones, 1, counts, '/')
+	#      ...maybe; but let's hope resulting K1' be still quite bigger than K2
+	synchrones = sweep(synchrones, 1, counts, '/')
+	synchrones[ sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,]))) , ]
 }
 
 # Compute the WER distance between the synchrones curves (in rows)
-computeWerDist = function(curves)
+computeWerDists = function(curves)
 {
 	if (!require("Rwave", quietly=TRUE))
 		stop("Unable to load Rwave library")