X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=493f90f31c1c20d0cfb591d4acc043ff32505a8a;hb=8702eb86906bd6d59e07bb887e690a20f29be63f;hp=87a5f914e137cb3f509443b58a1e59b80505b011;hpb=3eef8d3df59ded9a281cff51f79fe824198a7427;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 87a5f91..493f90f 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,77 +1,73 @@
-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_file,
-	getCoefs,K1,K2,nb_series_per_chunk,ncores,to_file,ftype)
+# Cluster one full task (nb_curves / ntasks series); only step 1
+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(inds, getCoefs, K1)) )
-		if (length(indices_clust) == 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
 	}
 	parallel::stopCluster(cl)
-	if (K2 == 0)
-		return (indices)
-	computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file,
-									 nb_series_per_chunk,ftype)
-	vector("integer",0)
+	indices #medoids
 }
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters1 = function(indices, getCoefs, K1)
-{
-	coefs = getCoefs(indices)
-	indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
-}
+computeClusters1 = function(coefs, K1)
+	cluster::pam(coefs, K1, diss=FALSE)$id.med
 
 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file,
-														nb_series_per_chunk, ftype)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
 {
-	curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk)
-	dists = computeWerDists(curves)
-	medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
-	if (to_file)
-	{
-		serialize(medoids, synchrones_file, ftype, nb_series_per_chunk)
-		return (NULL)
-	}
-	medoids
+	synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
+	medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ]
 }
 
 # Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk)
+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 ?
-	medoids = getSeries(indices)
 	K = nrow(medoids)
 	synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
 	counts = rep(0,K)
 	index = 1
 	repeat
 	{
-		series = getSeriesForSynchrones((index-1)+seq_len(nb_series_per_chunk))
-		if (is.null(series))
+		range = (index-1) + seq_len(nb_series_per_chunk)
+		ref_series = getRefSeries(range)
+		if (is.null(ref_series))
 			break
 		#get medoids indices for this chunk of series
-		index = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) )
-		synchrones[index,] = synchrones[index,] + series[i,]
-		counts[index] = counts[index] + 1
+		for (i in seq_len(nrow(ref_series)))
+		{
+			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)
+	#      ...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")