X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=493f90f31c1c20d0cfb591d4acc043ff32505a8a;hb=8702eb86906bd6d59e07bb887e690a20f29be63f;hp=6090517c6b6464d4c253ba52b8efdf29cb56c823;hpb=0e2dce80a3fddaca50c96c6c27a8b32468095d6c;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 6090517..493f90f 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,58 +1,73 @@
-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices, ncores)
+# 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("K1","getCoefs"),
-		envir=environment())
+	parallel::clusterExport(cl, varlist=c("getCoefs","K1"), envir=environment())
 	repeat
 	{
-		nb_workers = max( 1, round( length(indices_clust) / 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_clust)), length(indices_clust) )
-			indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
-		})
-		indices_clust = unlist( parallel::parLapply(cl, indices_workers, function(indices)
-			computeClusters1(indices, 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_clust)
-	if (WER == "end")
-		return (indices_clust)
-	#WER=="mix"
-	computeClusters2(indices_clust, K2, getSeries, to_file=TRUE)
+	parallel::stopCluster(cl)
+	indices #medoids
 }
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters1 = function(indices, getCoefs, K1)
-	indices[ cluster::pam(getCoefs(indices), 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, to_file)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
 {
-	if (is.null(indices))
-	{
-		#get series from file
-	}
-#Puis K-means après WER...
-	if (WER=="mix" > 0)
-	{
-		curves = computeSynchrones(indices)
-		dists = computeWerDists(curves)
-		indices = computeClusters(dists, K2, diss=TRUE)
-	}
-	if (to_file)
-		#write results to file (JUST series ; no possible ID here)
+	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(inds)
-	sapply(seq_along(inds), colMeans(getSeries(inds[[i]]$indices,inds[[i]]$ids)))
+computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
+{
+	K = nrow(medoids)
+	synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
+	counts = rep(0,K)
+	index = 1
+	repeat
+	{
+		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
+		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 columns)
-computeWerDist = function(curves)
+# Compute the WER distance between the synchrones curves (in rows)
+computeWerDists = function(curves)
 {
 	if (!require("Rwave", quietly=TRUE))
 		stop("Unable to load Rwave library")
@@ -74,7 +89,7 @@ computeWerDist = function(curves)
 
 	# (normalized) observations node with CWT
 	Xcwt4 <- lapply(seq_len(n), function(i) {
-		ts <- scale(ts(curves[,i]), center=TRUE, scale=scaled)
+		ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
 		totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
 		ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
 		#Normalization