X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=4d43b2b3801daa880ce004c7a2eb9f73f0894a9b;hp=0d37c243d4f76be57f157cb1ed5b59a0e4ef76b2;hb=363ae13430cdee6ba76b42b7316aa4b292b04d93;hpb=777c4b0274c059eeb5d4bd784ef773e819a7f7a2

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 0d37c24..4d43b2b 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -123,17 +123,46 @@ computeSynchrones = function(medoids, getRefSeries,
 	{
 		ref_series = getRefSeries(indices)
 		nb_series = nrow(ref_series)
-		#get medoids indices for this chunk of series
 
-		#TODO: debug this (address is OK but values are garbage: why?)
-#		 mi = .Call("computeMedoidsIndices", medoids@address, ref_series, PACKAGE="epclust")
+		if (parll)
+		{
+			require("bigmemory", quietly=TRUE)
+			require("synchronicity", quietly=TRUE)
+			require("epclust", quietly=TRUE)
+			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
+			medoids <- bigmemory::attach.big.matrix(medoids_desc)
+			m <- synchronicity::attach.mutex(m_desc)
+		}
+
+
 
-		#R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope)
-		mat_meds = medoids[,]
-		mi = rep(NA,nb_series)
-		for (i in 1:nb_series)
-			mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) )
-		rm(mat_meds); gc()
+#TODO: use dbs(),
+		#https://www.r-bloggers.com/debugging-parallel-code-with-dbs/
+		#http://gforge.se/2015/02/how-to-go-parallel-in-r-basics-tips/
+
+#OK ::
+#write(length(indices), file="TOTO")
+#write( computeMedoidsIndices(medoids@address, getRefSeries(indices[1:600])), file="TOTO")
+#stop()
+
+#		write(indices, file="TOTO", ncolumns=10, append=TRUE)
+#write("medoids", file = "TOTO", ncolumns=1, append=TRUE)
+#write(medoids[1,1:3], file = "TOTO", ncolumns=1, append=TRUE)
+#write("synchrones", file = "TOTO", ncolumns=1, append=TRUE)
+#write(synchrones[1,1:3], file = "TOTO", ncolumns=1, append=TRUE)
+
+#NOT OK :: (should just be "ref_series") ...or yes ? race problems mutex then ? ?!
+		#get medoids indices for this chunk of series
+		mi = computeMedoidsIndices(medoids@address, getRefSeries(indices[1:600]))  #ref_series)
+write("MI ::::", file = "TOTO", ncolumns=1, append=TRUE)
+write(mi[1:3], file = "TOTO", ncolumns=1, append=TRUE)
+
+#		#R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope)
+#		mat_meds = medoids[,]
+#		mi = rep(NA,nb_series)
+#		for (i in 1:nb_series)
+#			mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) )
+#		rm(mat_meds); gc()
 
 		for (i in seq_len(nb_series))
 		{
@@ -155,18 +184,19 @@ computeSynchrones = function(medoids, getRefSeries,
 	parll = (requireNamespace("synchronicity",quietly=TRUE)
 		&& parll && Sys.info()['sysname'] != "Windows")
 	if (parll)
+	{
 		m <- synchronicity::boost.mutex()
+		m_desc <- synchronicity::describe(m)
+		synchrones_desc = bigmemory::describe(synchrones)
+		medoids_desc = bigmemory::describe(medoids)
 
-	if (parll)
-	{
 		cl = parallel::makeCluster(ncores_clust)
 		parallel::clusterExport(cl,
-			varlist=c("synchrones","counts","verbose","medoids","getRefSeries"),
+			varlist=c("synchrones_desc","counts","verbose","m_desc","medoids_desc","getRefSeries"),
 			envir=environment())
 	}
 
 	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
-#browser()
 	ignored <-
 		if (parll)
 			parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
@@ -233,28 +263,33 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 		pairs = c(pairs, lapply(V, function(v) c(i,v)))
 	}
 
-	computeCWT = function(i)
-	{
-		ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
-		totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
-		ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
-		#Normalization
-		sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
-		sqres <- sweep(ts.cwt,2,sqs,'*')
-		sqres / max(Mod(sqres))
-	}
-
 	# Distance between rows i and j
 	computeDistancesIJ = function(pair)
 	{
+		require("bigmemory", quietly=TRUE)
+		require("epclust", quietly=TRUE)
+		synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
+		Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
+	
+		computeCWT = function(i)
+		{
+			ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
+			totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
+			ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
+			#Normalization
+			sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
+			sqres <- sweep(ts.cwt,2,sqs,'*')
+			sqres / max(Mod(sqres))
+		}
+
 		i = pair[1] ; j = pair[2]
 		if (verbose && j==i+1)
 			cat(paste("   Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
 		cwt_i = computeCWT(i)
 		cwt_j = computeCWT(j)
-		num <- .Call("filter", Mod(cwt_i * Conj(cwt_j)), PACKAGE="epclust")
-		WX  <- .Call("filter", Mod(cwt_i * Conj(cwt_i)), PACKAGE="epclust")
-		WY  <- .Call("filter", Mod(cwt_j * Conj(cwt_j)), PACKAGE="epclust")
+		num <- epclustFilter(Mod(cwt_i * Conj(cwt_j)))
+		WX  <- epclustFilter(Mod(cwt_i * Conj(cwt_i)))
+		WY  <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
 		wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
 		Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * (1 - wer2))
 		Xwer_dist[j,i] <- Xwer_dist[i,j]
@@ -264,9 +299,11 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	if (parll)
 	{
 		cl = parallel::makeCluster(ncores_clust)
-		parallel::clusterExport(cl,
-			varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
-			envir=environment())
+		synchrones_desc <- bigmemory::describe(synchrones)
+		Xwer_dist_desc_desc <- bigmemory::describe(Xwer_dist)
+
+		parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
+			"nvoice","w0","s0log","noctave","s0","verbose"), envir=environment())
 	}
 
 	ignored <-