X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=c22678632dcee57df836d4e75978299bb9eaa027;hb=6ad3f3fd0ec4f3cd1fd5de4a287c1893293e5bcc;hp=4d43b2b3801daa880ce004c7a2eb9f73f0894a9b;hpb=363ae13430cdee6ba76b42b7316aa4b292b04d93;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 4d43b2b..c226786 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -121,55 +121,29 @@ computeSynchrones = function(medoids, getRefSeries,
 
 	computeSynchronesChunk = function(indices)
 	{
-		ref_series = getRefSeries(indices)
-		nb_series = nrow(ref_series)
-
 		if (parll)
 		{
 			require("bigmemory", quietly=TRUE)
-			require("synchronicity", quietly=TRUE)
+			requireNamespace("synchronicity", quietly=TRUE)
 			require("epclust", quietly=TRUE)
 			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
+			counts <- bigmemory::attach.big.matrix(counts_desc)
 			medoids <- bigmemory::attach.big.matrix(medoids_desc)
 			m <- synchronicity::attach.mutex(m_desc)
 		}
 
+		ref_series = getRefSeries(indices)
+		nb_series = nrow(ref_series)
 
-
-#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()
+		mi = computeMedoidsIndices(medoids@address, ref_series)
 
 		for (i in seq_len(nb_series))
 		{
 			if (parll)
 				synchronicity::lock(m)
-			synchrones[mi[i],] = synchrones[mi[i],] + ref_series[i,]
-			counts[mi[i],1] = counts[mi[i],1] + 1
+			synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,]
+			counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts?
 			if (parll)
 				synchronicity::unlock(m)
 		}
@@ -188,12 +162,11 @@ write(mi[1:3], file = "TOTO", ncolumns=1, append=TRUE)
 		m <- synchronicity::boost.mutex()
 		m_desc <- synchronicity::describe(m)
 		synchrones_desc = bigmemory::describe(synchrones)
+		counts_desc = bigmemory::describe(counts)
 		medoids_desc = bigmemory::describe(medoids)
-
 		cl = parallel::makeCluster(ncores_clust)
-		parallel::clusterExport(cl,
-			varlist=c("synchrones_desc","counts","verbose","m_desc","medoids_desc","getRefSeries"),
-			envir=environment())
+		parallel::clusterExport(cl, varlist=c("synchrones_desc","counts_desc","counts",
+			"verbose","m_desc","medoids_desc","getRefSeries"), envir=environment())
 	}
 
 	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
@@ -235,6 +208,15 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	if (verbose)
 		cat(paste("--- Compute WER dists\n", sep=""))
 
+
+
+
+#TODO: serializer les CWT, les récupérer via getDataInFile 
+#--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
+
+
+
+
 	n <- nrow(synchrones)
 	delta <- ncol(synchrones)
 	#TODO: automatic tune of all these parameters ? (for other users)
@@ -252,28 +234,40 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	totnoct = noctave + as.integer(s0log/nvoice) + 1
 
 	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
-	fcoefs = rep(1/3, 3) #moving average on 3 values
 
 	# Generate n(n-1)/2 pairs for WER distances computations
+#	pairs = list()
+#	V = seq_len(n)
+#	for (i in 1:n)
+#	{
+#		V = V[-1]
+#		pairs = c(pairs, lapply(V, function(v) c(i,v)))
+#	}
+	# Generate "smart" pairs for WER distances computations
 	pairs = list()
-	V = seq_len(n)
-	for (i in 1:n)
+	F = floor(2*n/3)
+	for (i in 1:F)
+		pairs = c(pairs, lapply((i+1):n, function(v) c(i,v)))
+	V = (F+1):n
+	for (i in (F+1):(n-1))
 	{
 		V = V[-1]
-		pairs = c(pairs, lapply(V, function(v) c(i,v)))
-	}
+		pairs = c(pairs, 
 
 	# 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)
+		if (parll)
 		{
-			ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
+			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(index)
+		{
+			ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled)
 			totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
 			ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
 			#Normalization
@@ -285,14 +279,17 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 		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)
+		cwt_i <- computeCWT(i)
+		cwt_j <- computeCWT(j)
+
+#print(system.time( {
 		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[i,j] <- sqrt(delta * ncol(cwt_i) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1
 		Xwer_dist[j,i] <- Xwer_dist[i,j]
+#} ) )
 		Xwer_dist[i,i] = 0.
 	}
 
@@ -300,7 +297,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	{
 		cl = parallel::makeCluster(ncores_clust)
 		synchrones_desc <- bigmemory::describe(synchrones)
-		Xwer_dist_desc_desc <- bigmemory::describe(Xwer_dist)
+		Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
 
 		parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
 			"nvoice","w0","s0log","noctave","s0","verbose"), envir=environment())