X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=a4c273a7ce8dbc91ba3480fac4a83d61d0b70ae6;hb=a174b8ea1f322992068ab42810df017a2b9620ee;hp=c22678632dcee57df836d4e75978299bb9eaa027;hpb=6ad3f3fd0ec4f3cd1fd5de4a287c1893293e5bcc;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index c226786..a4c273a 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -67,8 +67,8 @@ clusteringTask1 = function(
 
 #' @rdname clustering
 #' @export
-clusteringTask2 = function(medoids, K2,
-	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
+clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves,
+	nb_series_per_chunk, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
 	if (verbose)
 		cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))
@@ -77,7 +77,7 @@ clusteringTask2 = function(medoids, K2,
 		return (medoids)
 	synchrones = computeSynchrones(medoids,
 		getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
-	distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
+	distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll)
 	medoids[ computeClusters2(distances,K2,verbose), ]
 }
 
@@ -203,20 +203,11 @@ computeSynchrones = function(medoids, getRefSeries,
 #' @return A matrix of size K1 x K1
 #'
 #' @export
-computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
+computeWerDists = function(synchrones, nbytes,endian,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)
@@ -227,32 +218,62 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
 	scalevector  <- 2^(4:(noctave * nvoice) / nvoice + 1)
 	#condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
-	s0=2
-	w0=2*pi
+	s0 = 2
+	w0 = 2*pi
 	scaled=FALSE
 	s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
 	totnoct = noctave + as.integer(s0log/nvoice) + 1
 
 	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
 
+	cwt_file = ".epclust_bin/cwt"
+	#TODO: args, nb_per_chunk, nbytes, endian
+
 	# 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()
-	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 = seq_len(n)
+	for (i in 1:n)
 	{
 		V = V[-1]
-		pairs = c(pairs, 
+		pairs = c(pairs, lapply(V, function(v) c(i,v)))
+	}
+
+	computeSaveCWT = 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
+		sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
+		sqres <- sweep(ts.cwt,2,sqs,'*')
+		res <- sqres / max(Mod(sqres))
+		#TODO: serializer les CWT, les récupérer via getDataInFile ;
+		#--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
+		binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian)
+	}
+
+	if (parll)
+	{
+		cl = parallel::makeCluster(ncores_clust)
+		synchrones_desc <- bigmemory::describe(synchrones)
+		Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
+		parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
+			"nvoice","w0","s0log","noctave","s0","verbose","getCWT"), envir=environment())
+	}
+
+	#precompute and serialize all CWT
+	ignored <-
+		if (parll)
+			parallel::parLapply(cl, 1:n, computeSaveCWT)
+		else
+			lapply(1:n, computeSaveCWT)
+
+	getCWT = function(index)
+	{
+		#from cwt_file ...
+		res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian)
+	###############TODO:	
+	}
 
 	# Distance between rows i and j
 	computeDistancesIJ = function(pair)
@@ -265,44 +286,21 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 			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
-			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)
+		cwt_i <- getCWT(i)
+		cwt_j <- getCWT(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)))
+		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) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1
 		Xwer_dist[j,i] <- Xwer_dist[i,j]
-#} ) )
 		Xwer_dist[i,i] = 0.
 	}
 
-	if (parll)
-	{
-		cl = parallel::makeCluster(ncores_clust)
-		synchrones_desc <- bigmemory::describe(synchrones)
-		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())
-	}
-
 	ignored <-
 		if (parll)
 			parallel::parLapply(cl, pairs, computeDistancesIJ)