X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2FcomputeWerDists.R;h=a813b8f615d8840762144973d75162d876f34b6f;hp=aae1cc12c4ceb27f01e569c1ca30aa763c6155d7;hb=3c5a4b0880db63367a474a568e1322b3999932fe;hpb=40f12a2f66d06fd77183ea02b996f5c66f90761c

diff --git a/epclust/R/computeWerDists.R b/epclust/R/computeWerDists.R
index aae1cc1..a813b8f 100644
--- a/epclust/R/computeWerDists.R
+++ b/epclust/R/computeWerDists.R
@@ -3,21 +3,24 @@
 #' Compute the WER distances between the synchrones curves (in columns), which are
 #' returned (e.g.) by \code{computeSynchrones()}
 #'
-#' @param synchrones A big.matrix of synchrones, in columns. The series have same
-#'   length as the series in the initial dataset
+#' @param indices Range of series indices to cluster
 #' @inheritParams claws
+#' @inheritParams computeSynchrones
 #'
-#' @return A distances matrix of size K1 x K1
+#' @return A distances matrix of size K x K where K == length(indices)
 #'
 #' @export
-computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
-	verbose=FALSE,parll=TRUE)
+computeWerDists = function(indices, getSeries, nb_series_per_chunk, nvoice, nbytes, endian,
+	ncores_clust=1, verbose=FALSE, parll=TRUE)
 {
-	n <- ncol(synchrones)
-	L <- nrow(synchrones)
+	n <- length(indices)
+	L <- length(getSeries(1)) #TODO: not very nice way to get L
 	noctave = ceiling(log2(L)) #min power of 2 to cover serie range
+	# Since a CWT contains noctave*nvoice complex series, we deduce the number of CWT to
+	# retrieve/put in one chunk.
+	nb_cwt_per_chunk = max(1, floor(nb_series_per_chunk / (nvoice*noctave*2)))
 
-	# Initialize result as a square big.matrix of size 'number of synchrones'
+	# Initialize result as a square big.matrix of size 'number of medoids'
 	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
 
 	# Generate n(n-1)/2 pairs for WER distances computations
@@ -30,7 +33,7 @@ computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
 	}
 
 	cwt_file = ".cwt.bin"
-	# Compute the synchrones[,indices] CWT, and store the results in the binary file
+	# Compute the getSeries(indices) CWT, and store the results in the binary file
 	computeSaveCWT = function(indices)
 	{
 		if (parll)
@@ -38,27 +41,25 @@ computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
 			require("bigmemory", quietly=TRUE)
 			require("Rwave", quietly=TRUE)
 			require("epclust", quietly=TRUE)
-			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
 		}
 
 		# Obtain CWT as big vectors of real part + imaginary part (concatenate)
 		ts_cwt <- sapply(indices, function(i) {
-			ts <- scale(ts(synchrones[,i]), center=TRUE, scale=FALSE)
+			ts <- scale(ts(getSeries(i)), center=TRUE, scale=FALSE)
 			ts_cwt <- Rwave::cwt(ts, noctave, nvoice, w0=2*pi, twoD=TRUE, plot=FALSE)
 			c( as.double(Re(ts_cwt)),as.double(Im(ts_cwt)) )
 		})
 
 		# Serialization
-		binarize(ts_cwt, cwt_file, 1, ",", nbytes, endian)
+		binarize(ts_cwt, cwt_file, nb_cwt_per_chunk, ",", 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("parll","synchrones_desc","Xwer_dist_desc",
-			"noctave","nvoice","verbose","getCWT"), envir=environment())
+		parallel::clusterExport(cl, varlist=c("parll","nb_cwt_per_chunk","L",
+			"Xwer_dist_desc","noctave","nvoice","getCWT"), envir=environment())
 	}
 
 	if (verbose)
@@ -71,7 +72,7 @@ computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
 			lapply(1:n, computeSaveCWT)
 
 	# Function to retrieve a synchrone CWT from (binary) file
-	getSynchroneCWT = function(index, L)
+	getCWT = function(index, L)
 	{
 		flat_cwt <- getDataInFile(index, cwt_file, nbytes, endian)
 		cwt_length = length(flat_cwt) / 2
@@ -84,8 +85,6 @@ computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
 
 
 #TODO: better repartition here, 
-	#better code in .splitIndices :: never exceed nb_per_chunk; arg: min_per_chunk (default: 1)
-###TODO: reintroduire nb_items_clust ======> l'autre est typiquement + grand !!! (pas de relation !)
 
 
 
@@ -97,7 +96,6 @@ computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
 			# parallel workers start with an empty environment
 			require("bigmemory", quietly=TRUE)
 			require("epclust", quietly=TRUE)
-			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
 			Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
 		}
 
@@ -106,9 +104,8 @@ computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
 			cat(paste("   Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
 
 		# Compute CWT of columns i and j in synchrones
-		L = nrow(synchrones)
-		cwt_i <- getSynchroneCWT(i, L)
-		cwt_j <- getSynchroneCWT(j, L)
+		cwt_i <- getCWT(i, L)
+		cwt_j <- getCWT(j, L)
 
 		# Compute the ratio of integrals formula 5.6 for WER^2
 		# in https://arxiv.org/abs/1101.4744v2 §5.3