[epclust.git] / epclust / R / clustering.R

#' @name clustering
#' @rdname clustering
#' @aliases clusteringTask1 computeClusters1 computeClusters2
#'
#' @title Two-stage clustering, withing one task (see \code{claws()})
#'
#' @description \code{clusteringTask1()} runs one full stage-1 task, which consists in
#'   iterated stage 1 clustering (on nb_curves / ntasks energy contributions, computed
#'   through discrete wavelets coefficients).
#'   \code{clusteringTask2()} runs a full stage-2 task, which consists in synchrones
#'   and then WER distances computations, before applying the clustering algorithm.
#'   \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic
#'   clustering procedures respectively for stage 1 and 2. The former applies the
#'   clustering algorithm (PAM) on a contributions matrix, while the latter clusters
#'   a chunk of series inside one task (~max nb_series_per_chunk)
#'
#' @param indices Range of series indices to cluster in parallel (initial data)
#' @param getContribs Function to retrieve contributions from initial series indices:
#'   \code{getContribs(indices)} outpus a contributions matrix
#' @param contribs matrix of contributions (e.g. output of \code{curvesToContribs()})
#' @param distances matrix of K1 x K1 (WER) distances between synchrones
#' @inheritParams computeSynchrones
#' @inheritParams claws
#'
#' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the
#'   computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus
#'   \code{computeClusters2()} outputs a big.matrix of medoids
#'   (of size limited by nb_series_per_chunk)
NULL

#' @rdname clustering
#' @export
clusteringTask1 = function(
	indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
{
	if (verbose)
		cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))

	if (parll)
	{
		cl = parallel::makeCluster(ncores_clust)
		parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
	}
	while (length(indices) > K1)
	{
		indices_workers = .spreadIndices(indices, nb_series_per_chunk)
		indices <-
			if (parll)
			{
				unlist( parallel::parLapply(cl, indices_workers, function(inds) {
					require("epclust", quietly=TRUE)
					inds[ computeClusters1(getContribs(inds), K1, verbose) ]
				}) )
			}
			else
			{
				unlist( lapply(indices_workers, function(inds)
					inds[ computeClusters1(getContribs(inds), K1, verbose) ]
				) )
			}
	}
	if (parll)
		parallel::stopCluster(cl)

	indices #medoids
}

#' @rdname clustering
#' @export
clusteringTask2 = function(medoids, K2,
	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
{
	if (verbose)
		cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))

	if (nrow(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)
	medoids[ computeClusters2(distances,K2,verbose), ]
}

#' @rdname clustering
#' @export
computeClusters1 = function(contribs, K1, verbose=FALSE)
{
	if (verbose)
		cat(paste("   computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
	cluster::pam(contribs, K1, diss=FALSE)$id.med
}

#' @rdname clustering
#' @export
computeClusters2 = function(distances, K2, verbose=FALSE)
{
	if (verbose)
		cat(paste("   computeClusters2() on ",nrow(distances)," lines\n", sep=""))
	cluster::pam(distances, K2, diss=TRUE)$id.med
}

#' computeSynchrones
#'
#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
#' using L2 distances.
#'
#' @param medoids big.matrix of medoids (curves of same length as initial series)
#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
#'   have been replaced by stage-1 medoids)
#' @param nb_ref_curves How many reference series? (This number is known at this stage)
#' @inheritParams claws
#'
#' @return A big.matrix of size K1 x L where L = data_length
#'
#' @export
computeSynchrones = function(medoids, getRefSeries,
	nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
{
	if (verbose)
		cat(paste("--- Compute synchrones\n", sep=""))

	computeSynchronesChunk = function(indices)
	{
		if (parll)
		{
			require("bigmemory", 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)

		#get medoids indices for this chunk of series
		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] ] = counts[ mi[i] ] + 1 #TODO: remove counts?
			if (parll)
				synchronicity::unlock(m)
		}
	}

	K = nrow(medoids) ; L = ncol(medoids)
	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
	# TODO: if size > RAM (not our case), use file-backed big.matrix
	synchrones = bigmemory::big.matrix(nrow=K, ncol=L, type="double", init=0.)
	counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
	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)
		counts_desc = bigmemory::describe(counts)
		medoids_desc = bigmemory::describe(medoids)
		cl = parallel::makeCluster(ncores_clust)
		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)
	ignored <-
		if (parll)
			parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
		else
			lapply(indices_workers, computeSynchronesChunk)

	if (parll)
		parallel::stopCluster(cl)

	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
	for (i in seq_len(K))
		synchrones[i,] = synchrones[i,] / counts[i,1]
	#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
	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
	if (all(noNA_rows))
		return (synchrones)
	# Else: some clusters are empty, need to slice synchrones
	synchrones[noNA_rows,]
}

#' computeWerDists
#'
#' Compute the WER distances between the synchrones curves (in rows), which are
#' returned (e.g.) by \code{computeSynchrones()}
#'
#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
#'   as the series in the initial dataset
#' @inheritParams claws
#'
#' @return A matrix of size K1 x K1
#'
#' @export
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)
	nvoice   <- 4
	# noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
	noctave = 13
	# 4 here represent 2^5 = 32 half-hours ~ 1 day
	#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
	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")

	# 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 = V[-1]
		pairs = c(pairs, 

	# Distance between rows i and j
	computeDistancesIJ = function(pair)
	{
		if (parll)
		{
			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
			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)

#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) * 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)
		else
			lapply(pairs, computeDistancesIJ)

	if (parll)
		parallel::stopCluster(cl)

	Xwer_dist[n,n] = 0.
	distances <- Xwer_dist[,]
	rm(Xwer_dist) ; gc()
	distances #~small matrix K1 x K1
}

# Helper function to divide indices into balanced sets
.spreadIndices = function(indices, nb_per_chunk)
{
	L = length(indices)
	nb_workers = floor( L / nb_per_chunk )
	if (nb_workers == 0)
	{
		# L < nb_series_per_chunk, simple case
		indices_workers = list(indices)
	}
	else
	{
		indices_workers = lapply( seq_len(nb_workers), function(i)
			indices[(nb_per_chunk*(i-1)+1):(nb_per_chunk*i)] )
		# Spread the remaining load among the workers
		rem = L %% nb_per_chunk
		while (rem > 0)
		{
			index = rem%%nb_workers + 1
			indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
			rem = rem - 1
		}
	}
	indices_workers
}
Commit	Line	Data
	1	#' @name clustering
	2	#' @rdname clustering
	3	#' @aliases clusteringTask1 computeClusters1 computeClusters2
	4	#'
	5	#' @title Two-stage clustering, withing one task (see \code{claws()})
	6	#'
	7	#' @description \code{clusteringTask1()} runs one full stage-1 task, which consists in
	8	#' iterated stage 1 clustering (on nb_curves / ntasks energy contributions, computed
	9	#' through discrete wavelets coefficients).
	10	#' \code{clusteringTask2()} runs a full stage-2 task, which consists in synchrones
	11	#' and then WER distances computations, before applying the clustering algorithm.
	12	#' \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic
	13	#' clustering procedures respectively for stage 1 and 2. The former applies the
	14	#' clustering algorithm (PAM) on a contributions matrix, while the latter clusters
	15	#' a chunk of series inside one task (~max nb_series_per_chunk)
	16	#'
	17	#' @param indices Range of series indices to cluster in parallel (initial data)
	18	#' @param getContribs Function to retrieve contributions from initial series indices:
	19	#' \code{getContribs(indices)} outpus a contributions matrix
	20	#' @param contribs matrix of contributions (e.g. output of \code{curvesToContribs()})
	21	#' @param distances matrix of K1 x K1 (WER) distances between synchrones
	22	#' @inheritParams computeSynchrones
	23	#' @inheritParams claws
	24	#'
	25	#' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the
	26	#' computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus
	27	#' \code{computeClusters2()} outputs a big.matrix of medoids
	28	#' (of size limited by nb_series_per_chunk)
	29	NULL
	30
	31	#' @rdname clustering
	32	#' @export
	33	clusteringTask1 = function(
	34	indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
	35	{
	36	if (verbose)
	37	cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
	38
	39	if (parll)
	40	{
	41	cl = parallel::makeCluster(ncores_clust)
	42	parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
	43	}
	44	while (length(indices) > K1)
	45	{
	46	indices_workers = .spreadIndices(indices, nb_series_per_chunk)
	47	indices <-
	48	if (parll)
	49	{
	50	unlist( parallel::parLapply(cl, indices_workers, function(inds) {
	51	require("epclust", quietly=TRUE)
	52	inds[ computeClusters1(getContribs(inds), K1, verbose) ]
	53	}) )
	54	}
	55	else
	56	{
	57	unlist( lapply(indices_workers, function(inds)
	58	inds[ computeClusters1(getContribs(inds), K1, verbose) ]
	59	) )
	60	}
	61	}
	62	if (parll)
	63	parallel::stopCluster(cl)
	64
	65	indices #medoids
	66	}
	67
	68	#' @rdname clustering
	69	#' @export
	70	clusteringTask2 = function(medoids, K2,
	71	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
	72	{
	73	if (verbose)
	74	cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))
	75
	76	if (nrow(medoids) <= K2)
	77	return (medoids)
	78	synchrones = computeSynchrones(medoids,
	79	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
	80	distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
	81	medoids[ computeClusters2(distances,K2,verbose), ]
	82	}
	83
	84	#' @rdname clustering
	85	#' @export
	86	computeClusters1 = function(contribs, K1, verbose=FALSE)
	87	{
	88	if (verbose)
	89	cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
	90	cluster::pam(contribs, K1, diss=FALSE)$id.med
	91	}
	92
	93	#' @rdname clustering
	94	#' @export
	95	computeClusters2 = function(distances, K2, verbose=FALSE)
	96	{
	97	if (verbose)
	98	cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep=""))
	99	cluster::pam(distances, K2, diss=TRUE)$id.med
	100	}
	101
	102	#' computeSynchrones
	103	#'
	104	#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
	105	#' using L2 distances.
	106	#'
	107	#' @param medoids big.matrix of medoids (curves of same length as initial series)
	108	#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
	109	#' have been replaced by stage-1 medoids)
	110	#' @param nb_ref_curves How many reference series? (This number is known at this stage)
	111	#' @inheritParams claws
	112	#'
	113	#' @return A big.matrix of size K1 x L where L = data_length
	114	#'
	115	#' @export
	116	computeSynchrones = function(medoids, getRefSeries,
	117	nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
	118	{
	119	if (verbose)
	120	cat(paste("--- Compute synchrones\n", sep=""))
	121
	122	computeSynchronesChunk = function(indices)
	123	{
	124	if (parll)
	125	{
	126	require("bigmemory", quietly=TRUE)
	127	requireNamespace("synchronicity", quietly=TRUE)
	128	require("epclust", quietly=TRUE)
	129	synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
	130	counts <- bigmemory::attach.big.matrix(counts_desc)
	131	medoids <- bigmemory::attach.big.matrix(medoids_desc)
	132	m <- synchronicity::attach.mutex(m_desc)
	133	}
	134
	135	ref_series = getRefSeries(indices)
	136	nb_series = nrow(ref_series)
	137
	138	#get medoids indices for this chunk of series
	139	mi = computeMedoidsIndices(medoids@address, ref_series)
	140
	141	for (i in seq_len(nb_series))
	142	{
	143	if (parll)
	144	synchronicity::lock(m)
	145	synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,]
	146	counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts?
	147	if (parll)
	148	synchronicity::unlock(m)
	149	}
	150	}
	151
	152	K = nrow(medoids) ; L = ncol(medoids)
	153	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
	154	# TODO: if size > RAM (not our case), use file-backed big.matrix
	155	synchrones = bigmemory::big.matrix(nrow=K, ncol=L, type="double", init=0.)
	156	counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
	157	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
	158	parll = (requireNamespace("synchronicity",quietly=TRUE)
	159	&& parll && Sys.info()['sysname'] != "Windows")
	160	if (parll)
	161	{
	162	m <- synchronicity::boost.mutex()
	163	m_desc <- synchronicity::describe(m)
	164	synchrones_desc = bigmemory::describe(synchrones)
	165	counts_desc = bigmemory::describe(counts)
	166	medoids_desc = bigmemory::describe(medoids)
	167	cl = parallel::makeCluster(ncores_clust)
	168	parallel::clusterExport(cl, varlist=c("synchrones_desc","counts_desc","counts",
	169	"verbose","m_desc","medoids_desc","getRefSeries"), envir=environment())
	170	}
	171
	172	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
	173	ignored <-
	174	if (parll)
	175	parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
	176	else
	177	lapply(indices_workers, computeSynchronesChunk)
	178
	179	if (parll)
	180	parallel::stopCluster(cl)
	181
	182	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
	183	for (i in seq_len(K))
	184	synchrones[i,] = synchrones[i,] / counts[i,1]
	185	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
	186	# ...maybe; but let's hope resulting K1' be still quite bigger than K2
	187	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
	188	if (all(noNA_rows))
	189	return (synchrones)
	190	# Else: some clusters are empty, need to slice synchrones
	191	synchrones[noNA_rows,]
	192	}
	193
	194	#' computeWerDists
	195	#'
	196	#' Compute the WER distances between the synchrones curves (in rows), which are
	197	#' returned (e.g.) by \code{computeSynchrones()}
	198	#'
	199	#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
	200	#' as the series in the initial dataset
	201	#' @inheritParams claws
	202	#'
	203	#' @return A matrix of size K1 x K1
	204	#'
	205	#' @export
	206	computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
	207	{
	208	if (verbose)
	209	cat(paste("--- Compute WER dists\n", sep=""))
	210
	211
	212
	213
	214	#TODO: serializer les CWT, les récupérer via getDataInFile
	215	#--> OK, faut juste stocker comme séries simples de taille deltancol (5317519)
	216
	217
	218
	219
	220	n <- nrow(synchrones)
	221	delta <- ncol(synchrones)
	222	#TODO: automatic tune of all these parameters ? (for other users)
	223	nvoice <- 4
	224	# noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
	225	noctave = 13
	226	# 4 here represent 2^5 = 32 half-hours ~ 1 day
	227	#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
	228	scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
	229	#condition: ( log2(s0w0/(2pi)) - 1 ) * nvoice + 1.5 >= 1
	230	s0=2
	231	w0=2*pi
	232	scaled=FALSE
	233	s0log = as.integer( (log2( s0w0/(2pi) ) - 1) * nvoice + 1.5 )
	234	totnoct = noctave + as.integer(s0log/nvoice) + 1
	235
	236	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
	237
	238	# Generate n(n-1)/2 pairs for WER distances computations
	239	# pairs = list()
	240	# V = seq_len(n)
	241	# for (i in 1:n)
	242	# {
	243	# V = V[-1]
	244	# pairs = c(pairs, lapply(V, function(v) c(i,v)))
	245	# }
	246	# Generate "smart" pairs for WER distances computations
	247	pairs = list()
	248	F = floor(2*n/3)
	249	for (i in 1:F)
	250	pairs = c(pairs, lapply((i+1):n, function(v) c(i,v)))
	251	V = (F+1):n
	252	for (i in (F+1):(n-1))
	253	{
	254	V = V[-1]
	255	pairs = c(pairs,
	256
	257	# Distance between rows i and j
	258	computeDistancesIJ = function(pair)
	259	{
	260	if (parll)
	261	{
	262	require("bigmemory", quietly=TRUE)
	263	require("epclust", quietly=TRUE)
	264	synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
	265	Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
	266	}
	267
	268	computeCWT = function(index)
	269	{
	270	ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled)
	271	totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
	272	ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
	273	#Normalization
	274	sqs <- sqrt(2^(0:(noctavenvoice)/nvoice)s0)
	275	sqres <- sweep(ts.cwt,2,sqs,'*')
	276	sqres / max(Mod(sqres))
	277	}
	278
	279	i = pair[1] ; j = pair[2]
	280	if (verbose && j==i+1)
	281	cat(paste(" Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
	282	cwt_i <- computeCWT(i)
	283	cwt_j <- computeCWT(j)
	284
	285	#print(system.time( {
	286	num <- epclustFilter(Mod(cwt_i * Conj(cwt_j)))
	287	WX <- epclustFilter(Mod(cwt_i * Conj(cwt_i)))
	288	WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
	289	wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
	290	Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1
	291	Xwer_dist[j,i] <- Xwer_dist[i,j]
	292	#} ) )
	293	Xwer_dist[i,i] = 0.
	294	}
	295
	296	if (parll)
	297	{
	298	cl = parallel::makeCluster(ncores_clust)
	299	synchrones_desc <- bigmemory::describe(synchrones)
	300	Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
	301
	302	parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
	303	"nvoice","w0","s0log","noctave","s0","verbose"), envir=environment())
	304	}
	305
	306	ignored <-
	307	if (parll)
	308	parallel::parLapply(cl, pairs, computeDistancesIJ)
	309	else
	310	lapply(pairs, computeDistancesIJ)
	311
	312	if (parll)
	313	parallel::stopCluster(cl)
	314
	315	Xwer_dist[n,n] = 0.
	316	distances <- Xwer_dist[,]
	317	rm(Xwer_dist) ; gc()
	318	distances #~small matrix K1 x K1
	319	}
	320
	321	# Helper function to divide indices into balanced sets
	322	.spreadIndices = function(indices, nb_per_chunk)
	323	{
	324	L = length(indices)
	325	nb_workers = floor( L / nb_per_chunk )
	326	if (nb_workers == 0)
	327	{
	328	# L < nb_series_per_chunk, simple case
	329	indices_workers = list(indices)
	330	}
	331	else
	332	{
	333	indices_workers = lapply( seq_len(nb_workers), function(i)
	334	indices[(nb_per_chunk(i-1)+1):(nb_per_chunki)] )
	335	# Spread the remaining load among the workers
	336	rem = L %% nb_per_chunk
	337	while (rem > 0)
	338	{
	339	index = rem%%nb_workers + 1
	340	indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
	341	rem = rem - 1
	342	}
	343	}
	344	indices_workers
	345	}