[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()})
#' @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 on ",length(indices)," lines\n", sep=""))

	wrapComputeClusters1 = function(inds) {
		if (parll)
			require("epclust", quietly=TRUE)
		if (verbose)
			cat(paste("   computeClusters1() on ",length(inds)," lines\n", sep=""))
		inds[ computeClusters1(getContribs(inds), K1) ]
	}

	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)
		if (parll)
			indices = unlist( parallel::parLapply(cl, indices_workers, wrapComputeClusters1) )
		else
			indices = unlist( lapply(indices_workers, wrapComputeClusters1) )
	}
	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 (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)
	# PAM in package 'cluster' cannot take big.matrix in input: need to cast it
	mat_dists = matrix(nrow=K1, ncol=K1)
	for (i in seq_len(K1))
		mat_dists[i,] = distances[i,]
	medoids[ computeClusters2(mat_dists,K2), ]
}

#' @rdname clustering
#' @export
computeClusters1 = function(contribs, K1)
	cluster::pam(contribs, K1, diss=FALSE)$id.med

#' @rdname clustering
#' @export
computeClusters2 = function(distances, K2)
	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)
{


#TODO: si parll, getMedoids + serialization, pass only getMedoids to nodes
# --> BOF... chaque node chargera tous les medoids (efficacité) :/ ==> faut que ça tienne en RAM
#au pire :: C-ifier et charger medoids 1 by 1...

	#MIEUX :: medoids DOIT etre une big.matrix partagée !

	computeSynchronesChunk = function(indices)
	{
		if (verbose)
			cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep=""))
		ref_series = getRefSeries(indices)
		#get medoids indices for this chunk of series
		for (i in seq_len(nrow(ref_series)))
		{
			j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
			if (parll)
				synchronicity::lock(m)
			synchrones[j,] = synchrones[j,] + ref_series[i,]
			counts[j,1] = counts[j,1] + 1
			if (parll)
				synchronicity::unlock(m)
		}
	}

	K = nrow(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=ncol(medoids),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()

	if (parll)
	{
		cl = parallel::makeCluster(ncores_clust)
		parallel::clusterExport(cl,
			varlist=c("synchrones","counts","verbose","medoids","getRefSeries"),
			envir=environment())
	}

	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
	ignored <-
		if (parll)
			parallel::parLapply(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 big.matrix of size K1 x K1
#'
#' @export
computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
{


#TODO: re-organize to call computeWerDist(x,y) [C] (in //?) from two indices + big.matrix


	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

	computeCWT = function(i)
	{
		if (verbose)
			cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep=""))
		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))
	}

	if (parll)
	{
		cl = parallel::makeCluster(ncores_clust)
		parallel::clusterExport(cl,
			varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
			envir=environment())
	}

	# list of CWT from synchrones
	# TODO: fit in RAM, OK? If not, 2 options: serialize, compute individual distances
	Xcwt4 <-
		if (parll)
			parallel::parLapply(cl, seq_len(n), computeCWT)
		else
			lapply(seq_len(n), computeCWT)

	if (parll)
		parallel::stopCluster(cl)

	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
	fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
	if (verbose)
		cat("*** Compute WER distances from CWT\n")

	#TODO: computeDistances(i,j), et répartir les n(n-1)/2 couples d'indices
	#là c'est trop déséquilibré

	computeDistancesLineI = function(i)
	{
		if (verbose)
			cat(paste("   Line ",i,"\n", sep=""))
		for (j in (i+1):n)
		{
			#TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
			num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
			WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
			WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
			wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
			if (parll)
				synchronicity::lock(m)
			Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
			Xwer_dist[j,i] <- Xwer_dist[i,j]
			if (parll)
				synchronicity::unlock(m)
		}
		Xwer_dist[i,i] = 0.
	}

	parll = (requireNamespace("synchronicity",quietly=TRUE)
		&& parll && Sys.info()['sysname'] != "Windows")
	if (parll)
		m <- synchronicity::boost.mutex()

	ignored <-
		if (parll)
		{
			parallel::mclapply(seq_len(n-1), computeDistancesLineI,
				mc.cores=ncores_clust, mc.allow.recursive=FALSE)
		}
		else
			lapply(seq_len(n-1), computeDistancesLineI)
	Xwer_dist[n,n] = 0.
	Xwer_dist
}

# 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
4bcfdbee BA	1	#' @name clustering
4bcfdbee BA	2	#' @rdname clustering
492cd9e7	3	#' @aliases clusteringTask1 computeClusters1 computeClusters2
4bcfdbee	4	#'
492cd9e7	5	#' @title Two-stage clustering, withing one task (see \code{claws()})
4bcfdbee	6	#'
492cd9e7 BA	7	#' @description \code{clusteringTask1()} runs one full stage-1 task, which consists in
492cd9e7 BA	8	#' iterated stage 1 clustering (on nb_curves / ntasks energy contributions, computed
bf5c0844 BA	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)
4bcfdbee BA	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	#' @inheritParams computeSynchrones
	22	#' @inheritParams claws
	23	#'
492cd9e7	24	#' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the
4bcfdbee	25	#' computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus
24ed5d83	26	#' \code{computeClusters2()} outputs a big.matrix of medoids
4bcfdbee BA	27	#' (of size limited by nb_series_per_chunk)
	28	NULL
	29
	30	#' @rdname clustering
	31	#' @export
492cd9e7 BA	32	clusteringTask1 = function(
492cd9e7 BA	33	indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
5c652979	34	{
492cd9e7 BA	35	if (verbose)
492cd9e7 BA	36	cat(paste("*** Clustering task on ",length(indices)," lines\n", sep=""))
4bcfdbee	37
492cd9e7 BA	38	wrapComputeClusters1 = function(inds) {
	39	if (parll)
	40	require("epclust", quietly=TRUE)
	41	if (verbose)
	42	cat(paste(" computeClusters1() on ",length(inds)," lines\n", sep=""))
	43	inds[ computeClusters1(getContribs(inds), K1) ]
	44	}
4bcfdbee	45
492cd9e7	46	if (parll)
7b13d0c2	47	{
492cd9e7 BA	48	cl = parallel::makeCluster(ncores_clust)
492cd9e7 BA	49	parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
7b13d0c2	50	}
492cd9e7 BA	51	while (length(indices) > K1)
	52	{
	53	indices_workers = .spreadIndices(indices, nb_series_per_chunk)
	54	if (parll)
	55	indices = unlist( parallel::parLapply(cl, indices_workers, wrapComputeClusters1) )
	56	else
	57	indices = unlist( lapply(indices_workers, wrapComputeClusters1) )
	58	}
	59	if (parll)
	60	parallel::stopCluster(cl)
	61
56857861	62	indices #medoids
5c652979 BA	63	}
5c652979 BA	64
4bcfdbee BA	65	#' @rdname clustering
4bcfdbee BA	66	#' @export
bf5c0844	67	clusteringTask2 = function(medoids, K2,
492cd9e7	68	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
5c652979	69	{
bf5c0844 BA	70	if (nrow(medoids) <= K2)
bf5c0844 BA	71	return (medoids)
492cd9e7 BA	72	synchrones = computeSynchrones(medoids,
	73	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
	74	distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
bf5c0844 BA	75	# PAM in package 'cluster' cannot take big.matrix in input: need to cast it
	76	mat_dists = matrix(nrow=K1, ncol=K1)
	77	for (i in seq_len(K1))
	78	mat_dists[i,] = distances[i,]
	79	medoids[ computeClusters2(mat_dists,K2), ]
5c652979 BA	80	}
5c652979 BA	81
bf5c0844 BA	82	#' @rdname clustering
	83	#' @export
	84	computeClusters1 = function(contribs, K1)
	85	cluster::pam(contribs, K1, diss=FALSE)$id.med
	86
	87	#' @rdname clustering
	88	#' @export
	89	computeClusters2 = function(distances, K2)
	90	cluster::pam(distances, K2, diss=TRUE)$id.med
	91
4bcfdbee BA	92	#' computeSynchrones
	93	#'
	94	#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
	95	#' using L2 distances.
	96	#'
24ed5d83	97	#' @param medoids big.matrix of medoids (curves of same length as initial series)
4bcfdbee BA	98	#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
4bcfdbee BA	99	#' have been replaced by stage-1 medoids)
492cd9e7	100	#' @param nb_ref_curves How many reference series? (This number is known at this stage)
4bcfdbee BA	101	#' @inheritParams claws
4bcfdbee BA	102	#'
24ed5d83 BA	103	#' @return A big.matrix of size K1 x L where L = data_length
24ed5d83 BA	104	#'
4bcfdbee	105	#' @export
492cd9e7 BA	106	computeSynchrones = function(medoids, getRefSeries,
492cd9e7 BA	107	nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
e205f218	108	{
24ed5d83 BA	109
	110
	111
	112	#TODO: si parll, getMedoids + serialization, pass only getMedoids to nodes
	113	# --> BOF... chaque node chargera tous les medoids (efficacité) :/ ==> faut que ça tienne en RAM
	114	#au pire :: C-ifier et charger medoids 1 by 1...
	115
	116	#MIEUX :: medoids DOIT etre une big.matrix partagée !
	117
492cd9e7	118	computeSynchronesChunk = function(indices)
3eef8d3d	119	{
c45fd663 BA	120	if (verbose)
c45fd663 BA	121	cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep=""))
492cd9e7	122	ref_series = getRefSeries(indices)
3eef8d3d	123	#get medoids indices for this chunk of series
56857861 BA	124	for (i in seq_len(nrow(ref_series)))
56857861 BA	125	{
8702eb86	126	j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
492cd9e7 BA	127	if (parll)
492cd9e7 BA	128	synchronicity::lock(m)
8702eb86	129	synchrones[j,] = synchrones[j,] + ref_series[i,]
492cd9e7 BA	130	counts[j,1] = counts[j,1] + 1
	131	if (parll)
	132	synchronicity::unlock(m)
	133	}
	134	}
	135
	136	K = nrow(medoids)
	137	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
24ed5d83	138	# TODO: if size > RAM (not our case), use file-backed big.matrix
492cd9e7 BA	139	synchrones = bigmemory::big.matrix(nrow=K,ncol=ncol(medoids),type="double",init=0.)
492cd9e7 BA	140	counts = bigmemory::big.matrix(nrow=K,ncol=1,type="double",init=0)
24ed5d83	141	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
492cd9e7 BA	142	parll = (requireNamespace("synchronicity",quietly=TRUE)
	143	&& parll && Sys.info()['sysname'] != "Windows")
	144	if (parll)
	145	m <- synchronicity::boost.mutex()
	146
24ed5d83 BA	147	if (parll)
	148	{
	149	cl = parallel::makeCluster(ncores_clust)
	150	parallel::clusterExport(cl,
	151	varlist=c("synchrones","counts","verbose","medoids","getRefSeries"),
	152	envir=environment())
	153	}
	154
492cd9e7	155	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
c45fd663	156	ignored <-
492cd9e7	157	if (parll)
24ed5d83	158	parallel::parLapply(indices_workers, computeSynchronesChunk)
492cd9e7	159	else
c45fd663	160	lapply(indices_workers, computeSynchronesChunk)
492cd9e7	161
24ed5d83 BA	162	if (parll)
	163	parallel::stopCluster(cl)
	164
	165	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
492cd9e7	166	for (i in seq_len(K))
24ed5d83	167	synchrones[i,] = synchrones[i,] / counts[i,1]
3eef8d3d	168	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
8702eb86	169	# ...maybe; but let's hope resulting K1' be still quite bigger than K2
24ed5d83 BA	170	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
	171	if (all(noNA_rows))
	172	return (synchrones)
	173	# Else: some clusters are empty, need to slice synchrones
	174	synchrones[noNA_rows,]
e205f218	175	}
1c6f223e	176
4bcfdbee BA	177	#' computeWerDists
	178	#'
	179	#' Compute the WER distances between the synchrones curves (in rows), which are
	180	#' returned (e.g.) by \code{computeSynchrones()}
	181	#'
24ed5d83 BA	182	#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
24ed5d83 BA	183	#' as the series in the initial dataset
492cd9e7	184	#' @inheritParams claws
4bcfdbee	185	#'
24ed5d83 BA	186	#' @return A big.matrix of size K1 x K1
24ed5d83 BA	187	#'
4bcfdbee	188	#' @export
492cd9e7	189	computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
d03c0621	190	{
24ed5d83 BA	191
	192
	193
	194	#TODO: re-organize to call computeWerDist(x,y) [C] (in //?) from two indices + big.matrix
	195
	196
4bcfdbee BA	197	n <- nrow(synchrones)
4bcfdbee BA	198	delta <- ncol(synchrones)
db6fc17d	199	#TODO: automatic tune of all these parameters ? (for other users)
d03c0621	200	nvoice <- 4
4bcfdbee	201	# noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
d7d55bc1 BA	202	noctave = 13
d7d55bc1 BA	203	# 4 here represent 2^5 = 32 half-hours ~ 1 day
db6fc17d	204	#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
24ed5d83	205	scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
db6fc17d BA	206	#condition: ( log2(s0w0/(2pi)) - 1 ) * nvoice + 1.5 >= 1
	207	s0=2
	208	w0=2*pi
	209	scaled=FALSE
	210	s0log = as.integer( (log2( s0w0/(2pi) ) - 1) * nvoice + 1.5 )
	211	totnoct = noctave + as.integer(s0log/nvoice) + 1
	212
492cd9e7 BA	213	computeCWT = function(i)
	214	{
	215	if (verbose)
	216	cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep=""))
4bcfdbee	217	ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
24ed5d83	218	totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
db6fc17d BA	219	ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
	220	#Normalization
	221	sqs <- sqrt(2^(0:(noctavenvoice)/nvoice)s0)
af3ea947	222	sqres <- sweep(ts.cwt,2,sqs,'*')
db6fc17d	223	sqres / max(Mod(sqres))
492cd9e7	224	}
3ccd1e39	225
492cd9e7 BA	226	if (parll)
	227	{
	228	cl = parallel::makeCluster(ncores_clust)
af3ea947 BA	229	parallel::clusterExport(cl,
	230	varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
	231	envir=environment())
492cd9e7 BA	232	}
492cd9e7 BA	233
24ed5d83 BA	234	# list of CWT from synchrones
24ed5d83 BA	235	# TODO: fit in RAM, OK? If not, 2 options: serialize, compute individual distances
492cd9e7 BA	236	Xcwt4 <-
	237	if (parll)
	238	parallel::parLapply(cl, seq_len(n), computeCWT)
	239	else
	240	lapply(seq_len(n), computeCWT)
	241
	242	if (parll)
	243	parallel::stopCluster(cl)
	244
	245	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
db6fc17d	246	fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
492cd9e7 BA	247	if (verbose)
	248	cat("*** Compute WER distances from CWT\n")
	249
24ed5d83 BA	250	#TODO: computeDistances(i,j), et répartir les n(n-1)/2 couples d'indices
	251	#là c'est trop déséquilibré
	252
492cd9e7	253	computeDistancesLineI = function(i)
1c6f223e	254	{
492cd9e7 BA	255	if (verbose)
492cd9e7 BA	256	cat(paste(" Line ",i,"\n", sep=""))
db6fc17d	257	for (j in (i+1):n)
d03c0621	258	{
492cd9e7	259	#TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
db6fc17d BA	260	num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
	261	WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
	262	WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
24ed5d83	263	wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
492cd9e7 BA	264	if (parll)
492cd9e7 BA	265	synchronicity::lock(m)
db6fc17d BA	266	Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
db6fc17d BA	267	Xwer_dist[j,i] <- Xwer_dist[i,j]
492cd9e7 BA	268	if (parll)
	269	synchronicity::unlock(m)
	270	}
	271	Xwer_dist[i,i] = 0.
	272	}
	273
	274	parll = (requireNamespace("synchronicity",quietly=TRUE)
	275	&& parll && Sys.info()['sysname'] != "Windows")
	276	if (parll)
	277	m <- synchronicity::boost.mutex()
	278
c45fd663	279	ignored <-
492cd9e7	280	if (parll)
c45fd663 BA	281	{
	282	parallel::mclapply(seq_len(n-1), computeDistancesLineI,
	283	mc.cores=ncores_clust, mc.allow.recursive=FALSE)
	284	}
492cd9e7	285	else
c45fd663	286	lapply(seq_len(n-1), computeDistancesLineI)
492cd9e7	287	Xwer_dist[n,n] = 0.
24ed5d83	288	Xwer_dist
492cd9e7 BA	289	}
	290
	291	# Helper function to divide indices into balanced sets
	292	.spreadIndices = function(indices, nb_per_chunk)
	293	{
	294	L = length(indices)
	295	nb_workers = floor( L / nb_per_chunk )
	296	if (nb_workers == 0)
	297	{
	298	# L < nb_series_per_chunk, simple case
	299	indices_workers = list(indices)
	300	}
	301	else
	302	{
	303	indices_workers = lapply( seq_len(nb_workers), function(i)
	304	indices[(nb_per_chunk(i-1)+1):(nb_per_chunki)] )
	305	# Spread the remaining load among the workers
	306	rem = L %% nb_per_chunk
	307	while (rem > 0)
	308	{
	309	index = rem%%nb_workers + 1
	310	indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
	311	rem = rem - 1
d03c0621	312	}
1c6f223e	313	}
492cd9e7	314	indices_workers
1c6f223e	315	}