[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)
{
	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	{
492cd9e7	109	computeSynchronesChunk = function(indices)
3eef8d3d	110	{
c45fd663 BA	111	if (verbose)
c45fd663 BA	112	cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep=""))
492cd9e7	113	ref_series = getRefSeries(indices)
3eef8d3d	114	#get medoids indices for this chunk of series
56857861 BA	115	for (i in seq_len(nrow(ref_series)))
56857861 BA	116	{
8702eb86	117	j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
492cd9e7 BA	118	if (parll)
492cd9e7 BA	119	synchronicity::lock(m)
8702eb86	120	synchrones[j,] = synchrones[j,] + ref_series[i,]
492cd9e7 BA	121	counts[j,1] = counts[j,1] + 1
	122	if (parll)
	123	synchronicity::unlock(m)
	124	}
	125	}
	126
	127	K = nrow(medoids)
	128	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
24ed5d83	129	# TODO: if size > RAM (not our case), use file-backed big.matrix
492cd9e7 BA	130	synchrones = bigmemory::big.matrix(nrow=K,ncol=ncol(medoids),type="double",init=0.)
492cd9e7 BA	131	counts = bigmemory::big.matrix(nrow=K,ncol=1,type="double",init=0)
24ed5d83	132	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
492cd9e7 BA	133	parll = (requireNamespace("synchronicity",quietly=TRUE)
	134	&& parll && Sys.info()['sysname'] != "Windows")
	135	if (parll)
	136	m <- synchronicity::boost.mutex()
	137
24ed5d83 BA	138	if (parll)
	139	{
	140	cl = parallel::makeCluster(ncores_clust)
	141	parallel::clusterExport(cl,
	142	varlist=c("synchrones","counts","verbose","medoids","getRefSeries"),
	143	envir=environment())
	144	}
	145
492cd9e7	146	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
c45fd663	147	ignored <-
492cd9e7	148	if (parll)
24ed5d83	149	parallel::parLapply(indices_workers, computeSynchronesChunk)
492cd9e7	150	else
c45fd663	151	lapply(indices_workers, computeSynchronesChunk)
492cd9e7	152
24ed5d83 BA	153	if (parll)
	154	parallel::stopCluster(cl)
	155
	156	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
492cd9e7	157	for (i in seq_len(K))
24ed5d83	158	synchrones[i,] = synchrones[i,] / counts[i,1]
3eef8d3d	159	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
8702eb86	160	# ...maybe; but let's hope resulting K1' be still quite bigger than K2
24ed5d83 BA	161	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
	162	if (all(noNA_rows))
	163	return (synchrones)
	164	# Else: some clusters are empty, need to slice synchrones
	165	synchrones[noNA_rows,]
e205f218	166	}
1c6f223e	167
4bcfdbee BA	168	#' computeWerDists
	169	#'
	170	#' Compute the WER distances between the synchrones curves (in rows), which are
	171	#' returned (e.g.) by \code{computeSynchrones()}
	172	#'
24ed5d83 BA	173	#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
24ed5d83 BA	174	#' as the series in the initial dataset
492cd9e7	175	#' @inheritParams claws
4bcfdbee	176	#'
24ed5d83 BA	177	#' @return A big.matrix of size K1 x K1
24ed5d83 BA	178	#'
4bcfdbee	179	#' @export
492cd9e7	180	computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
d03c0621	181	{
24ed5d83 BA	182
	183
	184
	185	#TODO: re-organize to call computeWerDist(x,y) [C] (in //?) from two indices + big.matrix
	186
	187
4bcfdbee BA	188	n <- nrow(synchrones)
4bcfdbee BA	189	delta <- ncol(synchrones)
db6fc17d	190	#TODO: automatic tune of all these parameters ? (for other users)
d03c0621	191	nvoice <- 4
4bcfdbee	192	# noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
d7d55bc1 BA	193	noctave = 13
d7d55bc1 BA	194	# 4 here represent 2^5 = 32 half-hours ~ 1 day
db6fc17d	195	#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
24ed5d83	196	scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
db6fc17d BA	197	#condition: ( log2(s0w0/(2pi)) - 1 ) * nvoice + 1.5 >= 1
	198	s0=2
	199	w0=2*pi
	200	scaled=FALSE
	201	s0log = as.integer( (log2( s0w0/(2pi) ) - 1) * nvoice + 1.5 )
	202	totnoct = noctave + as.integer(s0log/nvoice) + 1
	203
492cd9e7 BA	204	computeCWT = function(i)
	205	{
	206	if (verbose)
	207	cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep=""))
4bcfdbee	208	ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
24ed5d83	209	totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
db6fc17d BA	210	ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
	211	#Normalization
	212	sqs <- sqrt(2^(0:(noctavenvoice)/nvoice)s0)
af3ea947	213	sqres <- sweep(ts.cwt,2,sqs,'*')
db6fc17d	214	sqres / max(Mod(sqres))
492cd9e7	215	}
3ccd1e39	216
492cd9e7 BA	217	if (parll)
	218	{
	219	cl = parallel::makeCluster(ncores_clust)
af3ea947 BA	220	parallel::clusterExport(cl,
	221	varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
	222	envir=environment())
492cd9e7 BA	223	}
492cd9e7 BA	224
24ed5d83 BA	225	# list of CWT from synchrones
24ed5d83 BA	226	# TODO: fit in RAM, OK? If not, 2 options: serialize, compute individual distances
492cd9e7 BA	227	Xcwt4 <-
	228	if (parll)
	229	parallel::parLapply(cl, seq_len(n), computeCWT)
	230	else
	231	lapply(seq_len(n), computeCWT)
	232
	233	if (parll)
	234	parallel::stopCluster(cl)
	235
	236	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
db6fc17d	237	fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
492cd9e7 BA	238	if (verbose)
	239	cat("*** Compute WER distances from CWT\n")
	240
24ed5d83 BA	241	#TODO: computeDistances(i,j), et répartir les n(n-1)/2 couples d'indices
	242	#là c'est trop déséquilibré
	243
492cd9e7	244	computeDistancesLineI = function(i)
1c6f223e	245	{
492cd9e7 BA	246	if (verbose)
492cd9e7 BA	247	cat(paste(" Line ",i,"\n", sep=""))
db6fc17d	248	for (j in (i+1):n)
d03c0621	249	{
492cd9e7	250	#TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
db6fc17d BA	251	num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
	252	WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
	253	WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
24ed5d83	254	wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
492cd9e7 BA	255	if (parll)
492cd9e7 BA	256	synchronicity::lock(m)
db6fc17d BA	257	Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
db6fc17d BA	258	Xwer_dist[j,i] <- Xwer_dist[i,j]
492cd9e7 BA	259	if (parll)
	260	synchronicity::unlock(m)
	261	}
	262	Xwer_dist[i,i] = 0.
	263	}
	264
	265	parll = (requireNamespace("synchronicity",quietly=TRUE)
	266	&& parll && Sys.info()['sysname'] != "Windows")
	267	if (parll)
	268	m <- synchronicity::boost.mutex()
	269
c45fd663	270	ignored <-
492cd9e7	271	if (parll)
c45fd663 BA	272	{
	273	parallel::mclapply(seq_len(n-1), computeDistancesLineI,
	274	mc.cores=ncores_clust, mc.allow.recursive=FALSE)
	275	}
492cd9e7	276	else
c45fd663	277	lapply(seq_len(n-1), computeDistancesLineI)
492cd9e7	278	Xwer_dist[n,n] = 0.
24ed5d83	279	Xwer_dist
492cd9e7 BA	280	}
	281
	282	# Helper function to divide indices into balanced sets
	283	.spreadIndices = function(indices, nb_per_chunk)
	284	{
	285	L = length(indices)
	286	nb_workers = floor( L / nb_per_chunk )
	287	if (nb_workers == 0)
	288	{
	289	# L < nb_series_per_chunk, simple case
	290	indices_workers = list(indices)
	291	}
	292	else
	293	{
	294	indices_workers = lapply( seq_len(nb_workers), function(i)
	295	indices[(nb_per_chunk(i-1)+1):(nb_per_chunki)] )
	296	# Spread the remaining load among the workers
	297	rem = L %% nb_per_chunk
	298	while (rem > 0)
	299	{
	300	index = rem%%nb_workers + 1
	301	indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
	302	rem = rem - 1
d03c0621	303	}
1c6f223e	304	}
492cd9e7	305	indices_workers
1c6f223e	306	}