[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)
	{
		ref_series = getRefSeries(indices)
		nb_series = nrow(ref_series)

		if (parll)
		{
			require("bigmemory", quietly=TRUE)
			require("synchronicity", quietly=TRUE)
			require("epclust", quietly=TRUE)
			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
			medoids <- bigmemory::attach.big.matrix(medoids_desc)
			m <- synchronicity::attach.mutex(m_desc)
		}


#TODO: use dbs(),
		#https://www.r-bloggers.com/debugging-parallel-code-with-dbs/
		#http://gforge.se/2015/02/how-to-go-parallel-in-r-basics-tips/

#OK ::
#write(length(indices), file="TOTO")
#write( computeMedoidsIndices(medoids@address, getRefSeries(indices[1:600])), file="TOTO")
#stop()

#		write(indices, file="TOTO", ncolumns=10, append=TRUE)
#write("medoids", file = "TOTO", ncolumns=1, append=TRUE)
#write(medoids[1,1:3], file = "TOTO", ncolumns=1, append=TRUE)
#write("synchrones", file = "TOTO", ncolumns=1, append=TRUE)
#write(synchrones[1,1:3], file = "TOTO", ncolumns=1, append=TRUE)

#NOT OK :: (should just be "ref_series") ...or yes ? race problems mutex then ? ?!
		#get medoids indices for this chunk of series
		mi = computeMedoidsIndices(medoids@address, getRefSeries(indices[1:600]))  #ref_series)
write("MI ::::", file = "TOTO", ncolumns=1, append=TRUE)
write(mi[1:3], file = "TOTO", ncolumns=1, append=TRUE)

#		#R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope)
#		mat_meds = medoids[,]
#		mi = rep(NA,nb_series)
#		for (i in 1:nb_series)
#			mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) )
#		rm(mat_meds); gc()

		for (i in seq_len(nb_series))
		{
			if (parll)
				synchronicity::lock(m)
			synchrones[mi[i],] = synchrones[mi[i],] + ref_series[i,]
			counts[mi[i],1] = counts[mi[i],1] + 1
			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)
		medoids_desc = bigmemory::describe(medoids)

		cl = parallel::makeCluster(ncores_clust)
		parallel::clusterExport(cl,
			varlist=c("synchrones_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=""))

	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")
	fcoefs = rep(1/3, 3) #moving average on 3 values

	# 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)))
	}

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

		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)
		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) * (1 - wer2))
		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_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
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()})
777c4b02	21	#' @param distances matrix of K1 x K1 (WER) distances between synchrones
4bcfdbee BA	22	#' @inheritParams computeSynchrones
	23	#' @inheritParams claws
	24	#'
492cd9e7	25	#' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the
4bcfdbee	26	#' computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus
24ed5d83	27	#' \code{computeClusters2()} outputs a big.matrix of medoids
4bcfdbee BA	28	#' (of size limited by nb_series_per_chunk)
	29	NULL
	30
	31	#' @rdname clustering
	32	#' @export
492cd9e7 BA	33	clusteringTask1 = function(
492cd9e7 BA	34	indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
5c652979	35	{
492cd9e7	36	if (verbose)
e161499b	37	cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
4bcfdbee	38
492cd9e7	39	if (parll)
7b13d0c2	40	{
492cd9e7 BA	41	cl = parallel::makeCluster(ncores_clust)
492cd9e7 BA	42	parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
7b13d0c2	43	}
492cd9e7 BA	44	while (length(indices) > K1)
	45	{
	46	indices_workers = .spreadIndices(indices, nb_series_per_chunk)
e161499b BA	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	}
492cd9e7 BA	61	}
	62	if (parll)
	63	parallel::stopCluster(cl)
	64
56857861	65	indices #medoids
5c652979 BA	66	}
5c652979 BA	67
4bcfdbee BA	68	#' @rdname clustering
4bcfdbee BA	69	#' @export
bf5c0844	70	clusteringTask2 = function(medoids, K2,
492cd9e7	71	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
5c652979	72	{
e161499b BA	73	if (verbose)
	74	cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))
	75
bf5c0844 BA	76	if (nrow(medoids) <= K2)
bf5c0844 BA	77	return (medoids)
492cd9e7 BA	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)
777c4b02	81	medoids[ computeClusters2(distances,K2,verbose), ]
5c652979 BA	82	}
5c652979 BA	83
bf5c0844 BA	84	#' @rdname clustering
bf5c0844 BA	85	#' @export
e161499b BA	86	computeClusters1 = function(contribs, K1, verbose=FALSE)
	87	{
	88	if (verbose)
	89	cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
bf5c0844	90	cluster::pam(contribs, K1, diss=FALSE)$id.med
e161499b	91	}
bf5c0844 BA	92
	93	#' @rdname clustering
	94	#' @export
e161499b BA	95	computeClusters2 = function(distances, K2, verbose=FALSE)
	96	{
	97	if (verbose)
	98	cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep=""))
bf5c0844	99	cluster::pam(distances, K2, diss=TRUE)$id.med
e161499b	100	}
bf5c0844	101
4bcfdbee BA	102	#' computeSynchrones
	103	#'
	104	#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
	105	#' using L2 distances.
	106	#'
24ed5d83	107	#' @param medoids big.matrix of medoids (curves of same length as initial series)
4bcfdbee BA	108	#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
4bcfdbee BA	109	#' have been replaced by stage-1 medoids)
492cd9e7	110	#' @param nb_ref_curves How many reference series? (This number is known at this stage)
4bcfdbee BA	111	#' @inheritParams claws
4bcfdbee BA	112	#'
24ed5d83 BA	113	#' @return A big.matrix of size K1 x L where L = data_length
24ed5d83 BA	114	#'
4bcfdbee	115	#' @export
492cd9e7 BA	116	computeSynchrones = function(medoids, getRefSeries,
492cd9e7 BA	117	nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
e205f218	118	{
e161499b BA	119	if (verbose)
	120	cat(paste("--- Compute synchrones\n", sep=""))
	121
492cd9e7	122	computeSynchronesChunk = function(indices)
3eef8d3d	123	{
492cd9e7	124	ref_series = getRefSeries(indices)
e161499b	125	nb_series = nrow(ref_series)
e161499b	126
363ae134 BA	127	if (parll)
	128	{
	129	require("bigmemory", quietly=TRUE)
	130	require("synchronicity", quietly=TRUE)
	131	require("epclust", quietly=TRUE)
	132	synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
	133	medoids <- bigmemory::attach.big.matrix(medoids_desc)
	134	m <- synchronicity::attach.mutex(m_desc)
	135	}
	136
	137
e161499b	138
363ae134 BA	139	#TODO: use dbs(),
	140	#https://www.r-bloggers.com/debugging-parallel-code-with-dbs/
	141	#http://gforge.se/2015/02/how-to-go-parallel-in-r-basics-tips/
	142
	143	#OK ::
	144	#write(length(indices), file="TOTO")
	145	#write( computeMedoidsIndices(medoids@address, getRefSeries(indices[1:600])), file="TOTO")
	146	#stop()
	147
	148	# write(indices, file="TOTO", ncolumns=10, append=TRUE)
	149	#write("medoids", file = "TOTO", ncolumns=1, append=TRUE)
	150	#write(medoids[1,1:3], file = "TOTO", ncolumns=1, append=TRUE)
	151	#write("synchrones", file = "TOTO", ncolumns=1, append=TRUE)
	152	#write(synchrones[1,1:3], file = "TOTO", ncolumns=1, append=TRUE)
	153
	154	#NOT OK :: (should just be "ref_series") ...or yes ? race problems mutex then ? ?!
	155	#get medoids indices for this chunk of series
	156	mi = computeMedoidsIndices(medoids@address, getRefSeries(indices[1:600])) #ref_series)
	157	write("MI ::::", file = "TOTO", ncolumns=1, append=TRUE)
	158	write(mi[1:3], file = "TOTO", ncolumns=1, append=TRUE)
	159
	160	# #R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope)
	161	# mat_meds = medoids[,]
	162	# mi = rep(NA,nb_series)
	163	# for (i in 1:nb_series)
	164	# mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) )
	165	# rm(mat_meds); gc()
e161499b BA	166
e161499b BA	167	for (i in seq_len(nb_series))
56857861	168	{
492cd9e7 BA	169	if (parll)
492cd9e7 BA	170	synchronicity::lock(m)
e161499b BA	171	synchrones[mi[i],] = synchrones[mi[i],] + ref_series[i,]
e161499b BA	172	counts[mi[i],1] = counts[mi[i],1] + 1
492cd9e7 BA	173	if (parll)
	174	synchronicity::unlock(m)
	175	}
	176	}
	177
e161499b	178	K = nrow(medoids) ; L = ncol(medoids)
492cd9e7	179	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
24ed5d83	180	# TODO: if size > RAM (not our case), use file-backed big.matrix
e161499b BA	181	synchrones = bigmemory::big.matrix(nrow=K, ncol=L, type="double", init=0.)
e161499b BA	182	counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
24ed5d83	183	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
492cd9e7 BA	184	parll = (requireNamespace("synchronicity",quietly=TRUE)
	185	&& parll && Sys.info()['sysname'] != "Windows")
	186	if (parll)
363ae134	187	{
492cd9e7	188	m <- synchronicity::boost.mutex()
363ae134 BA	189	m_desc <- synchronicity::describe(m)
	190	synchrones_desc = bigmemory::describe(synchrones)
	191	medoids_desc = bigmemory::describe(medoids)
492cd9e7	192
24ed5d83 BA	193	cl = parallel::makeCluster(ncores_clust)
24ed5d83 BA	194	parallel::clusterExport(cl,
363ae134	195	varlist=c("synchrones_desc","counts","verbose","m_desc","medoids_desc","getRefSeries"),
24ed5d83 BA	196	envir=environment())
	197	}
	198
492cd9e7	199	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
c45fd663	200	ignored <-
492cd9e7	201	if (parll)
e161499b	202	parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
492cd9e7	203	else
c45fd663	204	lapply(indices_workers, computeSynchronesChunk)
492cd9e7	205
24ed5d83 BA	206	if (parll)
	207	parallel::stopCluster(cl)
	208
	209	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
492cd9e7	210	for (i in seq_len(K))
24ed5d83	211	synchrones[i,] = synchrones[i,] / counts[i,1]
3eef8d3d	212	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
8702eb86	213	# ...maybe; but let's hope resulting K1' be still quite bigger than K2
24ed5d83 BA	214	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
	215	if (all(noNA_rows))
	216	return (synchrones)
	217	# Else: some clusters are empty, need to slice synchrones
	218	synchrones[noNA_rows,]
e205f218	219	}
1c6f223e	220
4bcfdbee BA	221	#' computeWerDists
	222	#'
	223	#' Compute the WER distances between the synchrones curves (in rows), which are
	224	#' returned (e.g.) by \code{computeSynchrones()}
	225	#'
24ed5d83 BA	226	#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
24ed5d83 BA	227	#' as the series in the initial dataset
492cd9e7	228	#' @inheritParams claws
4bcfdbee	229	#'
777c4b02	230	#' @return A matrix of size K1 x K1
24ed5d83	231	#'
4bcfdbee	232	#' @export
492cd9e7	233	computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
d03c0621	234	{
e161499b BA	235	if (verbose)
e161499b BA	236	cat(paste("--- Compute WER dists\n", sep=""))
24ed5d83	237
4bcfdbee BA	238	n <- nrow(synchrones)
4bcfdbee BA	239	delta <- ncol(synchrones)
db6fc17d	240	#TODO: automatic tune of all these parameters ? (for other users)
d03c0621	241	nvoice <- 4
4bcfdbee	242	# noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
d7d55bc1 BA	243	noctave = 13
d7d55bc1 BA	244	# 4 here represent 2^5 = 32 half-hours ~ 1 day
db6fc17d	245	#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
24ed5d83	246	scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
db6fc17d BA	247	#condition: ( log2(s0w0/(2pi)) - 1 ) * nvoice + 1.5 >= 1
	248	s0=2
	249	w0=2*pi
	250	scaled=FALSE
	251	s0log = as.integer( (log2( s0w0/(2pi) ) - 1) * nvoice + 1.5 )
	252	totnoct = noctave + as.integer(s0log/nvoice) + 1
	253
e161499b BA	254	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
	255	fcoefs = rep(1/3, 3) #moving average on 3 values
	256
	257	# Generate n(n-1)/2 pairs for WER distances computations
	258	pairs = list()
	259	V = seq_len(n)
	260	for (i in 1:n)
	261	{
	262	V = V[-1]
	263	pairs = c(pairs, lapply(V, function(v) c(i,v)))
	264	}
	265
777c4b02	266	# Distance between rows i and j
e161499b BA	267	computeDistancesIJ = function(pair)
e161499b BA	268	{
363ae134 BA	269	require("bigmemory", quietly=TRUE)
	270	require("epclust", quietly=TRUE)
	271	synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
	272	Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
	273
	274	computeCWT = function(i)
	275	{
	276	ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
	277	totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
	278	ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
	279	#Normalization
	280	sqs <- sqrt(2^(0:(noctavenvoice)/nvoice)s0)
	281	sqres <- sweep(ts.cwt,2,sqs,'*')
	282	sqres / max(Mod(sqres))
	283	}
	284
e161499b BA	285	i = pair[1] ; j = pair[2]
	286	if (verbose && j==i+1)
	287	cat(paste(" Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
	288	cwt_i = computeCWT(i)
	289	cwt_j = computeCWT(j)
363ae134 BA	290	num <- epclustFilter(Mod(cwt_i * Conj(cwt_j)))
	291	WX <- epclustFilter(Mod(cwt_i * Conj(cwt_i)))
	292	WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
e161499b BA	293	wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
	294	Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * (1 - wer2))
	295	Xwer_dist[j,i] <- Xwer_dist[i,j]
	296	Xwer_dist[i,i] = 0.
	297	}
	298
492cd9e7 BA	299	if (parll)
	300	{
	301	cl = parallel::makeCluster(ncores_clust)
363ae134 BA	302	synchrones_desc <- bigmemory::describe(synchrones)
	303	Xwer_dist_desc_desc <- bigmemory::describe(Xwer_dist)
	304
	305	parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
	306	"nvoice","w0","s0log","noctave","s0","verbose"), envir=environment())
492cd9e7 BA	307	}
492cd9e7 BA	308
e161499b	309	ignored <-
492cd9e7	310	if (parll)
e161499b	311	parallel::parLapply(cl, pairs, computeDistancesIJ)
492cd9e7	312	else
e161499b	313	lapply(pairs, computeDistancesIJ)
492cd9e7 BA	314
	315	if (parll)
	316	parallel::stopCluster(cl)
	317
492cd9e7	318	Xwer_dist[n,n] = 0.
777c4b02 BA	319	distances <- Xwer_dist[,]
	320	rm(Xwer_dist) ; gc()
	321	distances #~small matrix K1 x K1
492cd9e7 BA	322	}
	323
	324	# Helper function to divide indices into balanced sets
	325	.spreadIndices = function(indices, nb_per_chunk)
	326	{
	327	L = length(indices)
	328	nb_workers = floor( L / nb_per_chunk )
	329	if (nb_workers == 0)
	330	{
	331	# L < nb_series_per_chunk, simple case
	332	indices_workers = list(indices)
	333	}
	334	else
	335	{
	336	indices_workers = lapply( seq_len(nb_workers), function(i)
	337	indices[(nb_per_chunk(i-1)+1):(nb_per_chunki)] )
	338	# Spread the remaining load among the workers
	339	rem = L %% nb_per_chunk
	340	while (rem > 0)
	341	{
	342	index = rem%%nb_workers + 1
	343	indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
	344	rem = rem - 1
d03c0621	345	}
1c6f223e	346	}
492cd9e7	347	indices_workers
1c6f223e	348	}