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

#' @name clustering
#' @rdname clustering
#' @aliases clusteringTask1 clusteringTask2 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_items_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, nbytes,endian,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, nbytes, endian, 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(        t(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 L x K1 where L = length of a serie
#'
#' @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? ...or as arg?!
			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=L, ncol=K, 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]
	#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
	bigmemory::as.big.matrix(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, nbytes,endian,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")

	cwt_file = ".epclust_bin/cwt"
	#TODO: args, nb_per_chunk, nbytes, endian

	# 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)))
	}

	computeSaveCWT = 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,'*')
		res <- sqres / max(Mod(sqres))
		#TODO: serializer les CWT, les récupérer via getDataInFile ;
		#--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
		binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian)
	}

	if (parll)
	{
		cl = parallel::makeCluster(ncores_clust)
		synchrones_desc <- bigmemory::describe(synchrones)
		Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
		parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
			"nvoice","w0","s0log","noctave","s0","verbose","getCWT"), envir=environment())
	}

	#precompute and serialize all CWT
	ignored <-
		if (parll)
			parallel::parLapply(cl, 1:n, computeSaveCWT)
		else
			lapply(1:n, computeSaveCWT)

	getCWT = function(index)
	{
		#from cwt_file ...
		res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian)
	###############TODO:
	}

	# 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)
		}

		i = pair[1] ; j = pair[2]
		if (verbose && j==i+1)
			cat(paste("   Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
		cwt_i <- getCWT(i)
		cwt_j <- getCWT(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) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1
		Xwer_dist[j,i] <- Xwer_dist[i,j]
		Xwer_dist[i,i] = 0.
	}

	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
eef6f6c9	3	#' @aliases clusteringTask1 clusteringTask2 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	33	clusteringTask1 = function(
eef6f6c9	34	indices, getContribs, K1, nb_items_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
a174b8ea BA	70	clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves,
a174b8ea BA	71	nb_series_per_chunk, nbytes,endian,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,
492cd9e7 BA	79	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
a174b8ea	80	distances = computeWerDists(synchrones, nbytes, endian, 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=""))
eef6f6c9	90	cluster::pam( t(contribs) , K1, diss=FALSE)$id.med
e161499b	91	}
bf5c0844 BA	92
	93	#' @rdname clustering
	94	#' @export
e161499b BA	95	computeClusters2 = function(distances, K2, verbose=FALSE)
	96	{
	97	if (verbose)
	98	cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep=""))
eef6f6c9	99	cluster::pam( distances , K2, diss=TRUE)$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	#'
eef6f6c9	113	#' @return A big.matrix of size L x K1 where L = length of a serie
24ed5d83	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	{
363ae134 BA	124	if (parll)
	125	{
	126	require("bigmemory", quietly=TRUE)
6ad3f3fd	127	requireNamespace("synchronicity", quietly=TRUE)
363ae134 BA	128	require("epclust", quietly=TRUE)
363ae134 BA	129	synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
6ad3f3fd	130	counts <- bigmemory::attach.big.matrix(counts_desc)
363ae134 BA	131	medoids <- bigmemory::attach.big.matrix(medoids_desc)
	132	m <- synchronicity::attach.mutex(m_desc)
	133	}
	134
6ad3f3fd BA	135	ref_series = getRefSeries(indices)
	136	nb_series = nrow(ref_series)
	137
363ae134	138	#get medoids indices for this chunk of series
2c14dbea	139	mi = computeMedoidsIndices(medoids@address, ref_series)
e161499b BA	140
e161499b BA	141	for (i in seq_len(nb_series))
56857861	142	{
492cd9e7 BA	143	if (parll)
492cd9e7 BA	144	synchronicity::lock(m)
eef6f6c9 BA	145	synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i]
eef6f6c9 BA	146	counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? ...or as arg?!
492cd9e7 BA	147	if (parll)
	148	synchronicity::unlock(m)
	149	}
	150	}
	151
e161499b	152	K = nrow(medoids) ; L = ncol(medoids)
492cd9e7	153	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
24ed5d83	154	# TODO: if size > RAM (not our case), use file-backed big.matrix
eef6f6c9	155	synchrones = bigmemory::big.matrix(nrow=L, ncol=K, type="double", init=0.)
e161499b	156	counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
24ed5d83	157	# synchronicity is only for Linux & MacOS; on Windows: run sequentially
492cd9e7 BA	158	parll = (requireNamespace("synchronicity",quietly=TRUE)
	159	&& parll && Sys.info()['sysname'] != "Windows")
	160	if (parll)
363ae134	161	{
492cd9e7	162	m <- synchronicity::boost.mutex()
363ae134 BA	163	m_desc <- synchronicity::describe(m)
363ae134 BA	164	synchrones_desc = bigmemory::describe(synchrones)
6ad3f3fd	165	counts_desc = bigmemory::describe(counts)
363ae134	166	medoids_desc = bigmemory::describe(medoids)
24ed5d83	167	cl = parallel::makeCluster(ncores_clust)
6ad3f3fd BA	168	parallel::clusterExport(cl, varlist=c("synchrones_desc","counts_desc","counts",
6ad3f3fd BA	169	"verbose","m_desc","medoids_desc","getRefSeries"), envir=environment())
24ed5d83 BA	170	}
24ed5d83 BA	171
492cd9e7	172	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
c45fd663	173	ignored <-
492cd9e7	174	if (parll)
e161499b	175	parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
492cd9e7	176	else
c45fd663	177	lapply(indices_workers, computeSynchronesChunk)
492cd9e7	178
24ed5d83 BA	179	if (parll)
	180	parallel::stopCluster(cl)
	181
	182	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
492cd9e7	183	for (i in seq_len(K))
eef6f6c9	184	synchrones[,i] = synchrones[,i] / counts[i]
3eef8d3d	185	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
8702eb86	186	# ...maybe; but let's hope resulting K1' be still quite bigger than K2
eef6f6c9	187	noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[,i])))
24ed5d83 BA	188	if (all(noNA_rows))
	189	return (synchrones)
	190	# Else: some clusters are empty, need to slice synchrones
eef6f6c9	191	bigmemory::as.big.matrix(synchrones[,noNA_rows])
e205f218	192	}
1c6f223e	193
4bcfdbee BA	194	#' computeWerDists
	195	#'
	196	#' Compute the WER distances between the synchrones curves (in rows), which are
	197	#' returned (e.g.) by \code{computeSynchrones()}
	198	#'
24ed5d83 BA	199	#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
24ed5d83 BA	200	#' as the series in the initial dataset
492cd9e7	201	#' @inheritParams claws
4bcfdbee	202	#'
777c4b02	203	#' @return A matrix of size K1 x K1
24ed5d83	204	#'
4bcfdbee	205	#' @export
a174b8ea	206	computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
d03c0621	207	{
e161499b BA	208	if (verbose)
e161499b BA	209	cat(paste("--- Compute WER dists\n", sep=""))
24ed5d83	210
4bcfdbee BA	211	n <- nrow(synchrones)
4bcfdbee BA	212	delta <- ncol(synchrones)
db6fc17d	213	#TODO: automatic tune of all these parameters ? (for other users)
d03c0621	214	nvoice <- 4
4bcfdbee	215	# noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
d7d55bc1 BA	216	noctave = 13
d7d55bc1 BA	217	# 4 here represent 2^5 = 32 half-hours ~ 1 day
db6fc17d	218	#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
24ed5d83	219	scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
db6fc17d	220	#condition: ( log2(s0w0/(2pi)) - 1 ) * nvoice + 1.5 >= 1
a174b8ea BA	221	s0 = 2
a174b8ea BA	222	w0 = 2*pi
db6fc17d BA	223	scaled=FALSE
	224	s0log = as.integer( (log2( s0w0/(2pi) ) - 1) * nvoice + 1.5 )
	225	totnoct = noctave + as.integer(s0log/nvoice) + 1
	226
e161499b	227	Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
e161499b	228
4204e877 BA	229	cwt_file = ".epclust_bin/cwt"
	230	#TODO: args, nb_per_chunk, nbytes, endian
	231
e161499b BA	232	# Generate n(n-1)/2 pairs for WER distances computations
e161499b BA	233	pairs = list()
4204e877 BA	234	V = seq_len(n)
4204e877 BA	235	for (i in 1:n)
e161499b BA	236	{
e161499b BA	237	V = V[-1]
4204e877 BA	238	pairs = c(pairs, lapply(V, function(v) c(i,v)))
4204e877 BA	239	}
a174b8ea	240
4204e877 BA	241	computeSaveCWT = function(index)
	242	{
	243	ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled)
	244	totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
	245	ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
	246	#Normalization
	247	sqs <- sqrt(2^(0:(noctavenvoice)/nvoice)s0)
	248	sqres <- sweep(ts.cwt,2,sqs,'*')
	249	res <- sqres / max(Mod(sqres))
	250	#TODO: serializer les CWT, les récupérer via getDataInFile ;
	251	#--> OK, faut juste stocker comme séries simples de taille deltancol (5317519)
a174b8ea	252	binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian)
4204e877 BA	253	}
	254
	255	if (parll)
	256	{
	257	cl = parallel::makeCluster(ncores_clust)
	258	synchrones_desc <- bigmemory::describe(synchrones)
	259	Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
	260	parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
	261	"nvoice","w0","s0log","noctave","s0","verbose","getCWT"), envir=environment())
	262	}
	263
	264	#precompute and serialize all CWT
	265	ignored <-
	266	if (parll)
	267	parallel::parLapply(cl, 1:n, computeSaveCWT)
	268	else
	269	lapply(1:n, computeSaveCWT)
	270
	271	getCWT = function(index)
	272	{
	273	#from cwt_file ...
a174b8ea	274	res <- getDataInFile(c(2index-1,2index), cwt_file, nbytes, endian)
eef6f6c9	275	###############TODO:
4204e877	276	}
e161499b	277
777c4b02	278	# Distance between rows i and j
e161499b BA	279	computeDistancesIJ = function(pair)
e161499b BA	280	{
2c14dbea	281	if (parll)
363ae134	282	{
2c14dbea BA	283	require("bigmemory", quietly=TRUE)
	284	require("epclust", quietly=TRUE)
	285	synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
	286	Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
	287	}
	288
e161499b BA	289	i = pair[1] ; j = pair[2]
	290	if (verbose && j==i+1)
	291	cat(paste(" Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
4204e877 BA	292	cwt_i <- getCWT(i)
4204e877 BA	293	cwt_j <- getCWT(j)
2c14dbea	294
363ae134 BA	295	num <- epclustFilter(Mod(cwt_i * Conj(cwt_j)))
363ae134 BA	296	WX <- epclustFilter(Mod(cwt_i * Conj(cwt_i)))
4204e877	297	WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
e161499b	298	wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
2c14dbea	299	Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1
e161499b BA	300	Xwer_dist[j,i] <- Xwer_dist[i,j]
	301	Xwer_dist[i,i] = 0.
	302	}
	303
e161499b	304	ignored <-
492cd9e7	305	if (parll)
e161499b	306	parallel::parLapply(cl, pairs, computeDistancesIJ)
492cd9e7	307	else
e161499b	308	lapply(pairs, computeDistancesIJ)
492cd9e7 BA	309
	310	if (parll)
	311	parallel::stopCluster(cl)
6ad3f3fd	312
492cd9e7	313	Xwer_dist[n,n] = 0.
777c4b02 BA	314	distances <- Xwer_dist[,]
	315	rm(Xwer_dist) ; gc()
	316	distances #~small matrix K1 x K1
492cd9e7 BA	317	}
	318
	319	# Helper function to divide indices into balanced sets
	320	.spreadIndices = function(indices, nb_per_chunk)
	321	{
	322	L = length(indices)
	323	nb_workers = floor( L / nb_per_chunk )
	324	if (nb_workers == 0)
	325	{
	326	# L < nb_series_per_chunk, simple case
	327	indices_workers = list(indices)
	328	}
	329	else
	330	{
	331	indices_workers = lapply( seq_len(nb_workers), function(i)
	332	indices[(nb_per_chunk(i-1)+1):(nb_per_chunki)] )
	333	# Spread the remaining load among the workers
	334	rem = L %% nb_per_chunk
	335	while (rem > 0)
	336	{
	337	index = rem%%nb_workers + 1
	338	indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
	339	rem = rem - 1
d03c0621	340	}
1c6f223e	341	}
492cd9e7	342	indices_workers
1c6f223e	343	}