X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=74d009e45495220304a0087554e619d3c9efc4e4;hb=492cd9e74a79cbcc0ecde55fa3071a44b7e463dc;hp=87a5f914e137cb3f509443b58a1e59b80505b011;hpb=3eef8d3df59ded9a281cff51f79fe824198a7427;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 87a5f91..74d009e 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,85 +1,169 @@
-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_file,
-	getCoefs,K1,K2,nb_series_per_chunk,ncores,to_file,ftype)
+#' @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{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 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)
 {
-	cl = parallel::makeCluster(ncores)
-	repeat
+	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)
 	{
-		nb_workers = max( 1, round( length(indices) / nb_series_per_chunk ) )
-		indices_workers = lapply(seq_len(nb_workers), function(i) {
-			upper_bound = ifelse( i<nb_workers,
-				min(nb_series_per_chunk*i,length(indices)), length(indices) )
-			indices[(nb_series_per_chunk*(i-1)+1):upper_bound]
-		})
-		indices = unlist( parallel::parLapply(cl, indices_workers, function(inds)
-			computeClusters1(inds, getCoefs, K1)) )
-		if (length(indices_clust) == K1)
-			break
+		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) )
 	}
-	parallel::stopCluster(cl)
-	if (K2 == 0)
-		return (indices)
-	computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file,
-									 nb_series_per_chunk,ftype)
-	vector("integer",0)
+	if (parll)
+		parallel::stopCluster(cl)
+
+	indices #medoids
 }
 
-# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters1 = function(indices, getCoefs, K1)
+#' @rdname clustering
+#' @export
+computeClusters1 = function(contribs, K1)
+	cluster::pam(contribs, K1, diss=FALSE)$id.med
+
+#' @rdname clustering
+#' @export
+computeClusters2 = function(medoids, K2,
+	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
-	coefs = getCoefs(indices)
-	indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
+	synchrones = computeSynchrones(medoids,
+		getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
+	distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
+	medoids[ cluster::pam(distances, K2, diss=TRUE)$medoids , ]
 }
 
-# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file,
-														nb_series_per_chunk, ftype)
+#' computeSynchrones
+#'
+#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
+#' using L2 distances.
+#'
+#' @param medoids Matrix of medoids (curves of same legnth 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
+#'
+#' @export
+computeSynchrones = function(medoids, getRefSeries,
+	nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
-	curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk)
-	dists = computeWerDists(curves)
-	medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
-	if (to_file)
+	computeSynchronesChunk = function(indices)
 	{
-		serialize(medoids, synchrones_file, ftype, nb_series_per_chunk)
-		return (NULL)
+		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)
+		}
 	}
-	medoids
-}
 
-# Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk)
-{
-	#les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les
-	#courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ?
-	medoids = getSeries(indices)
 	K = nrow(medoids)
-	synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
-	counts = rep(0,K)
-	index = 1
-	repeat
+	# Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
+	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)
+	# Fork (// run) only on Linux & MacOS; on Windows: run sequentially
+	parll = (requireNamespace("synchronicity",quietly=TRUE)
+		&& parll && Sys.info()['sysname'] != "Windows")
+	if (parll)
+		m <- synchronicity::boost.mutex()
+
+	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
+	for (inds in indices_workers)
 	{
-		series = getSeriesForSynchrones((index-1)+seq_len(nb_series_per_chunk))
-		if (is.null(series))
-			break
-		#get medoids indices for this chunk of series
-		index = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) )
-		synchrones[index,] = synchrones[index,] + series[i,]
-		counts[index] = counts[index] + 1
+		if (verbose)
+		{
+			cat(paste("--- Compute synchrones for indices range ",
+				min(inds)," -> ",max(inds),"\n", sep=""))
+		}
+		if (parll)
+			ignored <- parallel::mcparallel(computeSynchronesChunk(inds))
+		else
+			computeSynchronesChunk(inds)
+	}
+	if (parll)
+		parallel::mccollect()
+
+	mat_syncs = matrix(nrow=K, ncol=ncol(medoids))
+	vec_count = rep(NA, K)
+	#TODO: can we avoid this loop?
+	for (i in seq_len(K))
+	{
+		mat_syncs[i,] = synchrones[i,]
+		vec_count[i] = counts[i,1]
 	}
 	#NOTE: odds for some clusters to be empty? (when series already come from stage 2)
-	synchrones = sweep(synchrones, 1, counts, '/')
+	#      ...maybe; but let's hope resulting K1' be still quite bigger than K2
+	mat_syncs = sweep(mat_syncs, 1, vec_count, '/')
+	mat_syncs[ sapply(seq_len(K), function(i) all(!is.nan(mat_syncs[i,]))) , ]
 }
 
-# Compute the WER distance between the synchrones curves (in rows)
-computeWerDist = function(curves)
+#' computeWerDists
+#'
+#' Compute the WER distances between the synchrones curves (in rows), which are
+#' returned (e.g.) by \code{computeSynchrones()}
+#'
+#' @param synchrones A matrix of synchrones, in rows. The series have same length as the
+#'   series in the initial dataset
+#' @inheritParams claws
+#'
+#' @export
+computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
-	if (!require("Rwave", quietly=TRUE))
-		stop("Unable to load Rwave library")
-	n <- nrow(curves)
-	delta <- ncol(curves)
+	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(curves))
+	# 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 (?)
@@ -91,33 +175,107 @@ computeWerDist = function(curves)
 	s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
 	totnoct = noctave + as.integer(s0log/nvoice) + 1
 
-	# (normalized) observations node with CWT
-	Xcwt4 <- lapply(seq_len(n), function(i) {
-		ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
+	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=0)
 		ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
 		#Normalization
 		sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
 		sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
 		sqres / max(Mod(sqres))
-	})
+	}
 
-	Xwer_dist <- matrix(0., n, n)
+	if (parll)
+	{
+		cl = parallel::makeCluster(ncores_clust)
+		parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
+	}
+
+	# (normalized) observations node with CWT
+	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?!)
-	for (i in 1:(n-1))
+	if (verbose)
+		cat("*** Compute WER distances from CWT\n")
+
+	computeDistancesLineI = function(i)
 	{
+		if (verbose)
+			cat(paste("   Line ",i,"\n", sep=""))
 		for (j in (i+1):n)
 		{
-			#TODO: later, compute CWT here (because not enough storage space for 200k series)
-			#      'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
+			#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()
+
+	for (i in 1:(n-1))
+	{
+		if (parll)
+			ignored <- parallel::mcparallel(computeDistancesLineI(i))
+		else
+			computeDistancesLineI(i)
+	}
+	Xwer_dist[n,n] = 0.
+
+	if (parll)
+		parallel::mccollect()
+
+	mat_dists = matrix(nrow=n, ncol=n)
+	#TODO: avoid this loop?
+	for (i in 1:n)
+		mat_dists[i,] = Xwer_dist[i,]
+	mat_dists
+}
+
+# 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
 		}
 	}
-	diag(Xwer_dist) <- numeric(n)
-	Xwer_dist
+	indices_workers
 }