X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=8be871531f22e7a7dfe7b8828744b59f4c058c79;hb=a52836b23adb4bfa6722642ec6426fb7b5f39650;hp=14915abf861bace1b6d4bd4f9f68283c004bfff9;hpb=eef6f6c97277ea3ce760981e5244cbde7fc904a0;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 14915ab..8be8715 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -11,51 +11,49 @@
 #'   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)
+#'   first clustering algorithm on a contributions matrix, while the latter clusters
+#'   a set of series inside one task (~nb_items_clust1)
 #'
 #' @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)
+#' @return For \code{clusteringTask1()}, the indices of the computed (K1) medoids.
+#'   Indices are irrelevant for stage 2 clustering, thus \code{clusteringTask2()}
+#'   outputs a big.matrix of medoids (of size LxK2, K2 = final number of clusters)
 NULL
 
 #' @rdname clustering
 #' @export
-clusteringTask1 = function(
-	indices, getContribs, K1, nb_items_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
+clusteringTask1 = function(indices, getContribs, K1, algoClust1, nb_items_clust1,
+	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())
+		cl = parallel::makeCluster(ncores_clust, outfile = "")
+		parallel::clusterExport(cl, c("getContribs","K1","verbose"), envir=environment())
 	}
+	# Iterate clustering algorithm 1 until K1 medoids are found
 	while (length(indices) > K1)
 	{
-		indices_workers = .spreadIndices(indices, nb_series_per_chunk)
+		# Balance tasks by splitting the indices set - as evenly as possible
+		indices_workers = .spreadIndices(indices, nb_items_clust1)
+		if (verbose)
+			cat(paste("*** [iterated] Clustering task 1 on ",length(indices)," series\n", sep=""))
 		indices <-
 			if (parll)
 			{
 				unlist( parallel::parLapply(cl, indices_workers, function(inds) {
 					require("epclust", quietly=TRUE)
-					inds[ computeClusters1(getContribs(inds), K1, verbose) ]
+					inds[ algoClust1(getContribs(inds), K1) ]
 				}) )
 			}
 			else
 			{
 				unlist( lapply(indices_workers, function(inds)
-					inds[ computeClusters1(getContribs(inds), K1, verbose) ]
+					inds[ algoClust1(getContribs(inds), K1) ]
 				) )
 			}
 	}
@@ -67,42 +65,34 @@ clusteringTask1 = function(
 
 #' @rdname clustering
 #' @export
-clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves,
-	nb_series_per_chunk, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
+clusteringTask2 = function(medoids, K2, algoClust2, getRefSeries, nb_ref_curves,
+	nb_series_per_chunk, nvoice, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
 	if (verbose)
-		cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))
+		cat(paste("*** Clustering task 2 on ",ncol(medoids)," synchrones\n", sep=""))
 
-	if (nrow(medoids) <= K2)
+	if (ncol(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
-}
+	# A) Obtain synchrones, that is to say the cumulated power consumptions
+	#    for each of the K1 initial groups
+	synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves,
+		nb_series_per_chunk, ncores_clust, verbose, parll)
 
-#' @rdname clustering
-#' @export
-computeClusters2 = function(distances, K2, verbose=FALSE)
-{
+	# B) Compute the WER distances (Wavelets Extended coefficient of deteRmination)
+	distances = computeWerDists(
+		synchrones, nvoice, nbytes, endian, ncores_clust, verbose, parll)
+
+	# C) Apply clustering algorithm 2 on the WER distances matrix
 	if (verbose)
-		cat(paste("   computeClusters2() on ",nrow(distances)," lines\n", sep=""))
-	cluster::pam(       distances        , K2, diss=TRUE)$id.med
+		cat(paste("*** algoClust2() on ",nrow(distances)," items\n", sep=""))
+	medoids[ ,algoClust2(distances,K2) ]
 }
 
 #' computeSynchrones
 #'
 #' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
-#' using L2 distances.
+#' using euclidian distance.
 #'
 #' @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
@@ -113,12 +103,10 @@ computeClusters2 = function(distances, K2, verbose=FALSE)
 #' @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)
+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=""))
-
+	# Synchrones computation is embarassingly parallel: compute it by chunks of series
 	computeSynchronesChunk = function(indices)
 	{
 		if (parll)
@@ -126,50 +114,56 @@ computeSynchrones = function(medoids, getRefSeries,
 			require("bigmemory", quietly=TRUE)
 			requireNamespace("synchronicity", quietly=TRUE)
 			require("epclust", quietly=TRUE)
+			# The big.matrix objects need to be attached to be usable on the workers
 			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)
 		}
 
+		# Obtain a chunk of reference series
 		ref_series = getRefSeries(indices)
-		nb_series = nrow(ref_series)
+		nb_series = ncol(ref_series)
 
-		#get medoids indices for this chunk of series
+		# Get medoids indices for this chunk of series
 		mi = computeMedoidsIndices(medoids@address, ref_series)
 
+		# Update synchrones using mi above
 		for (i in seq_len(nb_series))
 		{
 			if (parll)
-				synchronicity::lock(m)
+				synchronicity::lock(m) #locking required because several writes at the same time
 			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)
 		}
+		NULL
 	}
 
-	K = nrow(medoids) ; L = ncol(medoids)
+	K = ncol(medoids) ; L = 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=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")
+	# NOTE: synchronicity is only for Linux & MacOS; on Windows: run sequentially
+	parll = (parll && requireNamespace("synchronicity",quietly=TRUE)
+		&& Sys.info()['sysname'] != "Windows")
 	if (parll)
 	{
-		m <- synchronicity::boost.mutex()
+		m <- synchronicity::boost.mutex() #for lock/unlock, see computeSynchronesChunk
+		# mutex and big.matrix objects cannot be passed directly:
+		# they will be accessed from their description
 		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())
+		parallel::clusterExport(cl, envir=environment(),
+			varlist=c("synchrones_desc","m_desc","medoids_desc","getRefSeries"))
 	}
 
-	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
+	if (verbose)
+		cat(paste("--- Compute ",K," synchrones with ",nb_ref_curves," series\n", sep=""))
+
+	# Balance tasks by splitting the indices set - maybe not so evenly, but
+	# max==TRUE in next call ensures that no set has more than nb_series_per_chunk items.
+	indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk, max=TRUE)
 	ignored <-
 		if (parll)
 			parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
@@ -179,56 +173,31 @@ computeSynchrones = function(medoids, getRefSeries,
 	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])
+	return (synchrones)
 }
 
 #' computeWerDists
 #'
-#' Compute the WER distances between the synchrones curves (in rows), which are
+#' Compute the WER distances between the synchrones curves (in columns), 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
+#' @param synchrones A big.matrix of synchrones, in columns. The series have same
+#'   length as the series in the initial dataset
 #' @inheritParams claws
 #'
-#' @return A matrix of size K1 x K1
+#' @return A distances matrix of size K1 x K1
 #'
 #' @export
-computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
+computeWerDists = function(synchrones, nvoice, 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
+	n <- ncol(synchrones)
+	L <- nrow(synchrones)
+	noctave = ceiling(log2(L)) #min power of 2 to cover serie range
 
+	# Initialize result as a square big.matrix of size 'number of synchrones'
 	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)
@@ -238,18 +207,23 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS
 		pairs = c(pairs, lapply(V, function(v) c(i,v)))
 	}
 
+	cwt_file = ".cwt.bin"
+	# Compute the synchrones[,index] CWT, and store it in the binary file above
 	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 && !exists(synchrones)) #avoid going here after first call on a worker
+		{
+			require("bigmemory", quietly=TRUE)
+			require("Rwave", quietly=TRUE)
+			require("epclust", quietly=TRUE)
+			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
+		}
+		ts <- scale(ts(synchrones[,index]), center=TRUE, scale=FALSE)
+		ts_cwt = Rwave::cwt(ts, noctave, nvoice, w0=2*pi, twoD=TRUE, plot=FALSE)
+
+		# Serialization
+		binarize(as.matrix(c(as.double(Re(ts_cwt)),as.double(Im(ts_cwt)))), cwt_file, 1,
+			",", nbytes, endian)
 	}
 
 	if (parll)
@@ -257,29 +231,35 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS
 		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())
+		parallel::clusterExport(cl, varlist=c("parll","synchrones_desc","Xwer_dist_desc",
+			"noctave","nvoice","verbose","getCWT"), envir=environment())
 	}
 
-	#precompute and serialize all CWT
+	if (verbose)
+		cat(paste("--- Precompute and serialize synchrones CWT\n", sep=""))
+
 	ignored <-
 		if (parll)
 			parallel::parLapply(cl, 1:n, computeSaveCWT)
 		else
 			lapply(1:n, computeSaveCWT)
 
-	getCWT = function(index)
+	# Function to retrieve a synchrone CWT from (binary) file
+	getSynchroneCWT = function(index, L)
 	{
-		#from cwt_file ...
-		res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian)
-	###############TODO:
+		flat_cwt <- getDataInFile(index, cwt_file, nbytes, endian)
+		cwt_length = length(flat_cwt) / 2
+		re_part = as.matrix(flat_cwt[1:cwt_length], nrow=L)
+		im_part = as.matrix(flat_cwt[(cwt_length+1):(2*cwt_length)], nrow=L)
+		re_part + 1i * im_part
 	}
 
-	# Distance between rows i and j
-	computeDistancesIJ = function(pair)
+	# Compute distance between columns i and j in synchrones
+	computeDistanceIJ = function(pair)
 	{
 		if (parll)
 		{
+			# parallel workers start with an empty environment
 			require("bigmemory", quietly=TRUE)
 			require("epclust", quietly=TRUE)
 			synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
@@ -287,51 +267,69 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS
 		}
 
 		i = pair[1] ; j = pair[2]
-		if (verbose && j==i+1)
+		if (verbose && j==i+1 && !parll)
 			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)))
+		# Compute CWT of columns i and j in synchrones
+		L = nrow(synchrones)
+		cwt_i <- getSynchroneCWT(i, L)
+		cwt_j <- getSynchroneCWT(j, L)
+
+		# Compute the ratio of integrals formula 5.6 for WER^2
+		# in https://arxiv.org/abs/1101.4744v2 §5.3
+		num <- filterMA(Mod(cwt_i * Conj(cwt_j)))
+		WX  <- filterMA(Mod(cwt_i * Conj(cwt_i)))
+		WY <- filterMA(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[i,j] <- sqrt(L * ncol(cwt_i) * (1 - wer2))
 		Xwer_dist[j,i] <- Xwer_dist[i,j]
-		Xwer_dist[i,i] = 0.
+		Xwer_dist[i,i] <- 0.
 	}
 
+	if (verbose)
+		cat(paste("--- Compute WER distances\n", sep=""))
+
 	ignored <-
 		if (parll)
-			parallel::parLapply(cl, pairs, computeDistancesIJ)
+			parallel::parLapply(cl, pairs, computeDistanceIJ)
 		else
-			lapply(pairs, computeDistancesIJ)
+			lapply(pairs, computeDistanceIJ)
 
 	if (parll)
 		parallel::stopCluster(cl)
 
+	unlink(cwt_file)
+
 	Xwer_dist[n,n] = 0.
-	distances <- Xwer_dist[,]
-	rm(Xwer_dist) ; gc()
-	distances #~small matrix K1 x K1
+	Xwer_dist[,] #~small matrix K1 x K1
 }
 
 # Helper function to divide indices into balanced sets
-.spreadIndices = function(indices, nb_per_chunk)
+# If max == TRUE, sets sizes cannot exceed nb_per_set
+.spreadIndices = function(indices, nb_per_set, max=FALSE)
 {
 	L = length(indices)
-	nb_workers = floor( L / nb_per_chunk )
-	if (nb_workers == 0)
+	nb_workers = floor( L / nb_per_set )
+	rem = L %% nb_per_set
+	if (nb_workers == 0 || (nb_workers==1 && rem==0))
 	{
-		# L < nb_series_per_chunk, simple case
+		# L <= nb_per_set, 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)] )
+			indices[(nb_per_set*(i-1)+1):(nb_per_set*i)] )
+
+		if (max)
+		{
+			# Sets are not so well balanced, but size is supposed to be critical
+			return ( c( indices_workers, if (rem>0) list((L-rem+1):L) else NULL ) )
+		}
+
 		# Spread the remaining load among the workers
-		rem = L %% nb_per_chunk
+		rem = L %% nb_per_set
 		while (rem > 0)
 		{
 			index = rem%%nb_workers + 1