X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=cda7fbe6c8fab73762d02d72a6568aea75df75f8;hb=1a1196f21036a321710f848d4cb28e6677f24904;hp=9a55495bb6f650a3445c11b281ddef359dd0c4c2;hpb=c45fd66342e40c8b5387fc6f0059c4d3a9718340;p=epclust.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 9a55495..cda7fbe 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -6,11 +6,13 @@
 #'
 #' @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)
+#'   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:
@@ -21,7 +23,7 @@
 #'
 #' @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
+#'   \code{computeClusters2()} outputs a big.matrix of medoids
 #'   (of size limited by nb_series_per_chunk)
 NULL
 
@@ -62,31 +64,44 @@ clusteringTask1 = function(
 
 #' @rdname clustering
 #' @export
-computeClusters1 = function(contribs, K1)
-	cluster::pam(contribs, K1, diss=FALSE)$id.med
-
-#' @rdname clustering
-#' @export
-computeClusters2 = function(medoids, K2,
+clusteringTask2 = function(medoids, K2,
 	getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
+	if (nrow(medoids) <= K2)
+		return (medoids)
 	synchrones = computeSynchrones(medoids,
 		getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
 	distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
-	medoids[ cluster::pam(distances, K2, diss=TRUE)$medoids , ]
+	# 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 Matrix of medoids (curves of same legnth as initial series)
+#' @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)
@@ -111,36 +126,43 @@ computeSynchrones = function(medoids, getRefSeries,
 
 	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)
-	# Fork (// run) only on Linux & MacOS; on Windows: run sequentially
+	# 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::mclapply(indices_workers, computeSynchronesChunk,
-				mc.cores=ncores_clust, mc.allow.recursive=FALSE)
-		}
+			parallel::parLapply(indices_workers, computeSynchronesChunk)
 		else
 			lapply(indices_workers, computeSynchronesChunk)
 
-	mat_syncs = matrix(nrow=K, ncol=ncol(medoids))
-	vec_count = rep(NA, K)
-	#TODO: can we avoid this loop?
+	if (parll)
+		parallel::stopCluster(cl)
+
+	#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
 	for (i in seq_len(K))
-	{
-		mat_syncs[i,] = synchrones[i,]
-		vec_count[i] = counts[i,1]
-	}
+		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
-	mat_syncs = sweep(mat_syncs, 1, vec_count, '/')
-	mat_syncs[ sapply(seq_len(K), function(i) all(!is.nan(mat_syncs[i,]))) , ]
+	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
@@ -148,13 +170,21 @@ computeSynchrones = function(medoids, getRefSeries,
 #' 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
+#' @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)
@@ -163,7 +193,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	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) * 2
+	scalevector  <- 2^(4:(noctave * nvoice) / nvoice + 1)
 	#condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
 	s0=2
 	w0=2*pi
@@ -176,7 +206,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 		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)
+		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)
@@ -192,7 +222,8 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 			envir=environment())
 	}
 
-	# (normalized) observations node with CWT
+	# 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)
@@ -207,6 +238,9 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 	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)
@@ -217,7 +251,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 			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)) )
+			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))
@@ -242,12 +276,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 		else
 			lapply(seq_len(n-1), computeDistancesLineI)
 	Xwer_dist[n,n] = 0.
-
-	mat_dists = matrix(nrow=n, ncol=n)
-	#TODO: avoid this loop?
-	for (i in 1:n)
-		mat_dists[i,] = Xwer_dist[i,]
-	mat_dists
+	Xwer_dist
 }
 
 # Helper function to divide indices into balanced sets