#' @name clustering
#' @rdname clustering
-#' @aliases clusteringTask1 computeClusters1 computeClusters2
+#' @aliases clusteringTask1 clusteringTask2 computeClusters1 computeClusters2
#'
#' @title Two-stage clustering, withing one task (see \code{claws()})
#'
#' 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_clust)
#'
#' @param indices Range of series indices to cluster in parallel (initial data)
#' @param getContribs Function to retrieve contributions from initial series indices:
#' @rdname clustering
#' @export
clusteringTask1 = function(
- indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
+ indices, getContribs, K1, nb_per_chunk, nb_items_clust, ncores_clust=1,
+ verbose=FALSE, parll=TRUE)
{
if (verbose)
cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
+
+
+
+
+
+##TODO: reviser le spreadIndices, tenant compte de nb_items_clust
+
+ ##TODO: reviser / harmoniser avec getContribs qui en récupère pt'et + pt'et - !!
+
+
+
if (parll)
{
cl = parallel::makeCluster(ncores_clust)
#' @rdname clustering
#' @export
-clusteringTask2 = function(medoids, K2,
- getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
+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=""))
return (medoids)
synchrones = computeSynchrones(medoids,
getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
- distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
+ distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll)
medoids[ computeClusters2(distances,K2,verbose), ]
}
{
if (verbose)
cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
- cluster::pam(contribs, K1, diss=FALSE)$id.med
+ cluster::pam( t(contribs) , K1, diss=FALSE)$id.med
}
#' @rdname clustering
{
if (verbose)
cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep=""))
- cluster::pam(distances, K2, diss=TRUE)$id.med
+ cluster::pam( distances , K2, diss=TRUE)$id.med
}
#' computeSynchrones
#' @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
+#' @return A big.matrix of size L x K1 where L = length of a serie
#'
#' @export
computeSynchrones = function(medoids, getRefSeries,
{
if (parll)
synchronicity::lock(m)
- synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,]
- counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts?
+ 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=K, ncol=L, type="double", init=0.)
+ 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)
#TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
for (i in seq_len(K))
- synchrones[i,] = synchrones[i,] / counts[i,1]
+ 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,])))
+ 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,]
+ bigmemory::as.big.matrix(synchrones[,noNA_rows])
}
#' computeWerDists
#' @return A matrix of size K1 x K1
#'
#' @export
-computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
+computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
{
if (verbose)
cat(paste("--- Compute WER dists\n", sep=""))
-
-
-
-#TODO: serializer les CWT, les récupérer via getDataInFile
-#--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
-
-
-
-
n <- nrow(synchrones)
delta <- ncol(synchrones)
#TODO: automatic tune of all these parameters ? (for other users)
#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
+ 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)))
-# }
- # Generate "smart" pairs for WER distances computations
pairs = list()
- F = floor(2*n/3)
- for (i in 1:F)
- pairs = c(pairs, lapply((i+1):n, function(v) c(i,v)))
- V = (F+1):n
- for (i in (F+1):(n-1))
+ V = seq_len(n)
+ for (i in 1:n)
{
V = V[-1]
- pairs = c(pairs,
+ 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)
Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
}
- computeCWT = 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,'*')
- 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)
+ cwt_i <- getCWT(i)
+ cwt_j <- getCWT(j)
-#print(system.time( {
num <- epclustFilter(Mod(cwt_i * Conj(cwt_j)))
WX <- epclustFilter(Mod(cwt_i * Conj(cwt_i)))
- WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
+ 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.
}
- 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"), envir=environment())
- }
-
ignored <-
if (parll)
parallel::parLapply(cl, pairs, computeDistancesIJ)