indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
{
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) ]
- }
+ cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
if (parll)
{
while (length(indices) > K1)
{
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) )
+ 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)
clusteringTask2 = function(medoids, K2,
getRefSeries, nb_ref_curves, nb_series_per_chunk, 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, ncores_clust, verbose, parll)
# 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), ]
+ medoids[ computeClusters2(distances[,],K2,verbose), ]
}
#' @rdname clustering
#' @export
-computeClusters1 = function(contribs, K1)
+computeClusters1 = function(contribs, K1, verbose=FALSE)
+{
+ if (verbose)
+ cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
cluster::pam(contribs, K1, diss=FALSE)$id.med
+}
#' @rdname clustering
#' @export
-computeClusters2 = function(distances, K2)
+computeClusters2 = function(distances, K2, verbose=FALSE)
+{
+ if (verbose)
+ cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep=""))
cluster::pam(distances, K2, diss=TRUE)$id.med
+}
#' computeSynchrones
#'
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 (verbose)
- cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep=""))
ref_series = getRefSeries(indices)
+ nb_series = nrow(ref_series)
#get medoids indices for this chunk of series
- for (i in seq_len(nrow(ref_series)))
+
+ #TODO: debug this (address is OK but values are garbage: why?)
+# mi = .Call("computeMedoidsIndices", medoids@address, ref_series, PACKAGE="epclust")
+
+ #R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope)
+ mat_meds = medoids[,]
+ mi = rep(NA,nb_series)
+ for (i in 1:nb_series)
+ mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) )
+ rm(mat_meds); gc()
+
+ for (i in seq_len(nb_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
+ synchrones[mi[i],] = synchrones[mi[i],] + ref_series[i,]
+ counts[mi[i],1] = counts[mi[i],1] + 1
if (parll)
synchronicity::unlock(m)
}
}
- K = nrow(medoids)
+ 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=ncol(medoids),type="double",init=0.)
- counts = bigmemory::big.matrix(nrow=K,ncol=1,type="double",init=0)
+ synchrones = bigmemory::big.matrix(nrow=K, ncol=L, 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")
}
indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
+ browser()
ignored <-
if (parll)
- parallel::parLapply(indices_workers, computeSynchronesChunk)
+ parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
else
lapply(indices_workers, computeSynchronesChunk)
#' @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
-
+ if (verbose)
+ cat(paste("--- Compute WER dists\n", sep=""))
n <- nrow(synchrones)
delta <- ncol(synchrones)
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")
+ fcoefs = rep(1/3, 3) #moving average on 3 values
+
+ # 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)))
+ }
+
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=FALSE)
ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
sqres / max(Mod(sqres))
}
+ computeDistancesIJ = function(pair)
+ {
+ 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)
+ num <- .Call("filter", Mod(cwt_i * Conj(cwt_j)), PACKAGE="epclust")
+ WX <- .Call("filter", Mod(cwt_i * Conj(cwt_i)), PACKAGE="epclust")
+ WY <- .Call("filter", Mod(cwt_j * Conj(cwt_j)), PACKAGE="epclust")
+ wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
+ Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * (1 - wer2))
+ Xwer_dist[j,i] <- Xwer_dist[i,j]
+ Xwer_dist[i,i] = 0.
+ }
+
if (parll)
{
cl = parallel::makeCluster(ncores_clust)
envir=environment())
}
- # list of CWT from synchrones
- # TODO: fit in RAM, OK? If not, 2 options: serialize, compute individual distances
- Xcwt4 <-
+ ignored <-
if (parll)
- parallel::parLapply(cl, seq_len(n), computeCWT)
+ parallel::parLapply(cl, pairs, computeDistancesIJ)
else
- lapply(seq_len(n), computeCWT)
+ lapply(pairs, computeDistancesIJ)
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?!)
- 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)
- cat(paste(" Line ",i,"\n", sep=""))
- for (j in (i+1):n)
- {
- #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()
-
- ignored <-
- if (parll)
- {
- parallel::mclapply(seq_len(n-1), computeDistancesLineI,
- mc.cores=ncores_clust, mc.allow.recursive=FALSE)
- }
- else
- lapply(seq_len(n-1), computeDistancesLineI)
Xwer_dist[n,n] = 0.
Xwer_dist
}
projects / epclust.git / blobdiff