-oneIteration = function(..........)
+# 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)
{
- cl_clust = parallel::makeCluster(ncores_clust)
- parallel::clusterExport(cl_clust, .............., envir=........)
- indices_clust = indices_task[[i]]
- repeat
- {
- nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
- indices_workers = list()
- #indices[[i]] == (start_index,number_of_elements)
- for (i in 1:nb_workers)
- {
- upper_bound = ifelse( i<nb_workers,
- min(nb_series_per_chunk*i,length(indices_clust)), length(indices_clust) )
- indices_workers[[i]] = indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
- }
- indices_clust = parallel::parSapply(cl, indices_workers, processChunk, K1, K2*(WER=="mix"))
- if ( (WER=="end" && length(indices_clust) == K1) ||
- (WER=="mix" && length(indices_clust) == K2) )
- {
- break
- }
- }
- parallel::stopCluster(cl_clust)
- res_clust
-}
-
-processChunk = function(indices, K1, K2)
-{
- #1) retrieve data (coeffs)
- coeffs = getCoeffs(indices)
- #2) cluster
- cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1)
- #3) WER (optional)
- if (K2 > 0)
+ cl = parallel::makeCluster(ncores)
+ repeat
{
- curves = computeSynchrones(cl)
- dists = computeWerDists(curves)
- cl = computeClusters(dists, K2)
+ 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
}
- cl
+ parallel::stopCluster(cl)
+ if (K2 == 0)
+ return (indices)
+ computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file)
+ vector("integer",0)
}
-computeClusters = function(data, K)
+# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
+computeClusters1 = function(indices, getCoefs, K1)
{
- library(cluster)
- pam_output = cluster::pam(data, K)
- return ( list( clusts=pam_output$clustering, medoids=pam_output$medoids,
- ranks=pam_output$id.med ) )
+ coefs = getCoefs(indices)
+ indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
}
-#TODO: appendCoeffs() en C --> serialize et append to file
-
-computeSynchrones = function(...)
+# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
+computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file)
{
+ curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones)
+ dists = computeWerDists(curves)
+ medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
+ if (to_file)
+ {
+ serialize(medoids, synchrones_file)
+ return (NULL)
+ }
+ medoids
+}
+# Compute the synchrones curves (sum of clusters elements) from a clustering result
+computeSynchrones = function(indices, getSeries, getSeriesForSynchrones)
+{
+ #les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les
+ #courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ?
+ series = getSeries(indices)
+ #...........
+ #sapply(seq_along(inds), colMeans(getSeries(inds[[i]]$indices,inds[[i]]$ids)))
}
-#Entrée : courbes synchrones, soit après étape 1 itérée, soit après chaqure étape 1
-computeWerDist = function(conso)
+# Compute the WER distance between the synchrones curves (in rows)
+computeWerDist = function(curves)
{
if (!require("Rwave", quietly=TRUE))
stop("Unable to load Rwave library")
- n <- nrow(conso)
- delta <- ncol(conso)
+ n <- nrow(curves)
+ delta <- ncol(curves)
#TODO: automatic tune of all these parameters ? (for other users)
nvoice <- 4
- # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(conso))
+ # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(curves))
noctave = 13
# 4 here represent 2^5 = 32 half-hours ~ 1 day
#NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
# (normalized) observations node with CWT
Xcwt4 <- lapply(seq_len(n), function(i) {
- ts <- scale(ts(conso[i,]), center=TRUE, scale=scaled)
+ ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
#Normalization
{
for (j in (i+1):n)
{
- #TODO: later, compute CWT here (because not enough storage space for 32M series)
+ #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
num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
projects / epclust.git / blobdiff