-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(K1, K2, WER, nb_series_per_chunk, indices_tasks, ncores_clust)
+# Cluster one full task (nb_curves / ntasks series); only step 1
+clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores)
{
- cl_clust = parallel::makeCluster(ncores_clust)
- #parallel::clusterExport(cl=cl_clust, varlist=c("fonctions_du_package"), envir=environment())
- indices_clust = indices_task[[i]]
+ cl = parallel::makeCluster(ncores)
+ parallel::clusterExport(cl, varlist=c("getCoefs","K1"), envir=environment())
repeat
{
- nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
- indices_workers = list()
- for (i in 1:nb_workers)
+ nb_workers = max( 1, floor( length(indices) / nb_series_per_chunk ) )
+ indices_workers = lapply( seq_len(nb_workers), function(i)
+ indices[(nb_series_per_chunk*(i-1)+1):(nb_series_per_chunk*i)] )
+ # Spread the remaining load among the workers
+ rem = length(indices) %% nb_series_per_chunk
+ while (rem > 0)
{
- 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]
+ index = rem%%nb_workers + 1
+ indices_workers[[index]] = c(indices_workers[[index]], tail(indices,rem))
+ rem = rem - 1
}
- indices_clust = parallel::parLapply(cl, indices_workers, clusterChunk, K1, K2*(WER=="mix"))
- if ((WER=="end" && length(indices_clust)==K1) || (WER=="mix" && length(indices_clust)==K2))
+ indices = unlist( parallel::parLapply( cl, indices_workers, function(inds) {
+ require("epclust", quietly=TRUE)
+ inds[ computeClusters1(getCoefs(inds), K1) ]
+ } ) )
+ if (length(indices) == K1)
break
}
- parallel::stopCluster(cl_clust)
- unlist(indices_clust)
-}
-
-# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-clusterChunk = function(indices, K1, K2)
-{
- coeffs = getCoeffs(indices)
- cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE)
- if (K2 > 0)
- {
- curves = computeSynchrones(cl)
- dists = computeWerDists(curves)
- cl = computeClusters(dists, K2, diss=TRUE)
- }
- indices[cl]
+ parallel::stopCluster(cl)
+ indices #medoids
}
# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters = function(md, K, diss)
+computeClusters1 = function(coefs, K1)
+ cluster::pam(coefs, K1, diss=FALSE)$id.med
+
+# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
{
- if (!require(cluster, quietly=TRUE))
- stop("Unable to load cluster library")
- cluster::pam(md, K, diss=diss)$id.med
+ synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
+ medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ]
}
# Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices)
+computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
{
- colSums( getData(indices) )
+ K = nrow(medoids)
+ synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
+ counts = rep(0,K)
+ index = 1
+ repeat
+ {
+ range = (index-1) + seq_len(nb_series_per_chunk)
+ ref_series = getRefSeries(range)
+ if (is.null(ref_series))
+ break
+ #get medoids indices for this chunk of series
+ for (i in seq_len(nrow(ref_series)))
+ {
+ j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
+ synchrones[j,] = synchrones[j,] + ref_series[i,]
+ counts[j] = counts[j] + 1
+ }
+ index = index + nb_series_per_chunk
+ }
+ #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
+ synchrones = sweep(synchrones, 1, counts, '/')
+ synchrones[ sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,]))) , ]
}
-# Compute the WER distance between the synchrones curves
-computeWerDist = function(curves)
+# Compute the WER distance between the synchrones curves (in rows)
+computeWerDists = function(curves)
{
if (!require("Rwave", quietly=TRUE))
stop("Unable to load Rwave library")
{
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