-oneIteration = function(..........)
+#' Two-stage clustering, within one task (see \code{claws()})
+#'
+#' \code{clusteringTask1()} runs one full stage-1 task, which consists in iterated
+#' clustering on nb_curves / ntasks energy contributions, computed through
+#' discrete wavelets coefficients.
+#' \code{clusteringTask2()} runs a full stage-2 task, which consists in WER distances
+#' computations between medoids (indices) output from stage 1, before applying
+#' the second clustering algorithm on the distances matrix.
+#'
+#' @param getContribs Function to retrieve contributions from initial series indices:
+#' \code{getContribs(indices)} outputs a contributions matrix, in columns
+#' @inheritParams claws
+#' @inheritParams computeSynchrones
+#' @inheritParams computeWerDists
+#'
+#' @return The indices of the computed (resp. K1 and K2) medoids.
+#'
+#' @name clustering
+#' @rdname clustering
+#' @aliases clusteringTask1 clusteringTask2
+NULL
+
+#' @rdname clustering
+#' @export
+clusteringTask1 <- function(indices, getContribs, K1, algoClust1, nb_items_clust,
+ ncores_clust=3, verbose=FALSE)
{
- 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)
+ if (verbose)
+ cat(paste("*** Clustering task 1 on ",length(indices)," series [start]\n", sep=""))
+
+ if (length(indices) <= K1)
+ return (indices)
+
+ parll <- (ncores_clust > 1)
+ if (parll)
+ {
+ # outfile=="" to see stderr/stdout on terminal
+ cl <-
+ if (verbose)
+ parallel::makeCluster(ncores_clust, outfile = "")
+ else
+ parallel::makeCluster(ncores_clust)
+ parallel::clusterExport(cl, c("getContribs","K1","verbose"), envir=environment())
+ }
+ # Iterate clustering algorithm 1 until K1 medoids are found
+ while (length(indices) > K1)
+ {
+ # Balance tasks by splitting the indices set - as evenly as possible
+ indices_workers <- .splitIndices(indices, nb_items_clust, min_size=K1+1)
+ indices <-
+ if (parll)
{
- 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]
+ unlist( parallel::parLapply(cl, indices_workers, function(inds) {
+ require("epclust", quietly=TRUE)
+ inds[ algoClust1(getContribs(inds), K1) ]
+ }) )
}
- 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) )
+ else
{
- break
+ unlist( lapply(indices_workers, function(inds)
+ inds[ algoClust1(getContribs(inds), K1) ]
+ ) )
}
+ if (verbose)
+ {
+ cat(paste("*** Clustering task 1 on ",length(indices)," medoids [iter]\n", sep=""))
}
- 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)
- {
- curves = computeSynchrones(cl)
- dists = computeWerDists(curves)
- cl = computeClusters(dists, K2)
}
- cl
-}
+ if (parll)
+ parallel::stopCluster(cl)
-computeClusters = function(data, K)
-{
- library(cluster)
- pam_output = cluster::pam(data, K)
- return ( list( clusts=pam_output$clustering, medoids=pam_output$medoids,
- ranks=pam_output$id.med ) )
+ indices #medoids
}
-#TODO: appendCoeffs() en C --> serialize et append to file
-
-computeSynchrones = function(...)
+#' @rdname clustering
+#' @export
+clusteringTask2 <- function(indices, getSeries, K2, algoClust2, nb_series_per_chunk,
+ smooth_lvl, nvoice, nbytes, endian, ncores_clust=3, verbose=FALSE)
{
+ if (verbose)
+ cat(paste("*** Clustering task 2 on ",length(indices)," medoids\n", sep=""))
-}
+ if (length(indices) <= K2)
+ return (indices)
-#Entrée : courbes synchrones, soit après étape 1 itérée, soit après chaqure étape 1
-computeWerDist = function(conso)
-{
- if (!require("Rwave", quietly=TRUE))
- stop("Unable to load Rwave library")
- n <- nrow(conso)
- delta <- ncol(conso)
- #TODO: automatic tune of all these parameters ? (for other users)
- nvoice <- 4
- # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(conso))
- 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
- #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
- 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
+ # A) Compute the WER distances (Wavelets Extended coefficient of deteRmination)
+ distances <- computeWerDists(indices, getSeries, nb_series_per_chunk,
+ smooth_lvl, nvoice, nbytes, endian, ncores_clust, verbose)
- # (normalized) observations node with CWT
- Xcwt4 <- lapply(seq_len(n), function(i) {
- ts <- scale(ts(conso[i,]), center=TRUE, scale=scaled)
- totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
- ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
- #Normalization
- sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
- sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
- sqres / max(Mod(sqres))
- })
-
- Xwer_dist <- matrix(0., n, n)
- fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
- for (i in 1:(n-1))
- {
- for (j in (i+1):n)
- {
- #TODO: later, compute CWT here (because not enough storage space for 32M 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)
- WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
- wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
- Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
- Xwer_dist[j,i] <- Xwer_dist[i,j]
- }
- }
- diag(Xwer_dist) <- numeric(n)
- Xwer_dist
+ # B) Apply clustering algorithm 2 on the WER distances matrix
+ if (verbose)
+ cat(paste("*** algoClust2() on ",nrow(distances)," items\n", sep=""))
+ indices[ algoClust2(distances,K2) ]
}