- synchrones = computeSynchrones(medoids,
- getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
- distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
- medoids[ cluster::pam(distances, K2, diss=TRUE)$medoids , ]
-}
-
-#' computeSynchrones
-#'
-#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
-#' using L2 distances.
-#'
-#' @param medoids Matrix of medoids (curves of same legnth as initial series)
-#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
-#' have been replaced by stage-1 medoids)
-#' @param nb_ref_curves How many reference series? (This number is known at this stage)
-#' @inheritParams claws
-#'
-#' @export
-computeSynchrones = function(medoids, getRefSeries,
- nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
-{
- computeSynchronesChunk = function(indices)
- {
- if (verbose)
- cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep=""))
- ref_series = getRefSeries(indices)
- #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 ) )
- if (parll)
- synchronicity::lock(m)
- synchrones[j,] = synchrones[j,] + ref_series[i,]
- counts[j,1] = counts[j,1] + 1
- if (parll)
- synchronicity::unlock(m)
- }
- }
-
- K = nrow(medoids)
- # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
- 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)
- # Fork (// run) only on Linux & MacOS; on Windows: run sequentially
- parll = (requireNamespace("synchronicity",quietly=TRUE)
- && parll && Sys.info()['sysname'] != "Windows")
- if (parll)
- m <- synchronicity::boost.mutex()
-
- indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
- ignored <-
- if (parll)
- {
- parallel::mclapply(indices_workers, computeSynchronesChunk,
- mc.cores=ncores_clust, mc.allow.recursive=FALSE)
- }
- else
- lapply(indices_workers, computeSynchronesChunk)
-
- mat_syncs = matrix(nrow=K, ncol=ncol(medoids))
- vec_count = rep(NA, K)
- #TODO: can we avoid this loop?
- for (i in seq_len(K))
- {
- mat_syncs[i,] = synchrones[i,]
- vec_count[i] = counts[i,1]
- }
- #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
- mat_syncs = sweep(mat_syncs, 1, vec_count, '/')
- mat_syncs[ sapply(seq_len(K), function(i) all(!is.nan(mat_syncs[i,]))) , ]
-}
-
-#' computeWerDists
-#'
-#' Compute the WER distances between the synchrones curves (in rows), which are
-#' returned (e.g.) by \code{computeSynchrones()}
-#'
-#' @param synchrones A matrix of synchrones, in rows. The series have same length as the
-#' series in the initial dataset
-#' @inheritParams claws
-#'
-#' @export
-computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
-{
- n <- nrow(synchrones)
- delta <- ncol(synchrones)
- #TODO: automatic tune of all these parameters ? (for other users)
- nvoice <- 4
- # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
- 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
-
- 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=0)
- 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))
- }
-
- if (parll)
- {
- cl = parallel::makeCluster(ncores_clust)
- parallel::clusterExport(cl,
- varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
- envir=environment())
- }
-
- # (normalized) observations node with CWT
- Xcwt4 <-
- if (parll)
- parallel::parLapply(cl, seq_len(n), computeCWT)
- else
- lapply(seq_len(n), computeCWT)
-
- 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?!)