- cat(paste("--- Compute synchrones\n", sep=""))
-
- computeSynchronesChunk = function(indices)
- {
- ref_series = getRefSeries(indices)
- nb_series = nrow(ref_series)
- #get medoids indices for this chunk of 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))
- {
- if (parll)
- synchronicity::lock(m)
- 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) ; 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=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")
- if (parll)
- m <- synchronicity::boost.mutex()
-
- if (parll)
- {
- cl = parallel::makeCluster(ncores_clust)
- parallel::clusterExport(cl,
- varlist=c("synchrones","counts","verbose","medoids","getRefSeries"),
- envir=environment())
- }
-
- indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
-#browser()
- ignored <-
- if (parll)
- parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
- else
- lapply(indices_workers, computeSynchronesChunk)
-
- if (parll)
- parallel::stopCluster(cl)
-
- #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
- for (i in seq_len(K))
- synchrones[i,] = synchrones[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
- noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
- if (all(noNA_rows))
- return (synchrones)
- # Else: some clusters are empty, need to slice synchrones
- synchrones[noNA_rows,]
-}
-
-#' computeWerDists
-#'
-#' Compute the WER distances between the synchrones curves (in rows), which are
-#' returned (e.g.) by \code{computeSynchrones()}
-#'
-#' @param synchrones A big.matrix of synchrones, in rows. The series have same length
-#' as the series in the initial dataset
-#' @inheritParams claws
-#'
-#' @return A matrix of size K1 x K1
-#'
-#' @export
-computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
-{
- if (verbose)
- cat(paste("--- Compute WER dists\n", sep=""))
-
- 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 + 1)
- #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
-
- 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)
- {
- 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)]
- #Normalization
- sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
- sqres <- sweep(ts.cwt,2,sqs,'*')
- sqres / max(Mod(sqres))
- }
-
- # Distance between rows i and j
- 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)
- parallel::clusterExport(cl,
- varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
- envir=environment())
- }
-
- ignored <-
- if (parll)
- parallel::parLapply(cl, pairs, computeDistancesIJ)
- else
- lapply(pairs, computeDistancesIJ)
-
- if (parll)
- parallel::stopCluster(cl)
-
- Xwer_dist[n,n] = 0.
- distances <- Xwer_dist[,]
- rm(Xwer_dist) ; gc()
- distances #~small matrix K1 x K1
-}
-
-# Helper function to divide indices into balanced sets
-.spreadIndices = function(indices, nb_per_chunk)
-{
- L = length(indices)
- nb_workers = floor( L / nb_per_chunk )
- if (nb_workers == 0)
- {
- # L < nb_series_per_chunk, simple case
- indices_workers = list(indices)
- }
- else
- {
- indices_workers = lapply( seq_len(nb_workers), function(i)
- indices[(nb_per_chunk*(i-1)+1):(nb_per_chunk*i)] )
- # Spread the remaining load among the workers
- rem = L %% nb_per_chunk
- while (rem > 0)
- {
- index = rem%%nb_workers + 1
- indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
- rem = rem - 1
- }
- }
- indices_workers