X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=c22678632dcee57df836d4e75978299bb9eaa027;hb=6ad3f3fd0ec4f3cd1fd5de4a287c1893293e5bcc;hp=92adda2c210c5374e916dc726670692914dd6722;hpb=e161499b97c782aadfc287c22b55f85724f86fae;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 92adda2..c226786 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -18,6 +18,7 @@ #' @param getContribs Function to retrieve contributions from initial series indices: #' \code{getContribs(indices)} outpus a contributions matrix #' @param contribs matrix of contributions (e.g. output of \code{curvesToContribs()}) +#' @param distances matrix of K1 x K1 (WER) distances between synchrones #' @inheritParams computeSynchrones #' @inheritParams claws #' @@ -77,8 +78,7 @@ clusteringTask2 = function(medoids, K2, synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll) distances = computeWerDists(synchrones, ncores_clust, verbose, parll) - # PAM in package 'cluster' cannot take big.matrix in input: need to cast it - medoids[ computeClusters2(distances[,],K2,verbose), ] + medoids[ computeClusters2(distances,K2,verbose), ] } #' @rdname clustering @@ -121,26 +121,29 @@ computeSynchrones = function(medoids, getRefSeries, computeSynchronesChunk = function(indices) { + if (parll) + { + require("bigmemory", quietly=TRUE) + requireNamespace("synchronicity", quietly=TRUE) + require("epclust", quietly=TRUE) + synchrones <- bigmemory::attach.big.matrix(synchrones_desc) + counts <- bigmemory::attach.big.matrix(counts_desc) + medoids <- bigmemory::attach.big.matrix(medoids_desc) + m <- synchronicity::attach.mutex(m_desc) + } + 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() + #get medoids indices for this chunk of series + mi = computeMedoidsIndices(medoids@address, ref_series) 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 + synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,] + counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? if (parll) synchronicity::unlock(m) } @@ -154,19 +157,19 @@ computeSynchrones = function(medoids, getRefSeries, # 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) { + m <- synchronicity::boost.mutex() + m_desc <- synchronicity::describe(m) + synchrones_desc = bigmemory::describe(synchrones) + counts_desc = bigmemory::describe(counts) + medoids_desc = bigmemory::describe(medoids) cl = parallel::makeCluster(ncores_clust) - parallel::clusterExport(cl, - varlist=c("synchrones","counts","verbose","medoids","getRefSeries"), - envir=environment()) + parallel::clusterExport(cl, varlist=c("synchrones_desc","counts_desc","counts", + "verbose","m_desc","medoids_desc","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) @@ -197,7 +200,7 @@ computeSynchrones = function(medoids, getRefSeries, #' as the series in the initial dataset #' @inheritParams claws #' -#' @return A big.matrix of size K1 x K1 +#' @return A matrix of size K1 x K1 #' #' @export computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) @@ -205,6 +208,15 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) if (verbose) cat(paste("--- Compute WER dists\n", sep="")) + + + +#TODO: serializer les CWT, les récupérer via getDataInFile +#--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519) + + + + n <- nrow(synchrones) delta <- ncol(synchrones) #TODO: automatic tune of all these parameters ? (for other users) @@ -222,50 +234,73 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) 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))) +# } + # Generate "smart" pairs for WER distances computations pairs = list() - V = seq_len(n) - for (i in 1:n) + F = floor(2*n/3) + for (i in 1:F) + pairs = c(pairs, lapply((i+1):n, function(v) c(i,v))) + V = (F+1):n + for (i in (F+1):(n-1)) { 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)) - } + pairs = c(pairs, + # Distance between rows i and j computeDistancesIJ = function(pair) { + if (parll) + { + require("bigmemory", quietly=TRUE) + require("epclust", quietly=TRUE) + synchrones <- bigmemory::attach.big.matrix(synchrones_desc) + Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc) + } + + computeCWT = function(index) + { + ts <- scale(ts(synchrones[index,]), 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)) + } + 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") + cwt_i <- computeCWT(i) + cwt_j <- computeCWT(j) + +#print(system.time( { + num <- epclustFilter(Mod(cwt_i * Conj(cwt_j))) + WX <- epclustFilter(Mod(cwt_i * Conj(cwt_i))) + WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j))) wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY)) - Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * (1 - wer2)) + Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1 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()) + synchrones_desc <- bigmemory::describe(synchrones) + Xwer_dist_desc <- bigmemory::describe(Xwer_dist) + + parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct", + "nvoice","w0","s0log","noctave","s0","verbose"), envir=environment()) } ignored <- @@ -278,7 +313,9 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) parallel::stopCluster(cl) Xwer_dist[n,n] = 0. - Xwer_dist + distances <- Xwer_dist[,] + rm(Xwer_dist) ; gc() + distances #~small matrix K1 x K1 } # Helper function to divide indices into balanced sets