X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=14915abf861bace1b6d4bd4f9f68283c004bfff9;hp=0d37c243d4f76be57f157cb1ed5b59a0e4ef76b2;hb=eef6f6c97277ea3ce760981e5244cbde7fc904a0;hpb=777c4b0274c059eeb5d4bd784ef773e819a7f7a2 diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 0d37c24..14915ab 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,6 +1,6 @@ #' @name clustering #' @rdname clustering -#' @aliases clusteringTask1 computeClusters1 computeClusters2 +#' @aliases clusteringTask1 clusteringTask2 computeClusters1 computeClusters2 #' #' @title Two-stage clustering, withing one task (see \code{claws()}) #' @@ -31,7 +31,7 @@ NULL #' @rdname clustering #' @export clusteringTask1 = function( - indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE) + indices, getContribs, K1, nb_items_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE) { if (verbose) cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep="")) @@ -67,8 +67,8 @@ clusteringTask1 = function( #' @rdname clustering #' @export -clusteringTask2 = function(medoids, K2, - getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) +clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves, + nb_series_per_chunk, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) { if (verbose) cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep="")) @@ -77,7 +77,7 @@ clusteringTask2 = function(medoids, K2, return (medoids) synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll) - distances = computeWerDists(synchrones, ncores_clust, verbose, parll) + distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll) medoids[ computeClusters2(distances,K2,verbose), ] } @@ -87,7 +87,7 @@ computeClusters1 = function(contribs, K1, verbose=FALSE) { if (verbose) cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep="")) - cluster::pam(contribs, K1, diss=FALSE)$id.med + cluster::pam( t(contribs) , K1, diss=FALSE)$id.med } #' @rdname clustering @@ -96,7 +96,7 @@ computeClusters2 = function(distances, K2, verbose=FALSE) { if (verbose) cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep="")) - cluster::pam(distances, K2, diss=TRUE)$id.med + cluster::pam( distances , K2, diss=TRUE)$id.med } #' computeSynchrones @@ -110,7 +110,7 @@ computeClusters2 = function(distances, K2, verbose=FALSE) #' @param nb_ref_curves How many reference series? (This number is known at this stage) #' @inheritParams claws #' -#' @return A big.matrix of size K1 x L where L = data_length +#' @return A big.matrix of size L x K1 where L = length of a serie #' #' @export computeSynchrones = function(medoids, getRefSeries, @@ -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? ...or as arg?! if (parll) synchronicity::unlock(m) } @@ -149,24 +152,24 @@ computeSynchrones = function(medoids, getRefSeries, 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.) + synchrones = bigmemory::big.matrix(nrow=L, ncol=K, 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) { + 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) @@ -178,14 +181,14 @@ computeSynchrones = function(medoids, getRefSeries, #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') ) for (i in seq_len(K)) - synchrones[i,] = synchrones[i,] / counts[i,1] + synchrones[,i] = synchrones[,i] / counts[i] #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,]))) + 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,] + bigmemory::as.big.matrix(synchrones[,noNA_rows]) } #' computeWerDists @@ -200,7 +203,7 @@ computeSynchrones = function(medoids, getRefSeries, #' @return A matrix of size K1 x K1 #' #' @export -computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) +computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) { if (verbose) cat(paste("--- Compute WER dists\n", sep="")) @@ -215,14 +218,16 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) #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 + 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 + + cwt_file = ".epclust_bin/cwt" + #TODO: args, nb_per_chunk, nbytes, endian # Generate n(n-1)/2 pairs for WER distances computations pairs = list() @@ -233,42 +238,69 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) pairs = c(pairs, lapply(V, function(v) c(i,v))) } - computeCWT = function(i) + computeSaveCWT = function(index) { - ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled) + 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)) + res <- sqres / max(Mod(sqres)) + #TODO: serializer les CWT, les récupérer via getDataInFile ; + #--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519) + binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian) + } + + if (parll) + { + cl = parallel::makeCluster(ncores_clust) + 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","getCWT"), envir=environment()) + } + + #precompute and serialize all CWT + ignored <- + if (parll) + parallel::parLapply(cl, 1:n, computeSaveCWT) + else + lapply(1:n, computeSaveCWT) + + getCWT = function(index) + { + #from cwt_file ... + res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian) + ###############TODO: } # 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) + } + 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 <- getCWT(i) + cwt_j <- getCWT(j) + + 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()) - } - ignored <- if (parll) parallel::parLapply(cl, pairs, computeDistancesIJ)