X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=b09c1bc1c899caf4b3f701db435747dc0c03f624;hp=36b476987452e84e2978e2093957d2f9d25c25e0;hb=0486fbadb122cb4d78c5d9f248c29800a59eb24e;hpb=37c82bbafbffc19e8b47a521952bac58f189e9ea diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 36b4769..b09c1bc 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -12,30 +12,24 @@ #' \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic #' clustering procedures respectively for stage 1 and 2. The former applies the #' first clustering algorithm on a contributions matrix, while the latter clusters -#' a set of series inside one task (~nb_items_clust) +#' a set of series inside one task (~nb_items_clust1) #' #' @param indices Range of series indices to cluster in parallel (initial data) #' @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 #' -#' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the -#' computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus -#' \code{computeClusters2()} outputs a big.matrix of medoids -#' (of size limited by nb_series_per_chunk) +#' @return For \code{clusteringTask1()}, the indices of the computed (K1) medoids. +#' Indices are irrelevant for stage 2 clustering, thus \code{clusteringTask2()} +#' outputs a big.matrix of medoids (of size LxK2, K2 = final number of clusters) NULL #' @rdname clustering #' @export -clusteringTask1 = function(indices, getContribs, K1, nb_items_clust1, +clusteringTask1 = function(indices, getContribs, K1, algoClust1, nb_items_clust1, ncores_clust=1, verbose=FALSE, parll=TRUE) { - if (verbose) - cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep="")) - if (parll) { cl = parallel::makeCluster(ncores_clust, outfile = "") @@ -43,19 +37,21 @@ clusteringTask1 = function(indices, getContribs, K1, nb_items_clust1, } while (length(indices) > K1) { - indices_workers = .spreadIndices(indices, nb_items_clust1, K1+1) + indices_workers = .spreadIndices(indices, nb_items_clust1) + if (verbose) + cat(paste("*** [iterated] Clustering task 1 on ",length(indices)," series\n", sep="")) indices <- if (parll) { unlist( parallel::parLapply(cl, indices_workers, function(inds) { require("epclust", quietly=TRUE) - inds[ computeClusters1(getContribs(inds), K1, verbose) ] + inds[ algoClust1(getContribs(inds), K1) ] }) ) } else { unlist( lapply(indices_workers, function(inds) - inds[ computeClusters1(getContribs(inds), K1, verbose) ] + inds[ algoClust1(getContribs(inds), K1) ] ) ) } } @@ -67,36 +63,20 @@ clusteringTask1 = function(indices, getContribs, K1, nb_items_clust1, #' @rdname clustering #' @export -clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves, - nb_series_per_chunk, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) +clusteringTask2 = function(medoids, K2, algoClust2, getRefSeries, nb_ref_curves, + nb_series_per_chunk, sync_mean, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) { if (verbose) - cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep="")) + cat(paste("*** Clustering task 2 on ",ncol(medoids)," synchrones\n", sep="")) - if (nrow(medoids) <= K2) + if (ncol(medoids) <= K2) return (medoids) - synchrones = computeSynchrones(medoids, - getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll) + synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, + nb_series_per_chunk, sync_mean, ncores_clust, verbose, parll) distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll) - medoids[ computeClusters2(distances,K2,verbose), ] -} - -#' @rdname clustering -#' @export -computeClusters1 = function(contribs, K1, verbose=FALSE) -{ if (verbose) - cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep="")) - cluster::pam( t(contribs) , K1, diss=FALSE)$id.med -} - -#' @rdname clustering -#' @export -computeClusters2 = function(distances, K2, verbose=FALSE) -{ - if (verbose) - cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep="")) - cluster::pam( distances , K2, diss=TRUE)$id.med + cat(paste(" algoClust2() on ",nrow(distances)," items\n", sep="")) + medoids[ algoClust2(distances,K2), ] } #' computeSynchrones @@ -113,12 +93,9 @@ computeClusters2 = function(distances, K2, verbose=FALSE) #' @return A big.matrix of size L x K1 where L = length of a serie #' #' @export -computeSynchrones = function(medoids, getRefSeries, - nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) +computeSynchrones = function(medoids, getRefSeries, nb_ref_curves, + nb_series_per_chunk, sync_mean, ncores_clust=1,verbose=FALSE,parll=TRUE) { - if (verbose) - cat(paste("--- Compute synchrones\n", sep="")) - computeSynchronesChunk = function(indices) { if (parll) @@ -127,7 +104,8 @@ computeSynchrones = function(medoids, getRefSeries, requireNamespace("synchronicity", quietly=TRUE) require("epclust", quietly=TRUE) synchrones <- bigmemory::attach.big.matrix(synchrones_desc) - counts <- bigmemory::attach.big.matrix(counts_desc) + if (sync_mean) + counts <- bigmemory::attach.big.matrix(counts_desc) medoids <- bigmemory::attach.big.matrix(medoids_desc) m <- synchronicity::attach.mutex(m_desc) } @@ -135,7 +113,7 @@ computeSynchrones = function(medoids, getRefSeries, ref_series = getRefSeries(indices) nb_series = nrow(ref_series) - #get medoids indices for this chunk of series + # Get medoids indices for this chunk of series mi = computeMedoidsIndices(medoids@address, ref_series) for (i in seq_len(nb_series)) @@ -143,17 +121,19 @@ computeSynchrones = function(medoids, getRefSeries, if (parll) synchronicity::lock(m) synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i] - counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? ...or as arg?! + if (sync_mean) + counts[ mi[i] ] = counts[ mi[i] ] + 1 if (parll) synchronicity::unlock(m) } } - K = nrow(medoids) ; L = ncol(medoids) + K = ncol(medoids) ; L = nrow(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=L, ncol=K, type="double", init=0.) - counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0) + if (sync_mean) + 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") @@ -162,13 +142,21 @@ computeSynchrones = function(medoids, getRefSeries, m <- synchronicity::boost.mutex() m_desc <- synchronicity::describe(m) synchrones_desc = bigmemory::describe(synchrones) - counts_desc = bigmemory::describe(counts) + if (sync_mean) + counts_desc = bigmemory::describe(counts) medoids_desc = bigmemory::describe(medoids) cl = parallel::makeCluster(ncores_clust) - parallel::clusterExport(cl, varlist=c("synchrones_desc","counts_desc","counts", - "verbose","m_desc","medoids_desc","getRefSeries"), envir=environment()) + varlist=c("synchrones_desc","sync_mean","m_desc","medoids_desc","getRefSeries") + if (sync_mean) + varlist = c(varlist, "counts_desc") + parallel::clusterExport(cl, varlist, envir=environment()) } + if (verbose) + { + if (verbose) + cat(paste("--- Compute ",K," synchrones with ",nb_ref_curves," series\n", sep="")) + } indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk) ignored <- if (parll) @@ -179,7 +167,10 @@ computeSynchrones = function(medoids, getRefSeries, if (parll) parallel::stopCluster(cl) - #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') ) + if (!sync_mean) + return (synchrones) + + #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 2, counts, '/') ) for (i in seq_len(K)) synchrones[,i] = synchrones[,i] / counts[i] #NOTE: odds for some clusters to be empty? (when series already come from stage 2) @@ -205,9 +196,6 @@ computeSynchrones = function(medoids, getRefSeries, #' @export computeWerDists = function(synchrones, nbytes,endian,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) @@ -260,7 +248,12 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct", "nvoice","w0","s0log","noctave","s0","verbose","getCWT"), envir=environment()) } - + + if (verbose) + { + cat(paste("--- Compute WER dists\n", sep="")) + # precompute save all CWT........ + } #precompute and serialize all CWT ignored <- if (parll) @@ -301,6 +294,10 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS Xwer_dist[i,i] = 0. } + if (verbose) + { + cat(paste("--- Compute WER dists\n", sep="")) + } ignored <- if (parll) parallel::parLapply(cl, pairs, computeDistancesIJ) @@ -317,11 +314,11 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS } # Helper function to divide indices into balanced sets -.spreadIndices = function(indices, max_per_set, min_nb_per_set = 1) +.spreadIndices = function(indices, nb_per_set) { L = length(indices) - min_nb_workers = floor( L / max_per_set ) - rem = L %% max_per_set + nb_workers = floor( L / nb_per_set ) + rem = L %% max_nb_per_set if (nb_workers == 0 || (nb_workers==1 && rem==0)) { # L <= max_nb_per_set, simple case @@ -330,19 +327,9 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS else { indices_workers = lapply( seq_len(nb_workers), function(i) - indices[(max_nb_per_set*(i-1)+1):(max_per_set*i)] ) - # Two cases: remainder is >= min_per_set (easy)... - if (rem >= min_nb_per_set) - indices_workers = c( indices_workers, list(tail(indices,rem)) ) - #...or < min_per_set: harder, need to remove indices from current sets to feed - # the too-small remainder. It may fail: then fallback to "slightly bigger sets" - else - { - save_indices_workers = indices_workers - small_set = tail(indices,rem) - # Try feeding small_set until it reaches min_per_set, whle keeping the others big enough - # Spread the remaining load among the workers - rem = L %% nb_per_chunk + indices[(nb_per_chunk*(i-1)+1):(nb_per_set*i)] ) + # Spread the remaining load among the workers + rem = L %% nb_per_set while (rem > 0) { index = rem%%nb_workers + 1