X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=a431ba86e6120aef106fdce8712eb52a5ef3c4b0;hb=9f05a4a0b703deffd7bdb9cd99b0aaa2246a5c83;hp=4519f44bf36dade463302ac84011c3e004b2d54e;hpb=4204e8774fdafe2db7ed44cd8cae018bc0c4e9d7;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 4519f44..a431ba8 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()}) #' @@ -11,51 +11,47 @@ #' and then WER distances computations, before applying the clustering algorithm. #' \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic #' clustering procedures respectively for stage 1 and 2. The former applies the -#' clustering algorithm (PAM) on a contributions matrix, while the latter clusters -#' a chunk of series inside one task (~max nb_series_per_chunk) +#' first clustering algorithm on a contributions matrix, while the latter clusters +#' 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_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE) +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) + cl = parallel::makeCluster(ncores_clust, outfile = "") parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment()) } while (length(indices) > K1) { - indices_workers = .spreadIndices(indices, nb_series_per_chunk) + 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( #' @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, 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) - distances = computeWerDists(synchrones, 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(contribs, K1, diss=FALSE)$id.med -} - -#' @rdname clustering -#' @export -computeClusters2 = function(distances, K2, verbose=FALSE) -{ + synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, + nb_series_per_chunk, sync_mean, ncores_clust, verbose, parll) + distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll) if (verbose) - cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep="")) - cluster::pam(distances, K2, diss=TRUE)$id.med + cat(paste(" algoClust2() on ",nrow(distances)," items\n", sep="")) + medoids[ ,algoClust2(distances,K2) ] } #' computeSynchrones @@ -110,15 +90,12 @@ 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, - 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) @@ -127,33 +104,36 @@ 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) } ref_series = getRefSeries(indices) - nb_series = nrow(ref_series) + nb_series = ncol(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)) { if (parll) synchronicity::lock(m) - synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,] - counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? + synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i] + 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=K, ncol=L, type="double", init=0.) - counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0) + synchrones = bigmemory::big.matrix(nrow=L, ncol=K, 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) @@ -179,16 +167,19 @@ 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,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 @@ -203,11 +194,8 @@ 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="")) - n <- nrow(synchrones) delta <- ncol(synchrones) #TODO: automatic tune of all these parameters ? (for other users) @@ -218,8 +206,8 @@ 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 @@ -237,7 +225,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) V = V[-1] pairs = c(pairs, lapply(V, function(v) c(i,v))) } - + computeSaveCWT = function(index) { ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled) @@ -249,7 +237,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) 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(res, cwt_file, 100, ",", nbytes, endian) + binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian) } if (parll) @@ -260,7 +248,12 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) 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) @@ -271,6 +264,8 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) 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 @@ -299,6 +294,10 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) Xwer_dist[i,i] = 0. } + if (verbose) + { + cat(paste("--- Compute WER dists\n", sep="")) + } ignored <- if (parll) parallel::parLapply(cl, pairs, computeDistancesIJ) @@ -315,21 +314,22 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) } # Helper function to divide indices into balanced sets -.spreadIndices = function(indices, nb_per_chunk) +.spreadIndices = function(indices, nb_per_set) { L = length(indices) - nb_workers = floor( L / nb_per_chunk ) - if (nb_workers == 0) + nb_workers = floor( L / nb_per_set ) + rem = L %% nb_per_set + if (nb_workers == 0 || (nb_workers==1 && rem==0)) { - # L < nb_series_per_chunk, simple case + # L <= nb_per_set, 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)] ) + indices[(nb_per_set*(i-1)+1):(nb_per_set*i)] ) # Spread the remaining load among the workers - rem = L %% nb_per_chunk + rem = L %% nb_per_set while (rem > 0) { index = rem%%nb_workers + 1