X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=886bfbcca2fbd1b52239c2403e3c521d0c2c7f18;hb=e0154a59e55143dac0fbd2a4739a3509bc958e76;hp=8be871531f22e7a7dfe7b8828744b59f4c058c79;hpb=a52836b23adb4bfa6722642ec6426fb7b5f39650;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 8be8715..886bfbc 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,47 +1,51 @@ -#' @name clustering -#' @rdname clustering -#' @aliases clusteringTask1 clusteringTask2 computeClusters1 computeClusters2 +#' Two-stage clustering, within one task (see \code{claws()}) #' -#' @title Two-stage clustering, withing one task (see \code{claws()}) +#' \code{clusteringTask1()} runs one full stage-1 task, which consists in iterated +#' clustering on nb_curves / ntasks energy contributions, computed through +#' discrete wavelets coefficients. +#' \code{clusteringTask2()} runs a full stage-2 task, which consists in WER distances +#' computations between medoids (indices) output from stage 1, before applying +#' the second clustering algorithm on the distances matrix. #' -#' @description \code{clusteringTask1()} runs one full stage-1 task, which consists in -#' iterated stage 1 clustering (on nb_curves / ntasks energy contributions, computed -#' through discrete wavelets coefficients). -#' \code{clusteringTask2()} runs a full stage-2 task, which consists in synchrones -#' 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 -#' 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 -#' @inheritParams computeSynchrones +#' \code{getContribs(indices)} outputs a contributions matrix, in columns #' @inheritParams claws +#' @inheritParams computeSynchrones +#' @inheritParams computeWerDists +#' +#' @return The indices of the computed (resp. K1 and K2) medoids. #' -#' @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) +#' @name clustering +#' @rdname clustering +#' @aliases clusteringTask1 clusteringTask2 NULL #' @rdname clustering #' @export -clusteringTask1 = function(indices, getContribs, K1, algoClust1, nb_items_clust1, - ncores_clust=1, verbose=FALSE, parll=TRUE) +clusteringTask1 <- function(indices, getContribs, K1, algoClust1, nb_items_clust, + ncores_clust=3, verbose=FALSE, parll=TRUE) { + if (verbose) + cat(paste("*** Clustering task 1 on ",length(indices)," series [start]\n", sep="")) + + if (length(indices) <= K1) + return (indices) + if (parll) { - cl = parallel::makeCluster(ncores_clust, outfile = "") + # outfile=="" to see stderr/stdout on terminal + cl <- + if (verbose) + parallel::makeCluster(ncores_clust, outfile = "") + else + parallel::makeCluster(ncores_clust) parallel::clusterExport(cl, c("getContribs","K1","verbose"), envir=environment()) } # Iterate clustering algorithm 1 until K1 medoids are found while (length(indices) > K1) { # Balance tasks by splitting the indices set - as evenly as possible - indices_workers = .spreadIndices(indices, nb_items_clust1) - if (verbose) - cat(paste("*** [iterated] Clustering task 1 on ",length(indices)," series\n", sep="")) + indices_workers <- .splitIndices(indices, nb_items_clust, min_size=K1+1) indices <- if (parll) { @@ -56,6 +60,10 @@ clusteringTask1 = function(indices, getContribs, K1, algoClust1, nb_items_clust1 inds[ algoClust1(getContribs(inds), K1) ] ) ) } + if (verbose) + { + cat(paste("*** Clustering task 1 on ",length(indices)," medoids [iter]\n", sep="")) + } } if (parll) parallel::stopCluster(cl) @@ -65,277 +73,21 @@ clusteringTask1 = function(indices, getContribs, K1, algoClust1, nb_items_clust1 #' @rdname clustering #' @export -clusteringTask2 = function(medoids, K2, algoClust2, getRefSeries, nb_ref_curves, - nb_series_per_chunk, nvoice, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) +clusteringTask2 <- function(indices, getSeries, K2, algoClust2, nb_series_per_chunk, + smooth_lvl, nvoice, nbytes, endian, ncores_clust=3, verbose=FALSE, parll=TRUE) { if (verbose) - cat(paste("*** Clustering task 2 on ",ncol(medoids)," synchrones\n", sep="")) + cat(paste("*** Clustering task 2 on ",length(indices)," medoids\n", sep="")) - if (ncol(medoids) <= K2) - return (medoids) + if (length(indices) <= K2) + return (indices) - # A) Obtain synchrones, that is to say the cumulated power consumptions - # for each of the K1 initial groups - synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, - nb_series_per_chunk, ncores_clust, verbose, parll) + # A) Compute the WER distances (Wavelets Extended coefficient of deteRmination) + distances <- computeWerDists(indices, getSeries, nb_series_per_chunk, + smooth_lvl, nvoice, nbytes, endian, ncores_clust, verbose, parll) - # B) Compute the WER distances (Wavelets Extended coefficient of deteRmination) - distances = computeWerDists( - synchrones, nvoice, nbytes, endian, ncores_clust, verbose, parll) - - # C) Apply clustering algorithm 2 on the WER distances matrix + # B) Apply clustering algorithm 2 on the WER distances matrix if (verbose) cat(paste("*** algoClust2() on ",nrow(distances)," items\n", sep="")) - medoids[ ,algoClust2(distances,K2) ] -} - -#' computeSynchrones -#' -#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids, -#' using euclidian distance. -#' -#' @param medoids big.matrix of medoids (curves of same length as initial series) -#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series -#' have been replaced by stage-1 medoids) -#' @param nb_ref_curves How many reference series? (This number is known at this stage) -#' @inheritParams claws -#' -#' @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) -{ - # Synchrones computation is embarassingly parallel: compute it by chunks of series - computeSynchronesChunk = function(indices) - { - if (parll) - { - require("bigmemory", quietly=TRUE) - requireNamespace("synchronicity", quietly=TRUE) - require("epclust", quietly=TRUE) - # The big.matrix objects need to be attached to be usable on the workers - synchrones <- bigmemory::attach.big.matrix(synchrones_desc) - medoids <- bigmemory::attach.big.matrix(medoids_desc) - m <- synchronicity::attach.mutex(m_desc) - } - - # Obtain a chunk of reference series - ref_series = getRefSeries(indices) - nb_series = ncol(ref_series) - - # Get medoids indices for this chunk of series - mi = computeMedoidsIndices(medoids@address, ref_series) - - # Update synchrones using mi above - for (i in seq_len(nb_series)) - { - if (parll) - synchronicity::lock(m) #locking required because several writes at the same time - synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i] - if (parll) - synchronicity::unlock(m) - } - NULL - } - - K = ncol(medoids) ; L = nrow(medoids) - # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in // - synchrones = bigmemory::big.matrix(nrow=L, ncol=K, type="double", init=0.) - # NOTE: synchronicity is only for Linux & MacOS; on Windows: run sequentially - parll = (parll && requireNamespace("synchronicity",quietly=TRUE) - && Sys.info()['sysname'] != "Windows") - if (parll) - { - m <- synchronicity::boost.mutex() #for lock/unlock, see computeSynchronesChunk - # mutex and big.matrix objects cannot be passed directly: - # they will be accessed from their description - m_desc <- synchronicity::describe(m) - synchrones_desc = bigmemory::describe(synchrones) - medoids_desc = bigmemory::describe(medoids) - cl = parallel::makeCluster(ncores_clust) - parallel::clusterExport(cl, envir=environment(), - varlist=c("synchrones_desc","m_desc","medoids_desc","getRefSeries")) - } - - if (verbose) - cat(paste("--- Compute ",K," synchrones with ",nb_ref_curves," series\n", sep="")) - - # Balance tasks by splitting the indices set - maybe not so evenly, but - # max==TRUE in next call ensures that no set has more than nb_series_per_chunk items. - indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk, max=TRUE) - ignored <- - if (parll) - parallel::parLapply(cl, indices_workers, computeSynchronesChunk) - else - lapply(indices_workers, computeSynchronesChunk) - - if (parll) - parallel::stopCluster(cl) - - return (synchrones) -} - -#' computeWerDists -#' -#' Compute the WER distances between the synchrones curves (in columns), which are -#' returned (e.g.) by \code{computeSynchrones()} -#' -#' @param synchrones A big.matrix of synchrones, in columns. The series have same -#' length as the series in the initial dataset -#' @inheritParams claws -#' -#' @return A distances matrix of size K1 x K1 -#' -#' @export -computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1, - verbose=FALSE,parll=TRUE) -{ - n <- ncol(synchrones) - L <- nrow(synchrones) - noctave = ceiling(log2(L)) #min power of 2 to cover serie range - - # Initialize result as a square big.matrix of size 'number of synchrones' - Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double") - - # 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))) - } - - cwt_file = ".cwt.bin" - # Compute the synchrones[,index] CWT, and store it in the binary file above - computeSaveCWT = function(index) - { - if (parll && !exists(synchrones)) #avoid going here after first call on a worker - { - require("bigmemory", quietly=TRUE) - require("Rwave", quietly=TRUE) - require("epclust", quietly=TRUE) - synchrones <- bigmemory::attach.big.matrix(synchrones_desc) - } - ts <- scale(ts(synchrones[,index]), center=TRUE, scale=FALSE) - ts_cwt = Rwave::cwt(ts, noctave, nvoice, w0=2*pi, twoD=TRUE, plot=FALSE) - - # Serialization - binarize(as.matrix(c(as.double(Re(ts_cwt)),as.double(Im(ts_cwt)))), cwt_file, 1, - ",", 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("parll","synchrones_desc","Xwer_dist_desc", - "noctave","nvoice","verbose","getCWT"), envir=environment()) - } - - if (verbose) - cat(paste("--- Precompute and serialize synchrones CWT\n", sep="")) - - ignored <- - if (parll) - parallel::parLapply(cl, 1:n, computeSaveCWT) - else - lapply(1:n, computeSaveCWT) - - # Function to retrieve a synchrone CWT from (binary) file - getSynchroneCWT = function(index, L) - { - flat_cwt <- getDataInFile(index, cwt_file, nbytes, endian) - cwt_length = length(flat_cwt) / 2 - re_part = as.matrix(flat_cwt[1:cwt_length], nrow=L) - im_part = as.matrix(flat_cwt[(cwt_length+1):(2*cwt_length)], nrow=L) - re_part + 1i * im_part - } - - # Compute distance between columns i and j in synchrones - computeDistanceIJ = function(pair) - { - if (parll) - { - # parallel workers start with an empty environment - 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 && !parll) - cat(paste(" Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep="")) - - # Compute CWT of columns i and j in synchrones - L = nrow(synchrones) - cwt_i <- getSynchroneCWT(i, L) - cwt_j <- getSynchroneCWT(j, L) - - # Compute the ratio of integrals formula 5.6 for WER^2 - # in https://arxiv.org/abs/1101.4744v2 §5.3 - num <- filterMA(Mod(cwt_i * Conj(cwt_j))) - WX <- filterMA(Mod(cwt_i * Conj(cwt_i))) - WY <- filterMA(Mod(cwt_j * Conj(cwt_j))) - wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY)) - - Xwer_dist[i,j] <- sqrt(L * ncol(cwt_i) * (1 - wer2)) - Xwer_dist[j,i] <- Xwer_dist[i,j] - Xwer_dist[i,i] <- 0. - } - - if (verbose) - cat(paste("--- Compute WER distances\n", sep="")) - - ignored <- - if (parll) - parallel::parLapply(cl, pairs, computeDistanceIJ) - else - lapply(pairs, computeDistanceIJ) - - if (parll) - parallel::stopCluster(cl) - - unlink(cwt_file) - - Xwer_dist[n,n] = 0. - Xwer_dist[,] #~small matrix K1 x K1 -} - -# Helper function to divide indices into balanced sets -# If max == TRUE, sets sizes cannot exceed nb_per_set -.spreadIndices = function(indices, nb_per_set, max=FALSE) -{ - L = length(indices) - nb_workers = floor( L / nb_per_set ) - rem = L %% nb_per_set - if (nb_workers == 0 || (nb_workers==1 && rem==0)) - { - # L <= nb_per_set, simple case - indices_workers = list(indices) - } - else - { - indices_workers = lapply( seq_len(nb_workers), function(i) - indices[(nb_per_set*(i-1)+1):(nb_per_set*i)] ) - - if (max) - { - # Sets are not so well balanced, but size is supposed to be critical - return ( c( indices_workers, if (rem>0) list((L-rem+1):L) else NULL ) ) - } - - # Spread the remaining load among the workers - rem = L %% nb_per_set - while (rem > 0) - { - index = rem%%nb_workers + 1 - indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1]) - rem = rem - 1 - } - } - indices_workers + indices[ algoClust2(distances,K2) ] }