X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=cda7fbe6c8fab73762d02d72a6568aea75df75f8;hb=1a1196f21036a321710f848d4cb28e6677f24904;hp=640837064273f0947ce82a2c9d2130ee37268221;hpb=4bcfdbee4e2157f232427a5bfdf240f34760110d;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 6408370..cda7fbe 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,15 +1,18 @@ #' @name clustering #' @rdname clustering -#' @aliases clusteringTask computeClusters1 computeClusters2 +#' @aliases clusteringTask1 computeClusters1 computeClusters2 #' -#' @title Two-stages clustering, withing one task (see \code{claws()}) +#' @title Two-stage clustering, withing one task (see \code{claws()}) #' -#' @description \code{clusteringTask()} runs one full task, which consists in iterated stage 1 -#' clustering (on nb_curves / ntasks energy contributions, computed through discrete -#' wavelets coefficients). \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) +#' @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 +#' clustering algorithm (PAM) on a contributions matrix, while the latter clusters +#' a chunk of series inside one task (~max nb_series_per_chunk) #' #' @param indices Range of series indices to cluster in parallel (initial data) #' @param getContribs Function to retrieve contributions from initial series indices: @@ -18,53 +21,64 @@ #' @inheritParams computeSynchrones #' @inheritParams claws #' -#' @return For \code{clusteringTask()} and \code{computeClusters1()}, the indices of the +#' @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 matrix of medoids +#' \code{computeClusters2()} outputs a big.matrix of medoids #' (of size limited by nb_series_per_chunk) NULL #' @rdname clustering #' @export -clusteringTask = function(indices, getContribs, K1, nb_series_per_chunk, ncores_clust) +clusteringTask1 = function( + indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE) { + if (verbose) + cat(paste("*** Clustering task on ",length(indices)," lines\n", sep="")) -#NOTE: comment out parallel sections for debugging -#propagate verbose arg ?! + wrapComputeClusters1 = function(inds) { + if (parll) + require("epclust", quietly=TRUE) + if (verbose) + cat(paste(" computeClusters1() on ",length(inds)," lines\n", sep="")) + inds[ computeClusters1(getContribs(inds), K1) ] + } -# cl = parallel::makeCluster(ncores_clust) -# parallel::clusterExport(cl, varlist=c("getContribs","K1"), envir=environment()) - repeat + if (parll) { - -print(length(indices)) - - nb_workers = max( 1, floor( length(indices) / nb_series_per_chunk ) ) - indices_workers = lapply( seq_len(nb_workers), function(i) - indices[(nb_series_per_chunk*(i-1)+1):(nb_series_per_chunk*i)] ) - # Spread the remaining load among the workers - rem = length(indices) %% nb_series_per_chunk - while (rem > 0) - { - index = rem%%nb_workers + 1 - indices_workers[[index]] = c(indices_workers[[index]], tail(indices,rem)) - rem = rem - 1 - } -# indices = unlist( parallel::parLapply( cl, indices_workers, function(inds) { - indices = unlist( lapply( indices_workers, function(inds) { -# require("epclust", quietly=TRUE) - -print(paste(" ",length(inds))) ## PROBLEME ICI : 21104 ??! - - inds[ computeClusters1(getContribs(inds), K1) ] - } ) ) - if (length(indices) == K1) - break + cl = parallel::makeCluster(ncores_clust) + parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment()) + } + while (length(indices) > K1) + { + indices_workers = .spreadIndices(indices, nb_series_per_chunk) + if (parll) + indices = unlist( parallel::parLapply(cl, indices_workers, wrapComputeClusters1) ) + else + indices = unlist( lapply(indices_workers, wrapComputeClusters1) ) } -# parallel::stopCluster(cl) + if (parll) + parallel::stopCluster(cl) + indices #medoids } +#' @rdname clustering +#' @export +clusteringTask2 = function(medoids, K2, + getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) +{ + if (nrow(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) + # PAM in package 'cluster' cannot take big.matrix in input: need to cast it + mat_dists = matrix(nrow=K1, ncol=K1) + for (i in seq_len(K1)) + mat_dists[i,] = distances[i,] + medoids[ computeClusters2(mat_dists,K2), ] +} + #' @rdname clustering #' @export computeClusters1 = function(contribs, K1) @@ -72,48 +86,83 @@ computeClusters1 = function(contribs, K1) #' @rdname clustering #' @export -computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk) -{ - synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk) - medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ] -} +computeClusters2 = function(distances, K2) + cluster::pam(distances, K2, diss=TRUE)$id.med #' computeSynchrones #' #' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids, #' using L2 distances. #' -#' @param medoids Matrix of medoids (curves of same legnth as initial series) +#' @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 K1 x L where L = data_length +#' #' @export -computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk) +computeSynchrones = function(medoids, getRefSeries, + nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) { - K = nrow(medoids) - synchrones = matrix(0, nrow=K, ncol=ncol(medoids)) - counts = rep(0,K) - index = 1 - repeat + computeSynchronesChunk = function(indices) { - range = (index-1) + seq_len(nb_series_per_chunk) - ref_series = getRefSeries(range) - if (is.null(ref_series)) - break + if (verbose) + cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep="")) + ref_series = getRefSeries(indices) #get medoids indices for this chunk of series for (i in seq_len(nrow(ref_series))) { j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) ) + if (parll) + synchronicity::lock(m) synchrones[j,] = synchrones[j,] + ref_series[i,] - counts[j] = counts[j] + 1 + counts[j,1] = counts[j,1] + 1 + if (parll) + synchronicity::unlock(m) } - index = index + nb_series_per_chunk } + + K = 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=ncol(medoids),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) + { + cl = parallel::makeCluster(ncores_clust) + parallel::clusterExport(cl, + varlist=c("synchrones","counts","verbose","medoids","getRefSeries"), + envir=environment()) + } + + indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk) + ignored <- + if (parll) + parallel::parLapply(indices_workers, computeSynchronesChunk) + else + lapply(indices_workers, computeSynchronesChunk) + + if (parll) + parallel::stopCluster(cl) + + #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') ) + for (i in seq_len(K)) + synchrones[i,] = synchrones[i,] / counts[i,1] #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 - synchrones = sweep(synchrones, 1, counts, '/') - synchrones[ 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,] } #' computeWerDists @@ -121,12 +170,21 @@ computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk) #' Compute the WER distances between the synchrones curves (in rows), which are #' returned (e.g.) by \code{computeSynchrones()} #' -#' @param synchrones A matrix of synchrones, in rows. The series have same length as the -#' series in the initial dataset +#' @param synchrones A big.matrix of synchrones, in rows. The series have same length +#' as the series in the initial dataset +#' @inheritParams claws +#' +#' @return A big.matrix of size K1 x K1 #' #' @export -computeWerDists = function(synchrones) +computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) { + + + +#TODO: re-organize to call computeWerDist(x,y) [C] (in //?) from two indices + big.matrix + + n <- nrow(synchrones) delta <- ncol(synchrones) #TODO: automatic tune of all these parameters ? (for other users) @@ -135,7 +193,7 @@ computeWerDists = function(synchrones) noctave = 13 # 4 here represent 2^5 = 32 half-hours ~ 1 day #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?) - scalevector <- 2^(4:(noctave * nvoice) / nvoice) * 2 + scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1) #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1 s0=2 w0=2*pi @@ -143,33 +201,106 @@ computeWerDists = function(synchrones) s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 ) totnoct = noctave + as.integer(s0log/nvoice) + 1 - # (normalized) observations node with CWT - Xcwt4 <- lapply(seq_len(n), function(i) { + computeCWT = function(i) + { + if (verbose) + cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep="")) ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled) - totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0) + 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,MARGIN=2,sqs,'*') + sqres <- sweep(ts.cwt,2,sqs,'*') sqres / max(Mod(sqres)) - }) + } - Xwer_dist <- matrix(0., n, n) + if (parll) + { + cl = parallel::makeCluster(ncores_clust) + parallel::clusterExport(cl, + varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"), + envir=environment()) + } + + # list of CWT from synchrones + # TODO: fit in RAM, OK? If not, 2 options: serialize, compute individual distances + Xcwt4 <- + if (parll) + parallel::parLapply(cl, seq_len(n), computeCWT) + else + lapply(seq_len(n), computeCWT) + + if (parll) + parallel::stopCluster(cl) + + Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double") fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!) - for (i in 1:(n-1)) + if (verbose) + cat("*** Compute WER distances from CWT\n") + + #TODO: computeDistances(i,j), et répartir les n(n-1)/2 couples d'indices + #là c'est trop déséquilibré + + computeDistancesLineI = function(i) { + if (verbose) + cat(paste(" Line ",i,"\n", sep="")) for (j in (i+1):n) { - #TODO: later, compute CWT here (because not enough storage space for 200k series) - # 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C + #TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE) WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE) WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE) - wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) ) + wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) ) + if (parll) + synchronicity::lock(m) Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2)) Xwer_dist[j,i] <- Xwer_dist[i,j] + if (parll) + synchronicity::unlock(m) } + Xwer_dist[i,i] = 0. } - diag(Xwer_dist) <- numeric(n) + + parll = (requireNamespace("synchronicity",quietly=TRUE) + && parll && Sys.info()['sysname'] != "Windows") + if (parll) + m <- synchronicity::boost.mutex() + + ignored <- + if (parll) + { + parallel::mclapply(seq_len(n-1), computeDistancesLineI, + mc.cores=ncores_clust, mc.allow.recursive=FALSE) + } + else + lapply(seq_len(n-1), computeDistancesLineI) + Xwer_dist[n,n] = 0. Xwer_dist } + +# Helper function to divide indices into balanced sets +.spreadIndices = function(indices, nb_per_chunk) +{ + L = length(indices) + nb_workers = floor( L / nb_per_chunk ) + if (nb_workers == 0) + { + # L < nb_series_per_chunk, 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)] ) + # Spread the remaining load among the workers + rem = L %% nb_per_chunk + while (rem > 0) + { + index = rem%%nb_workers + 1 + indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1]) + rem = rem - 1 + } + } + indices_workers +}