X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=8be871531f22e7a7dfe7b8828744b59f4c058c79;hb=a52836b23adb4bfa6722642ec6426fb7b5f39650;hp=f5e497fa0784078768e9ab7bf9d530817510a661;hpb=bf5c08443087a23ea3d1a7ab993568e608a8b5dd;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index f5e497f..8be8715 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()}) #' @@ -11,50 +11,51 @@ #' 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()}) #' @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 on ",length(indices)," lines\n", sep="")) - - 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) ] - } - if (parll) { - cl = parallel::makeCluster(ncores_clust) - parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment()) + cl = parallel::makeCluster(ncores_clust, outfile = "") + parallel::clusterExport(cl, c("getContribs","K1","verbose"), envir=environment()) } + # Iterate clustering algorithm 1 until K1 medoids are found 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) ) + # 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 <- + if (parll) + { + unlist( parallel::parLapply(cl, indices_workers, function(inds) { + require("epclust", quietly=TRUE) + inds[ algoClust1(getContribs(inds), K1) ] + }) ) + } + else + { + unlist( lapply(indices_workers, function(inds) + inds[ algoClust1(getContribs(inds), K1) ] + ) ) + } } if (parll) parallel::stopCluster(cl) @@ -64,35 +65,34 @@ 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, nvoice, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) { - if (nrow(medoids) <= K2) + if (verbose) + cat(paste("*** Clustering task 2 on ",ncol(medoids)," synchrones\n", sep="")) + + 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) - # 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) - cluster::pam(contribs, K1, diss=FALSE)$id.med + # A) Obtain synchrones, that is to say the cumulated power consumptions + # for each of the K1 initial groups + synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, + nb_series_per_chunk, ncores_clust, verbose, parll) -#' @rdname clustering -#' @export -computeClusters2 = function(distances, K2) - cluster::pam(distances, K2, diss=TRUE)$id.med + # 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 + 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 L2 distances. +#' 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 @@ -100,210 +100,236 @@ computeClusters2 = function(distances, K2) #' @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, ncores_clust=1,verbose=FALSE,parll=TRUE) { - - - -#TODO: si parll, getMedoids + serialization, pass only getMedoids to nodes -# --> BOF... chaque node chargera tous les medoids (efficacité) :/ ==> faut que ça tienne en RAM -#au pire :: C-ifier et charger medoids 1 by 1... - - #MIEUX :: medoids DOIT etre une big.matrix partagée ! - + # Synchrones computation is embarassingly parallel: compute it by chunks of series computeSynchronesChunk = function(indices) { - if (verbose) - cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep="")) + 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) - #get medoids indices for this chunk of series - for (i in seq_len(nrow(ref_series))) + 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)) { - 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,1] = counts[j,1] + 1 + 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 = nrow(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=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() - + 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, - varlist=c("synchrones","counts","verbose","medoids","getRefSeries"), - envir=environment()) + parallel::clusterExport(cl, envir=environment(), + varlist=c("synchrones_desc","m_desc","medoids_desc","getRefSeries")) } - indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk) + 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(indices_workers, computeSynchronesChunk) + parallel::parLapply(cl, 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 - 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,] + return (synchrones) } #' computeWerDists #' -#' Compute the WER distances between the synchrones curves (in rows), which are +#' 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 rows. The series have same length -#' as the series in the initial dataset +#' @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 big.matrix of size K1 x K1 +#' @return A distances matrix of size K1 x K1 #' #' @export -computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) +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))) + } -#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) - nvoice <- 4 - # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(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 + 1) - #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1 - 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 - - computeCWT = function(i) + cwt_file = ".cwt.bin" + # Compute the synchrones[,index] CWT, and store it in the binary file above + computeSaveCWT = function(index) { - 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=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)) + 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) - parallel::clusterExport(cl, - varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"), - envir=environment()) + 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()) } - # list of CWT from synchrones - # TODO: fit in RAM, OK? If not, 2 options: serialize, compute individual distances - Xcwt4 <- + if (verbose) + cat(paste("--- Precompute and serialize synchrones CWT\n", sep="")) + + ignored <- if (parll) - parallel::parLapply(cl, seq_len(n), computeCWT) + parallel::parLapply(cl, 1:n, computeSaveCWT) else - lapply(seq_len(n), computeCWT) - - if (parll) - parallel::stopCluster(cl) + lapply(1:n, computeSaveCWT) - 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?!) - 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 + # 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 + } - computeDistancesLineI = function(i) + # Compute distance between columns i and j in synchrones + computeDistanceIJ = function(pair) { - if (verbose) - cat(paste(" Line ",i,"\n", sep="")) - for (j in (i+1):n) + if (parll) { - #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)) ) - 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) + # 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) } - Xwer_dist[i,i] = 0. + + 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. } - parll = (requireNamespace("synchronicity",quietly=TRUE) - && parll && Sys.info()['sysname'] != "Windows") - if (parll) - m <- synchronicity::boost.mutex() + if (verbose) + cat(paste("--- Compute WER distances\n", sep="")) ignored <- if (parll) - { - parallel::mclapply(seq_len(n-1), computeDistancesLineI, - mc.cores=ncores_clust, mc.allow.recursive=FALSE) - } + parallel::parLapply(cl, pairs, computeDistanceIJ) else - lapply(seq_len(n-1), computeDistancesLineI) + lapply(pairs, computeDistanceIJ) + + if (parll) + parallel::stopCluster(cl) + + unlink(cwt_file) + Xwer_dist[n,n] = 0. - Xwer_dist + Xwer_dist[,] #~small matrix K1 x K1 } # Helper function to divide indices into balanced sets -.spreadIndices = function(indices, nb_per_chunk) +# 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_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)] ) + + 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_chunk + rem = L %% nb_per_set while (rem > 0) { index = rem%%nb_workers + 1