X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=92adda2c210c5374e916dc726670692914dd6722;hb=e161499b97c782aadfc287c22b55f85724f86fae;hp=42e894c805eab138e80b038eaa836d78cfa74103;hpb=74f571a72fd63ae92466d944a9ab4a111d177121;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 42e894c..92adda2 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,70 +1,219 @@ -# Cluster one full task (nb_curves / ntasks series) -clusteringTask = function(K1, K2, WER, nb_series_per_chunk, indices_tasks, ncores_clust) +#' @name clustering +#' @rdname clustering +#' @aliases clusteringTask1 computeClusters1 computeClusters2 +#' +#' @title Two-stage clustering, withing one task (see \code{claws()}) +#' +#' @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: +#' \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) +NULL + +#' @rdname clustering +#' @export +clusteringTask1 = function( + indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE) { - cl_clust = parallel::makeCluster(ncores_clust) - #parallel::clusterExport(cl=cl_clust, varlist=c("fonctions_du_package"), envir=environment()) - indices_clust = indices_task[[i]] - repeat + if (verbose) + cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep="")) + + if (parll) { - nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) ) - indices_workers = list() - for (i in 1:nb_workers) - { - upper_bound = ifelse( i K1) + { + indices_workers = .spreadIndices(indices, nb_series_per_chunk) + indices <- + if (parll) + { + unlist( parallel::parLapply(cl, indices_workers, function(inds) { + require("epclust", quietly=TRUE) + inds[ computeClusters1(getContribs(inds), K1, verbose) ] + }) ) + } + else + { + unlist( lapply(indices_workers, function(inds) + inds[ computeClusters1(getContribs(inds), K1, verbose) ] + ) ) + } + } + if (parll) + parallel::stopCluster(cl) + + indices #medoids } -# Cluster a chunk of series inside one task (~max nb_series_per_chunk) -clusterChunk = function(indices, K1, K2) +#' @rdname clustering +#' @export +clusteringTask2 = function(medoids, K2, + getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) { - coeffs = getCoeffs(indices) - cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE) - if (K2 > 0) - { - curves = computeSynchrones(cl) - dists = computeWerDists(curves) - cl = computeClusters(dists, K2, diss=TRUE) - } - indices[cl] + if (verbose) + cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep="")) + + 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 + 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)$id.med } -# Apply the clustering algorithm (PAM) on a coeffs or distances matrix -computeClusters = function(md, K, diss) +#' @rdname clustering +#' @export +computeClusters2 = function(distances, K2, verbose=FALSE) { - if (!require(cluster, quietly=TRUE)) - stop("Unable to load cluster library") - cluster::pam(md, K, diss=diss)$id.med + if (verbose) + cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep="")) + cluster::pam(distances, K2, diss=TRUE)$id.med } -# Compute the synchrones curves (sum of clusters elements) from a clustering result -computeSynchrones = function(indices) +#' computeSynchrones +#' +#' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids, +#' using L2 distances. +#' +#' @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_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) { - colSums( getData(indices) ) + if (verbose) + cat(paste("--- Compute synchrones\n", sep="")) + + computeSynchronesChunk = function(indices) + { + ref_series = getRefSeries(indices) + nb_series = nrow(ref_series) + #get medoids indices for this chunk of series + + #TODO: debug this (address is OK but values are garbage: why?) +# mi = .Call("computeMedoidsIndices", medoids@address, ref_series, PACKAGE="epclust") + + #R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope) + mat_meds = medoids[,] + mi = rep(NA,nb_series) + for (i in 1:nb_series) + mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) ) + rm(mat_meds); gc() + + for (i in seq_len(nb_series)) + { + if (parll) + synchronicity::lock(m) + synchrones[mi[i],] = synchrones[mi[i],] + ref_series[i,] + counts[mi[i],1] = counts[mi[i],1] + 1 + if (parll) + synchronicity::unlock(m) + } + } + + K = nrow(medoids) ; L = ncol(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) + # 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) + browser() + ignored <- + if (parll) + 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,] } -# Compute the WER distance between the synchrones curves -computeWerDist = function(curves) +#' computeWerDists +#' +#' Compute the WER distances between the synchrones curves (in rows), 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 +#' @inheritParams claws +#' +#' @return A big.matrix of size K1 x K1 +#' +#' @export +computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) { - if (!require("Rwave", quietly=TRUE)) - stop("Unable to load Rwave library") - n <- nrow(curves) - delta <- ncol(curves) + 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) nvoice <- 4 - # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(curves)) + # 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) * 2 + scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1) #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1 s0=2 w0=2*pi @@ -72,33 +221,88 @@ computeWerDist = function(curves) 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) { - ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled) - totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0) + Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double") + fcoefs = rep(1/3, 3) #moving average on 3 values + + # 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))) + } + + computeCWT = function(i) + { + 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,MARGIN=2,sqs,'*') + sqres <- sweep(ts.cwt,2,sqs,'*') sqres / max(Mod(sqres)) - }) + } + + computeDistancesIJ = function(pair) + { + i = pair[1] ; j = pair[2] + if (verbose && j==i+1) + cat(paste(" Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep="")) + cwt_i = computeCWT(i) + cwt_j = computeCWT(j) + num <- .Call("filter", Mod(cwt_i * Conj(cwt_j)), PACKAGE="epclust") + WX <- .Call("filter", Mod(cwt_i * Conj(cwt_i)), PACKAGE="epclust") + WY <- .Call("filter", Mod(cwt_j * Conj(cwt_j)), PACKAGE="epclust") + wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY)) + Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * (1 - wer2)) + Xwer_dist[j,i] <- Xwer_dist[i,j] + Xwer_dist[i,i] = 0. + } - Xwer_dist <- matrix(0., n, n) - fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!) - for (i in 1:(n-1)) + if (parll) { - for (j in (i+1):n) + cl = parallel::makeCluster(ncores_clust) + parallel::clusterExport(cl, + varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"), + envir=environment()) + } + + ignored <- + if (parll) + parallel::parLapply(cl, pairs, computeDistancesIJ) + else + lapply(pairs, computeDistancesIJ) + + if (parll) + parallel::stopCluster(cl) + + 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) { - #TODO: later, compute CWT here (because not enough storage space for 32M series) - # '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)) ) - Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2)) - Xwer_dist[j,i] <- Xwer_dist[i,j] + index = rem%%nb_workers + 1 + indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1]) + rem = rem - 1 } } - diag(Xwer_dist) <- numeric(n) - Xwer_dist + indices_workers }