X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=92adda2c210c5374e916dc726670692914dd6722;hb=e161499b97c782aadfc287c22b55f85724f86fae;hp=9a55495bb6f650a3445c11b281ddef359dd0c4c2;hpb=c45fd66342e40c8b5387fc6f0059c4d3a9718340;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 9a55495..92adda2 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -6,11 +6,13 @@ #' #' @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{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) +#' 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: @@ -21,7 +23,7 @@ #' #' @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 @@ -31,15 +33,7 @@ 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="")) - - 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) ] - } + cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep="")) if (parll) { @@ -49,10 +43,20 @@ clusteringTask1 = function( 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) ) + 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) @@ -62,18 +66,37 @@ clusteringTask1 = function( #' @rdname clustering #' @export -computeClusters1 = function(contribs, K1) - cluster::pam(contribs, K1, diss=FALSE)$id.med - -#' @rdname clustering -#' @export -computeClusters2 = function(medoids, K2, +clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) { + if (verbose) + cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep="")) + + if (nrow(medoids) <= K2) + return (medoids) synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll) distances = computeWerDists(synchrones, ncores_clust, verbose, parll) - medoids[ cluster::pam(distances, K2, diss=TRUE)$medoids , ] + # 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)$id.med +} + +#' @rdname clustering +#' @export +computeClusters2 = function(distances, K2, verbose=FALSE) +{ + if (verbose) + cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep="")) + cluster::pam(distances, K2, diss=TRUE)$id.med } #' computeSynchrones @@ -81,66 +104,88 @@ computeClusters2 = function(medoids, K2, #' 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_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE) { + if (verbose) + cat(paste("--- Compute synchrones\n", sep="")) + computeSynchronesChunk = function(indices) { - if (verbose) - cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep="")) ref_series = getRefSeries(indices) + nb_series = nrow(ref_series) #get medoids indices for this chunk of series - for (i in seq_len(nrow(ref_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)) { - 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 + 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) + K = nrow(medoids) ; L = ncol(medoids) # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in // - 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) - # Fork (// run) only on Linux & MacOS; on Windows: run sequentially + # 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::mclapply(indices_workers, computeSynchronesChunk, - mc.cores=ncores_clust, mc.allow.recursive=FALSE) - } + parallel::parLapply(cl, indices_workers, computeSynchronesChunk) else lapply(indices_workers, computeSynchronesChunk) - mat_syncs = matrix(nrow=K, ncol=ncol(medoids)) - vec_count = rep(NA, K) - #TODO: can we avoid this loop? + if (parll) + parallel::stopCluster(cl) + + #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') ) for (i in seq_len(K)) - { - mat_syncs[i,] = synchrones[i,] - vec_count[i] = counts[i,1] - } + 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 - mat_syncs = sweep(mat_syncs, 1, vec_count, '/') - mat_syncs[ sapply(seq_len(K), function(i) all(!is.nan(mat_syncs[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 @@ -148,13 +193,18 @@ computeSynchrones = function(medoids, getRefSeries, #' 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, 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) @@ -163,7 +213,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) 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 @@ -171,12 +221,22 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 ) totnoct = noctave + as.integer(s0log/nvoice) + 1 + 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) { - 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) @@ -184,6 +244,22 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) 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. + } + if (parll) { cl = parallel::makeCluster(ncores_clust) @@ -192,62 +268,17 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE) envir=environment()) } - # (normalized) observations node with CWT - Xcwt4 <- + ignored <- if (parll) - parallel::parLapply(cl, seq_len(n), computeCWT) + parallel::parLapply(cl, pairs, computeDistancesIJ) else - lapply(seq_len(n), computeCWT) + lapply(pairs, computeDistancesIJ) 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?!) - if (verbose) - cat("*** Compute WER distances from CWT\n") - - computeDistancesLineI = function(i) - { - if (verbose) - cat(paste(" Line ",i,"\n", sep="")) - for (j in (i+1):n) - { - #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) - } - Xwer_dist[i,i] = 0. - } - - 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. - - mat_dists = matrix(nrow=n, ncol=n) - #TODO: avoid this loop? - for (i in 1:n) - mat_dists[i,] = Xwer_dist[i,] - mat_dists + Xwer_dist } # Helper function to divide indices into balanced sets