X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=2ce4267ef35e717a7bea0a8667f648367d38fbcf;hb=d9bb53c5e1392018bf67f92140edb10137f3423c;hp=70d263e951f68b1cdc742caf15cf46f4aaf0fe83;hpb=2b9f5356793c245a5e10229a74ac0dabd8f62508;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 70d263e..2ce4267 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -12,62 +12,48 @@ #' \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_clust) +#' 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()}) -#' @param distances matrix of K1 x K1 (WER) distances between synchrones #' @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_per_chunk, nb_items_clust, 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 1 on ",length(indices)," lines\n", sep="")) - - - - - - -##TODO: reviser le spreadIndices, tenant compte de nb_items_clust - - ##TODO: reviser / harmoniser avec getContribs qui en récupère pt'et + pt'et - !! - - - 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) + # 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[ computeClusters1(getContribs(inds), K1, verbose) ] + inds[ algoClust1(getContribs(inds), K1) ] }) ) } else { unlist( lapply(indices_workers, function(inds) - inds[ computeClusters1(getContribs(inds), K1, verbose) ] + inds[ algoClust1(getContribs(inds), K1) ] ) ) } } @@ -79,42 +65,33 @@ clusteringTask1 = function( #' @rdname clustering #' @export -clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves, +clusteringTask2 = function(medoids, K2, algoClust2, getRefSeries, nb_ref_curves, nb_series_per_chunk, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) { if (verbose) - cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep="")) + cat(paste("*** Clustering task 2 on ",ncol(medoids)," synchrones\n", sep="")) - if (nrow(medoids) <= K2) + if (ncol(medoids) <= K2) return (medoids) - synchrones = computeSynchrones(medoids, - getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll) - distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll) - 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( t(contribs) , K1, diss=FALSE)$id.med -} + # A) Obtain synchrones, that is to say the cumulated power consumptions + # for each of the K1 initial groups + synchrones = computeSynchrones(medoids, getRefSeries, nb_ref_curves, + nb_series_per_chunk, ncores_clust, verbose, parll) -#' @rdname clustering -#' @export -computeClusters2 = function(distances, K2, verbose=FALSE) -{ + # B) Compute the WER distances (Wavelets Extended coefficient of deteRmination) + distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll) + + # C) Apply clustering algorithm 2 on the WER distances matrix if (verbose) - cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep="")) - cluster::pam( distances , K2, diss=TRUE)$id.med + 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 @@ -125,12 +102,10 @@ computeClusters2 = function(distances, K2, verbose=FALSE) #' @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) { - if (verbose) - cat(paste("--- Compute synchrones\n", sep="")) - + # Synchrones computation is embarassingly parallel: compute it by chunks of series computeSynchronesChunk = function(indices) { if (parll) @@ -138,50 +113,55 @@ computeSynchrones = function(medoids, getRefSeries, 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) - counts <- bigmemory::attach.big.matrix(counts_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 = nrow(ref_series) + nb_series = ncol(ref_series) - #get medoids indices for this chunk of 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) + synchronicity::lock(m) #locking required because several writes at the same time synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i] - counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? ...or as arg?! if (parll) synchronicity::unlock(m) } } - K = nrow(medoids) ; L = ncol(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=L, ncol=K, 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 + # NOTE: 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() + 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) - counts_desc = bigmemory::describe(counts) medoids_desc = bigmemory::describe(medoids) cl = parallel::makeCluster(ncores_clust) - parallel::clusterExport(cl, varlist=c("synchrones_desc","counts_desc","counts", - "verbose","m_desc","medoids_desc","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(cl, indices_workers, computeSynchronesChunk) @@ -191,16 +171,7 @@ computeSynchrones = function(medoids, getRefSeries, 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] - #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 - bigmemory::as.big.matrix(synchrones[,noNA_rows]) + return (synchrones) } #' computeWerDists @@ -217,24 +188,13 @@ computeSynchrones = function(medoids, getRefSeries, #' @export computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE) { - if (verbose) - cat(paste("--- Compute WER dists\n", sep="")) - - n <- nrow(synchrones) - delta <- ncol(synchrones) + n <- ncol(synchrones) + L <- nrow(synchrones) #TODO: automatic tune of all these parameters ? (for other users) + # 4 here represent 2^5 = 32 half-hours ~ 1 day 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 Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double") @@ -252,15 +212,15 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS computeSaveCWT = function(index) { - ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled) - totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE) + ts <- scale(ts(synchrones[,index]), center=TRUE, scale=FALSE) + totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0=2*pi, twoD=TRUE, 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,'*') res <- sqres / max(Mod(sqres)) #TODO: serializer les CWT, les récupérer via getDataInFile ; - #--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519) + #--> OK, faut juste stocker comme séries simples de taille L*n' (53*17519) binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian) } @@ -269,10 +229,16 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS cl = parallel::makeCluster(ncores_clust) synchrones_desc <- bigmemory::describe(synchrones) Xwer_dist_desc <- bigmemory::describe(Xwer_dist) - parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct", - "nvoice","w0","s0log","noctave","s0","verbose","getCWT"), envir=environment()) + parallel::clusterExport(cl, envir=environment(), + varlist=c("synchrones_desc","Xwer_dist_desc","totnoct","nvoice","w0","s0log", + "noctave","s0","verbose","getCWT")) + } + + if (verbose) + { + cat(paste("--- Compute WER dists\n", sep="")) + # precompute save all CWT........ } - #precompute and serialize all CWT ignored <- if (parll) @@ -308,11 +274,15 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS WX <- epclustFilter(Mod(cwt_i * Conj(cwt_i))) WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j))) wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY)) - Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1 + Xwer_dist[i,j] <- sqrt(L * ncol(cwt_i) * max(1 - wer2, 0.)) Xwer_dist[j,i] <- Xwer_dist[i,j] Xwer_dist[i,i] = 0. } + if (verbose) + { + cat(paste("--- Compute WER dists\n", sep="")) + } ignored <- if (parll) parallel::parLapply(cl, pairs, computeDistancesIJ) @@ -329,21 +299,30 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS } # 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, (L-rem+1):L ) ) + } + # 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