X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=640837064273f0947ce82a2c9d2130ee37268221;hb=4bcfdbee4e2157f232427a5bfdf240f34760110d;hp=42e894c805eab138e80b038eaa836d78cfa74103;hpb=74f571a72fd63ae92466d944a9ab4a111d177121;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 42e894c..6408370 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,66 +1,137 @@ -# 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 clusteringTask computeClusters1 computeClusters2 +#' +#' @title Two-stages 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) +#' +#' @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{clusteringTask()} 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 +#' (of size limited by nb_series_per_chunk) +NULL + +#' @rdname clustering +#' @export +clusteringTask = function(indices, getContribs, K1, nb_series_per_chunk, ncores_clust) { - cl_clust = parallel::makeCluster(ncores_clust) - #parallel::clusterExport(cl=cl_clust, varlist=c("fonctions_du_package"), envir=environment()) - indices_clust = indices_task[[i]] + +#NOTE: comment out parallel sections for debugging +#propagate verbose arg ?! + +# cl = parallel::makeCluster(ncores_clust) +# parallel::clusterExport(cl, varlist=c("getContribs","K1"), envir=environment()) repeat { - nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) ) - indices_workers = list() - for (i in 1:nb_workers) + +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) { - upper_bound = ifelse( i 0) - { - curves = computeSynchrones(cl) - dists = computeWerDists(curves) - cl = computeClusters(dists, K2, diss=TRUE) - } - indices[cl] -} +#' @rdname clustering +#' @export +computeClusters1 = function(contribs, K1) + cluster::pam(contribs, K1, diss=FALSE)$id.med -# Apply the clustering algorithm (PAM) on a coeffs or distances matrix -computeClusters = function(md, K, diss) +#' @rdname clustering +#' @export +computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk) { - if (!require(cluster, quietly=TRUE)) - stop("Unable to load cluster library") - cluster::pam(md, K, diss=diss)$id.med + synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk) + medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ] } -# 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 Matrix of medoids (curves of same legnth as initial series) +#' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series +#' have been replaced by stage-1 medoids) +#' @inheritParams claws +#' +#' @export +computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk) { - colSums( getData(indices) ) + K = nrow(medoids) + synchrones = matrix(0, nrow=K, ncol=ncol(medoids)) + counts = rep(0,K) + index = 1 + repeat + { + range = (index-1) + seq_len(nb_series_per_chunk) + ref_series = getRefSeries(range) + if (is.null(ref_series)) + break + #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 ) ) + synchrones[j,] = synchrones[j,] + ref_series[i,] + counts[j] = counts[j] + 1 + } + index = index + nb_series_per_chunk + } + #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,]))) , ] } -# 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 matrix of synchrones, in rows. The series have same length as the +#' series in the initial dataset +#' +#' @export +computeWerDists = function(synchrones) { - if (!require("Rwave", quietly=TRUE)) - stop("Unable to load Rwave library") - n <- nrow(curves) - delta <- ncol(curves) + 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 (?) @@ -74,7 +145,7 @@ computeWerDist = function(curves) # (normalized) observations node with CWT Xcwt4 <- lapply(seq_len(n), function(i) { - ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled) + ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled) totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0) ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)] #Normalization @@ -89,7 +160,7 @@ computeWerDist = function(curves) { for (j in (i+1):n) { - #TODO: later, compute CWT here (because not enough storage space for 32M series) + #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 num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE) WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)