X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=640837064273f0947ce82a2c9d2130ee37268221;hb=4bcfdbee4e2157f232427a5bfdf240f34760110d;hp=87a5f914e137cb3f509443b58a1e59b80505b011;hpb=3eef8d3df59ded9a281cff51f79fe824198a7427;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index 87a5f91..6408370 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,85 +1,137 @@ -# Cluster one full task (nb_curves / ntasks series) -clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_file, - getCoefs,K1,K2,nb_series_per_chunk,ncores,to_file,ftype) +#' @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 = parallel::makeCluster(ncores) + +#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) / nb_series_per_chunk ) ) - indices_workers = lapply(seq_len(nb_workers), function(i) { - upper_bound = ifelse( i 0) + { + index = rem%%nb_workers + 1 + indices_workers[[index]] = c(indices_workers[[index]], tail(indices,rem)) + rem = rem - 1 + } +# indices = unlist( parallel::parLapply( cl, indices_workers, function(inds) { + indices = unlist( lapply( indices_workers, function(inds) { +# require("epclust", quietly=TRUE) + +print(paste(" ",length(inds))) ## PROBLEME ICI : 21104 ??! + + inds[ computeClusters1(getContribs(inds), K1) ] + } ) ) + if (length(indices) == K1) break } - parallel::stopCluster(cl) - if (K2 == 0) - return (indices) - computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file, - nb_series_per_chunk,ftype) - vector("integer",0) +# parallel::stopCluster(cl) + indices #medoids } -# Apply the clustering algorithm (PAM) on a coeffs or distances matrix -computeClusters1 = function(indices, getCoefs, K1) -{ - coefs = getCoefs(indices) - indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ] -} +#' @rdname clustering +#' @export +computeClusters1 = function(contribs, K1) + cluster::pam(contribs, K1, diss=FALSE)$id.med -# Cluster a chunk of series inside one task (~max nb_series_per_chunk) -computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file, - nb_series_per_chunk, ftype) +#' @rdname clustering +#' @export +computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk) { - curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk) - dists = computeWerDists(curves) - medoids = cluster::pam(dists, K2, diss=TRUE)$medoids - if (to_file) - { - serialize(medoids, synchrones_file, ftype, nb_series_per_chunk) - return (NULL) - } - medoids + synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk) + medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ] } -# Compute the synchrones curves (sum of clusters elements) from a clustering result -computeSynchrones = function(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk) +#' 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) { - #les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les - #courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ? - medoids = getSeries(indices) K = nrow(medoids) synchrones = matrix(0, nrow=K, ncol=ncol(medoids)) counts = rep(0,K) index = 1 repeat { - series = getSeriesForSynchrones((index-1)+seq_len(nb_series_per_chunk)) - if (is.null(series)) + 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 - index = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) ) - synchrones[index,] = synchrones[index,] + series[i,] - counts[index] = counts[index] + 1 + 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 (in rows) -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 (?) @@ -93,7 +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