X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=493f90f31c1c20d0cfb591d4acc043ff32505a8a;hb=8702eb86906bd6d59e07bb887e690a20f29be63f;hp=e27ea353e479fb8185afb124f02fbcab56c9d4e0;hpb=5c6529795907ba1b34d4552cbfd0e0cbb77cac0f;p=epclust.git diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R index e27ea35..493f90f 100644 --- a/epclust/R/clustering.R +++ b/epclust/R/clustering.R @@ -1,71 +1,81 @@ -oneIteration = function(..........) +# Cluster one full task (nb_curves / ntasks series); only step 1 +clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores) { - cl_clust = parallel::makeCluster(ncores_clust) - parallel::clusterExport(cl_clust, .............., envir=........) - indices_clust = indices_task[[i]] - repeat + cl = parallel::makeCluster(ncores) + parallel::clusterExport(cl, varlist=c("getCoefs","K1"), envir=environment()) + repeat + { + 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) { - nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) ) - indices_workers = list() - #indices[[i]] == (start_index,number_of_elements) - for (i in 1:nb_workers) - { - upper_bound = ifelse( i 0) - { - curves = computeSynchrones(cl) - dists = computeWerDists(curves) - cl = computeClusters(dists, K2) + indices = unlist( parallel::parLapply( cl, indices_workers, function(inds) { + require("epclust", quietly=TRUE) + inds[ computeClusters1(getCoefs(inds), K1) ] + } ) ) + if (length(indices) == K1) + break } - cl + parallel::stopCluster(cl) + indices #medoids } -computeClusters = function(data, K) +# Apply the clustering algorithm (PAM) on a coeffs or distances matrix +computeClusters1 = function(coefs, K1) + cluster::pam(coefs, K1, diss=FALSE)$id.med + +# Cluster a chunk of series inside one task (~max nb_series_per_chunk) +computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk) { - library(cluster) - pam_output = cluster::pam(data, K) - return ( list( clusts=pam_output$clustering, medoids=pam_output$medoids, - ranks=pam_output$id.med ) ) + synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk) + medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ] } -#TODO: appendCoeffs() en C --> serialize et append to file - -computeSynchrones = function(...) +# Compute the synchrones curves (sum of clusters elements) from a clustering result +computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk) { - + 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,]))) , ] } -#Entrée : courbes synchrones, soit après étape 1 itérée, soit après chaqure étape 1 -computeWerDist = function(conso) +# Compute the WER distance between the synchrones curves (in rows) +computeWerDists = function(curves) { if (!require("Rwave", quietly=TRUE)) stop("Unable to load Rwave library") - n <- nrow(conso) - delta <- ncol(conso) + n <- nrow(curves) + delta <- ncol(curves) #TODO: automatic tune of all these parameters ? (for other users) nvoice <- 4 - # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(conso)) + # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(curves)) noctave = 13 # 4 here represent 2^5 = 32 half-hours ~ 1 day #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?) @@ -79,7 +89,7 @@ computeWerDist = function(conso) # (normalized) observations node with CWT Xcwt4 <- lapply(seq_len(n), function(i) { - ts <- scale(ts(conso[i,]), center=TRUE, scale=scaled) + ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled) totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0) ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)] #Normalization @@ -94,7 +104,7 @@ computeWerDist = function(conso) { 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)