X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=09e1ed7feca546b476b3e69d8b9e379e535a967d;hb=14c10f2d252f45349e0b4fbf87e17dfbfae39f92;hp=fe78e630b4dd1a697d62cbbe9d68a41bf125d050;hpb=e0154a59e55143dac0fbd2a4739a3509bc958e76;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index fe78e63..09e1ed7 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -62,7 +62,7 @@ #' @param nvoice Number of voices within each octave for CWT computations #' @param random TRUE (default) for random chunks repartition #' @param ntasks Number of tasks (parallel iterations to obtain K1 [if WER=="end"] -#' or K2 [if WER=="mix"] medoids); default: 1. +#' or K2 [if WER=="mix"] medoids); default: 1.\cr #' Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks #' @param ncores_tasks Number of parallel tasks ('1' == sequential tasks) #' @param ncores_clust Number of parallel clusterings in one task @@ -70,7 +70,6 @@ #' @param nbytes 4 or 8 bytes to (de)serialize a floating-point number #' @param endian Endianness for (de)serialization: "little" or "big" #' @param verbose FALSE: nothing printed; TRUE: some execution traces -#' @param parll TRUE: run in parallel. FALSE: run sequentially #' #' @return A list: #' \itemize{ @@ -87,7 +86,7 @@ #' @examples #' \dontrun{ #' # WER distances computations are too long for CRAN (for now) -#' parll = FALSE #on this small example, sequential run is faster +#' # Note: on this small example, sequential run is faster #' #' # Random series around cos(x,2x,3x)/sin(x,2x,3x) #' x <- seq(0,50,0.05) @@ -101,12 +100,12 @@ #' series = series[,permut] #' #dim(series) #c(240,1001) #' res_ascii <- claws(series, K1=30, K2=6, nb_series_per_chunk=500, -#' nb_items_clust=100, random=FALSE, verbose=TRUE, parll=parll) +#' nb_items_clust=100, random=FALSE, verbose=TRUE, ncores_clust=1) #' #' # Same example, from CSV file #' csv_file <- tempfile(pattern="epclust_series.csv_") #' write.table(t(series), csv_file, sep=",", row.names=FALSE, col.names=FALSE) -#' res_csv <- claws(csv_file, 30, 6, 500, 100, random=FALSE, parll=parll) +#' res_csv <- claws(csv_file, 30, 6, 500, 100, random=FALSE, ncores_clust=1) #' #' # Same example, from binary file #' bin_file <- tempfile(pattern="epclust_series.bin_") @@ -114,7 +113,7 @@ #' endian <- "little" #' binarize(csv_file, bin_file, 500, ",", nbytes, endian) #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian) -#' res_bin <- claws(getSeries, 30, 6, 500, 100, random=FALSE, parll=parll) +#' res_bin <- claws(getSeries, 30, 6, 500, 100, random=FALSE, ncores_clust=1) #' unlink(csv_file) #' unlink(bin_file) #' @@ -147,7 +146,7 @@ #' df_series <- dbGetQuery(series_db, request) #' matrix(df_series[,"value"], nrow=serie_length) #' } -#' res_db <- claws(getSeries, 30, 6, 500, 100, random=FALSE, parll=parll) +#' res_db <- claws(getSeries, 30, 6, 500, 100, random=FALSE, ncores_clust=1) #' dbDisconnect(series_db) #' #' # All results should be equal: @@ -161,7 +160,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE,pamonce=1)$id.med, wav_filt="d8", contrib_type="absolute", WER="end", smooth_lvl=3, nvoice=4, random=TRUE, ntasks=1, ncores_tasks=1, ncores_clust=3, sep=",", nbytes=4, - endian=.Platform$endian, verbose=FALSE, parll=TRUE) + endian=.Platform$endian, verbose=FALSE) { # Check/transform arguments if (!is.matrix(series) && !bigmemory::is.big.matrix(series) @@ -191,7 +190,6 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, stop("'sep': character") nbytes <- .toInteger(nbytes, function(x) x==4 || x==8) verbose <- .toLogical(verbose) - parll <- .toLogical(parll) # Binarize series if it is not a function; the aim is to always use a function, # to uniformize treatments. An equally good alternative would be to use a file-backed @@ -243,6 +241,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, indices_all[((i-1)*nb_series_per_task+1):upper_bound] }) + parll <- (ncores_tasks > 1) if (parll && ntasks>1) { # Initialize parallel runs: outfile="" allow to output verbose traces in the console @@ -252,7 +251,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, parallel::makeCluster(ncores_tasks, outfile="") else parallel::makeCluster(ncores_tasks) - varlist <- c("ncores_clust","verbose","parll", #task 1 & 2 + varlist <- c("ncores_clust","verbose", #task 1 & 2 "K1","getContribs","algoClust1","nb_items_clust") #task 1 if (WER=="mix") { @@ -274,11 +273,11 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, if (parll && ntasks>1) require("epclust", quietly=TRUE) indices_medoids <- clusteringTask1(inds, getContribs, K1, algoClust1, - nb_items_clust, ncores_clust, verbose, parll) + nb_items_clust, ncores_clust, verbose) if (WER=="mix") { indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, - nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_clust,verbose,parll) + nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_clust,verbose) } indices_medoids } @@ -292,7 +291,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, } # As explained above, we obtain after all runs ntasks*[K1 or K2] medoids indices, - # depending wether WER=="end" or "mix", respectively. + # depending whether WER=="end" or "mix", respectively. indices_medoids_all <- if (parll && ntasks>1) unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) ) @@ -313,16 +312,16 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, if (verbose) cat("...Run final // stage 1 + stage 2\n") indices_medoids <- clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1, - nb_items_clust, ncores_tasks*ncores_clust, verbose, parll) + nb_items_clust, ncores_tasks*ncores_clust, verbose) indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, - nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose,parll) + nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose) # Compute synchrones, that is to say the cumulated power consumptions for each of the K2 # final groups. medoids <- getSeries(indices_medoids) synchrones <- computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk, - ncores_last_stage, verbose, parll) + ncores_last_stage, verbose) # NOTE: no need to use big.matrix here, since there are only K2 << K1 << N remaining curves list("medoids"=medoids, "ranks"=indices_medoids, "synchrones"=synchrones)