X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=09e1ed7feca546b476b3e69d8b9e379e535a967d;hb=2203730448baaaaa6164729fb1db9cca7a488872;hp=e3fa807d34d54b8837e1e5c6949d077f76cab216;hpb=dc86eb0c992e6e4ab119d48398d040c4cf3a75fd;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index e3fa807..09e1ed7 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -62,16 +62,14 @@ #' @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 #' @param sep Separator in CSV input file (if any provided) -#' @param nbytes Number of bytes to serialize a floating-point number: 4 or 8 +#' @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 -#' @param reuse_bin Re-use previously stored binary series and contributions #' #' @return A list: #' \itemize{ @@ -88,6 +86,7 @@ #' @examples #' \dontrun{ #' # WER distances computations are too long for CRAN (for now) +#' # 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) @@ -100,12 +99,13 @@ #' permut <- (0:239)%%6 * 40 + (0:239)%/%6 + 1 #' series = series[,permut] #' #dim(series) #c(240,1001) -#' res_ascii <- claws(series, K1=30, K2=6, 100, random=FALSE, verbose=TRUE) +#' res_ascii <- claws(series, K1=30, K2=6, nb_series_per_chunk=500, +#' 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, K1=30, K2=6, 100, random=FALSE) +#' 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_") @@ -113,7 +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, K1=30, K2=6, 100, random=FALSE) +#' res_bin <- claws(getSeries, 30, 6, 500, 100, random=FALSE, ncores_clust=1) #' unlink(csv_file) #' unlink(bin_file) #' @@ -133,6 +133,9 @@ #' serie_length <- as.integer( dbGetQuery(series_db, #' paste("SELECT COUNT(*) FROM times_values WHERE id == ",indexToID_inDB[1],sep="")) ) #' getSeries <- function(indices) { +#' indices = indices[ indices <= length(indexToID_inDB) ] +#' if (length(indices) == 0) +#' return (NULL) #' request <- "SELECT id,value FROM times_values WHERE id in (" #' for (i in seq_along(indices)) { #' request <- paste(request, indexToID_inDB[ indices[i] ], sep="") @@ -141,13 +144,9 @@ #' } #' request <- paste(request, ")", sep="") #' df_series <- dbGetQuery(series_db, request) -#' if (nrow(df_series) >= 1) -#' matrix(df_series[,"value"], nrow=serie_length) -#' else -#' NULL +#' matrix(df_series[,"value"], nrow=serie_length) #' } -#' # reuse_bin==FALSE: DB do not garantee ordering -#' res_db <- claws(getSeries, K1=30, K2=6, 100, random=FALSE, reuse_bin=FALSE) +#' res_db <- claws(getSeries, 30, 6, 500, 100, random=FALSE, ncores_clust=1) #' dbDisconnect(series_db) #' #' # All results should be equal: @@ -156,18 +155,13 @@ #' & res_ascii$ranks == res_db$ranks) #' } #' @export -claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1, +claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=5*K1, algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE,pamonce=1)$id.med, algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE,pamonce=1)$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$endian, verbose=FALSE, parll=TRUE, reuse_bin=TRUE) + endian=.Platform$endian, verbose=FALSE) { - - -#TODO: comprendre differences.......... debuguer getSeries for DB - - # Check/transform arguments if (!is.matrix(series) && !bigmemory::is.big.matrix(series) && !is.function(series) @@ -196,7 +190,6 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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 @@ -206,11 +199,8 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1, if (verbose) cat("...Serialize time-series (or retrieve past binary file)\n") series_file <- ".series.epclust.bin" - if (!file.exists(series_file) || !reuse_bin) - { - unlink(series_file,) + if (!file.exists(series_file)) binarize(series, series_file, nb_series_per_chunk, sep, nbytes, endian) - } getSeries <- function(inds) getDataInFile(inds, series_file, nbytes, endian) } else @@ -220,9 +210,8 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1, contribs_file <- ".contribs.epclust.bin" if (verbose) cat("...Compute contributions and serialize them (or retrieve past binary file)\n") - if (!file.exists(contribs_file) || !reuse_bin) + if (!file.exists(contribs_file)) { - unlink(contribs_file,) nb_curves <- binarizeTransform(getSeries, function(curves) curvesToContribs(curves, wav_filt, contrib_type), contribs_file, nb_series_per_chunk, nbytes, endian) @@ -252,6 +241,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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 @@ -261,7 +251,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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") { @@ -283,11 +273,11 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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 } @@ -301,7 +291,7 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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) ) @@ -322,16 +312,16 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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)