X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=00d2a882e8745950599d839e953db56ef4d746fd;hp=ce650ff6522ab9d8f774fd526d3506fbb6317b25;hb=282342bafdc9ff65c5df98c6e2304d63b33b9fb2;hpb=3c5a4b0880db63367a474a568e1322b3999932fe diff --git a/epclust/R/main.R b/epclust/R/main.R index ce650ff..00d2a88 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -59,6 +59,7 @@ #' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix) #' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply #' stage 2 at the end of each task +#' @param smooth_lvl Smoothing level: odd integer, 1 == no smoothing. 3 seems good #' @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"] @@ -89,19 +90,19 @@ #' # WER distances computations are too long for CRAN (for now) #' #' # Random series around cos(x,2x,3x)/sin(x,2x,3x) -#' x = seq(0,500,0.05) -#' L = length(x) #10001 -#' ref_series = matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 ) +#' x <- seq(0,500,0.05) +#' L <- length(x) #10001 +#' ref_series <- matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 ) #' library(wmtsa) -#' series = do.call( cbind, lapply( 1:6, function(i) +#' series <- do.call( cbind, lapply( 1:6, function(i) #' do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=400)) ) ) #' #dim(series) #c(2400,10001) -#' res_ascii = claws(series, K1=60, K2=6, 200, verbose=TRUE) +#' res_ascii <- claws(series, K1=60, K2=6, 200, verbose=TRUE) #' #' # Same example, from CSV file -#' csv_file = "/tmp/epclust_series.csv" +#' csv_file <- "/tmp/epclust_series.csv" #' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE) -#' res_csv = claws(csv_file, K1=60, K2=6, 200) +#' res_csv <- claws(csv_file, K1=60, K2=6, 200) #' #' # Same example, from binary file #' bin_file <- "/tmp/epclust_series.bin" @@ -119,9 +120,9 @@ #' # Prepare data.frame in DB-format #' n <- nrow(series) #' time_values <- data.frame( -#' id = rep(1:n,each=L), -#' time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ), -#' value = as.double(t(series)) ) +#' id <- rep(1:n,each=L), +#' time <- rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ), +#' value <- as.double(t(series)) ) #' dbWriteTable(series_db, "times_values", times_values) #' # Fill associative array, map index to identifier #' indexToID_inDB <- as.character( @@ -139,7 +140,7 @@ #' else #' NULL #' } -#' res_db = claws(getSeries, K1=60, K2=6, 200)) +#' res_db <- claws(getSeries, K1=60, K2=6, 200)) #' dbDisconnect(series_db) #' #' # All results should be the same: @@ -153,8 +154,8 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*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", nvoice=4, random=TRUE, - ntasks=1, ncores_tasks=1, ncores_clust=4, sep=",", nbytes=4, + 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) { # Check/transform arguments @@ -169,10 +170,10 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1, nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1) nb_items_clust <- .toInteger(nb_items_clust, function(x) x>K1) random <- .toLogical(random) - tryCatch( {ignored <- wavelets::wt.filter(wav_filt)}, - error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") ) - ctypes = c("relative","absolute","logit") - contrib_type = ctypes[ pmatch(contrib_type,ctypes) ] + tryCatch({ignored <- wavelets::wt.filter(wav_filt)}, + error=function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") ) + ctypes <- c("relative","absolute","logit") + contrib_type <- ctypes[ pmatch(contrib_type,ctypes) ] if (is.na(contrib_type)) stop("'contrib_type' in {'relative','absolute','logit'}") if (WER!="end" && WER!="mix") @@ -194,48 +195,48 @@ 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" + series_file <- ".series.epclust.bin" 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) + getSeries <- function(inds) getDataInFile(inds, series_file, nbytes, endian) } else - getSeries = series + getSeries <- series # Serialize all computed wavelets contributions into a file - contribs_file = ".contribs.epclust.bin" - index = 1 - nb_curves = 0 + contribs_file <- ".contribs.epclust.bin" + index <- 1 + nb_curves <- 0 if (verbose) cat("...Compute contributions and serialize them (or retrieve past binary file)\n") if (!file.exists(contribs_file)) { - nb_curves = binarizeTransform(getSeries, + nb_curves <- binarizeTransform(getSeries, function(curves) curvesToContribs(curves, wav_filt, contrib_type), contribs_file, nb_series_per_chunk, nbytes, endian) } else { # TODO: duplicate from getDataInFile() in de_serialize.R - contribs_size = file.info(contribs_file)$size #number of bytes in the file - contrib_length = readBin(contribs_file, "integer", n=1, size=8, endian=endian) - nb_curves = (contribs_size-8) / (nbytes*contrib_length) + contribs_size <- file.info(contribs_file)$size #number of bytes in the file + contrib_length <- readBin(contribs_file, "integer", n=1, size=8, endian=endian) + nb_curves <- (contribs_size-8) / (nbytes*contrib_length) } - getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian) + getContribs <- function(indices) getDataInFile(indices, contribs_file, nbytes, endian) # A few sanity checks: do not continue if too few data available. if (nb_curves < K2) stop("Not enough data: less series than final number of clusters") - nb_series_per_task = round(nb_curves / ntasks) + nb_series_per_task <- round(nb_curves / ntasks) if (nb_series_per_task < K2) stop("Too many tasks: less series in one task than final number of clusters") # Generate a random permutation of 1:N (if random==TRUE); # otherwise just use arrival (storage) order. - indices_all = if (random) sample(nb_curves) else seq_len(nb_curves) + indices_all <- if (random) sample(nb_curves) else seq_len(nb_curves) # Split (all) indices into ntasks groups of ~same size - indices_tasks = lapply(seq_len(ntasks), function(i) { - upper_bound = ifelse( i clusteringTask1(...) --> K1 medoids (indices) # stage 2: K1 indices --> K1xK1 WER distances --> clusteringTask2(...) --> K2 medoids, - # where n = N / ntasks, N being the total number of curves. - runTwoStepClustering = function(inds) + # where n == N / ntasks, N being the total number of curves. + runTwoStepClustering <- function(inds) { # When running in parallel, the environment is blank: we need to load the required # packages, and pass useful variables. if (parll && ntasks>1) require("epclust", quietly=TRUE) - indices_medoids = clusteringTask1(inds, getContribs, K1, algoClust1, + indices_medoids <- clusteringTask1(inds, getContribs, K1, algoClust1, nb_items_clust, ncores_clust, verbose, parll) if (WER=="mix") { - indices_medoids = clusteringTask2(indices_medoids, getSeries, K2, algoClust2, - nb_series_per_chunk, nvoice, nbytes, endian, ncores_clust, verbose, parll) + indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, + nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_clust,verbose,parll) } indices_medoids } if (verbose) { - message = paste("...Run ",ntasks," x stage 1", sep="") + message <- paste("...Run ",ntasks," x stage 1", sep="") if (WER=="mix") - message = paste(message," + stage 2", sep="") + message <- paste(message," + stage 2", sep="") cat(paste(message,"\n", sep="")) } @@ -304,15 +305,15 @@ claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1, # Run last clustering tasks to obtain only K2 medoids indices if (verbose) cat("...Run final // stage 1 + stage 2\n") - indices_medoids = clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1, + indices_medoids <- clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1, nb_items_clust, ncores_tasks*ncores_clust, verbose, parll) - indices_medoids = clusteringTask2(indices_medoids, getContribs, K2, algoClust2, - nb_series_per_chunk, nvoice, nbytes, endian, ncores_last_stage, verbose, parll) + indices_medoids <- clusteringTask2(indices_medoids, getContribs, K2, algoClust2, + nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose,parll) # 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, + medoids <- getSeries(indices_medoids) + synchrones <- computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk, ncores_last_stage, verbose, parll) # NOTE: no need to use big.matrix here, since there are only K2 << K1 << N remaining curves