X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=00d2a882e8745950599d839e953db56ef4d746fd;hb=282342bafdc9ff65c5df98c6e2304d63b33b9fb2;hp=f6662678f9db2ae812054979a4173728ca08efd3;hpb=a52836b23adb4bfa6722642ec6426fb7b5f39650;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index f666267..00d2a88 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -11,31 +11,30 @@ #' \item Divide series into \code{ntasks} groups to process in parallel. In each task: #' \enumerate{ #' \item iterate the first clustering algorithm on its aggregated outputs, -#' on inputs of size \code{nb_items_clust1} +#' on inputs of size \code{nb_series_per_chunk} #' \item optionally, if WER=="mix": #' a) compute the K1 synchrones curves, -#' b) compute WER distances (K1xK1 matrix) between synchrones and -#' c) apply the second clustering algorithm +#' a) compute WER distances (K1xK1 matrix) between medoids and +#' b) apply the second clustering algorithm (output: K2 indices) #' } #' \item Launch a final task on the aggregated outputs of all previous tasks: -#' in the case WER=="end" this task takes indices in input, otherwise -#' (medoid) curves +#' ntasks*K1 if WER=="end", ntasks*K2 otherwise +#' \item Compute synchrones (sum of series within each final group) #' } #' \cr -#' The main argument -- \code{getSeries} -- has a quite misleading name, since it can be -#' either a [big.]matrix, a CSV file, a connection or a user function to retrieve -#' series; the name was chosen because all types of arguments are converted to a function. -#' When \code{getSeries} is given as a function, it must take a single argument, +#' The main argument -- \code{series} -- has a quite misleading name, since it can be +#' either a [big.]matrix, a CSV file, a connection or a user function to retrieve series. +#' When \code{series} is given as a function, it must take a single argument, #' 'indices', integer vector equal to the indices of the curves to retrieve; -#' see SQLite example. The nature and role of other arguments should be clear. +#' see SQLite example. #' WARNING: the return value must be a matrix (in columns), or NULL if no matches. #' \cr #' Note: Since we don't make assumptions on initial data, there is a possibility that -#' even when serialized, contributions or synchrones do not fit in RAM. For example, +#' even when serialized, contributions do not fit in RAM. For example, #' 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore, #' it's safer to place these in (binary) files; that's what we do. #' -#' @param getSeries Access to the (time-)series, which can be of one of the three +#' @param series Access to the (time-)series, which can be of one of the three #' following types: #' \itemize{ #' \item [big.]matrix: each column contains the (time-ordered) values of one time-serie @@ -47,6 +46,7 @@ #' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series]) #' @param K2 Number of clusters to be found after stage 2 (K2 << K1) #' @param nb_series_per_chunk (Maximum) number of series to retrieve in one batch +#' @param nb_items_clust (~Maximum) number of items in clustering algorithm 1 input #' @param algoClust1 Clustering algorithm for stage 1. A function which takes (data, K) #' as argument where data is a matrix in columns and K the desired number of clusters, #' and outputs K medoids ranks. Default: PAM. In our method, this function is called @@ -54,28 +54,31 @@ #' @param algoClust2 Clustering algorithm for stage 2. A function which takes (dists, K) #' as argument where dists is a matrix of distances and K the desired number of clusters, #' and outputs K medoids ranks. Default: PAM. In our method, this function is called -#' on a matrix of K1 x K1 (WER) distances computed between synchrones -#' @param nb_items_clust1 (~Maximum) number of items in input of the clustering algorithm -#' for stage 1. At worst, a clustering algorithm might be called with ~2*nb_items_clust1 -#' items; but this could only happen at the last few iterations. +#' on a matrix of K1 x K1 (WER) distances computed between medoids after algorithm 1 #' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter #' @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"] #' or K2 [if WER=="mix"] medoids); default: 1. #' Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks #' @param ncores_tasks Number of parallel tasks (1 to disable: sequential tasks) -#' @param ncores_clust Number of parallel clusterings in one task (4 should be a minimum) +#' @param ncores_clust Number of parallel clusterings in one task (3 should be a minimum) #' @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 endian Endianness for (de)serialization ("little" or "big") #' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage) #' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison) #' -#' @return A matrix of the final K2 medoids curves, in columns +#' @return A list with +#' \itemize{ +#' medoids: a matrix of the final K2 medoids curves, in columns +#' ranks: corresponding indices in the dataset +#' synchrones: a matrix of the K2 sum of series within each final group +#' } #' #' @references Clustering functional data using Wavelets [2013]; #' A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi. @@ -87,19 +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) -#' medoids_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) -#' medoids_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" @@ -107,7 +110,7 @@ #' endian <- "little" #' binarize(csv_file, bin_file, 500, nbytes, endian) #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian) -#' medoids_bin <- claws(getSeries, K1=60, K2=6, 200) +#' res_bin <- claws(getSeries, K1=60, K2=6, 200) #' unlink(csv_file) #' unlink(bin_file) #' @@ -117,9 +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( @@ -137,43 +140,40 @@ #' else #' NULL #' } -#' medoids_db = claws(getSeries, K1=60, K2=6, 200)) +#' res_db <- claws(getSeries, K1=60, K2=6, 200)) #' dbDisconnect(series_db) #' -#' # All computed medoids should be the same: -#' digest::sha1(medoids_ascii) -#' digest::sha1(medoids_csv) -#' digest::sha1(medoids_bin) -#' digest::sha1(medoids_db) +#' # All results should be the same: +#' library(digest) +#' digest::sha1(res_ascii) +#' digest::sha1(res_csv) +#' digest::sha1(res_bin) +#' digest::sha1(res_db) #' } #' @export -claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, - algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE)$id.med, - algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE)$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, +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", 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 - if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries) - && !is.function(getSeries) - && !methods::is(getSeries,"connection") && !is.character(getSeries)) + if (!is.matrix(series) && !bigmemory::is.big.matrix(series) + && !is.function(series) + && !methods::is(series,"connection") && !is.character(series)) { - stop("'getSeries': [big]matrix, function, file or valid connection (no NA)") + stop("'series': [big]matrix, function, file or valid connection (no NA)") } K1 <- .toInteger(K1, function(x) x>=2) K2 <- .toInteger(K2, function(x) x>=2) nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1) - # K1 (number of clusters at step 1) cannot exceed nb_series_per_chunk, because we will need - # to load K1 series in memory for clustering stage 2. - if (K1 > nb_series_per_chunk) - stop("'K1' cannot exceed 'nb_series_per_chunk'") - nb_items_clust1 <- .toInteger(nb_items_clust1, function(x) x>K1) + 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") @@ -188,53 +188,55 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, verbose <- .toLogical(verbose) parll <- .toLogical(parll) - # Binarize series if getSeries is not a function; the aim is to always use a function, + # 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 # bigmemory::big.matrix, but it would break the "all-is-function" pattern. - if (!is.function(getSeries)) + if (!is.function(series)) { if (verbose) cat("...Serialize time-series (or retrieve past binary file)\n") - series_file = ".series.bin" + series_file <- ".series.epclust.bin" if (!file.exists(series_file)) - binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian) - getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian) + binarize(series, series_file, nb_series_per_chunk, sep, nbytes, endian) + getSeries <- function(inds) getDataInFile(inds, series_file, nbytes, endian) } + else + getSeries <- series # Serialize all computed wavelets contributions into a file - contribs_file = ".contribs.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, - function(series) curvesToContribs(series, wav_filt, contrib_type), + 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( i1) - varlist = c(varlist, "medoids_file") - parallel::clusterExport(cl, varlist, envir = environment()) + cl <- parallel::makeCluster(ncores_tasks, outfile="") + varlist <- c("ncores_clust","verbose","parll", #task 1 & 2 + "K1","getContribs","algoClust1","nb_items_clust") #task 1 + if (WER=="mix") + { + # Add variables for task 2 + varlist <- c(varlist, "K2","getSeries","algoClust2","nb_series_per_chunk", + "smooth_lvl","nvoice","nbytes","endian") + } + parallel::clusterExport(cl, varlist, envir <- environment()) } # This function achieves one complete clustering task, divided in stage 1 + stage 2. - # stage 1: n indices --> clusteringTask1(...) --> K1 medoids - # stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids, - # where n = N / ntasks, N being the total number of curves. - runTwoStepClustering = function(inds) + # stage 1: n indices --> 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) { # 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, nb_series_per_chunk, ncores_clust, verbose, parll) - if (WER=="mix" && ntasks>1) + indices_medoids <- clusteringTask1(inds, getContribs, K1, algoClust1, + nb_items_clust, ncores_clust, verbose, parll) + if (WER=="mix") { - if (parll) - require("bigmemory", quietly=TRUE) - medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) ) - medoids2 = clusteringTask2(medoids1, K2, algoClust2, getSeries, nb_curves, - nb_series_per_chunk, nvoice, nbytes, endian, ncores_clust, verbose, parll) - binarize(medoids2, medoids_file, nb_series_per_chunk, sep, nbytes, endian) - return (vector("integer",0)) + indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, + nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_clust,verbose,parll) } indices_medoids } - # Synchrones (medoids) need to be stored only if WER=="mix"; indeed in this case, every - # task output is a set of new (medoids) curves. If WER=="end" however, output is just a - # set of indices, representing some initial series. - if (WER=="mix" && ntasks>1) - {medoids_file = ".medoids.bin" ; unlink(medoids_file)} - 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="")) } - # As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"], - # or nothing (empty vector) if WER=="mix"; in this case, synchrones are stored in a file. - indices <- + # As explained above, we obtain after all runs ntasks*[K1 or K2] medoids indices, + # depending wether WER=="end" or "mix", respectively. + indices_medoids_all <- if (parll && ntasks>1) unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) ) else unlist( lapply(indices_tasks, runTwoStepClustering) ) + if (parll && ntasks>1) parallel::stopCluster(cl) - # Right before the final stage, two situations are possible: - # a. data to be processed now sit in a binary format in medoids_file (if WER=="mix") - # b. data still is the initial set of curves, referenced by the ntasks*K1 indices - # So, the function getSeries() will potentially change. However, computeSynchrones() - # requires a function retrieving the initial series. Thus, the next line saves future - # conditional instructions. - getRefSeries = getSeries + # For the last stage, ncores_tasks*(ncores_clusts+1) cores should be available: + # - ntasks for level 1 parallelism + # - ntasks*ncores_clust for level 2 parallelism, + # but since an extension MPI <--> tasks / OpenMP <--> sub-tasks is on the way, + # it's better to just re-use ncores_clust + ncores_last_stage <- ncores_clust - if (WER=="mix" && ntasks>1) - { - indices = seq_len(ntasks*K2) - # Now series (synchrones) must be retrieved from medoids_file - getSeries = function(inds) getDataInFile(inds, medoids_file, nbytes, endian) - # Contributions must be re-computed - unlink(contribs_file) - index = 1 - if (verbose) - cat("...Serialize contributions computed on synchrones\n") - ignored = binarizeTransform(getSeries, - function(series) curvesToContribs(series, wav_filt, contrib_type), - contribs_file, nb_series_per_chunk, nbytes, endian) - } - - # Run step2 on resulting indices or series (from file) + # Run last clustering tasks to obtain only K2 medoids indices if (verbose) cat("...Run final // stage 1 + stage 2\n") - indices_medoids = clusteringTask1(indices, getContribs, K1, algoClust1, - nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll) - medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) ) - medoids2 = clusteringTask2(medoids1, K2, algoClust2, getRefSeries, nb_curves, - nb_series_per_chunk, nvoice, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll) - - # Cleanup: remove temporary binary files - tryCatch( - {unlink(series_file); unlink(contribs_file); unlink(medoids_file)}, - error = function(e) {}) - - # Return medoids as a standard matrix, since K2 series have to fit in RAM - # (clustering algorithm 1 takes K1 > K2 of them as input) - medoids2[,] -} + 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,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose,parll) -#' curvesToContribs -#' -#' Compute the discrete wavelet coefficients for each series, and aggregate them in -#' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2 -#' -#' @param series [big.]matrix of series (in columns), of size L x n -#' @inheritParams claws -#' -#' @return A [big.]matrix of size log(L) x n containing contributions in columns -#' -#' @export -curvesToContribs = function(series, wav_filt, contrib_type, coin=FALSE) -{ - series = as.matrix(series) #1D serie could occur - L = nrow(series) - D = ceiling( log2(L) ) - # Series are interpolated to all have length 2^D - nb_sample_points = 2^D - apply(series, 2, function(x) { - interpolated_curve = spline(1:L, x, n=nb_sample_points)$y - W = wavelets::dwt(interpolated_curve, filter=wav_filt, D)@W - # Compute the sum of squared discrete wavelet coefficients, for each scale - nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) ) - if (contrib_type!="absolute") - nrj = nrj / sum(nrj) - if (contrib_type=="logit") - nrj = - log(1 - nrj) - nrj - }) -} + # 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) -# Check integer arguments with functional conditions -.toInteger <- function(x, condition) -{ - errWarn <- function(ignored) - paste("Cannot convert argument' ",substitute(x),"' to integer", sep="") - if (!is.integer(x)) - tryCatch({x = as.integer(x)[1]; if (is.na(x)) stop()}, - warning = errWarn, error = errWarn) - if (!condition(x)) - { - stop(paste("Argument '",substitute(x), - "' does not verify condition ",body(condition), sep="")) - } - x -} - -# Check logical arguments -.toLogical <- function(x) -{ - errWarn <- function(ignored) - paste("Cannot convert argument' ",substitute(x),"' to logical", sep="") - if (!is.logical(x)) - tryCatch({x = as.logical(x)[1]; if (is.na(x)) stop()}, - warning = errWarn, error = errWarn) - x + # 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) }