X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;fp=epclust%2FR%2Fmain.R;h=603f7bfbbec05e2c71db48bcc75a7132507eb2f4;hb=40f12a2f66d06fd77183ea02b996f5c66f90761c;hp=f6662678f9db2ae812054979a4173728ca08efd3;hpb=a52836b23adb4bfa6722642ec6426fb7b5f39650;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index f666267..603f7bf 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 @@ -46,7 +45,8 @@ #' } #' @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_series_per_chunk (Maximum) number of series to retrieve in one batch; +#' this value is also used for the (maximum) number of series to cluster at a time #' @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 @@ -54,10 +54,7 @@ #' @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 @@ -68,14 +65,19 @@ #' 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. @@ -94,12 +96,12 @@ #' 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" #' 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 +109,7 @@ #' 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) #' @@ -137,29 +139,30 @@ #' 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, +claws <- function(getSeries, K1, K2, nb_series_per_chunk, + 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, 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) @@ -168,7 +171,6 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, # 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) random <- .toLogical(random) tryCatch( {ignored <- wavelets::wt.filter(wav_filt)}, error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") ) @@ -188,21 +190,23 @@ 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) + 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" + contribs_file = ".contribs.epclust.bin" index = 1 nb_curves = 0 if (verbose) @@ -210,7 +214,7 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, if (!file.exists(contribs_file)) { nb_curves = binarizeTransform(getSeries, - function(series) curvesToContribs(series, wav_filt, contrib_type), + function(curves) curvesToContribs(curves, wav_filt, contrib_type), contribs_file, nb_series_per_chunk, nbytes, endian) } else @@ -243,12 +247,9 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, # Initialize parallel runs: outfile="" allow to output verbose traces in the console # under Linux. All necessary variables are passed to the workers. cl = parallel::makeCluster(ncores_tasks, outfile="") - varlist = c("getSeries","getContribs","K1","K2","algoClust1","algoClust2", - "nb_series_per_chunk","nb_items_clust1","ncores_clust", - "nvoice","sep","nbytes","endian","verbose","parll") - if (WER=="mix" && ntasks>1) - varlist = c(varlist, "medoids_file") - parallel::clusterExport(cl, varlist, envir = environment()) + parallel::clusterExport(cl, envir = environment(), + varlist = c("getSeries","getContribs","K1","K2","algoClust1","algoClust2", + "nb_series_per_chunk","ncores_clust","nvoice","nbytes","endian","verbose","parll")) } # This function achieves one complete clustering task, divided in stage 1 + stage 2. @@ -261,27 +262,16 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, # 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_series_per_chunk, 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, + indices_medoids = clusteringTask2(indices_medoids, getSeries, K2, algoClust2, 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 } - # 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="") @@ -292,110 +282,32 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1, # 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 <- + 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 - - 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) - } + # Right before the final stage, input data still is the initial set of curves, referenced + # by the ntasks*[K1 or K2] medoids indices. - # Run step2 on resulting indices or series (from file) + # Run last clustering tasks to obtain only K2 medoids indices, from ntasks*[K1 or K2] + # indices, depending wether WER=="end" or WER=="mix" if (verbose) cat("...Run final // stage 1 + stage 2\n") - indices_medoids = clusteringTask1(indices, getContribs, K1, algoClust1, + indices_medoids = clusteringTask1(indices_medoids_all, 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, + indices_medoids = clusteringTask2(indices_medoids, getContribs, K2, algoClust2, 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) {}) + # Compute synchrones + medoids = getSeries(indices_medoids) + synchrones = computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk, + ncores_tasks*ncores_clust, verbose, parll) - # 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[,] -} - -#' 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 - }) -} - -# 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) }