X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=4fdc5ae899c61aa3347e0aba1a843c12a5ecd012;hb=8546023eccc529272cf3e50f8dad17eed9d7b047;hp=603f7bfbbec05e2c71db48bcc75a7132507eb2f4;hpb=40f12a2f66d06fd77183ea02b996f5c66f90761c;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index 603f7bf..4fdc5ae 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -11,30 +11,31 @@ #' \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_series_per_chunk} -#' \item optionally, if WER=="mix": -#' a) compute the K1 synchrones curves, -#' a) compute WER distances (K1xK1 matrix) between medoids and -#' b) apply the second clustering algorithm (output: K2 indices) +#' on inputs of size \code{nb_items_clust}\cr +#' -> K1 medoids indices +#' \item optionally, if WER=="mix":\cr +#' a. compute WER distances (K1xK1) between medoids\cr +#' b. apply the 2nd clustering algorithm\cr +#' -> K2 medoids indices #' } #' \item Launch a final task on the aggregated outputs of all previous tasks: #' ntasks*K1 if WER=="end", ntasks*K2 otherwise #' \item Compute synchrones (sum of series within each final group) #' } -#' \cr +#' #' 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; +#' 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. #' 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 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 series Access to the (time-)series, which can be of one of the three +#' @param series Access to the N (time-)series, which can be of one of the four #' following types: #' \itemize{ #' \item [big.]matrix: each column contains the (time-ordered) values of one time-serie @@ -43,40 +44,39 @@ #' \item function: a custom way to retrieve the curves; it has only one argument: #' the indices of the series to be retrieved. See SQLite example #' } -#' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series]) +#' @param K1 Number of clusters to be found after stage 1 (K1 << N) #' @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; -#' this value is also used for the (maximum) number of series to cluster at a time +#' @param nb_series_per_chunk Number of series to retrieve in one batch +#' @param nb_items_clust Number of items in 1st clustering algorithm 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 -#' on iterated medoids during stage 1 +#' and outputs K medoids ranks. Default: PAM. #' @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 medoids after algorithm 1 +#' and outputs K medoids ranks. Default: PAM. #' @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. #' @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 (3 should be a minimum) +#' @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 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) +#' @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 with +#' @return A list: #' \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 +#' \item medoids: matrix of the final K2 medoids curves +#' \item ranks: corresponding indices in the dataset +#' \item synchrones: sum of series within each final group #' } #' #' @references Clustering functional data using Wavelets [2013]; @@ -87,29 +87,34 @@ #' @examples #' \dontrun{ #' # WER distances computations are too long for CRAN (for now) +#' parll = FALSE #on this small example, sequential run is faster #' #' # 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(0,50,0.05) +#' L <- length(x) #1001 +#' 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) -#' 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) +#' series <- do.call( cbind, lapply( 1:6, function(i) +#' do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=40)) ) ) +#' # Mix series so that all groups are evenly spread +#' 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, nb_series_per_chunk=500, +#' nb_items_clust=100, random=FALSE, verbose=TRUE, parll=parll) #' #' # Same example, from CSV file -#' 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) +#' 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) #' #' # Same example, from binary file -#' bin_file <- "/tmp/epclust_series.bin" +#' bin_file <- tempfile(pattern="epclust_series.bin_") #' nbytes <- 8 #' endian <- "little" -#' binarize(csv_file, bin_file, 500, nbytes, endian) +#' binarize(csv_file, bin_file, 500, ",", nbytes, endian) #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian) -#' res_bin <- claws(getSeries, K1=60, K2=6, 200) +#' res_bin <- claws(getSeries, 30, 6, 500, 100, random=FALSE, parll=parll) #' unlink(csv_file) #' unlink(bin_file) #' @@ -117,44 +122,45 @@ #' library(DBI) #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:") #' # Prepare data.frame in DB-format -#' n <- nrow(series) -#' time_values <- data.frame( +#' n <- ncol(series) +#' times_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)) ) +#' time = rep( as.POSIXct(1800*(1:L),"GMT",origin="2001-01-01"), n ), +#' value = as.double(series) ) #' dbWriteTable(series_db, "times_values", times_values) #' # Fill associative array, map index to identifier #' indexToID_inDB <- as.character( -#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] ) +#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM times_values')[,"id"] ) #' serie_length <- as.integer( dbGetQuery(series_db, -#' paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) ) +#' 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 indices) -#' request <- paste(request, indexToID_inDB[i], ",", sep="") +#' for (i in seq_along(indices)) { +#' request <- paste(request, indexToID_inDB[ indices[i] ], sep="") +#' if (i < length(indices)) +#' request <- paste(request, ",", sep="") +#' } #' request <- paste(request, ")", sep="") #' df_series <- dbGetQuery(series_db, request) -#' if (length(df_series) >= 1) -#' as.matrix(df_series[,"value"], nrow=serie_length) -#' else -#' NULL +#' matrix(df_series[,"value"], nrow=serie_length) #' } -#' res_db = claws(getSeries, K1=60, K2=6, 200)) +#' res_db <- claws(getSeries, 30, 6, 500, 100, random=FALSE, parll=parll) #' dbDisconnect(series_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) +#' # All results should be equal: +#' all(res_ascii$ranks == res_csv$ranks +#' & res_ascii$ranks == res_bin$ranks +#' & res_ascii$ranks == res_db$ranks) #' } #' @export -claws <- function(getSeries, K1, K2, nb_series_per_chunk, +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", 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 @@ -167,15 +173,12 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, 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_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") @@ -197,48 +200,46 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, { 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" 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 - # 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) + 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="")) } - # 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. + # As explained above, we obtain after all runs ntasks*[K1 or K2] medoids indices, + # depending whether WER=="end" or "mix", respectively. indices_medoids_all <- if (parll && ntasks>1) unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) ) @@ -291,22 +302,27 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, if (parll && ntasks>1) parallel::stopCluster(cl) - # Right before the final stage, input data still is the initial set of curves, referenced - # by the ntasks*[K1 or K2] medoids indices. + # 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 - # Run last clustering tasks to obtain only K2 medoids indices, from ntasks*[K1 or K2] - # indices, depending wether WER=="end" or WER=="mix" + # 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, - nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll) - indices_medoids = clusteringTask2(indices_medoids, getContribs, K2, algoClust2, - nb_series_per_chunk, nvoice, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll) + indices_medoids <- clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1, + nb_items_clust, ncores_tasks*ncores_clust, verbose, parll) + + indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, + nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose,parll) - # Compute synchrones - medoids = getSeries(indices_medoids) - synchrones = computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk, - ncores_tasks*ncores_clust, 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, + ncores_last_stage, verbose, parll) # 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)