X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=0b598329b87935a3ea668f8953e6967f8bd9ea5f;hp=e7943517587e46abbace81bb5b6397628e72328a;hb=e205f2187f0ccdff00bffc47642392ec5e33214d;hpb=5c6529795907ba1b34d4552cbfd0e0cbb77cac0f diff --git a/epclust/R/main.R b/epclust/R/main.R index e794351..0b59832 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -7,8 +7,8 @@ #' \itemize{ #' \item data.frame: each line contains its ID in the first cell, and all values after #' \item connection: any R connection object (e.g. a file) providing lines as described above -#' \item function: a custom way to retrieve the curves; it has two arguments: the start index -#' (start) and number of curves (n); see example in package vignette. +#' \item function: a custom way to retrieve the curves; it has two arguments: the ranks to be +#' retrieved, and the IDs - at least one of them must be present (priority: ranks). #' } #' @param K1 Number of super-consumers to be found after stage 1 (K1 << N) #' @param K2 Number of clusters to be found after stage 2 (K2 << K1) @@ -22,6 +22,7 @@ #' @param ncores_tasks "MPI" number of parallel tasks (1 to disable: sequential tasks) #' @param ncores_clust "OpenMP" number of parallel clusterings in one task #' @param random Randomize chunks repartition +#' @param ... Other arguments to be passed to \code{data} function #' #' @return A data.frame of the final medoids curves (identifiers + values) #' @@ -33,32 +34,48 @@ #' "LIMIT ", n, " ORDER BY date", sep="")) #' return (df) #' } +#' #####TODO: if DB, array rank --> ID at first retrieval, when computing coeffs; so:: NO use of IDs ! #' #TODO: 3 examples, data.frame / binary file / DB sqLite #' + sampleCurves : wavBootstrap de package wmtsa #' cl = epclust(getData, K1=200, K2=15, ntasks=1000, nb_series_per_chunk=5000, WER="mix") #' @export -epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1, - wf="haar", WER="end", ncores_tasks=1, ncores_clust=4, random=TRUE) +epclust = function(series,K1,K2,ntasks=1,nb_series_per_chunk=50*K1,min_series_per_chunk=5*K1, + wf="haar",WER="end",ncores_tasks=1,ncores_clust=4,random=TRUE,...) { - #0) check arguments - if (!is.data.frame(data) && !is.function(data)) + # Check/transform arguments + bin_dir = "epclust.bin/" + dir.create(bin_dir, showWarnings=FALSE, mode="0755") + if (!is.function(series)) + { + series_file = paste(bin_dir,"data",sep="") + unlink(series_file) + } + if (is.matrix(series)) + serialize(series, series_file) + else if (!is.function(series)) { tryCatch( { - if (is.character(data)) - data_con = file(data, open="r") - else if (!isOpen(data)) + if (is.character(series)) + series_con = file(series, open="r") + else if (!isOpen(series)) { - open(data) - data_con = data + open(series) + series_con = series } + serialize(series_con, series_file) + close(series_con) }, - error=function(e) "data should be a data.frame, a function or a valid connection" + error=function(e) "series should be a data.frame, a function or a valid connection" ) } + if (!is.function(series)) + series = function(indices) getDataInFile(indices, series_file) + getSeries = series + K1 = toInteger(K1, function(x) x>=2) K2 = toInteger(K2, function(x) x>=2) - ntasks = toInteger(ntasks) + ntasks = toInteger(ntasks, function(x) x>=1) nb_series_per_chunk = toInteger(nb_series_per_chunk, function(x) x>=K1) min_series_per_chunk = toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk) ncores_tasks = toInteger(ncores_tasks, function(x) x>=1) @@ -66,26 +83,22 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series if (WER!="end" && WER!="mix") stop("WER takes values in {'end','mix'}") - #1) Serialize all wavelets coefficients (+ IDs) onto a file - coeffs_file = ".coeffs" + # Serialize all wavelets coefficients (+ IDs) onto a file + coefs_file = paste(bin_dir,"coefs",sep="") + unlink(coefs_file) index = 1 nb_curves = 0 - nb_coeffs = NA repeat { - coeffs_chunk = computeCoeffs(data, index, nb_series_per_chunk, wf) - if (is.null(coeffs_chunk)) + series = getSeries((index-1)+seq_len(nb_series_per_chunk)) + if (is.null(series)) break - serialized_coeffs = serialize(coeffs_chunk) - appendBinary(coeffs_file, serialized_coeffs) + coeffs_chunk = curvesToCoeffs(series, wf) + serialize(coeffs_chunk, coefs_file) index = index + nb_series_per_chunk nb_curves = nb_curves + nrow(coeffs_chunk) - if (is.na(nb_coeffs)) - nb_coeffs = ncol(coeffs_chunk)-1 } - -# finalizeSerialization(coeffs_file) ........, nb_curves, ) -#TODO: is it really useful ?! we will always have these informations (nb_curves, nb_coeffs) + getCoefs = function(indices) getDataInFile(indices, coefs_file) if (nb_curves < min_series_per_chunk) stop("Not enough data: less rows than min_series_per_chunk!") @@ -93,24 +106,42 @@ epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series if (nb_series_per_task < min_series_per_chunk) stop("Too many tasks: less series in one task than min_series_per_chunk!") - #2) Cluster coefficients in parallel (by nb_series_per_chunk) - # All indices, relative to complete dataset + # Cluster coefficients in parallel (by nb_series_per_chunk) indices = if (random) sample(nb_curves) else seq_len(nb_curves) - # Indices to be processed in each task - indices_tasks = list() - for (i in seq_len(ntasks)) - { + indices_tasks = lapply(seq_len(ntasks), function(i) { upper_bound = ifelse( i series on file) + indices = unlist( parallel::parLapply(cl, indices_tasks, function(inds) { + clusteringTask(inds, getSeries, getSeries, getCoefs, K1, K2*(WER=="mix"), + nb_series_per_chunk,ncores_clust,to_file=TRUE) + }) ) + parallel::stopCluster(cl) + + getSeriesForSynchrones = getSeries + synchrones_file = paste(bin_dir,"synchrones",sep="") + if (WER=="mix") + { + indices = seq_len(ntasks*K2) + #Now series must be retrieved from synchrones_file + getSeries = function(inds) getDataInFile(inds, synchrones_file) + #Coefs must be re-computed + unlink(coefs_file) + index = 1 + repeat + { + series = getSeries((index-1)+seq_len(nb_series_per_chunk)) + if (is.null(series)) + break + coeffs_chunk = curvesToCoeffs(series, wf) + serialize(coeffs_chunk, coefs_file) + index = index + nb_series_per_chunk + } } - library(parallel, quietly=TRUE) - cl_tasks = parallel::makeCluster(ncores_tasks) - parallel::clusterExport(cl_tasks, ..........ncores_clust, indices_tasks, nb_series_per_chunk, processChunk, K1, - K2, WER, ) - ranks = parallel::parSapply(cl_tasks, seq_along(indices_tasks), oneIteration) - parallel::stopCluster(cl_tasks) - #3) Run step1+2 step on resulting ranks - ranks = oneIteration(.........) - return (list("ranks"=ranks, "medoids"=getSeries(data, ranks))) + # Run step2 on resulting indices or series (from file) + clusteringTask(indices, getSeries, getSeriesForSynchrones, getCoefs, K1, K2, + nb_series_per_chunk, ncores_tasks*ncores_clust, to_file=FALSE) }