X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=0b598329b87935a3ea668f8953e6967f8bd9ea5f;hp=867843b813ff561f17588cb2ec0a18b7e35b0329;hb=e205f2187f0ccdff00bffc47642392ec5e33214d;hpb=1c6f223e4dc7f7f022fd18b1c99deff0da022387 diff --git a/epclust/R/main.R b/epclust/R/main.R index 867843b..0b59832 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,5 +1,3 @@ -#' @include defaults.R - #' @title Cluster power curves with PAM in parallel #' #' @description Groups electricity power curves (or any series of similar nature) by applying PAM @@ -9,8 +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) @@ -18,14 +16,13 @@ #' Note: ntasks << N, so that N is "roughly divisible" by N (number of series) #' @param nb_series_per_chunk (Maximum) number of series in each group, inside a task #' @param min_series_per_chunk Minimum number of series in each group -#' @param writeTmp Function to write temporary wavelets coefficients (+ identifiers); -#' see defaults in defaults.R -#' @param readTmp Function to read temporary wavelets coefficients (see defaults.R) #' @param wf Wavelet transform filter; see ?wt.filter. Default: haar #' @param WER "end" to apply stage 2 after stage 1 has iterated and finished, or "mix" #' to apply it after every stage 1 -#' @param ncores_tasks number of parallel tasks (1 to disable: sequential tasks) -#' @param ncores_clust number of parallel clusterings in one task +#' @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) #' @@ -37,147 +34,114 @@ #' "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, - writeTmp=defaultWriteTmp, readTmp=defaultReadTmp, wf="haar", WER="end", - ncores_tasks=1, ncores_clust=4) +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,...) { - #TODO: setRefClass(...) to avoid copy data: - #http://stackoverflow.com/questions/2603184/r-pass-by-reference - - #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="data should be a data.frame, a function or a valid connection") - if (!is.integer(K) || K < 2) - stop("K should be an integer greater or equal to 2") - if (!is.integer(nb_series_per_chunk) || nb_series_per_chunk < K) - stop("nb_series_per_chunk should be an integer greater or equal to K") - if (!is.function(writeTmp) || !is.function(readTmp)) - stop("read/writeTmp should be functional (see defaults.R)") + 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, 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) + ncores_clust = toInteger(ncores_clust, function(x) x>=1) if (WER!="end" && WER!="mix") stop("WER takes values in {'end','mix'}") - #concerning ncores, any non-integer type will be treated as "use parallel:detectCores()/4" - #1) acquire data (process curves, get as coeffs) - #TODO: for data.frame and custom function, run in parallel (connections are sequential[?!]) + # Serialize all wavelets coefficients (+ IDs) onto a file + coefs_file = paste(bin_dir,"coefs",sep="") + unlink(coefs_file) index = 1 nb_curves = 0 repeat { - coeffs_chunk = NULL - if (is.data.frame(data)) - { - #full data matrix - if (index < nrow(data)) - { - coeffs_chunk = curvesToCoeffs( - data[index:(min(index+nb_series_per_chunk-1,nrow(data))),], wf) - } - } else if (is.function(data)) - { - #custom user function to retrieve next n curves, probably to read from DB - coeffs_chunk = curvesToCoeffs( data(index, nb_series_per_chunk), wf ) - } else - { - #incremental connection - #TODO: find a better way to parse than using a temp file - ascii_lines = readLines(data_con, nb_series_per_chunk) - if (length(ascii_lines > 0)) - { - series_chunk_file = ".tmp/series_chunk" - writeLines(ascii_lines, series_chunk_file) - coeffs_chunk = curvesToCoeffs( read.csv(series_chunk_file), wf ) - } - } - if (is.null(coeffs_chunk)) + series = getSeries((index-1)+seq_len(nb_series_per_chunk)) + if (is.null(series)) break - writeTmp(coeffs_chunk) - nb_curves = nb_curves + nrow(coeffs_chunk) + coeffs_chunk = curvesToCoeffs(series, wf) + serialize(coeffs_chunk, coefs_file) index = index + nb_series_per_chunk + nb_curves = nb_curves + nrow(coeffs_chunk) } - if (exists(data_con)) - close(data_con) + 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!") + nb_series_per_task = round(nb_curves / ntasks) + if (nb_series_per_task < min_series_per_chunk) + stop("Too many tasks: less series in one task than min_series_per_chunk!") - #2) process coeffs (by nb_series_per_chunk) and cluster them in parallel - library(parallel) - cl_tasks = parallel::makeCluster(ncores_tasks) - #Nothing to export because each worker retrieve and put data from/on files (or DB) - #parallel::clusterExport(cl=cl, varlist=c("nothing","to","export"), envir=environment()) - #TODO: be careful of writing to a new temp file, then flush initial one, then re-use it... - res_tasks = parallel::parSapply(cl_tasks, 1:ntasks, function() { - cl_clust = parallel::makeCluster(ncores_clust) - repeat - { - #while there are jobs to do - #(i.e. size of tmp "file" is greater than ntasks * nb_series_per_chunk) - nb_workers = nb_curves %/% nb_series_per_chunk - indices = list() - #indices[[i]] == (start_index,number_of_elements) - for (i in 1:nb_workers) - indices[[i]] = c(nb_series_per_chunk*(i-1)+1, nb_series_per_chunk) - remainder = nb_curves %% nb_series_per_chunk - if (remainder >= min_series_per_chunk) - { - nb_workers = nb_workers + 1 - indices[[nb_workers]] = c(nb_curves-remainder+1, nb_curves) - } else if (remainder > 0) - { - #spread the load among other workers - #... - } - res_clust = parallel::parSapply(cl, indices, processChunk, K, WER=="mix") - #C) flush tmp file (current parallel processes will write in it) - } - parallel:stopCluster(cl_clust) + # Cluster coefficients in parallel (by nb_series_per_chunk) + indices = if (random) sample(nb_curves) else seq_len(nb_curves) + 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) - #4) apply stage 2 (in parallel ? inside task 2) ?) - if (WER == "end") + getSeriesForSynchrones = getSeries + synchrones_file = paste(bin_dir,"synchrones",sep="") + if (WER=="mix") { - #from center curves, apply stage 2... - #TODO: + 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 + } } - return (list(medoids=medoids, ids=ids)) + # 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) } - -processChunk = function(indice, K, WER) -{ - #1) retrieve data - coeffs = readTmp(indice[1], indice[2]) - #2) cluster - cl = getClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K) - #3) WER (optional) - #TODO: -} - -#TODO: difficulté : retrouver courbe à partir de l'identifiant (DB ok mais le reste ?) -#aussi : que passe-t-on aux noeuds ? curvesToCoeffs en // ? -#enfin : WER ?!