X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=280cc1714a8f6196a8ed9e18ad20eff62db7653f;hb=56857861dc15088cf58e7438968fe5714b22168e;hp=e7943517587e46abbace81bb5b6397628e72328a;hpb=5c6529795907ba1b34d4552cbfd0e0cbb77cac0f;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index e794351..280cc17 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,14 +1,18 @@ -#' @title Cluster power curves with PAM in parallel +#' @include utils.R +#' @include clustering.R +NULL + +#' Cluster power curves with PAM in parallel CLAWS: CLustering with wAvelets and Wer distanceS #' -#' @description Groups electricity power curves (or any series of similar nature) by applying PAM +#' Groups electricity power curves (or any series of similar nature) by applying PAM #' algorithm in parallel to chunks of size \code{nb_series_per_chunk} #' #' @param data Access to the data, which can be of one of the three following types: #' \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 +26,7 @@ #' @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) #' @@ -33,59 +38,69 @@ #' "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) +claws = function(getSeries, K1, K2, + random=TRUE, #randomize series order? + wf="haar", #stage 1 + WER="end", #stage 2 + ntasks=1, ncores_tasks=1, ncores_clust=4, #control parallelism + nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1, #chunk size + sep=",", #ASCII input separator + nbytes=4, endian=.Platform$endian) #serialization (write,read) { - #0) check arguments - if (!is.data.frame(data) && !is.function(data)) + # Check/transform arguments + if (!is.matrix(getSeries) && !is.function(getSeries) && + !is(getSeries, "connection" && !is.character(getSeries))) { - tryCatch( - { - if (is.character(data)) - data_con = file(data, open="r") - else if (!isOpen(data)) - { - open(data) - data_con = data - } - }, - error=function(e) "data should be a data.frame, a function or a valid connection" - ) + stop("'getSeries': matrix, function, file or valid connection (no NA)") } - K1 = toInteger(K1, function(x) x>=2) - K2 = toInteger(K2, function(x) x>=2) - ntasks = toInteger(ntasks) - 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) + K1 = .toInteger(K1, function(x) x>=2) + K2 = .toInteger(K2, function(x) x>=2) + if (!is.logical(random)) + stop("'random': logical") + tryCatch( + {ignored <- wt.filter(wf)}, + error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter")) if (WER!="end" && WER!="mix") stop("WER takes values in {'end','mix'}") + ntasks = .toInteger(ntasks, function(x) x>=1) + ncores_tasks = .toInteger(ncores_tasks, function(x) x>=1) + ncores_clust = .toInteger(ncores_clust, 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) + if (!is.character(sep)) + stop("'sep': character") + nbytes = .toInteger(nbytes, function(x) x==4 || x==8) - #1) Serialize all wavelets coefficients (+ IDs) onto a file - coeffs_file = ".coeffs" + # Serialize series if required, to always use a function + bin_dir = "epclust.bin/" + dir.create(bin_dir, showWarnings=FALSE, mode="0755") + if (!is.function(getSeries)) + { + series_file = paste(bin_dir,"data",sep="") ; unlink(series_file) + serialize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian) + getSeries = function(indices) getDataInFile(indices, series_file, nbytes, endian) + } + + # 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, nb_series_per_chunk, sep, nbytes, endian) 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, nbytes, endian) if (nb_curves < min_series_per_chunk) stop("Not enough data: less rows than min_series_per_chunk!") @@ -93,24 +108,76 @@ 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 - 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)) - { + # Cluster coefficients in parallel (by nb_series_per_chunk) + indices_all = 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) { + indices_medoids = clusteringTask(inds,getCoefs,K1,nb_series_per_chunk,ncores_clust) + if (WER=="mix") + { + medoids2 = computeClusters2( + getSeries(indices_medoids), K2, getSeries, nb_series_per_chunk) + serialize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian) + return (vector("integer",0)) + } + indices_medoids + }) ) + parallel::stopCluster(cl) + + getSeriesForSynchrones = getSeries + synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file) + if (WER=="mix") + { + indices = seq_len(ntasks*K2) + #Now series must be retrieved from synchrones_file + getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian) + #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, nb_series_per_chunk, sep, nbytes, endian) + 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) + indices_medoids = clusteringTask( + indices, getCoefs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust) + computeClusters2(getSeries(indices_medoids),K2,getSeriesForSynchrones,nb_series_per_chunk) +} + +# helper +curvesToCoeffs = function(series, wf) +{ + L = length(series[1,]) + D = ceiling( log2(L) ) + nb_sample_points = 2^D + apply(series, 1, function(x) { + interpolated_curve = spline(1:L, x, n=nb_sample_points)$y + W = wavelets::dwt(interpolated_curve, filter=wf, D)@W + rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) ) + }) +} + +# helper +.toInteger <- function(x, condition) +{ + if (!is.integer(x)) + tryCatch( + {x = as.integer(x)[1]}, + error = function(e) paste("Cannot convert argument",substitute(x),"to integer") + ) + if (!condition(x)) + stop(paste("Argument",substitute(x),"does not verify condition",body(condition))) + x }