X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=977e61b235da2ea1ac4e0fc3c4cd40bbddcc049f;hb=e161499b97c782aadfc287c22b55f85724f86fae;hp=1347fae27a623a43cf9db53a74580c85690f5313;hpb=4efef8ccd1522278f53aa5ce265f3a6cfb6fbd9f;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index 1347fae..977e61b 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,7 +1,3 @@ -#' @include de_serialize.R -#' @include clustering.R -NULL - #' CLAWS: CLustering with wAvelets and Wer distanceS #' #' Groups electricity power curves (or any series of similar nature) by applying PAM @@ -11,28 +7,33 @@ NULL #' @param getSeries Access to the (time-)series, which can be of one of the three #' following types: #' \itemize{ -#' \item matrix: each line contains all the values for one time-serie, ordered by time -#' \item connection: any R connection object (e.g. a file) providing lines as described above +#' \item [big.]matrix: each line contains all the values for one time-serie, ordered by time +#' \item connection: any R connection object providing lines as described above +#' \item character: name of a CSV file containing series in rows (no header) #' \item function: a custom way to retrieve the curves; it has only one argument: #' the indices of the series to be retrieved. See examples #' } +#' @inheritParams clustering #' @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) -#' @param random TRUE (default) for random chunks repartition -#' @param wf Wavelet transform filter; see ?wavelets::wt.filter. Default: haar +#' @param wf Wavelet transform filter; see ?wavelets::wt.filter +#' @param ctype Type of contribution: "relative" or "absolute" (or 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 random TRUE (default) for random chunks repartition #' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1. #' Note: ntasks << N, so that N is "roughly divisible" by N (number of series) #' @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 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 sep Separator in CSV input file (relevant only if getSeries is a file name) +#' @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 to use for (de)serialization. Use "little" or "big" for portability +#' @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 medoids curves (K2) in rows +#' @return A big.matrix of the final medoids curves (K2) in rows #' #' @examples #' \dontrun{ @@ -42,25 +43,25 @@ NULL #' 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)), -#' byrows=TRUE, ncol=L ) +#' byrow=TRUE, ncol=L ) #' library(wmtsa) #' series = do.call( rbind, lapply( 1:6, function(i) #' do.call(rbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) ) #' #dim(series) #c(2400,10001) -#' medoids_ascii = claws(series_RData, K1=60, K2=6, wf="d8", nb_series_per_chunk=500) +#' medoids_ascii = claws(series, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500) #' #' # 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, wf="d8", nb_series_per_chunk=500) +#' medoids_csv = claws(csv_file, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500) #' #' # Same example, from binary file #' bin_file = "/tmp/epclust_series.bin" #' nbytes = 8 #' endian = "little" -#' epclust::serialize(csv_file, bin_file, 500, nbytes, endian) +#' epclust::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, wf="d8", nb_series_per_chunk=500) +#' medoids_bin = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500) #' unlink(csv_file) #' unlink(bin_file) #' @@ -69,59 +70,57 @@ NULL #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:") #' # Prepare data.frame in DB-format #' n = nrow(series) -#' formatted_series = data.frame( -#' ID = rep(1:n,each=L), -#' time = as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), -#' value - - - - -#' TODO - - -#' times_values = as.data.frame(series) +#' time_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)) ) #' dbWriteTable(series_db, "times_values", times_values) -#' # NOTE: assume that DB internal data is not reorganized when computing coefficients -#' indexToID_inDB <<- list() +#' # Fill associative array, map index to identifier +#' indexToID_inDB <- as.character( +#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] ) #' getSeries = function(indices) { -#' con = dbConnect(drv = RSQLite::SQLite(), dbname = db_file) -#' if (indices %in% indexToID_inDB) -#' { -#' df = dbGetQuery(con, paste( -#' "SELECT value FROM times_values GROUP BY id OFFSET ",start, -#' "LIMIT ", n, " ORDER BY date", sep="")) -#' return (df) -#' } -#' else -#' { -#' ... -#' } +#' request = "SELECT id,value FROM times_values WHERE id in (" +#' for (i in indices) +#' request = paste(request, i, ",", sep="") +#' request = paste(request, ")", sep="") +#' df_series = dbGetQuery(series_db, request) +#' # Assume that all series share same length at this stage +#' ts_length = sum(df_series[,"id"] == df_series[1,"id"]) +#' t( as.matrix(df_series[,"value"], nrow=ts_length) ) #' } -#' dbDisconnect(mydb) +#' medoids_db = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500) +#' 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) #' } #' @export claws = function(getSeries, K1, K2, - random=TRUE, #randomize series order? - wf="haar", #stage 1 + wf,ctype, #stage 1 WER="end", #stage 2 + random=TRUE, #randomize series order? 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$endian) #serialization (write,read) + nbytes=4, endian=.Platform$endian, #serialization (write,read) + verbose=FALSE, parll=TRUE) { # Check/transform arguments - if (!is.matrix(getSeries) && !is.function(getSeries) && - !is(getSeries, "connection" && !is.character(getSeries))) + if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries) + && !is.function(getSeries) + && !methods::is(getSeries,"connection") && !is.character(getSeries)) { - stop("'getSeries': matrix, function, file or valid connection (no NA)") + stop("'getSeries': [big]matrix, function, file or valid connection (no NA)") } 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)}, + {ignored <- wavelets::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'}") @@ -135,30 +134,27 @@ claws = function(getSeries, K1, K2, nbytes = .toInteger(nbytes, function(x) x==4 || x==8) # Serialize series if required, to always use a function - bin_dir = "epclust.bin/" + bin_dir = ".epclust_bin/" dir.create(bin_dir, showWarnings=FALSE, mode="0755") if (!is.function(getSeries)) { + if (verbose) + cat("...Serialize time-series\n") 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) + binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian) + getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian) } - # Serialize all wavelets coefficients (+ IDs) onto a file - coefs_file = paste(bin_dir,"coefs",sep="") ; unlink(coefs_file) + # Serialize all computed wavelets contributions into a file + contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file) index = 1 nb_curves = 0 - repeat - { - series = getSeries((index-1)+seq_len(nb_series_per_chunk)) - if (is.null(series)) - break - coefs_chunk = curvesToCoefs(series, wf) - serialize(coefs_chunk, coefs_file, nb_series_per_chunk, sep, nbytes, endian) - index = index + nb_series_per_chunk - nb_curves = nb_curves + nrow(coefs_chunk) - } - getCoefs = function(indices) getDataInFile(indices, coefs_file, nbytes, endian) + if (verbose) + cat("...Compute contributions and serialize them\n") + nb_curves = binarizeTransform(getSeries, + function(series) curvesToContribs(series, wf, ctype), + contribs_file, nb_series_per_chunk, nbytes, endian) + getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian) if (nb_curves < min_series_per_chunk) stop("Not enough data: less rows than min_series_per_chunk!") @@ -166,69 +162,114 @@ claws = function(getSeries, K1, K2, if (nb_series_per_task < min_series_per_chunk) stop("Too many tasks: less series in one task than min_series_per_chunk!") - # Cluster coefficients in parallel (by nb_series_per_chunk) + runTwoStepClustering = function(inds) + { + if (parll && ntasks>1) + require("epclust", quietly=TRUE) + indices_medoids = clusteringTask1( + inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll) + if (WER=="mix") + { + medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) ) + medoids2 = clusteringTask2(medoids1, + K2, getSeries, nb_curves, nb_series_per_chunk, ncores_clust, verbose, parll) + binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian) + return (vector("integer",0)) + } + indices_medoids + } + + # Cluster contributions 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) { - require("epclust", quietly=TRUE) - indices_medoids = clusteringTask(inds,getCoefs,K1,nb_series_per_chunk,ncores_clust) + if (verbose) + { + message = paste("...Run ",ntasks," x stage 1", sep="") 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) + message = paste(message," + stage 2", sep="") + cat(paste(message,"\n", sep="")) + } + if (WER=="mix") + {synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)} + if (parll && ntasks>1) + { + cl = parallel::makeCluster(ncores_tasks) + varlist = c("getSeries","getContribs","K1","K2","verbose","parll", + "nb_series_per_chunk","ntasks","ncores_clust","sep","nbytes","endian") + if (WER=="mix") + varlist = c(varlist, "synchrones_file") + parallel::clusterExport(cl, varlist=varlist, envir = environment()) + } + + # 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file + if (parll && ntasks>1) + indices = unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) ) + else + indices = unlist( lapply(indices_tasks, runTwoStepClustering) ) + if (parll && ntasks>1) + parallel::stopCluster(cl) getRefSeries = 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) + #Contributions must be re-computed + unlink(contribs_file) index = 1 - repeat - { - series = getSeries((index-1)+seq_len(nb_series_per_chunk)) - if (is.null(series)) - break - coefs_chunk = curvesToCoefs(series, wf) - serialize(coefs_chunk, coefs_file, nb_series_per_chunk, sep, nbytes, endian) - index = index + nb_series_per_chunk - } + if (verbose) + cat("...Serialize contributions computed on synchrones\n") + ignored = binarizeTransform(getSeries, + function(series) curvesToContribs(series, wf, ctype), + contribs_file, nb_series_per_chunk, nbytes, endian) } # 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,getRefSeries,nb_series_per_chunk) + if (verbose) + cat("...Run final // stage 1 + stage 2\n") + indices_medoids = clusteringTask1( + indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll) + medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) ) + medoids2 = clusteringTask2(medoids1, K2, + getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll) + + # Cleanup + unlink(bin_dir, recursive=TRUE) + + medoids2 } -# helper -curvesToCoefs = function(series, wf) +#' 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 Matrix of series (in rows), of size n x L +#' @inheritParams claws +#' +#' @return A matrix of size n x log(L) containing contributions in rows +#' +#' @export +curvesToContribs = function(series, wf, ctype) { L = length(series[1,]) D = ceiling( log2(L) ) nb_sample_points = 2^D + cont_types = c("relative","absolute") + ctype = cont_types[ pmatch(ctype,cont_types) ] t( 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) ) ) ) ) + nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) ) + if (ctype=="relative") nrj / sum(nrj) else nrj }) ) } -# helper +# Check integer arguments with functional conditions .toInteger <- function(x, condition) { if (!is.integer(x))