X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=5e47f192e9bb95373f4b8ac92428d7e13d5872e9;hb=8702eb86906bd6d59e07bb887e690a20f29be63f;hp=e18ea7b54767ecd98ba4f8870d91e670cdde1442;hpb=d7d55bc1e74711b0da84578ecdebc43eeb259599;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index e18ea7b..5e47f19 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,33 +1,38 @@ -#' @include defaults.R +#' @include de_serialize.R +#' @include clustering.R +NULL -#' @title 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 -#' algorithm in parallel to chunks of size \code{nb_series_per_chunk} +#' 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}. Input series +#' must be sampled on the same time grid, no missing values. #' -#' @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. -#' } +#' @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 function: a custom way to retrieve the curves; it has only one argument: +#' the indices of the series to be retrieved. See examples +#' } #' @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 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 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 nb_series_per_chunk (Maximum) number of series in each group, inside a 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 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 sep Separator in CSV input file (relevant only if getSeries is a file name) +#' @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 #' -#' @return A data.frame of the final medoids curves (identifiers + values) +#' @return A matrix of the final medoids curves #' #' @examples #' getData = function(start, n) { @@ -37,148 +42,146 @@ #' "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) +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) { - #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)) - tryCatch( - { - if (is.character(data)) - { - data_con = file(data, open="r") - } else if (!isOpen(data)) - { - open(data) - data_con = data - } - }, - 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)") + # Check/transform arguments + if (!is.matrix(getSeries) && !is.function(getSeries) && + !is(getSeries, "connection" && !is.character(getSeries))) + { + stop("'getSeries': 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)}, + error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter")) 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" + 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) acquire data (process curves, get as coeffs) - #TODO: for data.frame and custom function, run in parallel (connections are sequential[?!]) + # 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 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) + 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) } - if (exists(data_con)) - close(data_con) + 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!") + 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 + # 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") { - #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) + 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)) } - parallel:stopCluster(cl_clust) - }) - parallel::stopCluster(cl_tasks) - - #3) readTmp last results, apply PAM on it, and return medoids + identifiers - final_coeffs = readTmp(1, nb_series_per_chunk) - if (nrow(final_coeffs) == K) - { - return ( list( medoids=coeffsToCurves(final_coeffs[,2:ncol(final_coeffs)]), - ids=final_coeffs[,1] ) ) - } - pam_output = getClusters(as.matrix(final_coeffs[,2:ncol(final_coeffs)]), K) - medoids = coeffsToCurves(pam_output$medoids, wf) - ids = final_coeffs[,1] [pam_output$ranks] + indices_medoids + }) ) + parallel::stopCluster(cl) - #4) apply stage 2 (in parallel ? inside task 2) ?) - if (WER == "end") + getRefSeries = getSeries + synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file) + if (WER=="mix") { - #from center curves, apply stage 2... - #TODO: + indices = seq_len(ntasks*K2) + #Now series must be retrieved from synchrones_file + getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian) + #Coefs must be re-computed + unlink(coefs_file) + index = 1 + repeat + { + series = getSeries((index-1)+seq_len(nb_series_per_chunk)) + if (is.null(series)) + break + coefs_chunk = curvesToCoefs(series, wf) + serialize(coefs_chunk, coefs_file, nb_series_per_chunk, sep, nbytes, endian) + index = index + nb_series_per_chunk + } } - return (list(medoids=medoids, ids=ids)) + # Run step2 on resulting indices or series (from file) + indices_medoids = clusteringTask( + indices, getCoefs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust) + computeClusters2(getSeries(indices_medoids),K2,getRefSeries,nb_series_per_chunk) } -processChunk = function(indice, K, WER) +# helper +curvesToCoefs = function(series, wf) { - #1) retrieve data - coeffs = readTmp(indice[1], indice[2]) - #2) cluster - cl = getClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K) - #3) WER (optional) - #TODO: + L = length(series[1,]) + D = ceiling( log2(L) ) + nb_sample_points = 2^D + t( apply(series, 1, function(x) { + interpolated_curve = spline(1:L, x, n=nb_sample_points)$y + W = wavelets::dwt(interpolated_curve, filter=wf, D)@W + rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) ) + }) ) } -#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 ?! -#TODO: bout de code qui calcule les courbes synchrones après étapes 1+2 à partir des ID médoïdes +# 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 +}