X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=b09e93418836dd5786037323dca1d94538a2e5b4;hb=4bcfdbee4e2157f232427a5bfdf240f34760110d;hp=eded9523e4c2cc1c8316ed01617e35dfa13c6b18;hpb=dc1aa85a96bbf815b0d896c22a9b4a539a9e8a9c;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index eded952..b09e934 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,161 +1,273 @@ -#' @include defaults.R - -#' @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 K Number of clusters -#' @param nb_series_per_chunk (Maximum) number of series in each group +#' @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 +#' } +#' @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 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 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 number of parallel processes; if NULL, use parallel::detectCores() +#' @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) +#' +#' @return A matrix of the final medoids curves (K2) in rows +#' +#' @examples +#' \dontrun{ +#' # WER distances computations are a bit too long for CRAN (for now) +#' +#' # Random series around cos(x,2x,3x)/sin(x,2x,3x) +#' 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)), +#' 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, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500) #' -#' @return A data.frame of the final medoids curves (identifiers + values) -epclust = function(data, K, nb_series_per_chunk, min_series_per_chunk=10*K, - writeTmp=defaultWriteTmp, readTmp=defaultReadTmp, wf="haar", WER="end", ncores=NULL) +#' # 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, "d8", "rel", nb_series_per_chunk=500) +#' +#' # Same example, from binary file +#' bin_file = "/tmp/epclust_series.bin" +#' nbytes = 8 +#' endian = "little" +#' 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, "d8", "rel", nb_series_per_chunk=500) +#' unlink(csv_file) +#' unlink(bin_file) +#' +#' # Same example, from SQLite database +#' library(DBI) +#' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:") +#' # Prepare data.frame in DB-format +#' n = nrow(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) +#' # Fill associative array, map index to identifier +#' indexToID_inDB <- as.character( +#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] ) +#' getSeries = function(indices) { +#' 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) ) +#' } +#' 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, + 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) + verbose=FALSE) { - #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) && + !methods::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 <- 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'}") - #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) + + # 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)) + { + if (verbose) + cat("...Serialize time-series\n") + series_file = paste(bin_dir,"data",sep="") ; unlink(series_file) + binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian) + getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian) + } - #1) acquire data (process curves, get as coeffs) - #TODO: for data.frame and custom function, run in parallel (connections are sequential[?!]) + # Serialize all computed wavelets contributions onto a file + contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file) index = 1 nb_curves = 0 + if (verbose) + cat("...Compute contributions and serialize them\n") 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) + contribs_chunk = curvesToContribs(series, wf, ctype) + binarize(contribs_chunk, contribs_file, nb_series_per_chunk, sep, nbytes, endian) index = index + nb_series_per_chunk + nb_curves = nb_curves + nrow(contribs_chunk) } - if (exists(data_con)) - close(data_con) + 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!") + 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) - ncores = ifelse(is.integer(ncores), ncores, parallel::detectCores()%/%4) - cl = parallel::makeCluster(ncores) - parallel::clusterExport(cl=cl, varlist=c("TODO:", "what", "to", "export?"), envir=environment()) - #TODO: be careful of writing to a new temp file, then flush initial one, then re-use it... - repeat - { - #while there is jobs to do (i.e. size of tmp "file" is greater than 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) + # 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) { + indices = unlist( lapply(indices_tasks, function(inds) { +# require("epclust", quietly=TRUE) + + browser() #TODO: CONTINUE DEBUG HERE + + indices_medoids = clusteringTask(inds,getContribs,K1,nb_series_per_chunk,ncores_clust) + if (WER=="mix") { - #spread the load among other workers - #... + medoids2 = computeClusters2( + getSeries(indices_medoids), K2, getSeries, nb_series_per_chunk) + binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian) + return (vector("integer",0)) } - li = parallel::parLapply(cl, indices, processChunk, K, WER=="mix") - #C) flush tmp file (current parallel processes will write in it) - } - parallel::stopCluster(cl) + indices_medoids + }) ) +# parallel::stopCluster(cl) - #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) + getRefSeries = getSeries + synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file) + if (WER=="mix") { - return ( list( medoids=coeffsToCurves(final_coeffs[,2:ncol(final_coeffs)]), - ids=final_coeffs[,1] ) ) + indices = seq_len(ntasks*K2) + #Now series must be retrieved from synchrones_file + getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian) + #Contributions must be re-computed + unlink(contribs_file) + index = 1 + if (verbose) + cat("...Serialize contributions computed on synchrones\n") + repeat + { + series = getSeries((index-1)+seq_len(nb_series_per_chunk)) + if (is.null(series)) + break + contribs_chunk = curvesToContribs(series, wf, ctype) + binarize(contribs_chunk, contribs_file, nb_series_per_chunk, sep, nbytes, endian) + index = index + nb_series_per_chunk + } } - pam_output = getClusters(as.matrix(final_coeffs[,2:ncol(final_coeffs)]), K) - medoids = coeffsToCurves(pam_output$medoids, wf) - ids = final_coeffs[,1] [pam_output$ranks] - #4) apply stage 2 (in parallel ? inside task 2) ?) - if (WER == "end") - { - #from center curves, apply stage 2... - #TODO: - } + # Run step2 on resulting indices or series (from file) + if (verbose) + cat("...Run final // stage 1 + stage 2\n") + indices_medoids = clusteringTask( + indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust) + medoids = computeClusters2(getSeries(indices_medoids),K2,getRefSeries,nb_series_per_chunk) + + # Cleanup + unlink(bin_dir, recursive=TRUE) - return (list(medoids=medoids, ids=ids)) + medoids } -processChunk = function(indice, K, WER) +#' curvesToContribs +#' +#' Compute the discrete wavelet coefficients for each series, and aggregate them in +#' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2 +#' +#' @param series Matrix of series (in rows), of size n x L +#' @inheritParams claws +#' +#' @return A matrix of size n x log(L) containing contributions in rows +#' +#' @export +curvesToContribs = function(series, wf, ctype) { - #1) retrieve data - coeffs = readTmp(indice[1], indice[2]) - #2) cluster - cl = getClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K) - #3) WER (optional) - #TODO: + L = length(series[1,]) + D = ceiling( log2(L) ) + nb_sample_points = 2^D + cont_types = c("relative","absolute") + ctype = cont_types[ pmatch(ctype,cont_types) ] + t( apply(series, 1, function(x) { + interpolated_curve = spline(1:L, x, n=nb_sample_points)$y + W = wavelets::dwt(interpolated_curve, filter=wf, D)@W + nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) ) + if (ctype=="relative") nrj / sum(nrj) else nrj + }) ) } -#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 ?! +# Helper for main function: check integer arguments with functiional conditions +.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 +}