X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=86dac64c150c6d1a6c1b4f8bf8756030ca89ae5d;hp=eded9523e4c2cc1c8316ed01617e35dfa13c6b18;hb=eef6f6c97277ea3ce760981e5244cbde7fc904a0;hpb=dc1aa85a96bbf815b0d896c22a9b4a539a9e8a9c diff --git a/epclust/R/main.R b/epclust/R/main.R index eded952..86dac64 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,161 +1,345 @@ -#' @include defaults.R - -#' @title Cluster power curves with PAM in parallel +#' CLAWS: CLustering with wAvelets and Wer distanceS +#' +#' Cluster electricity power curves (or any series of similar nature) by applying a +#' two stage procedure in parallel (see details). +#' Input series must be sampled on the same time grid, no missing values. +#' +#' @details Summary of the function execution flow: +#' \enumerate{ +#' \item Compute and serialize all contributions, obtained through discrete wavelet +#' decomposition (see Antoniadis & al. [2013]) +#' \item Divide series into \code{ntasks} groups to process in parallel. In each task: +#' \enumerate{ +#' \item iterate the first clustering algorithm on its aggregated outputs, +#' on inputs of size \code{nb_items_clust} +#' \item optionally, if WER=="mix": +#' a) compute the K1 synchrones curves, +#' b) compute WER distances (K1xK1 matrix) between synchrones and +#' c) apply the second clustering algorithm +#' } +#' \item Launch a final task on the aggregated outputs of all previous tasks: +#' in the case WER=="end" this task takes indices in input, otherwise +#' (medoid) curves +#' } +#' The main argument -- \code{getSeries} -- has a quite misleading name, since it can be +#' either a [big.]matrix, a CSV file, a connection or a user function to retrieve +#' series; the name was chosen because all types of arguments are converted to a function. +#' When \code{getSeries} is given as a function, it must take a single argument, +#' 'indices', integer vector equal to the indices of the curves to retrieve; +#' see SQLite example. The nature and role of other arguments should be clear +#' +#' @param getSeries Access to the (time-)series, which can be of one of the three +#' following types: +#' \itemize{ +#' \item [big.]matrix: each column contains the (time-ordered) values of one time-serie +#' \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 SQLite example +#' } +#' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series]) +#' @param K2 Number of clusters to be found after stage 2 (K2 << K1) +#' @param nb_per_chunk (Maximum) number of items to retrieve in one batch, for both types of +#' retrieval: resp. series and contribution; in a vector of size 2 +#' @param nb_items_clust1 (Maximum) number of items in input of the clustering algorithm +#' for stage 1 +#' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter +#' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (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 [if WER=="end"] +#' or K2 [if WER=="mix"] medoids); default: 1. +#' Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks +#' @param ncores_tasks Number of parallel tasks (1 to disable: sequential tasks) +#' @param ncores_clust Number of parallel clusterings in one task (4 should be a minimum) +#' @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 for (de)serialization ("little" or "big") +#' @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 K2 medoids curves, in columns #' -#' @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} +#' @references Clustering functional data using Wavelets [2013]; +#' A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi. +#' Inter. J. of Wavelets, Multiresolution and Information Procesing, +#' vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033 #' -#' @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. +#' @examples +#' \dontrun{ +#' # WER distances computations are 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)), ncol=6 ) +#' library(wmtsa) +#' series = do.call( cbind, lapply( 1:6, function(i) +#' do.call(cbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) ) +#' #dim(series) #c(2400,10001) +#' medoids_ascii = claws(series, K1=60, K2=6, nb_per_chunk=c(200,500), verbose=TRUE) +#' +#' # 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, nb_per_chunk=c(200,500)) +#' +#' # Same example, from binary file +#' bin_file <- "/tmp/epclust_series.bin" +#' nbytes <- 8 +#' endian <- "little" +#' 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, nb_per_chunk=c(200,500)) +#' 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"] ) +#' serie_length <- as.integer( dbGetQuery(series_db, +#' paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) ) +#' getSeries <- function(indices) { +#' request <- "SELECT id,value FROM times_values WHERE id in (" +#' for (i in indices) +#' request <- paste(request, indexToID_inDB[i], ",", sep="") +#' request <- paste(request, ")", sep="") +#' df_series <- dbGetQuery(series_db, request) +#' as.matrix(df_series[,"value"], nrow=serie_length) #' } -#' @param K Number of clusters -#' @param nb_series_per_chunk (Maximum) number of series in each group -#' @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() +#' medoids_db = claws(getSeries, K1=60, K2=6, nb_per_chunk=c(200,500)) +#' dbDisconnect(series_db) #' -#' @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) +#' # 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, + nb_per_chunk,nb_items_clust1=7*K1 #volumes of data + wav_filt="d8",contrib_type="absolute", #stage 1 + WER="end", #stage 2 + random=TRUE, #randomize series order? + ntasks=1, ncores_tasks=1, ncores_clust=4, #parallelism + sep=",", #ASCII input separator + nbytes=4, endian=.Platform$endian, #serialization (write,read) + verbose=FALSE, parll=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)) - 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) && !bigmemory::is.big.matrix(getSeries) + && !is.function(getSeries) + && !methods::is(getSeries,"connection") && !is.character(getSeries)) + { + 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.numeric(nb_per_chunk) || length(nb_per_chunk)!=2) + stop("'nb_per_chunk': numeric, size 2") + nb_per_chunk[1] <- .toInteger(nb_per_chunk[1], function(x) x>=1) + # A batch of contributions should have at least as many elements as a batch of series, + # because it always contains much less values + nb_per_chunk[2] <- max(.toInteger(nb_per_chunk[2],function(x) x>=1), nb_per_chunk[1]) + nb_items_clust1 <- .toInteger(nb_items_clust1, function(x) x>K1) + random <- .toLogical(random) + tryCatch + ( + {ignored <- wavelets::wt.filter(wav_filt)}, + error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") + ) + ctypes = c("relative","absolute","logit") + contrib_type = ctypes[ pmatch(contrib_type,ctypes) ] + if (is.na(contrib_type)) + stop("'contrib_type' in {'relative','absolute','logit'}") 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" + stop("'WER': in {'end','mix'}") + random <- .toLogical(random) + 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) + if (!is.character(sep)) + stop("'sep': character") + nbytes <- .toInteger(nbytes, function(x) x==4 || x==8) + verbose <- .toLogical(verbose) + parll <- .toLogical(parll) - #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)) + { + 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) + } + + # Serialize all computed wavelets contributions into a file + contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file) index = 1 nb_curves = 0 - repeat + 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 < K2) + stop("Not enough data: less series than final number of clusters") + nb_series_per_task = round(nb_curves / ntasks) + if (nb_series_per_task < K2) + stop("Too many tasks: less series in one task than final number of clusters") + + runTwoStepClustering = function(inds) { - 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)) + 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") { - #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 (parll && ntasks>1) + require("bigmemory", quietly=TRUE) + medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) ) + medoids2 = clusteringTask2(medoids1, K2, getSeries, nb_curves, nb_series_per_chunk, + nbytes, endian, ncores_clust, verbose, parll) + binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian) + return (vector("integer",0)) } - if (is.null(coeffs_chunk)) - break - writeTmp(coeffs_chunk) - nb_curves = nb_curves + nrow(coeffs_chunk) - index = index + nb_series_per_chunk + indices_medoids } - if (exists(data_con)) - close(data_con) - if (nb_curves < min_series_per_chunk) - stop("Not enough data: less rows 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 + # 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= 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 - #... - } - li = parallel::parLapply(cl, indices, processChunk, K, WER=="mix") - #C) flush tmp file (current parallel processes will write in it) + message = paste("...Run ",ntasks," x stage 1", sep="") + if (WER=="mix") + message = paste(message," + stage 2", sep="") + cat(paste(message,"\n", sep="")) } - 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) + if (WER=="mix") + {synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)} + if (parll && ntasks>1) { - return ( list( medoids=coeffsToCurves(final_coeffs[,2:ncol(final_coeffs)]), - ids=final_coeffs[,1] ) ) + cl = parallel::makeCluster(ncores_tasks, outfile="") + 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()) } - 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") + # 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file + indices <- + if (parll && ntasks>1) + unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) ) + else + unlist( lapply(indices_tasks, runTwoStepClustering) ) + if (parll && ntasks>1) + parallel::stopCluster(cl) + + getRefSeries = getSeries + 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) + #Contributions must be re-computed + unlink(contribs_file) + index = 1 + 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) } - return (list(medoids=medoids, ids=ids)) + # Run step2 on resulting indices or series (from file) + 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, + nbytes, endian, ncores_tasks*ncores_clust, verbose, parll) + + # Cleanup + unlink(bin_dir, recursive=TRUE) + + medoids2[,] } -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 [big.]matrix of series (in columns), of size L x n +#' @inheritParams claws +#' +#' @return A [big.]matrix of size log(L) x n containing contributions in columns +#' +#' @export +curvesToContribs = function(series, wav_filt, contrib_type) { - #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 = nrow(series) + D = ceiling( log2(L) ) + nb_sample_points = 2^D + apply(series, 2, 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 (contrib_type!="absolute") + nrj = nrj / sum(nrj) + if (contrib_type=="logit") + nrj = - log(1 - nrj) + 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 ?! +# Check integer arguments with functional conditions +.toInteger <- function(x, condition) +{ + errWarn <- function(ignored) + paste("Cannot convert argument' ",substitute(x),"' to integer", sep="") + if (!is.integer(x)) + tryCatch({x = as.integer(x)[1]; if (is.na(x)) stop()}, + warning = errWarn, error = errWarn) + if (!condition(x)) + { + stop(paste("Argument '",substitute(x), + "' does not verify condition ",body(condition), sep="")) + } + x +} + +# Check logical arguments +.toLogical <- function(x) +{ + errWarn <- function(ignored) + paste("Cannot convert argument' ",substitute(x),"' to logical", sep="") + if (!is.logical(x)) + tryCatch({x = as.logical(x)[1]; if (is.na(x)) stop()}, + warning = errWarn, error = errWarn) + x +}