X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=a039d1cc029f94f641d6943b7aacc63d27c38002;hb=37c82bbafbffc19e8b47a521952bac58f189e9ea;hp=977e61b235da2ea1ac4e0fc3c4cd40bbddcc049f;hpb=e161499b97c782aadfc287c22b55f85724f86fae;p=epclust.git diff --git a/epclust/R/main.R b/epclust/R/main.R index 977e61b..a039d1c 100644 --- a/epclust/R/main.R +++ b/epclust/R/main.R @@ -1,67 +1,103 @@ #' CLAWS: CLustering with wAvelets and Wer distanceS #' -#' 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. +#' 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 line contains all the values for one time-serie, ordered by time +#' \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 examples +#' the indices of the series to be retrieved. See SQLite example #' } -#' @inheritParams clustering -#' @param K1 Number of super-consumers to be found after stage 1 (K1 << N) +#' @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 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 nb_series_per_chunk (Maximum) number of series to retrieve in one batch +#' @param algo_clust1 Clustering algorithm for stage 1. A function which takes (data, K) +#' as argument where data is a matrix in columns and K the desired number of clusters, +#' and outputs K medoids ranks. Default: PAM +#' @param algo_clust2 Clustering algorithm for stage 2. A function which takes (dists, K) +#' as argument where dists is a matrix of distances and K the desired number of clusters, +#' and outputs K clusters representatives (curves). Default: k-means +#' @param nb_items_clust1 (~Maximum) number of items in input of the clustering algorithm +#' for stage 1. At worst, a clustering algorithm might be called with ~2*nb_items_clust1 +#' items; but this could only happen at the last few iterations. +#' @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 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 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 to use for (de)serialization. Use "little" or "big" for portability +#' @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 big.matrix of the final medoids curves (K2) in rows +#' @return A matrix of the final K2 medoids curves, in columns +#' +#' @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 #' #' @examples #' \dontrun{ -#' # WER distances computations are a bit too long for CRAN (for now) +#' # 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)), -#' byrow=TRUE, ncol=L ) +#' 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( rbind, lapply( 1:6, function(i) -#' do.call(rbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) ) +#' 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, "d8", "rel", nb_series_per_chunk=500) +#' medoids_ascii = claws(series, K1=60, K2=6, 200, 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, "d8", "rel", nb_series_per_chunk=500) +#' medoids_csv = claws(csv_file, K1=60, K2=6, 200) #' #' # 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) +#' 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, 200) #' unlink(csv_file) #' unlink(bin_file) #' @@ -69,8 +105,8 @@ #' library(DBI) #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:") #' # Prepare data.frame in DB-format -#' n = nrow(series) -#' time_values = data.frame( +#' 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)) ) @@ -78,17 +114,17 @@ #' # 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 (" +#' 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, 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) ) +#' 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) #' } -#' medoids_db = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500) +#' medoids_db = claws(getSeries, K1=60, K2=6, 200)) #' dbDisconnect(series_db) #' #' # All computed medoids should be the same: @@ -98,14 +134,16 @@ #' 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$endian, #serialization (write,read) +claws <- function(getSeries, K1, K2, nb_series_per_chunk, + nb_items_clust1=7*K1, + algo_clust1=function(data,K) cluster::pam(data,K,diss=FALSE), + algo_clust2=function(dists,K) stats::kmeans(dists,K,iter.max=50,nstart=3), + wav_filt="d8", contrib_type="absolute", + WER="end", + random=TRUE, + ntasks=1, ncores_tasks=1, ncores_clust=4, + sep=",", + nbytes=4, endian=.Platform$endian, verbose=FALSE, parll=TRUE) { # Check/transform arguments @@ -115,27 +153,46 @@ claws = function(getSeries, K1, K2, { 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 <- wavelets::wt.filter(wf)}, - error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter")) + K1 <- .toInteger(K1, function(x) x>=2) + K2 <- .toInteger(K2, function(x) x>=2) + nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1) + # K1 (number of clusters at step 1) cannot exceed nb_series_per_chunk, because we will need + # to load K1 series in memory for clustering stage 2. + if (K1 > nb_series_per_chunk) + stop("'K1' cannot exceed 'nb_series_per_chunk'") + 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'}") - 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) + 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) + nbytes <- .toInteger(nbytes, function(x) x==4 || x==8) + verbose <- .toLogical(verbose) + parll <- .toLogical(parll) - # Serialize series if required, to always use a function - bin_dir = ".epclust_bin/" + # Since we don't make assumptions on initial data, there is a possibility that even + # when serialized, contributions or synchrones do not fit in RAM. For example, + # 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore, + # it's safer to place these in (binary) files, located in the following folder. + bin_dir <- ".epclust_bin/" dir.create(bin_dir, showWarnings=FALSE, mode="0755") + + # Binarize series if getSeries is not a function; the aim is to always use a function, + # to uniformize treatments. An equally good alternative would be to use a file-backed + # bigmemory::big.matrix, but it would break the uniformity. if (!is.function(getSeries)) { if (verbose) @@ -156,35 +213,66 @@ claws = function(getSeries, K1, K2, 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!") + # A few sanity checks: do not continue if too few data available. + 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 < min_series_per_chunk) - stop("Too many tasks: less series in one task than min_series_per_chunk!") + if (nb_series_per_task < K2) + stop("Too many tasks: less series in one task than final number of clusters") + + # Generate a random permutation of 1:N (if random==TRUE); otherwise just use arrival + # (storage) order. + indices_all = if (random) sample(nb_curves) else seq_len(nb_curves) + # Split (all) indices into ntasks groups of ~same size + indices_tasks = lapply(seq_len(ntasks), function(i) { + upper_bound = ifelse( i1) + { + # Initialize parallel runs: outfile="" allow to output verbose traces in the console + # under Linux. All necessary variables are passed to the workers. + cl = parallel::makeCluster(ncores_tasks, outfile="") + varlist = c("getSeries","getContribs","K1","K2","algo_clust1","algo_clust2", + "nb_series_per_chunk","nb_items_clust","ncores_clust","sep", + "nbytes","endian","verbose","parll") + if (WER=="mix") + varlist = c(varlist, "medoids_file") + parallel::clusterExport(cl, varlist, envir = environment()) + } + + # This function achieves one complete clustering task, divided in stage 1 + stage 2. + # stage 1: n indices --> clusteringTask1(...) --> K1 medoids + # stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids, + # where n = N / ntasks, N being the total number of curves. runTwoStepClustering = function(inds) { + # When running in parallel, the environment is blank: we need to load required + # packages, and pass useful variables. 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") { + 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, ncores_clust, verbose, parll) - binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian) + medoids2 = clusteringTask2(medoids1, K2, getSeries, nb_curves, nb_series_per_chunk, + nbytes, endian, ncores_clust, verbose, parll) + binarize(medoids2, medoids_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( i1) - { - 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) ) + # As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"], + # or nothing (empty vector) if WER=="mix"; in this case, medoids (synchrones) are stored + # in a 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) + # Right before the final stage, two situations are possible: + # a. data to be processed now sit in binary format in medoids_file (if WER=="mix") + # b. data still is the initial set of curves, referenced by the ntasks*K1 indices + # So, the function getSeries() will potentially change. However, computeSynchrones() + # requires a function retrieving the initial series. Thus, the next line saves future + # conditional instructions. getRefSeries = getSeries + 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) - #Contributions must be re-computed + # Now series (synchrones) must be retrieved from medoids_file + getSeries = function(inds) getDataInFile(inds, medoids_file, nbytes, endian) + # Contributions must be re-computed unlink(contribs_file) index = 1 if (verbose) @@ -228,19 +315,24 @@ claws = function(getSeries, K1, K2, contribs_file, nb_series_per_chunk, nbytes, endian) } +#TODO: check THAT + + # 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, ncores_tasks*ncores_clust, verbose, parll) + medoids2 = clusteringTask2(medoids1, K2, getRefSeries, nb_curves, nb_series_per_chunk, + nbytes, endian, ncores_tasks*ncores_clust, verbose, parll) - # Cleanup + # Cleanup: remove temporary binary files and their folder unlink(bin_dir, recursive=TRUE) - medoids2 + # Return medoids as a standard matrix, since K2 series have to fit in RAM + # (clustering algorithm 1 takes K1 > K2 of them as input) + medoids2[,] } #' curvesToContribs @@ -248,36 +340,52 @@ claws = function(getSeries, K1, K2, #' 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 +#' @param series [big.]matrix of series (in columns), of size L x n #' @inheritParams claws #' -#' @return A matrix of size n x log(L) containing contributions in rows +#' @return A [big.]matrix of size log(L) x n containing contributions in columns #' #' @export -curvesToContribs = function(series, wf, ctype) +curvesToContribs = function(series, wav_filt, contrib_type) { - L = length(series[1,]) + L = nrow(series) 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) { + 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 (ctype=="relative") nrj / sum(nrj) else nrj - }) ) + if (contrib_type!="absolute") + nrj = nrj / sum(nrj) + if (contrib_type=="logit") + nrj = - log(1 - nrj) + nrj + }) } # 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]}, - error = function(e) paste("Cannot convert argument",substitute(x),"to integer") - ) + 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))) + { + 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 }