epclust/R/main.R

   1 #' CLAWS: CLustering with wAvelets and Wer distanceS
   2 #'
   3 #' Cluster electricity power curves (or any series of similar nature) by applying a
   4 #' two stage procedure in parallel (see details).
   5 #' Input series must be sampled on the same time grid, no missing values.
   6 #'
   7 #' @details Summary of the function execution flow:
   8 #'   \enumerate{
   9 #'     \item Compute and serialize all contributions, obtained through discrete wavelet
  10 #'       decomposition (see Antoniadis & al. [2013])
  11 #'     \item Divide series into \code{ntasks} groups to process in parallel. In each task:
  12 #'     \enumerate{
  13 #'       \item iterate the first clustering algorithm on its aggregated outputs,
  14 #'         on inputs of size \code{nb_items_clust1}
  15 #'       \item optionally, if WER=="mix":
  16 #'         a) compute the K1 synchrones curves,
  17 #'         b) compute WER distances (K1xK1 matrix) between synchrones and
  18 #'         c) apply the second clustering algorithm
  19 #'     }
  20 #'     \item Launch a final task on the aggregated outputs of all previous tasks:
  21 #'       in the case WER=="end" this task takes indices in input, otherwise
  22 #'       (medoid) curves
  23 #'   }
  24 #'   The main argument -- \code{getSeries} -- has a quite misleading name, since it can be
  25 #'   either a [big.]matrix, a CSV file, a connection or a user function to retrieve
  26 #'   series; the name was chosen because all types of arguments are converted to a function.
  27 #'   When \code{getSeries} is given as a function, it must take a single argument,
  28 #'   'indices', integer vector equal to the indices of the curves to retrieve;
  29 #'   see SQLite example. The nature and role of other arguments should be clear
  30 #'
  31 #' @param getSeries Access to the (time-)series, which can be of one of the three
  32 #'   following types:
  33 #'   \itemize{
  34 #'     \item [big.]matrix: each column contains the (time-ordered) values of one time-serie
  35 #'     \item connection: any R connection object providing lines as described above
  36 #'     \item character: name of a CSV file containing series in rows (no header)
  37 #'     \item function: a custom way to retrieve the curves; it has only one argument:
  38 #'       the indices of the series to be retrieved. See SQLite example
  39 #'   }
  40 #' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series])
  41 #' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
  42 #' @param nb_series_per_chunk (Maximum) number of series to retrieve in one batch
  43 #' @param algoClust1 Clustering algorithm for stage 1. A function which takes (data, K)
  44 #'   as argument where data is a matrix in columns and K the desired number of clusters,
  45 #'   and outputs K medoids ranks. Default: PAM.
  46 #'   In our method, this function is called on iterated medoids during stage 1
  47 #' @param algoClust2 Clustering algorithm for stage 2. A function which takes (dists, K)
  48 #'   as argument where dists is a matrix of distances and K the desired number of clusters,
  49 #'   and outputs K clusters representatives (curves). Default: PAM.
  50 #'   In our method, this function is called on a matrix of K1 x K1 (WER) distances computed
  51 #    between synchrones
  52 #' @param nb_items_clust1 (~Maximum) number of items in input of the clustering algorithm
  53 #'   for stage 1. At worst, a clustering algorithm might be called with ~2*nb_items_clust1
  54 #'   items; but this could only happen at the last few iterations.
  55 #' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter
  56 #' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix)
  57 #' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply
  58 #'   stage 2 at the end of each task
  59 #' @param sync_mean TRUE to compute a synchrone as a mean curve, FALSE for a sum
  60 #' @param random TRUE (default) for random chunks repartition
  61 #' @param ntasks Number of tasks (parallel iterations to obtain K1 [if WER=="end"]
  62 #'   or K2 [if WER=="mix"] medoids); default: 1.
  63 #'   Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks
  64 #' @param ncores_tasks Number of parallel tasks (1 to disable: sequential tasks)
  65 #' @param ncores_clust Number of parallel clusterings in one task (4 should be a minimum)
  66 #' @param sep Separator in CSV input file (if any provided)
  67 #' @param nbytes Number of bytes to serialize a floating-point number; 4 or 8
  68 #' @param endian Endianness for (de)serialization ("little" or "big")
  69 #' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
  70 #' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
  71 #'
  72 #' @return A matrix of the final K2 medoids curves, in columns
  73 #'
  74 #' @references Clustering functional data using Wavelets [2013];
  75 #'   A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi.
  76 #'   Inter. J. of Wavelets, Multiresolution and Information Procesing,
  77 #'   vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033
  78 #'
  79 #' @examples
  80 #' \dontrun{
  81 #' # WER distances computations are too long for CRAN (for now)
  82 #'
  83 #' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
  84 #' x = seq(0,500,0.05)
  85 #' L = length(x) #10001
  86 #' ref_series = matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 )
  87 #' library(wmtsa)
  88 #' series = do.call( cbind, lapply( 1:6, function(i)
  89 #'   do.call(cbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
  90 #' #dim(series) #c(2400,10001)
  91 #' medoids_ascii = claws(series, K1=60, K2=6, 200, verbose=TRUE)
  92 #'
  93 #' # Same example, from CSV file
  94 #' csv_file = "/tmp/epclust_series.csv"
  95 #' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
  96 #' medoids_csv = claws(csv_file, K1=60, K2=6, 200)
  97 #'
  98 #' # Same example, from binary file
  99 #' bin_file <- "/tmp/epclust_series.bin"
 100 #' nbytes <- 8
 101 #' endian <- "little"
 102 #' binarize(csv_file, bin_file, 500, nbytes, endian)
 103 #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian)
 104 #' medoids_bin <- claws(getSeries, K1=60, K2=6, 200)
 105 #' unlink(csv_file)
 106 #' unlink(bin_file)
 107 #'
 108 #' # Same example, from SQLite database
 109 #' library(DBI)
 110 #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
 111 #' # Prepare data.frame in DB-format
 112 #' n <- nrow(series)
 113 #' time_values <- data.frame(
 114 #'   id = rep(1:n,each=L),
 115 #'   time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
 116 #'   value = as.double(t(series)) )
 117 #' dbWriteTable(series_db, "times_values", times_values)
 118 #' # Fill associative array, map index to identifier
 119 #' indexToID_inDB <- as.character(
 120 #'   dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
 121 #' serie_length <- as.integer( dbGetQuery(series_db,
 122 #'   paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) )
 123 #' getSeries <- function(indices) {
 124 #'   request <- "SELECT id,value FROM times_values WHERE id in ("
 125 #'   for (i in indices)
 126 #'     request <- paste(request, indexToID_inDB[i], ",", sep="")
 127 #'   request <- paste(request, ")", sep="")
 128 #'   df_series <- dbGetQuery(series_db, request)
 129 #'   as.matrix(df_series[,"value"], nrow=serie_length)
 130 #' }
 131 #' medoids_db = claws(getSeries, K1=60, K2=6, 200))
 132 #' dbDisconnect(series_db)
 133 #'
 134 #' # All computed medoids should be the same:
 135 #' digest::sha1(medoids_ascii)
 136 #' digest::sha1(medoids_csv)
 137 #' digest::sha1(medoids_bin)
 138 #' digest::sha1(medoids_db)
 139 #' }
 140 #' @export
 141 claws <- function(getSeries, K1, K2, nb_series_per_chunk,
 142     nb_items_clust1=7*K1,
 143     algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE)$id.med,
 144     algoClust2=function(dists,K) t( cluster::pam(dists,K,diss=TRUE)$medoids ),
 145     wav_filt="d8", contrib_type="absolute",
 146     WER="end",sync_mean=TRUE,
 147     random=TRUE,
 148     ntasks=1, ncores_tasks=1, ncores_clust=4,
 149     sep=",",
 150     nbytes=4, endian=.Platform$endian,
 151     verbose=FALSE, parll=TRUE)
 152 {
 153     # Check/transform arguments
 154     if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
 155         && !is.function(getSeries)
 156         && !methods::is(getSeries,"connection") && !is.character(getSeries))
 157     {
 158         stop("'getSeries': [big]matrix, function, file or valid connection (no NA)")
 159     }
 160     K1 <- .toInteger(K1, function(x) x>=2)
 161     K2 <- .toInteger(K2, function(x) x>=2)
 162     nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1)
 163     # K1 (number of clusters at step 1) cannot exceed nb_series_per_chunk, because we will need
 164     # to load K1 series in memory for clustering stage 2.
 165     if (K1 > nb_series_per_chunk)
 166         stop("'K1' cannot exceed 'nb_series_per_chunk'")
 167     nb_items_clust1 <- .toInteger(nb_items_clust1, function(x) x>K1)
 168     random <- .toLogical(random)
 169     tryCatch( {ignored <- wavelets::wt.filter(wav_filt)},
 170         error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") )
 171     ctypes = c("relative","absolute","logit")
 172     contrib_type = ctypes[ pmatch(contrib_type,ctypes) ]
 173     if (is.na(contrib_type))
 174         stop("'contrib_type' in {'relative','absolute','logit'}")
 175     if (WER!="end" && WER!="mix")
 176         stop("'WER': in {'end','mix'}")
 177     sync_mean <- .toLogical(sync_mean)
 178     random <- .toLogical(random)
 179     ntasks <- .toInteger(ntasks, function(x) x>=1)
 180     ncores_tasks <- .toInteger(ncores_tasks, function(x) x>=1)
 181     ncores_clust <- .toInteger(ncores_clust, function(x) x>=1)
 182     if (!is.character(sep))
 183         stop("'sep': character")
 184     nbytes <- .toInteger(nbytes, function(x) x==4 || x==8)
 185     verbose <- .toLogical(verbose)
 186     parll <- .toLogical(parll)
 187
 188     # Since we don't make assumptions on initial data, there is a possibility that even
 189     # when serialized, contributions or synchrones do not fit in RAM. For example,
 190     # 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore,
 191     # it's safer to place these in (binary) files, located in the following folder.
 192     bin_dir <- ".epclust_bin/"
 193     dir.create(bin_dir, showWarnings=FALSE, mode="0755")
 194
 195     # Binarize series if getSeries is not a function; the aim is to always use a function,
 196     # to uniformize treatments. An equally good alternative would be to use a file-backed
 197     # bigmemory::big.matrix, but it would break the uniformity.
 198     if (!is.function(getSeries))
 199     {
 200         if (verbose)
 201             cat("...Serialize time-series\n")
 202         series_file = paste(bin_dir,"data",sep="") ; unlink(series_file)
 203         binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
 204         getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
 205     }
 206
 207     # Serialize all computed wavelets contributions into a file
 208     contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file)
 209     index = 1
 210     nb_curves = 0
 211     if (verbose)
 212         cat("...Compute contributions and serialize them\n")
 213     nb_curves = binarizeTransform(getSeries,
 214         function(series) curvesToContribs(series, wf, ctype),
 215         contribs_file, nb_series_per_chunk, nbytes, endian)
 216     getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
 217
 218     # A few sanity checks: do not continue if too few data available.
 219     if (nb_curves < K2)
 220         stop("Not enough data: less series than final number of clusters")
 221     nb_series_per_task = round(nb_curves / ntasks)
 222     if (nb_series_per_task < K2)
 223         stop("Too many tasks: less series in one task than final number of clusters")
 224
 225     # Generate a random permutation of 1:N (if random==TRUE); otherwise just use arrival
 226     # (storage) order.
 227     indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
 228     # Split (all) indices into ntasks groups of ~same size
 229     indices_tasks = lapply(seq_len(ntasks), function(i) {
 230         upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
 231         indices_all[((i-1)*nb_series_per_task+1):upper_bound]
 232     })
 233
 234     if (parll && ntasks>1)
 235     {
 236         # Initialize parallel runs: outfile="" allow to output verbose traces in the console
 237         # under Linux. All necessary variables are passed to the workers.
 238         cl = parallel::makeCluster(ncores_tasks, outfile="")
 239         varlist = c("getSeries","getContribs","K1","K2","algoClust1","algoClust2",
 240             "nb_series_per_chunk","nb_items_clust1","ncores_clust","sep",
 241             "nbytes","endian","verbose","parll")
 242         if (WER=="mix")
 243             varlist = c(varlist, "medoids_file")
 244         parallel::clusterExport(cl, varlist, envir = environment())
 245     }
 246
 247     # This function achieves one complete clustering task, divided in stage 1 + stage 2.
 248     # stage 1: n indices  --> clusteringTask1(...) --> K1 medoids
 249     # stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids,
 250     # where n = N / ntasks, N being the total number of curves.
 251     runTwoStepClustering = function(inds)
 252     {
 253         # When running in parallel, the environment is blank: we need to load required
 254         # packages, and pass useful variables.
 255         if (parll && ntasks>1)
 256             require("epclust", quietly=TRUE)
 257         indices_medoids = clusteringTask1(
 258             inds, getContribs, K1, algoClust1, nb_series_per_chunk, ncores_clust, verbose, parll)
 259         if (WER=="mix")
 260         {
 261             if (parll && ntasks>1)
 262                 require("bigmemory", quietly=TRUE)
 263             medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
 264             medoids2 = clusteringTask2(medoids1, K2, algoClust2, getSeries, nb_curves,
 265                 nb_series_per_chunk, sync_mean, nbytes, endian, ncores_clust, verbose, parll)
 266             binarize(medoids2, medoids_file, nb_series_per_chunk, sep, nbytes, endian)
 267             return (vector("integer",0))
 268         }
 269         indices_medoids
 270     }
 271
 272     # Synchrones (medoids) need to be stored only if WER=="mix"; indeed in this case, every
 273     # task output is a set of new (medoids) curves. If WER=="end" however, output is just a
 274     # set of indices, representing some initial series.
 275     if (WER=="mix")
 276         {medoids_file = paste(bin_dir,"medoids",sep="") ; unlink(medoids_file)}
 277
 278     if (verbose)
 279     {
 280         message = paste("...Run ",ntasks," x stage 1", sep="")
 281         if (WER=="mix")
 282             message = paste(message," + stage 2", sep="")
 283         cat(paste(message,"\n", sep=""))
 284     }
 285
 286     # As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"],
 287     # or nothing (empty vector) if WER=="mix"; in this case, medoids (synchrones) are stored
 288     # in a file.
 289     indices <-
 290         if (parll && ntasks>1)
 291             unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
 292         else
 293             unlist( lapply(indices_tasks, runTwoStepClustering) )
 294     if (parll && ntasks>1)
 295         parallel::stopCluster(cl)
 296
 297     # Right before the final stage, two situations are possible:
 298     #  a. data to be processed now sit in binary format in medoids_file (if WER=="mix")
 299     #  b. data still is the initial set of curves, referenced by the ntasks*K1 indices
 300     # So, the function getSeries() will potentially change. However, computeSynchrones()
 301     # requires a function retrieving the initial series. Thus, the next line saves future
 302     # conditional instructions.
 303     getRefSeries = getSeries
 304
 305     if (WER=="mix")
 306     {
 307         indices = seq_len(ntasks*K2)
 308         # Now series (synchrones) must be retrieved from medoids_file
 309         getSeries = function(inds) getDataInFile(inds, medoids_file, nbytes, endian)
 310         # Contributions must be re-computed
 311         unlink(contribs_file)
 312         index = 1
 313         if (verbose)
 314             cat("...Serialize contributions computed on synchrones\n")
 315         ignored = binarizeTransform(getSeries,
 316             function(series) curvesToContribs(series, wf, ctype),
 317             contribs_file, nb_series_per_chunk, nbytes, endian)
 318     }
 319
 320 #TODO: check THAT
 321
 322
 323     # Run step2 on resulting indices or series (from file)
 324     if (verbose)
 325         cat("...Run final // stage 1 + stage 2\n")
 326     indices_medoids = clusteringTask1(indices, getContribs, K1, algoClust1,
 327         nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
 328     medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
 329     medoids2 = clusteringTask2(medoids1, K2, algoClust2, getRefSeries, nb_curves,
 330         nb_series_per_chunk, sync_mean, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
 331
 332     # Cleanup: remove temporary binary files and their folder
 333     unlink(bin_dir, recursive=TRUE)
 334
 335     # Return medoids as a standard matrix, since K2 series have to fit in RAM
 336     # (clustering algorithm 1 takes K1 > K2 of them as input)
 337     medoids2[,]
 338 }
 339
 340 #' curvesToContribs
 341 #'
 342 #' Compute the discrete wavelet coefficients for each series, and aggregate them in
 343 #' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2
 344 #'
 345 #' @param series [big.]matrix of series (in columns), of size L x n
 346 #' @inheritParams claws
 347 #'
 348 #' @return A [big.]matrix of size log(L) x n containing contributions in columns
 349 #'
 350 #' @export
 351 curvesToContribs = function(series, wav_filt, contrib_type)
 352 {
 353     L = nrow(series)
 354     D = ceiling( log2(L) )
 355     nb_sample_points = 2^D
 356     apply(series, 2, function(x) {
 357         interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
 358         W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
 359         nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
 360         if (contrib_type!="absolute")
 361             nrj = nrj / sum(nrj)
 362         if (contrib_type=="logit")
 363             nrj = - log(1 - nrj)
 364         nrj
 365     })
 366 }
 367
 368 # Check integer arguments with functional conditions
 369 .toInteger <- function(x, condition)
 370 {
 371     errWarn <- function(ignored)
 372         paste("Cannot convert argument' ",substitute(x),"' to integer", sep="")
 373     if (!is.integer(x))
 374         tryCatch({x = as.integer(x)[1]; if (is.na(x)) stop()},
 375             warning = errWarn, error = errWarn)
 376     if (!condition(x))
 377     {
 378         stop(paste("Argument '",substitute(x),
 379             "' does not verify condition ",body(condition), sep=""))
 380     }
 381     x
 382 }
 383
 384 # Check logical arguments
 385 .toLogical <- function(x)
 386 {
 387     errWarn <- function(ignored)
 388         paste("Cannot convert argument' ",substitute(x),"' to logical", sep="")
 389     if (!is.logical(x))
 390         tryCatch({x = as.logical(x)[1]; if (is.na(x)) stop()},
 391             warning = errWarn, error = errWarn)
 392     x
 393 }