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 #' 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_clust}\cr
  15 #'         -> K1 medoids indices
  16 #'     \item optionally, if WER=="mix":\cr
  17 #'       a. compute WER distances (K1xK1) between medoids\cr
  18 #'       b. apply the 2nd clustering algorithm\cr
  19 #'          -> K2 medoids indices
  20 #'   }
  21 #'   \item Launch a final task on the aggregated outputs of all previous tasks:
  22 #'     ntasks*K1 if WER=="end", ntasks*K2 otherwise
  23 #'   \item Compute synchrones (sum of series within each final group)
  24 #' }
  25 #'
  26 #' The main argument -- \code{series} -- has a quite misleading name, since it can be
  27 #' either a [big.]matrix, a CSV file, a connection or a user function to retrieve series.
  28 #' When \code{series} is given as a function it must take a single argument,
  29 #' 'indices': integer vector equal to the indices of the curves to retrieve;
  30 #' see SQLite example.
  31 #' WARNING: the return value must be a matrix (in columns), or NULL if no matches.
  32 #'
  33 #' Note: Since we don't make assumptions on initial data, there is a possibility that
  34 #' even when serialized, contributions do not fit in RAM. For example,
  35 #' 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore,
  36 #' it's safer to place these in (binary) files; that's what we do.
  37 #'
  38 #' @param series Access to the N (time-)series, which can be of one of the four
  39 #'   following types:
  40 #'   \itemize{
  41 #'     \item [big.]matrix: each column contains the (time-ordered) values of one time-serie
  42 #'     \item connection: any R connection object providing lines as described above
  43 #'     \item character: name of a CSV file containing series in rows (no header)
  44 #'     \item function: a custom way to retrieve the curves; it has only one argument:
  45 #'       the indices of the series to be retrieved. See SQLite example
  46 #'   }
  47 #' @param K1 Number of clusters to be found after stage 1 (K1 << N)
  48 #' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
  49 #' @param nb_series_per_chunk Number of series to retrieve in one batch
  50 #' @param nb_items_clust Number of items in 1st clustering algorithm input
  51 #' @param algoClust1 Clustering algorithm for stage 1. A function which takes (data, K)
  52 #'   as argument where data is a matrix in columns and K the desired number of clusters,
  53 #'   and outputs K medoids ranks. Default: PAM.
  54 #' @param algoClust2 Clustering algorithm for stage 2. A function which takes (dists, K)
  55 #'   as argument where dists is a matrix of distances and K the desired number of clusters,
  56 #'   and outputs K medoids ranks. Default: PAM.
  57 #' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter
  58 #' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix)
  59 #' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply
  60 #'   stage 2 at the end of each task
  61 #' @param smooth_lvl Smoothing level: odd integer, 1 == no smoothing.
  62 #' @param nvoice Number of voices within each octave for CWT computations
  63 #' @param random TRUE (default) for random chunks repartition
  64 #' @param ntasks Number of tasks (parallel iterations to obtain K1 [if WER=="end"]
  65 #'   or K2 [if WER=="mix"] medoids); default: 1.
  66 #'   Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks
  67 #' @param ncores_tasks Number of parallel tasks ('1' == sequential tasks)
  68 #' @param ncores_clust Number of parallel clusterings in one task
  69 #' @param sep Separator in CSV input file (if any provided)
  70 #' @param nbytes Number of bytes to serialize a floating-point number: 4 or 8
  71 #' @param endian Endianness for (de)serialization: "little" or "big"
  72 #' @param verbose FALSE: nothing printed; TRUE: some execution traces
  73 #' @param parll TRUE: run in parallel. FALSE: run sequentially
  74 #'
  75 #' @return A list:
  76 #' \itemize{
  77 #'   \item medoids: matrix of the final K2 medoids curves
  78 #'   \item ranks: corresponding indices in the dataset
  79 #'   \item synchrones: sum of series within each final group
  80 #' }
  81 #'
  82 #' @references Clustering functional data using Wavelets [2013];
  83 #'   A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi.
  84 #'   Inter. J. of Wavelets, Multiresolution and Information Procesing,
  85 #'   vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033
  86 #'
  87 #' @examples
  88 #' \dontrun{
  89 #' # WER distances computations are too long for CRAN (for now)
  90 #'
  91 #' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
  92 #' x <- seq(0,50,0.05)
  93 #' L <- length(x) #1001
  94 #' ref_series <- matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 )
  95 #' library(wmtsa)
  96 #' series <- do.call( cbind, lapply( 1:6, function(i)
  97 #'   do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=40)) ) )
  98 #' #dim(series) #c(240,1001)
  99 #' res_ascii <- claws(series, K1=30, K2=6, 100, verbose=TRUE)
 100 #'
 101 #' # Same example, from CSV file
 102 #' csv_file <- tempfile(pattern="epclust_series.csv_")
 103 #' write.table(t(series), csv_file, sep=",", row.names=FALSE, col.names=FALSE)
 104 #' res_csv <- claws(csv_file, K1=30, K2=6, 100)
 105 #'
 106 #' # Same example, from binary file
 107 #' bin_file <- tempfile(pattern="epclust_series.bin_")
 108 #' nbytes <- 8
 109 #' endian <- "little"
 110 #' binarize(csv_file, bin_file, 500, nbytes, endian)
 111 #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian)
 112 #' res_bin <- claws(getSeries, K1=30, K2=6, 100)
 113 #' unlink(csv_file)
 114 #' unlink(bin_file)
 115 #'
 116 #' # Same example, from SQLite database
 117 #' library(DBI)
 118 #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
 119 #' # Prepare data.frame in DB-format
 120 #' n <- nrow(series)
 121 #' time_values <- data.frame(
 122 #'   id <- rep(1:n,each=L),
 123 #'   time <- rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
 124 #'   value <- as.double(t(series)) )
 125 #' dbWriteTable(series_db, "times_values", times_values)
 126 #' # Fill associative array, map index to identifier
 127 #' indexToID_inDB <- as.character(
 128 #'   dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
 129 #' serie_length <- as.integer( dbGetQuery(series_db,
 130 #'   paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) )
 131 #' getSeries <- function(indices) {
 132 #'   request <- "SELECT id,value FROM times_values WHERE id in ("
 133 #'   for (i in indices)
 134 #'     request <- paste(request, indexToID_inDB[i], ",", sep="")
 135 #'   request <- paste(request, ")", sep="")
 136 #'   df_series <- dbGetQuery(series_db, request)
 137 #'   if (length(df_series) >= 1)
 138 #'     as.matrix(df_series[,"value"], nrow=serie_length)
 139 #'   else
 140 #'     NULL
 141 #' }
 142 #' res_db <- claws(getSeries, K1=30, K2=6, 100))
 143 #' dbDisconnect(series_db)
 144 #'
 145 #' # All results should be the same:
 146 #' library(digest)
 147 #' digest::sha1(res_ascii)
 148 #' digest::sha1(res_csv)
 149 #' digest::sha1(res_bin)
 150 #' digest::sha1(res_db)
 151 #' }
 152 #' @export
 153 claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1,
 154     algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE,pamonce=1)$id.med,
 155     algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE,pamonce=1)$id.med,
 156     wav_filt="d8", contrib_type="absolute", WER="end", smooth_lvl=3, nvoice=4,
 157     random=TRUE, ntasks=1, ncores_tasks=1, ncores_clust=3, sep=",", nbytes=4,
 158     endian=.Platform$endian, verbose=FALSE, parll=TRUE)
 159 {
 160     # Check/transform arguments
 161     if (!is.matrix(series) && !bigmemory::is.big.matrix(series)
 162         && !is.function(series)
 163         && !methods::is(series,"connection") && !is.character(series))
 164     {
 165         stop("'series': [big]matrix, function, file or valid connection (no NA)")
 166     }
 167     K1 <- .toInteger(K1, function(x) x>=2)
 168     K2 <- .toInteger(K2, function(x) x>=2)
 169     nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1)
 170     nb_items_clust <- .toInteger(nb_items_clust, function(x) x>K1)
 171     random <- .toLogical(random)
 172     tryCatch({ignored <- wavelets::wt.filter(wav_filt)},
 173         error=function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") )
 174     ctypes <- c("relative","absolute","logit")
 175     contrib_type <- ctypes[ pmatch(contrib_type,ctypes) ]
 176     if (is.na(contrib_type))
 177         stop("'contrib_type' in {'relative','absolute','logit'}")
 178     if (WER!="end" && WER!="mix")
 179         stop("'WER': in {'end','mix'}")
 180     random <- .toLogical(random)
 181     ntasks <- .toInteger(ntasks, function(x) x>=1)
 182     ncores_tasks <- .toInteger(ncores_tasks, function(x) x>=1)
 183     ncores_clust <- .toInteger(ncores_clust, function(x) x>=1)
 184     if (!is.character(sep))
 185         stop("'sep': character")
 186     nbytes <- .toInteger(nbytes, function(x) x==4 || x==8)
 187     verbose <- .toLogical(verbose)
 188     parll <- .toLogical(parll)
 189
 190     # Binarize series if it is not a function; the aim is to always use a function,
 191     # to uniformize treatments. An equally good alternative would be to use a file-backed
 192     # bigmemory::big.matrix, but it would break the "all-is-function" pattern.
 193     if (!is.function(series))
 194     {
 195         if (verbose)
 196             cat("...Serialize time-series (or retrieve past binary file)\n")
 197         series_file <- ".series.epclust.bin"
 198         if (!file.exists(series_file))
 199             binarize(series, series_file, nb_series_per_chunk, sep, nbytes, endian)
 200         getSeries <- function(inds) getDataInFile(inds, series_file, nbytes, endian)
 201     }
 202     else
 203         getSeries <- series
 204
 205     # Serialize all computed wavelets contributions into a file
 206     contribs_file <- ".contribs.epclust.bin"
 207     index <- 1
 208     nb_curves <- 0
 209     if (verbose)
 210         cat("...Compute contributions and serialize them (or retrieve past binary file)\n")
 211     if (!file.exists(contribs_file))
 212     {
 213         nb_curves <- binarizeTransform(getSeries,
 214             function(curves) curvesToContribs(curves, wav_filt, contrib_type),
 215             contribs_file, nb_series_per_chunk, nbytes, endian)
 216     }
 217     else
 218     {
 219         # TODO: duplicate from getDataInFile() in de_serialize.R
 220         contribs_size <- file.info(contribs_file)$size #number of bytes in the file
 221         contrib_length <- readBin(contribs_file, "integer", n=1, size=8, endian=endian)
 222         nb_curves <- (contribs_size-8) / (nbytes*contrib_length)
 223     }
 224     getContribs <- function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
 225
 226     # A few sanity checks: do not continue if too few data available.
 227     if (nb_curves < K2)
 228         stop("Not enough data: less series than final number of clusters")
 229     nb_series_per_task <- round(nb_curves / ntasks)
 230     if (nb_series_per_task < K2)
 231         stop("Too many tasks: less series in one task than final number of clusters")
 232
 233     # Generate a random permutation of 1:N (if random==TRUE);
 234     # otherwise just use arrival (storage) order.
 235     indices_all <- if (random) sample(nb_curves) else seq_len(nb_curves)
 236     # Split (all) indices into ntasks groups of ~same size
 237     indices_tasks <- lapply(seq_len(ntasks), function(i) {
 238         upper_bound <- ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
 239         indices_all[((i-1)*nb_series_per_task+1):upper_bound]
 240     })
 241
 242     if (parll && ntasks>1)
 243     {
 244         # Initialize parallel runs: outfile="" allow to output verbose traces in the console
 245         # under Linux. All necessary variables are passed to the workers.
 246         cl <-
 247             if (verbose)
 248                 parallel::makeCluster(ncores_tasks, outfile="")
 249             else
 250                 parallel::makeCluster(ncores_tasks)
 251         varlist <- c("ncores_clust","verbose","parll", #task 1 & 2
 252             "K1","getContribs","algoClust1","nb_items_clust") #task 1
 253         if (WER=="mix")
 254         {
 255             # Add variables for task 2
 256             varlist <- c(varlist, "K2","getSeries","algoClust2","nb_series_per_chunk",
 257                 "smooth_lvl","nvoice","nbytes","endian")
 258         }
 259         parallel::clusterExport(cl, varlist, envir <- environment())
 260     }
 261
 262     # This function achieves one complete clustering task, divided in stage 1 + stage 2.
 263     # stage 1: n indices  --> clusteringTask1(...) --> K1 medoids (indices)
 264     # stage 2: K1 indices --> K1xK1 WER distances --> clusteringTask2(...) --> K2 medoids,
 265     # where n == N / ntasks, N being the total number of curves.
 266     runTwoStepClustering <- function(inds)
 267     {
 268         # When running in parallel, the environment is blank: we need to load the required
 269         # packages, and pass useful variables.
 270         if (parll && ntasks>1)
 271             require("epclust", quietly=TRUE)
 272         indices_medoids <- clusteringTask1(inds, getContribs, K1, algoClust1,
 273             nb_items_clust, ncores_clust, verbose, parll)
 274         if (WER=="mix")
 275         {
 276             indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2,
 277                 nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_clust,verbose,parll)
 278         }
 279         indices_medoids
 280     }
 281
 282     if (verbose)
 283     {
 284         message <- paste("...Run ",ntasks," x stage 1", sep="")
 285         if (WER=="mix")
 286             message <- paste(message," + stage 2", sep="")
 287         cat(paste(message,"\n", sep=""))
 288     }
 289
 290     # As explained above, we obtain after all runs ntasks*[K1 or K2] medoids indices,
 291     # depending wether WER=="end" or "mix", respectively.
 292     indices_medoids_all <-
 293         if (parll && ntasks>1)
 294             unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
 295         else
 296             unlist( lapply(indices_tasks, runTwoStepClustering) )
 297
 298     if (parll && ntasks>1)
 299         parallel::stopCluster(cl)
 300
 301     # For the last stage, ncores_tasks*(ncores_clusts+1) cores should be available:
 302     #  - ntasks for level 1 parallelism
 303     #  - ntasks*ncores_clust for level 2 parallelism,
 304     # but since an extension MPI <--> tasks / OpenMP <--> sub-tasks is on the way,
 305     # it's better to just re-use ncores_clust
 306     ncores_last_stage <- ncores_clust
 307
 308
 309
 310 #TODO: here, save all inputs to clusteringTask2 and compare :: must have differences...
 311
 312
 313
 314     # Run last clustering tasks to obtain only K2 medoids indices
 315     if (verbose)
 316         cat("...Run final // stage 1 + stage 2\n")
 317     indices_medoids <- clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1,
 318         nb_items_clust, ncores_tasks*ncores_clust, verbose, parll)
 319     indices_medoids <- clusteringTask2(indices_medoids, getContribs, K2, algoClust2,
 320         nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose,parll)
 321
 322     # Compute synchrones, that is to say the cumulated power consumptions for each of the K2
 323     # final groups.
 324     medoids <- getSeries(indices_medoids)
 325     synchrones <- computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk,
 326         ncores_last_stage, verbose, parll)
 327
 328     # NOTE: no need to use big.matrix here, since there are only K2 << K1 << N remaining curves
 329     list("medoids"=medoids, "ranks"=indices_medoids, "synchrones"=synchrones)
 330 }