epclust/R/clustering.R

   1 #' Two-stage clustering, within one task (see \code{claws()})
   2 #'
   3 #' \code{clusteringTask1()} runs one full stage-1 task, which consists in iterated
   4 #' stage 1 clustering on nb_curves / ntasks energy contributions, computed through
   5 #' discrete wavelets coefficients.
   6 #' \code{clusteringTask2()} runs a full stage-2 task, which consists in WER distances
   7 #' computations between medoids (indices) output from stage 1, before applying
   8 #' the second clustering algorithm on the distances matrix.
   9 #'
  10 #' @param getContribs Function to retrieve contributions from initial series indices:
  11 #'   \code{getContribs(indices)} outputs a contributions matrix
  12 #' @inheritParams claws
  13 #' @inheritParams computeSynchrones
  14 #' @inheritParams computeWerDists
  15 #'
  16 #' @return The indices of the computed (resp. K1 and K2) medoids.
  17 #'
  18 #' @name clustering
  19 #' @rdname clustering
  20 #' @aliases clusteringTask1 clusteringTask2
  21 NULL
  22
  23 #' @rdname clustering
  24 #' @export
  25 clusteringTask1 <- function(indices, getContribs, K1, algoClust1, nb_items_clust,
  26     ncores_clust=1, verbose=FALSE, parll=TRUE)
  27 {
  28     if (parll)
  29     {
  30         # outfile=="" to see stderr/stdout on terminal
  31         cl <- parallel::makeCluster(ncores_clust, outfile = "")
  32         parallel::clusterExport(cl, c("getContribs","K1","verbose"), envir=environment())
  33     }
  34     # Iterate clustering algorithm 1 until K1 medoids are found
  35     while (length(indices) > K1)
  36     {
  37         # Balance tasks by splitting the indices set - as evenly as possible
  38         indices_workers <- .splitIndices(indices, nb_items_clust, min_size=K1+1)
  39         if (verbose)
  40             cat(paste("*** [iterated] Clustering task 1 on ",length(indices)," series\n", sep=""))
  41         indices <-
  42             if (parll)
  43             {
  44                 unlist( parallel::parLapply(cl, indices_workers, function(inds) {
  45                     require("epclust", quietly=TRUE)
  46                     inds[ algoClust1(getContribs(inds), K1) ]
  47                 }) )
  48             }
  49             else
  50             {
  51                 unlist( lapply(indices_workers, function(inds)
  52                     inds[ algoClust1(getContribs(inds), K1) ]
  53                 ) )
  54             }
  55     }
  56     if (parll)
  57         parallel::stopCluster(cl)
  58
  59     indices #medoids
  60 }
  61
  62 #' @rdname clustering
  63 #' @export
  64 clusteringTask2 <- function(indices, getSeries, K2, algoClust2, nb_series_per_chunk,
  65     smooth_lvl, nvoice, nbytes, endian, ncores_clust=1, verbose=FALSE, parll=TRUE)
  66 {
  67     if (verbose)
  68         cat(paste("*** Clustering task 2 on ",length(indices)," medoids\n", sep=""))
  69
  70     if (length(indices) <= K2)
  71         return (indices)
  72
  73     # A) Compute the WER distances (Wavelets Extended coefficient of deteRmination)
  74     distances <- computeWerDists(indices, getSeries, nb_series_per_chunk,
  75         smooth_lvl, nvoice, nbytes, endian, ncores_clust, verbose, parll)
  76
  77     # B) Apply clustering algorithm 2 on the WER distances matrix
  78     if (verbose)
  79         cat(paste("*** algoClust2() on ",nrow(distances)," items\n", sep=""))
  80     indices[ algoClust2(distances,K2) ]
  81 }