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 #' 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, in columns
  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=3, verbose=FALSE, parll=TRUE)
  27 {
  28     if (parll)
  29     {
  30         # outfile=="" to see stderr/stdout on terminal
  31         cl <-
  32             if (verbose)
  33                 parallel::makeCluster(ncores_clust, outfile = "")
  34             else
  35                 parallel::makeCluster(ncores_clust)
  36         parallel::clusterExport(cl, c("getContribs","K1","verbose"), envir=environment())
  37     }
  38     # Iterate clustering algorithm 1 until K1 medoids are found
  39     while (length(indices) > K1)
  40     {
  41         # Balance tasks by splitting the indices set - as evenly as possible
  42         indices_workers <- .splitIndices(indices, nb_items_clust, min_size=K1+1)
  43         if (verbose)
  44             cat(paste("*** [iterated] Clustering task 1 on ",length(indices)," series\n", sep=""))
  45         indices <-
  46             if (parll)
  47             {
  48                 unlist( parallel::parLapply(cl, indices_workers, function(inds) {
  49                     require("epclust", quietly=TRUE)
  50                     inds[ algoClust1(getContribs(inds), K1) ]
  51                 }) )
  52             }
  53             else
  54             {
  55                 unlist( lapply(indices_workers, function(inds)
  56                     inds[ algoClust1(getContribs(inds), K1) ]
  57                 ) )
  58             }
  59     }
  60     if (parll)
  61         parallel::stopCluster(cl)
  62
  63     indices #medoids
  64 }
  65
  66 #' @rdname clustering
  67 #' @export
  68 clusteringTask2 <- function(indices, getSeries, K2, algoClust2, nb_series_per_chunk,
  69     smooth_lvl, nvoice, nbytes, endian, ncores_clust=3, verbose=FALSE, parll=TRUE)
  70 {
  71     if (verbose)
  72         cat(paste("*** Clustering task 2 on ",length(indices)," medoids\n", sep=""))
  73
  74     if (length(indices) <= K2)
  75         return (indices)
  76
  77     # A) Compute the WER distances (Wavelets Extended coefficient of deteRmination)
  78     distances <- computeWerDists(indices, getSeries, nb_series_per_chunk,
  79         smooth_lvl, nvoice, nbytes, endian, ncores_clust, verbose, parll)
  80
  81     # B) Apply clustering algorithm 2 on the WER distances matrix
  82     if (verbose)
  83         cat(paste("*** algoClust2() on ",nrow(distances)," items\n", sep=""))
  84     indices[ algoClust2(distances,K2) ]
  85 }