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