epclust/R/main.R

   1 #' @title Cluster power curves with PAM in parallel
   2 #'
   3 #' @description Groups electricity power curves (or any series of similar nature) by applying PAM
   4 #' algorithm in parallel to chunks of size \code{nb_series_per_chunk}
   5 #'
   6 #' @param data Access to the data, which can be of one of the three following types:
   7 #' \itemize{
   8 #'   \item data.frame: each line contains its ID in the first cell, and all values after
   9 #'   \item connection: any R connection object (e.g. a file) providing lines as described above
  10 #'   \item function: a custom way to retrieve the curves; it has two arguments: the ranks to be
  11 #'     retrieved, and the IDs - at least one of them must be present (priority: ranks).
  12 #' }
  13 #' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
  14 #' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
  15 #' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
  16 #'   Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
  17 #' @param nb_series_per_chunk (Maximum) number of series in each group, inside a task
  18 #' @param min_series_per_chunk Minimum number of series in each group
  19 #' @param wf Wavelet transform filter; see ?wt.filter. Default: haar
  20 #' @param WER "end" to apply stage 2 after stage 1 has iterated and finished, or "mix"
  21 #'   to apply it after every stage 1
  22 #' @param ncores_tasks "MPI" number of parallel tasks (1 to disable: sequential tasks)
  23 #' @param ncores_clust "OpenMP" number of parallel clusterings in one task
  24 #' @param random Randomize chunks repartition
  25 #'
  26 #' @return A data.frame of the final medoids curves (identifiers + values)
  27 #'
  28 #' @examples
  29 #' getData = function(start, n) {
  30 #'   con = dbConnect(drv = RSQLite::SQLite(), dbname = "mydata.sqlite")
  31 #'   df = dbGetQuery(con, paste(
  32 #'     "SELECT * FROM times_values GROUP BY id OFFSET ",start,
  33 #'     "LIMIT ", n, " ORDER BY date", sep=""))
  34 #'   return (df)
  35 #' }
  36 #'   #TODO: 3 examples, data.frame / binary file / DB sqLite
  37 #'   + sampleCurves : wavBootstrap de package wmtsa
  38 #' cl = epclust(getData, K1=200, K2=15, ntasks=1000, nb_series_per_chunk=5000, WER="mix")
  39 #' @export
  40 epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1,
  41     wf="haar", WER="end", ncores_tasks=1, ncores_clust=4, random=TRUE)
  42 {
  43     # Check arguments
  44     if (!is.data.frame(data) && !is.function(data))
  45     {
  46         tryCatch(
  47             {
  48                 if (is.character(data))
  49                     data_con = file(data, open="r")
  50                 else if (!isOpen(data))
  51                 {
  52                     open(data)
  53                     data_con = data
  54                 }
  55             },
  56             error=function(e) "data should be a data.frame, a function or a valid connection"
  57         )
  58     }
  59     K1 = toInteger(K1, function(x) x>=2)
  60     K2 = toInteger(K2, function(x) x>=2)
  61     ntasks = toInteger(ntasks, function(x) x>=1)
  62     nb_series_per_chunk = toInteger(nb_series_per_chunk, function(x) x>=K1)
  63     min_series_per_chunk = toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk)
  64     ncores_tasks = toInteger(ncores_tasks, function(x) x>=1)
  65     ncores_clust = toInteger(ncores_clust, function(x) x>=1)
  66     if (WER!="end" && WER!="mix")
  67         stop("WER takes values in {'end','mix'}")
  68
  69     # Serialize all wavelets coefficients (+ IDs) onto a file
  70     unlink(".coeffs")
  71     index = 1
  72     nb_curves = 0
  73     nb_coeffs = NA
  74     repeat
  75     {
  76         coeffs_chunk = computeCoeffs(data, index, nb_series_per_chunk, wf)
  77         if (is.null(coeffs_chunk))
  78             break
  79         writeCoeffs(coeffs_chunk)
  80         index = index + nb_series_per_chunk
  81         nb_curves = nb_curves + nrow(coeffs_chunk)
  82         if (is.na(nb_coeffs))
  83             nb_coeffs = ncol(coeffs_chunk)-1
  84     }
  85
  86     if (nb_curves < min_series_per_chunk)
  87         stop("Not enough data: less rows than min_series_per_chunk!")
  88     nb_series_per_task = round(nb_curves / ntasks)
  89     if (nb_series_per_task < min_series_per_chunk)
  90         stop("Too many tasks: less series in one task than min_series_per_chunk!")
  91
  92     # Cluster coefficients in parallel (by nb_series_per_chunk)
  93     indices = if (random) sample(nb_curves) else seq_len(nb_curves)
  94     indices_tasks = lapply(seq_len(ntasks), function(i) {
  95         upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
  96         indices[((i-1)*nb_series_per_task+1):upper_bound]
  97     })
  98     library(parallel, quietly=TRUE)
  99     cl_tasks = parallel::makeCluster(ncores_tasks)
 100     parallel::clusterExport(cl_tasks,
 101         varlist=c("K1","K2","WER","nb_series_per_chunk","ncores_clust"),#TODO: pass also
 102                         #nb_coeffs...and filename (in a list... ?)
 103         envir=environment())
 104     indices = parallel::parLapply(cl_tasks, indices_tasks, clusteringTask)
 105     parallel::stopCluster(cl_tasks)
 106
 107     # Run step1+2 step on resulting ranks
 108     indices = clusterChunk(indices, K1, K2)
 109     return (list("indices"=indices, "medoids"=getSeries(data, indices)))
 110 }