set final draft for package
[epclust.git] / epclust / R / main.R
CommitLineData
7f0781b7
BA
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
cea14f3a 4#' algorithm in parallel to chunks of size \code{nb_series_per_chunk}
7f0781b7
BA
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 start index
11#' (start) and number of curves (n); see example in package vignette.
12#' }
1c6f223e
BA
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
cea14f3a 18#' @param min_series_per_chunk Minimum number of series in each group
3465b246 19#' @param wf Wavelet transform filter; see ?wt.filter. Default: haar
7f0781b7
BA
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
5c652979
BA
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
7f0781b7
BA
25#'
26#' @return A data.frame of the final medoids curves (identifiers + values)
1c6f223e
BA
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#' }
5c652979
BA
36#' #TODO: 3 examples, data.frame / binary file / DB sqLite
37#' + sampleCurves : wavBootstrap de package wmtsa
1c6f223e
BA
38#' cl = epclust(getData, K1=200, K2=15, ntasks=1000, nb_series_per_chunk=5000, WER="mix")
39#' @export
5c652979
BA
40epclust = 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)
ac1d4231 42{
7f0781b7
BA
43 #0) check arguments
44 if (!is.data.frame(data) && !is.function(data))
5c652979 45 {
6ecf5c2d
BA
46 tryCatch(
47 {
48 if (is.character(data))
cea14f3a 49 data_con = file(data, open="r")
5c652979 50 else if (!isOpen(data))
6ecf5c2d
BA
51 {
52 open(data)
cea14f3a 53 data_con = data
6ecf5c2d
BA
54 }
55 },
5c652979
BA
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)
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)
7f0781b7
BA
66 if (WER!="end" && WER!="mix")
67 stop("WER takes values in {'end','mix'}")
ac1d4231 68
5c652979
BA
69 #1) Serialize all wavelets coefficients (+ IDs) onto a file
70 coeffs_file = ".coeffs"
7f0781b7 71 index = 1
cea14f3a 72 nb_curves = 0
5c652979 73 nb_coeffs = NA
6ecf5c2d 74 repeat
ac1d4231 75 {
5c652979 76 coeffs_chunk = computeCoeffs(data, index, nb_series_per_chunk, wf)
cea14f3a
BA
77 if (is.null(coeffs_chunk))
78 break
5c652979
BA
79 serialized_coeffs = serialize(coeffs_chunk)
80 appendBinary(coeffs_file, serialized_coeffs)
cea14f3a 81 index = index + nb_series_per_chunk
5c652979
BA
82 nb_curves = nb_curves + nrow(coeffs_chunk)
83 if (is.na(nb_coeffs))
84 nb_coeffs = ncol(coeffs_chunk)-1
8e6accca
BA
85 }
86
5c652979
BA
87# finalizeSerialization(coeffs_file) ........, nb_curves, )
88#TODO: is it really useful ?! we will always have these informations (nb_curves, nb_coeffs)
3d061515 89
5c652979
BA
90 if (nb_curves < min_series_per_chunk)
91 stop("Not enough data: less rows than min_series_per_chunk!")
92 nb_series_per_task = round(nb_curves / ntasks)
93 if (nb_series_per_task < min_series_per_chunk)
94 stop("Too many tasks: less series in one task than min_series_per_chunk!")
ac1d4231 95
5c652979
BA
96 #2) Cluster coefficients in parallel (by nb_series_per_chunk)
97 # All indices, relative to complete dataset
98 indices = if (random) sample(nb_curves) else seq_len(nb_curves)
99 # Indices to be processed in each task
100 indices_tasks = list()
101 for (i in seq_len(ntasks))
8e6accca 102 {
5c652979
BA
103 upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
104 indices_task[[i]] = indices[((i-1)*nb_series_per_task+1):upper_bound]
8e6accca 105 }
5c652979
BA
106 library(parallel, quietly=TRUE)
107 cl_tasks = parallel::makeCluster(ncores_tasks)
108 parallel::clusterExport(cl_tasks, ..........ncores_clust, indices_tasks, nb_series_per_chunk, processChunk, K1,
109 K2, WER, )
110 ranks = parallel::parSapply(cl_tasks, seq_along(indices_tasks), oneIteration)
111 parallel::stopCluster(cl_tasks)
3465b246 112
5c652979
BA
113 #3) Run step1+2 step on resulting ranks
114 ranks = oneIteration(.........)
115 return (list("ranks"=ranks, "medoids"=getSeries(data, ranks)))
cea14f3a 116}