#' @param ncores_tasks "MPI" number of parallel tasks (1 to disable: sequential tasks)
#' @param ncores_clust "OpenMP" number of parallel clusterings in one task
#' @param random Randomize chunks repartition
+#' @param ... Other arguments to be passed to \code{data} function
#'
#' @return A data.frame of the final medoids curves (identifiers + values)
#'
#' "LIMIT ", n, " ORDER BY date", sep=""))
#' return (df)
#' }
+#' #####TODO: if DB, array rank --> ID at first retrieval, when computing coeffs; so:: NO use of IDs !
#' #TODO: 3 examples, data.frame / binary file / DB sqLite
#' + sampleCurves : wavBootstrap de package wmtsa
#' cl = epclust(getData, K1=200, K2=15, ntasks=1000, nb_series_per_chunk=5000, WER="mix")
#' @export
-epclust = function(data, K1, K2, ntasks=1, nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1,
- wf="haar", WER="end", ncores_tasks=1, ncores_clust=4, random=TRUE)
+epclust = function(series,K1,K2,ntasks=1,nb_series_per_chunk=50*K1,min_series_per_chunk=5*K1,
+ wf="haar",WER="end",ncores_tasks=1,ncores_clust=4,random=TRUE,...)
{
- # Check arguments
- if (!is.data.frame(data) && !is.function(data))
+ # Check/transform arguments
+ bin_dir = "epclust.bin/"
+ dir.create(bin_dir, showWarnings=FALSE, mode="0755")
+ if (!is.function(series))
+ {
+ series_file = paste(bin_dir,"data",sep="")
+ unlink(series_file)
+ }
+ if (is.matrix(series))
+ serialize(series, series_file)
+ else if (!is.function(series))
{
tryCatch(
{
- if (is.character(data))
- data_con = file(data, open="r")
- else if (!isOpen(data))
+ if (is.character(series))
+ series_con = file(series, open="r")
+ else if (!isOpen(series))
{
- open(data)
- data_con = data
+ open(series)
+ series_con = series
}
+ serialize(series_con, series_file)
+ close(series_con)
},
- error=function(e) "data should be a data.frame, a function or a valid connection"
+ error=function(e) "series should be a data.frame, a function or a valid connection"
)
}
+ if (!is.function(series))
+ series = function(indices) getDataInFile(indices, series_file)
+ getSeries = series
+
K1 = toInteger(K1, function(x) x>=2)
K2 = toInteger(K2, function(x) x>=2)
ntasks = toInteger(ntasks, function(x) x>=1)
stop("WER takes values in {'end','mix'}")
# Serialize all wavelets coefficients (+ IDs) onto a file
- coeffs_file = ".coeffs"
- ids_files = ".ids"
+ coefs_file = paste(bin_dir,"coefs",sep="")
+ unlink(coefs_file)
index = 1
nb_curves = 0
- nb_coeffs = NA
repeat
{
- coeffs_chunk = computeCoeffs(data, index, nb_series_per_chunk, wf)
- if (is.null(coeffs_chunk))
+ series = getSeries((index-1)+seq_len(nb_series_per_chunk))
+ if (is.null(series))
break
- serialize(coeffs_chunk, coeffs_file, append=TRUE)
+ coeffs_chunk = curvesToCoeffs(series, wf)
+ serialize(coeffs_chunk, coefs_file)
index = index + nb_series_per_chunk
nb_curves = nb_curves + nrow(coeffs_chunk)
- if (is.na(nb_coeffs))
- nb_coeffs = ncol(coeffs_chunk)-1
}
+ getCoefs = function(indices) getDataInFile(indices, coefs_file)
if (nb_curves < min_series_per_chunk)
stop("Not enough data: less rows than min_series_per_chunk!")
stop("Too many tasks: less series in one task than min_series_per_chunk!")
# Cluster coefficients in parallel (by nb_series_per_chunk)
- indices = if (random) sample(nb_curves) else seq_len(nb_curves) #all indices
- indices_tasks = list() #indices to be processed in each task
- for (i in seq_len(ntasks))
- {
+ indices = if (random) sample(nb_curves) else seq_len(nb_curves)
+ indices_tasks = lapply(seq_len(ntasks), function(i) {
upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
- indices_task[[i]] = indices[((i-1)*nb_series_per_task+1):upper_bound]
- }
- library(parallel, quietly=TRUE)
- cl_tasks = parallel::makeCluster(ncores_tasks)
- #parallel::clusterExport(cl=cl_tasks, varlist=c("ncores_clust", ...), envir=environment())
- indices = parallel::parLapply(cl_tasks, indices_tasks, clusteringStep12, )
- parallel::stopCluster(cl_tasks)
+ indices[((i-1)*nb_series_per_task+1):upper_bound]
+ })
+ cl = parallel::makeCluster(ncores_tasks)
+ #1000*K1 (or K2) indices (or NOTHING--> series on file)
+ indices = unlist( parallel::parLapply(cl, indices_tasks, function(inds) {
+ clusteringTask(inds, getSeries, getSeries, getCoefs, K1, K2*(WER=="mix"),
+ nb_series_per_chunk,ncores_clust,to_file=TRUE)
+ }) )
+ parallel::stopCluster(cl)
-##TODO: passer data ?!
+ getSeriesForSynchrones = getSeries
+ synchrones_file = paste(bin_dir,"synchrones",sep="")
+ if (WER=="mix")
+ {
+ indices = seq_len(ntasks*K2)
+ #Now series must be retrieved from synchrones_file
+ getSeries = function(inds) getDataInFile(inds, synchrones_file)
+ #Coefs must be re-computed
+ unlink(coefs_file)
+ index = 1
+ repeat
+ {
+ series = getSeries((index-1)+seq_len(nb_series_per_chunk))
+ if (is.null(series))
+ break
+ coeffs_chunk = curvesToCoeffs(series, wf)
+ serialize(coeffs_chunk, coefs_file)
+ index = index + nb_series_per_chunk
+ }
+ }
- # Run step1+2 step on resulting ranks
- ranks = clusteringStep12()
- return (list("ranks"=ranks, "medoids"=getSeries(data, ranks)))
+ # Run step2 on resulting indices or series (from file)
+ clusteringTask(indices, getSeries, getSeriesForSynchrones, getCoefs, K1, K2,
+ nb_series_per_chunk, ncores_tasks*ncores_clust, to_file=FALSE)
}
projects / epclust.git / blobdiff