#' @param nbytes Number of bytes to serialize a floating-point number; 4 or 8
#' @param endian Endianness to use for (de)serialization. Use "little" or "big" for portability
#'
-#' @return A matrix of the final medoids curves
+#' @return A matrix of the final medoids curves (K2) in rows
#'
#' @examples
-#' getData = function(start, n) {
-#' con = dbConnect(drv = RSQLite::SQLite(), dbname = "mydata.sqlite")
-#' df = dbGetQuery(con, paste(
-#' "SELECT * FROM times_values GROUP BY id OFFSET ",start,
+#' \dontrun{
+#' # WER distances computations are a bit too long for CRAN (for now)
+#'
+#' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
+#' x = seq(0,500,0.05)
+#' L = length(x) #10001
+#' ref_series = matrix( c(cos(x), cos(2*x), cos(3*x), sin(x), sin(2*x), sin(3*x)),
+#' byrows=TRUE, ncol=L )
+#' library(wmtsa)
+#' series = do.call( rbind, lapply( 1:6, function(i)
+#' do.call(rbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
+#' #dim(series) #c(2400,10001)
+#' medoids_ascii = claws(series_RData, K1=60, K2=6, wf="d8", nb_series_per_chunk=500)
+#'
+#' # Same example, from CSV file
+#' csv_file = "/tmp/epclust_series.csv"
+#' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
+#' medoids_csv = claws(csv_file, K1=60, K2=6, wf="d8", nb_series_per_chunk=500)
+#'
+#' # Same example, from binary file
+#' bin_file = "/tmp/epclust_series.bin"
+#' nbytes = 8
+#' endian = "little"
+#' epclust::serialize(csv_file, bin_file, 500, nbytes, endian)
+#' getSeries = function(indices) getDataInFile(indices, bin_file, nbytes, endian)
+#' medoids_bin = claws(getSeries, K1=60, K2=6, wf="d8", nb_series_per_chunk=500)
+#' unlink(csv_file)
+#' unlink(bin_file)
+#'
+#' # Same example, from SQLite database
+#' library(DBI)
+#' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
+#' # Prepare data.frame in DB-format
+#' n = nrow(series)
+#' formatted_series = data.frame(
+#' ID = rep(1:n,each=L),
+#' time = as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"),
+#' value
+
+
+
+
+#' TODO
+
+
+#' times_values = as.data.frame(series)
+#' dbWriteTable(series_db, "times_values", times_values)
+#' # NOTE: assume that DB internal data is not reorganized when computing coefficients
+#' indexToID_inDB <<- list()
+#' getSeries = function(indices) {
+#' con = dbConnect(drv = RSQLite::SQLite(), dbname = db_file)
+#' if (indices %in% indexToID_inDB)
+#' {
+#' df = dbGetQuery(con, paste(
+#' "SELECT value FROM times_values GROUP BY id OFFSET ",start,
#' "LIMIT ", n, " ORDER BY date", sep=""))
-#' return (df)
+#' return (df)
+#' }
+#' else
+#' {
+#' ...
+#' }
+#' }
+#' dbDisconnect(mydb)
#' }
-#' #####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
claws = function(getSeries, K1, K2,
random=TRUE, #randomize series order?
cl = parallel::makeCluster(ncores_tasks)
# 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file
indices = unlist( parallel::parLapply(cl, indices_tasks, function(inds) {
+ require("epclust", quietly=TRUE)
indices_medoids = clusteringTask(inds,getCoefs,K1,nb_series_per_chunk,ncores_clust)
if (WER=="mix")
{
--- /dev/null
+citHeader("To cite epclust in publications use:")
+
+citEntry(entry = "Manual",
+ title = ".",
+ author = personList(as.person("Benjamin Auder"),
+ as.person("Jairo Cugliari"),
+ as.person("Yannig Goude")),
+ as.person("Jean-Michel Poggi"))
+ organization = "Paris-Sud, Saclay & Lyon 2",
+ address = "Orsay, Saclay & Lyon, France",
+ year = "2017",
+ url = "https://git.auder.net/?p=edfclust.git",
+
+ textVersion =
+ paste("Benjamin Auder, Jairo Cugliari, Yannig Goude, Jean-Michel Poggi (2017).",
+ "EPCLUST: Electric Power curves CLUSTering.",
+ "URL https://git.auder.net/?p=edfclust.git")
+)
projects / epclust.git / commitdiff