[epclust.git] / epclust / R / main.R

#' CLAWS: CLustering with wAvelets and Wer distanceS
#'
#' Groups electricity power curves (or any series of similar nature) by applying PAM
#' algorithm in parallel to chunks of size \code{nb_series_per_chunk}. Input series
#' must be sampled on the same time grid, no missing values.
#'
#' @param getSeries Access to the (time-)series, which can be of one of the three
#'   following types:
#'   \itemize{
#'     \item matrix: each line contains all the values for one time-serie, ordered by time
#'     \item connection: any R connection object (e.g. a file) providing lines as described above
#'     \item function: a custom way to retrieve the curves; it has only one argument:
#'       the indices of the series to be retrieved. See examples
#'   }
#' @inheritParams clustering
#' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
#' @param wf Wavelet transform filter; see ?wavelets::wt.filter
#' @param ctype Type of contribution: "relative" or "absolute" (or any prefix)
#' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply stage 2
#'   at the end of each task
#' @param random TRUE (default) for random chunks repartition
#' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
#'   Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
#' @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 nb_series_per_chunk (~Maximum) number of series in each group, inside a task
#' @param min_series_per_chunk Minimum number of series in each group
#' @param sep Separator in CSV input file (if any provided)
#' @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
#' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
#' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
#'
#' @return A matrix of the final medoids curves (K2) in rows
#'
#' @examples
#' \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)),
#'   byrow=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, K1=60, K2=6, "d8", "rel", 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, "d8", "rel", nb_series_per_chunk=500)
#'
#' # Same example, from binary file
#' bin_file = "/tmp/epclust_series.bin"
#' nbytes = 8
#' endian = "little"
#' epclust::binarize(csv_file, bin_file, 500, nbytes, endian)
#' getSeries = function(indices) getDataInFile(indices, bin_file, nbytes, endian)
#' medoids_bin = claws(getSeries, K1=60, K2=6, "d8", "rel", 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)
#' time_values = data.frame(
#'   id = rep(1:n,each=L),
#'   time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
#'   value = as.double(t(series)) )
#' dbWriteTable(series_db, "times_values", times_values)
#' # Fill associative array, map index to identifier
#' indexToID_inDB <- as.character(
#'   dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
#' getSeries = function(indices) {
#'   request = "SELECT id,value FROM times_values WHERE id in ("
#'   for (i in indices)
#'     request = paste(request, i, ",", sep="")
#'   request = paste(request, ")", sep="")
#'   df_series = dbGetQuery(series_db, request)
#'   # Assume that all series share same length at this stage
#'   ts_length = sum(df_series[,"id"] == df_series[1,"id"])
#'   t( as.matrix(df_series[,"value"], nrow=ts_length) )
#' }
#' medoids_db = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
#' dbDisconnect(series_db)
#'
#' # All computed medoids should be the same:
#' digest::sha1(medoids_ascii)
#' digest::sha1(medoids_csv)
#' digest::sha1(medoids_bin)
#' digest::sha1(medoids_db)
#' }
#' @export
claws = function(getSeries, K1, K2,
	wf,ctype, #stage 1
	WER="end", #stage 2
	random=TRUE, #randomize series order?
	ntasks=1, ncores_tasks=1, ncores_clust=4, #control parallelism
	nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1, #chunk size
	sep=",", #ASCII input separator
	nbytes=4, endian=.Platform$endian, #serialization (write,read)
	verbose=FALSE, parll=TRUE)
{
	# Check/transform arguments
	if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
		&& !is.function(getSeries)
		&& !methods::is(getSeries,"connection") && !is.character(getSeries))
	{
		stop("'getSeries': [big]matrix, function, file or valid connection (no NA)")
	}
	K1 = .toInteger(K1, function(x) x>=2)
	K2 = .toInteger(K2, function(x) x>=2)
	if (!is.logical(random))
		stop("'random': logical")
	tryCatch(
		{ignored <- wavelets::wt.filter(wf)},
		error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter"))
	if (WER!="end" && WER!="mix")
		stop("WER takes values in {'end','mix'}")
	ntasks = .toInteger(ntasks, function(x) x>=1)
	ncores_tasks = .toInteger(ncores_tasks, function(x) x>=1)
	ncores_clust = .toInteger(ncores_clust, function(x) x>=1)
	nb_series_per_chunk = .toInteger(nb_series_per_chunk, function(x) x>=K1)
	min_series_per_chunk = .toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk)
	if (!is.character(sep))
		stop("'sep': character")
	nbytes = .toInteger(nbytes, function(x) x==4 || x==8)

	# Serialize series if required, to always use a function
	bin_dir = ".epclust_bin/"
	dir.create(bin_dir, showWarnings=FALSE, mode="0755")
	if (!is.function(getSeries))
	{
		if (verbose)
			cat("...Serialize time-series\n")
		series_file = paste(bin_dir,"data",sep="") ; unlink(series_file)
		binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
		getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
	}

	# Serialize all computed wavelets contributions onto a file
	contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file)
	index = 1
	nb_curves = 0
	if (verbose)
		cat("...Compute contributions and serialize them\n")
	nb_curves = binarizeTransform(getSeries,
		function(series) curvesToContribs(series, wf, ctype),
		contribs_file, nb_series_per_chunk, nbytes, endian)
	getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)

	if (nb_curves < min_series_per_chunk)
		stop("Not enough data: less rows than min_series_per_chunk!")
	nb_series_per_task = round(nb_curves / ntasks)
	if (nb_series_per_task < min_series_per_chunk)
		stop("Too many tasks: less series in one task than min_series_per_chunk!")

	runTwoStepClustering = function(inds)
	{
		if (parll)
			require("epclust", quietly=TRUE)
		indices_medoids = clusteringTask1(
			inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll)
		if (WER=="mix")
		{


#TODO: getSeries(indices_medoids) BAD ; il faudrait une big.matrix de medoids en entree
			#OK en RAM il y en aura 1000 (donc 1000*K1*17519... OK)
			#...mais du coup chaque process ne re-dupliquera pas medoids


			medoids2 = computeClusters2(getSeries(indices_medoids),
				K2, getSeries, nb_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
			binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian)
			return (vector("integer",0))
		}
		indices_medoids
	}

	# Cluster contributions in parallel (by nb_series_per_chunk)
	indices_all = 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_all[((i-1)*nb_series_per_task+1):upper_bound]
	})
	if (verbose)
		cat(paste("...Run ",ntasks," x stage 1 in parallel\n",sep=""))
	if (WER=="mix")
		{synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)}
	if (parll)
	{
		cl = parallel::makeCluster(ncores_tasks)
		varlist = c("getSeries","getContribs","K1","K2","verbose","parll",
			"nb_series_per_chunk","ncores_clust","sep","nbytes","endian")
		if (WER=="mix")
			varlist = c(varlist, "synchrones_file")
		parallel::clusterExport(cl, varlist=varlist, envir = environment())
	}

	# 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file
	if (parll)
		indices = unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
	else
		indices = unlist( lapply(indices_tasks, runTwoStepClustering) )
	if (parll)
		parallel::stopCluster(cl)

	getRefSeries = getSeries
	if (WER=="mix")
	{
		indices = seq_len(ntasks*K2)
		#Now series must be retrieved from synchrones_file
		getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian)
		#Contributions must be re-computed
		unlink(contribs_file)
		index = 1
		if (verbose)
			cat("...Serialize contributions computed on synchrones\n")
		ignored = binarizeTransform(getSeries,
			function(series) curvesToContribs(series, wf, ctype),
			contribs_file, nb_series_per_chunk, nbytes, endian)
	}

	# Run step2 on resulting indices or series (from file)
	if (verbose)
		cat("...Run final // stage 1 + stage 2\n")
	indices_medoids = clusteringTask1(
		indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
	medoids = computeClusters2(getSeries(indices_medoids), K2,
		getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)

	# Cleanup
	unlink(bin_dir, recursive=TRUE)

	medoids
}

#' curvesToContribs
#'
#' Compute the discrete wavelet coefficients for each series, and aggregate them in
#' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2
#'
#' @param series Matrix of series (in rows), of size n x L
#' @inheritParams claws
#'
#' @return A matrix of size n x log(L) containing contributions in rows
#'
#' @export
curvesToContribs = function(series, wf, ctype)
{
	L = length(series[1,])
	D = ceiling( log2(L) )
	nb_sample_points = 2^D
	cont_types = c("relative","absolute")
	ctype = cont_types[ pmatch(ctype,cont_types) ]
	t( apply(series, 1, function(x) {
		interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
		W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
		nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
		if (ctype=="relative") nrj / sum(nrj) else nrj
	}) )
}

# Check integer arguments with functional conditions
.toInteger <- function(x, condition)
{
	if (!is.integer(x))
		tryCatch(
			{x = as.integer(x)[1]},
			error = function(e) paste("Cannot convert argument",substitute(x),"to integer")
		)
	if (!condition(x))
		stop(paste("Argument",substitute(x),"does not verify condition",body(condition)))
	x
}
Commit	Line	Data
8702eb86	1	#' CLAWS: CLustering with wAvelets and Wer distanceS
7f0781b7	2	#'
56857861	3	#' Groups electricity power curves (or any series of similar nature) by applying PAM
8702eb86 BA	4	#' algorithm in parallel to chunks of size \code{nb_series_per_chunk}. Input series
8702eb86 BA	5	#' must be sampled on the same time grid, no missing values.
7f0781b7	6	#'
8702eb86 BA	7	#' @param getSeries Access to the (time-)series, which can be of one of the three
	8	#' following types:
	9	#' \itemize{
	10	#' \item matrix: each line contains all the values for one time-serie, ordered by time
	11	#' \item connection: any R connection object (e.g. a file) providing lines as described above
	12	#' \item function: a custom way to retrieve the curves; it has only one argument:
	13	#' the indices of the series to be retrieved. See examples
	14	#' }
4bcfdbee	15	#' @inheritParams clustering
1c6f223e BA	16	#' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
1c6f223e BA	17	#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
4bcfdbee BA	18	#' @param wf Wavelet transform filter; see ?wavelets::wt.filter
4bcfdbee BA	19	#' @param ctype Type of contribution: "relative" or "absolute" (or any prefix)
8702eb86 BA	20	#' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply stage 2
8702eb86 BA	21	#' at the end of each task
4bcfdbee	22	#' @param random TRUE (default) for random chunks repartition
1c6f223e BA	23	#' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
1c6f223e BA	24	#' Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
5c652979 BA	25	#' @param ncores_tasks "MPI" number of parallel tasks (1 to disable: sequential tasks)
5c652979 BA	26	#' @param ncores_clust "OpenMP" number of parallel clusterings in one task
8702eb86 BA	27	#' @param nb_series_per_chunk (~Maximum) number of series in each group, inside a task
8702eb86 BA	28	#' @param min_series_per_chunk Minimum number of series in each group
4bcfdbee	29	#' @param sep Separator in CSV input file (if any provided)
8702eb86 BA	30	#' @param nbytes Number of bytes to serialize a floating-point number; 4 or 8
8702eb86 BA	31	#' @param endian Endianness to use for (de)serialization. Use "little" or "big" for portability
4bcfdbee	32	#' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
492cd9e7	33	#' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
7f0781b7	34	#'
4efef8cc	35	#' @return A matrix of the final medoids curves (K2) in rows
1c6f223e BA	36	#'
1c6f223e BA	37	#' @examples
4efef8cc BA	38	#' \dontrun{
	39	#' # WER distances computations are a bit too long for CRAN (for now)
	40	#'
	41	#' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
	42	#' x = seq(0,500,0.05)
	43	#' L = length(x) #10001
	44	#' ref_series = matrix( c(cos(x), cos(2x), cos(3x), sin(x), sin(2x), sin(3x)),
4bcfdbee	45	#' byrow=TRUE, ncol=L )
4efef8cc BA	46	#' library(wmtsa)
	47	#' series = do.call( rbind, lapply( 1:6, function(i)
	48	#' do.call(rbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
	49	#' #dim(series) #c(2400,10001)
4bcfdbee	50	#' medoids_ascii = claws(series, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
4efef8cc BA	51	#'
	52	#' # Same example, from CSV file
	53	#' csv_file = "/tmp/epclust_series.csv"
	54	#' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
4bcfdbee	55	#' medoids_csv = claws(csv_file, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
4efef8cc BA	56	#'
	57	#' # Same example, from binary file
	58	#' bin_file = "/tmp/epclust_series.bin"
	59	#' nbytes = 8
	60	#' endian = "little"
4bcfdbee	61	#' epclust::binarize(csv_file, bin_file, 500, nbytes, endian)
4efef8cc	62	#' getSeries = function(indices) getDataInFile(indices, bin_file, nbytes, endian)
4bcfdbee	63	#' medoids_bin = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
4efef8cc BA	64	#' unlink(csv_file)
	65	#' unlink(bin_file)
	66	#'
	67	#' # Same example, from SQLite database
	68	#' library(DBI)
	69	#' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
	70	#' # Prepare data.frame in DB-format
	71	#' n = nrow(series)
4bcfdbee BA	72	#' time_values = data.frame(
	73	#' id = rep(1:n,each=L),
	74	#' time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
	75	#' value = as.double(t(series)) )
4efef8cc	76	#' dbWriteTable(series_db, "times_values", times_values)
4bcfdbee BA	77	#' # Fill associative array, map index to identifier
	78	#' indexToID_inDB <- as.character(
	79	#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
4efef8cc	80	#' getSeries = function(indices) {
4bcfdbee BA	81	#' request = "SELECT id,value FROM times_values WHERE id in ("
	82	#' for (i in indices)
	83	#' request = paste(request, i, ",", sep="")
	84	#' request = paste(request, ")", sep="")
	85	#' df_series = dbGetQuery(series_db, request)
	86	#' # Assume that all series share same length at this stage
	87	#' ts_length = sum(df_series[,"id"] == df_series[1,"id"])
	88	#' t( as.matrix(df_series[,"value"], nrow=ts_length) )
4efef8cc	89	#' }
4bcfdbee BA	90	#' medoids_db = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
	91	#' dbDisconnect(series_db)
	92	#'
	93	#' # All computed medoids should be the same:
	94	#' digest::sha1(medoids_ascii)
	95	#' digest::sha1(medoids_csv)
	96	#' digest::sha1(medoids_bin)
	97	#' digest::sha1(medoids_db)
1c6f223e	98	#' }
1c6f223e	99	#' @export
56857861	100	claws = function(getSeries, K1, K2,
4bcfdbee	101	wf,ctype, #stage 1
56857861	102	WER="end", #stage 2
4bcfdbee	103	random=TRUE, #randomize series order?
56857861 BA	104	ntasks=1, ncores_tasks=1, ncores_clust=4, #control parallelism
	105	nb_series_per_chunk=50K1, min_series_per_chunk=5K1, #chunk size
	106	sep=",", #ASCII input separator
4bcfdbee	107	nbytes=4, endian=.Platform$endian, #serialization (write,read)
492cd9e7	108	verbose=FALSE, parll=TRUE)
ac1d4231	109	{
0e2dce80	110	# Check/transform arguments
492cd9e7 BA	111	if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
	112	&& !is.function(getSeries)
	113	&& !methods::is(getSeries,"connection") && !is.character(getSeries))
0e2dce80	114	{
492cd9e7	115	stop("'getSeries': [big]matrix, function, file or valid connection (no NA)")
5c652979	116	}
56857861 BA	117	K1 = .toInteger(K1, function(x) x>=2)
	118	K2 = .toInteger(K2, function(x) x>=2)
	119	if (!is.logical(random))
	120	stop("'random': logical")
	121	tryCatch(
4bcfdbee	122	{ignored <- wavelets::wt.filter(wf)},
56857861	123	error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter"))
7f0781b7 BA	124	if (WER!="end" && WER!="mix")
7f0781b7 BA	125	stop("WER takes values in {'end','mix'}")
56857861 BA	126	ntasks = .toInteger(ntasks, function(x) x>=1)
	127	ncores_tasks = .toInteger(ncores_tasks, function(x) x>=1)
	128	ncores_clust = .toInteger(ncores_clust, function(x) x>=1)
	129	nb_series_per_chunk = .toInteger(nb_series_per_chunk, function(x) x>=K1)
	130	min_series_per_chunk = .toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk)
	131	if (!is.character(sep))
	132	stop("'sep': character")
	133	nbytes = .toInteger(nbytes, function(x) x==4 \|\| x==8)
	134
	135	# Serialize series if required, to always use a function
dc646a97	136	bin_dir = ".epclust_bin/"
56857861 BA	137	dir.create(bin_dir, showWarnings=FALSE, mode="0755")
	138	if (!is.function(getSeries))
	139	{
4bcfdbee BA	140	if (verbose)
4bcfdbee BA	141	cat("...Serialize time-series\n")
56857861	142	series_file = paste(bin_dir,"data",sep="") ; unlink(series_file)
4bcfdbee BA	143	binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
4bcfdbee BA	144	getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
56857861	145	}
ac1d4231	146
4bcfdbee BA	147	# Serialize all computed wavelets contributions onto a file
4bcfdbee BA	148	contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file)
7f0781b7	149	index = 1
cea14f3a	150	nb_curves = 0
4bcfdbee BA	151	if (verbose)
4bcfdbee BA	152	cat("...Compute contributions and serialize them\n")
492cd9e7 BA	153	nb_curves = binarizeTransform(getSeries,
	154	function(series) curvesToContribs(series, wf, ctype),
	155	contribs_file, nb_series_per_chunk, nbytes, endian)
4bcfdbee	156	getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
8e6accca	157
5c652979 BA	158	if (nb_curves < min_series_per_chunk)
	159	stop("Not enough data: less rows than min_series_per_chunk!")
	160	nb_series_per_task = round(nb_curves / ntasks)
	161	if (nb_series_per_task < min_series_per_chunk)
	162	stop("Too many tasks: less series in one task than min_series_per_chunk!")
ac1d4231	163
492cd9e7 BA	164	runTwoStepClustering = function(inds)
	165	{
	166	if (parll)
	167	require("epclust", quietly=TRUE)
	168	indices_medoids = clusteringTask1(
	169	inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll)
56857861 BA	170	if (WER=="mix")
56857861 BA	171	{
24ed5d83 BA	172
	173
	174
	175
	176	#TODO: getSeries(indices_medoids) BAD ; il faudrait une big.matrix de medoids en entree
	177	#OK en RAM il y en aura 1000 (donc 1000K117519... OK)
	178	#...mais du coup chaque process ne re-dupliquera pas medoids
	179
	180
492cd9e7 BA	181	medoids2 = computeClusters2(getSeries(indices_medoids),
492cd9e7 BA	182	K2, getSeries, nb_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
4bcfdbee	183	binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian)
56857861 BA	184	return (vector("integer",0))
	185	}
	186	indices_medoids
492cd9e7 BA	187	}
492cd9e7 BA	188
c45fd663 BA	189	# Cluster contributions in parallel (by nb_series_per_chunk)
	190	indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
	191	indices_tasks = lapply(seq_len(ntasks), function(i) {
	192	upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
	193	indices_all[((i-1)*nb_series_per_task+1):upper_bound]
	194	})
	195	if (verbose)
	196	cat(paste("...Run ",ntasks," x stage 1 in parallel\n",sep=""))
	197	if (WER=="mix")
	198	{synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)}
	199	if (parll)
	200	{
	201	cl = parallel::makeCluster(ncores_tasks)
	202	varlist = c("getSeries","getContribs","K1","K2","verbose","parll",
	203	"nb_series_per_chunk","ncores_clust","sep","nbytes","endian")
	204	if (WER=="mix")
	205	varlist = c(varlist, "synchrones_file")
	206	parallel::clusterExport(cl, varlist=varlist, envir = environment())
	207	}
	208
492cd9e7 BA	209	# 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file
	210	if (parll)
	211	indices = unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
	212	else
	213	indices = unlist( lapply(indices_tasks, runTwoStepClustering) )
	214	if (parll)
	215	parallel::stopCluster(cl)
3465b246	216
8702eb86	217	getRefSeries = getSeries
e205f218 BA	218	if (WER=="mix")
	219	{
	220	indices = seq_len(ntasks*K2)
	221	#Now series must be retrieved from synchrones_file
56857861	222	getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian)
4bcfdbee BA	223	#Contributions must be re-computed
4bcfdbee BA	224	unlink(contribs_file)
e205f218	225	index = 1
4bcfdbee BA	226	if (verbose)
4bcfdbee BA	227	cat("...Serialize contributions computed on synchrones\n")
492cd9e7 BA	228	ignored = binarizeTransform(getSeries,
	229	function(series) curvesToContribs(series, wf, ctype),
	230	contribs_file, nb_series_per_chunk, nbytes, endian)
e205f218	231	}
0e2dce80 BA	232
0e2dce80 BA	233	# Run step2 on resulting indices or series (from file)
4bcfdbee BA	234	if (verbose)
4bcfdbee BA	235	cat("...Run final // stage 1 + stage 2\n")
492cd9e7	236	indices_medoids = clusteringTask1(
af3ea947 BA	237	indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
	238	medoids = computeClusters2(getSeries(indices_medoids), K2,
	239	getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
4bcfdbee BA	240
	241	# Cleanup
	242	unlink(bin_dir, recursive=TRUE)
	243
	244	medoids
56857861 BA	245	}
56857861 BA	246
4bcfdbee BA	247	#' curvesToContribs
	248	#'
	249	#' Compute the discrete wavelet coefficients for each series, and aggregate them in
	250	#' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2
	251	#'
	252	#' @param series Matrix of series (in rows), of size n x L
	253	#' @inheritParams claws
	254	#'
	255	#' @return A matrix of size n x log(L) containing contributions in rows
	256	#'
	257	#' @export
	258	curvesToContribs = function(series, wf, ctype)
56857861 BA	259	{
	260	L = length(series[1,])
	261	D = ceiling( log2(L) )
	262	nb_sample_points = 2^D
4bcfdbee BA	263	cont_types = c("relative","absolute")
4bcfdbee BA	264	ctype = cont_types[ pmatch(ctype,cont_types) ]
8702eb86	265	t( apply(series, 1, function(x) {
56857861 BA	266	interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
56857861 BA	267	W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
4bcfdbee BA	268	nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
4bcfdbee BA	269	if (ctype=="relative") nrj / sum(nrj) else nrj
8702eb86	270	}) )
56857861 BA	271	}
56857861 BA	272
492cd9e7	273	# Check integer arguments with functional conditions
56857861 BA	274	.toInteger <- function(x, condition)
	275	{
	276	if (!is.integer(x))
	277	tryCatch(
	278	{x = as.integer(x)[1]},
	279	error = function(e) paste("Cannot convert argument",substitute(x),"to integer")
	280	)
	281	if (!condition(x))
	282	stop(paste("Argument",substitute(x),"does not verify condition",body(condition)))
	283	x
cea14f3a	284	}