[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 [big.]matrix: each line contains all the values for one time-serie, ordered by time
#'     \item connection: any R connection object providing lines as described above
#'     \item character: name of a CSV file containing series in rows (no header)
#'     \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 big.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 into 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 && ntasks>1)
			require("epclust", quietly=TRUE)
		indices_medoids = clusteringTask1(
			inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll)
		if (WER=="mix")
		{
			medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
			medoids2 = clusteringTask2(medoids1,
				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)
	{
		message = paste("...Run ",ntasks," x stage 1", sep="")
		if (WER=="mix")
			message = paste(message," + stage 2", sep="")
		cat(paste(message,"\n", sep=""))
	}
	if (WER=="mix")
		{synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)}
	if (parll && ntasks>1)
	{
		cl = parallel::makeCluster(ncores_tasks)
		varlist = c("getSeries","getContribs","K1","K2","verbose","parll",
			"nb_series_per_chunk","ntasks","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 && ntasks>1)
		indices = unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
	else
		indices = unlist( lapply(indices_tasks, runTwoStepClustering) )
	if (parll && ntasks>1)
		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)
	medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
	medoids2 = clusteringTask2(medoids1, K2,
		getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)

	# Cleanup
	unlink(bin_dir, recursive=TRUE)

	medoids2
}

#' 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{
bf5c0844 BA	10	#' \item [big.]matrix: each line contains all the values for one time-serie, ordered by time
	11	#' \item connection: any R connection object providing lines as described above
	12	#' \item character: name of a CSV file containing series in rows (no header)
8702eb86 BA	13	#' \item function: a custom way to retrieve the curves; it has only one argument:
	14	#' the indices of the series to be retrieved. See examples
	15	#' }
4bcfdbee	16	#' @inheritParams clustering
1c6f223e BA	17	#' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
1c6f223e BA	18	#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
4bcfdbee BA	19	#' @param wf Wavelet transform filter; see ?wavelets::wt.filter
4bcfdbee BA	20	#' @param ctype Type of contribution: "relative" or "absolute" (or any prefix)
8702eb86 BA	21	#' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply stage 2
8702eb86 BA	22	#' at the end of each task
4bcfdbee	23	#' @param random TRUE (default) for random chunks repartition
1c6f223e BA	24	#' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
1c6f223e BA	25	#' Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
5c652979 BA	26	#' @param ncores_tasks "MPI" number of parallel tasks (1 to disable: sequential tasks)
5c652979 BA	27	#' @param ncores_clust "OpenMP" number of parallel clusterings in one task
8702eb86 BA	28	#' @param nb_series_per_chunk (~Maximum) number of series in each group, inside a task
8702eb86 BA	29	#' @param min_series_per_chunk Minimum number of series in each group
4bcfdbee	30	#' @param sep Separator in CSV input file (if any provided)
8702eb86 BA	31	#' @param nbytes Number of bytes to serialize a floating-point number; 4 or 8
8702eb86 BA	32	#' @param endian Endianness to use for (de)serialization. Use "little" or "big" for portability
4bcfdbee	33	#' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
492cd9e7	34	#' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
7f0781b7	35	#'
bf5c0844	36	#' @return A big.matrix of the final medoids curves (K2) in rows
1c6f223e BA	37	#'
1c6f223e BA	38	#' @examples
4efef8cc BA	39	#' \dontrun{
	40	#' # WER distances computations are a bit too long for CRAN (for now)
	41	#'
	42	#' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
	43	#' x = seq(0,500,0.05)
	44	#' L = length(x) #10001
	45	#' ref_series = matrix( c(cos(x), cos(2x), cos(3x), sin(x), sin(2x), sin(3x)),
4bcfdbee	46	#' byrow=TRUE, ncol=L )
4efef8cc BA	47	#' library(wmtsa)
	48	#' series = do.call( rbind, lapply( 1:6, function(i)
	49	#' do.call(rbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
	50	#' #dim(series) #c(2400,10001)
4bcfdbee	51	#' medoids_ascii = claws(series, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
4efef8cc BA	52	#'
	53	#' # Same example, from CSV file
	54	#' csv_file = "/tmp/epclust_series.csv"
	55	#' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
4bcfdbee	56	#' medoids_csv = claws(csv_file, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
4efef8cc BA	57	#'
	58	#' # Same example, from binary file
	59	#' bin_file = "/tmp/epclust_series.bin"
	60	#' nbytes = 8
	61	#' endian = "little"
4bcfdbee	62	#' epclust::binarize(csv_file, bin_file, 500, nbytes, endian)
4efef8cc	63	#' getSeries = function(indices) getDataInFile(indices, bin_file, nbytes, endian)
4bcfdbee	64	#' medoids_bin = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
4efef8cc BA	65	#' unlink(csv_file)
	66	#' unlink(bin_file)
	67	#'
	68	#' # Same example, from SQLite database
	69	#' library(DBI)
	70	#' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
	71	#' # Prepare data.frame in DB-format
	72	#' n = nrow(series)
4bcfdbee BA	73	#' time_values = data.frame(
	74	#' id = rep(1:n,each=L),
	75	#' time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
	76	#' value = as.double(t(series)) )
4efef8cc	77	#' dbWriteTable(series_db, "times_values", times_values)
4bcfdbee BA	78	#' # Fill associative array, map index to identifier
	79	#' indexToID_inDB <- as.character(
	80	#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
4efef8cc	81	#' getSeries = function(indices) {
4bcfdbee BA	82	#' request = "SELECT id,value FROM times_values WHERE id in ("
	83	#' for (i in indices)
	84	#' request = paste(request, i, ",", sep="")
	85	#' request = paste(request, ")", sep="")
	86	#' df_series = dbGetQuery(series_db, request)
	87	#' # Assume that all series share same length at this stage
	88	#' ts_length = sum(df_series[,"id"] == df_series[1,"id"])
	89	#' t( as.matrix(df_series[,"value"], nrow=ts_length) )
4efef8cc	90	#' }
4bcfdbee BA	91	#' medoids_db = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
	92	#' dbDisconnect(series_db)
	93	#'
	94	#' # All computed medoids should be the same:
	95	#' digest::sha1(medoids_ascii)
	96	#' digest::sha1(medoids_csv)
	97	#' digest::sha1(medoids_bin)
	98	#' digest::sha1(medoids_db)
1c6f223e	99	#' }
1c6f223e	100	#' @export
56857861	101	claws = function(getSeries, K1, K2,
4bcfdbee	102	wf,ctype, #stage 1
56857861	103	WER="end", #stage 2
4bcfdbee	104	random=TRUE, #randomize series order?
56857861 BA	105	ntasks=1, ncores_tasks=1, ncores_clust=4, #control parallelism
	106	nb_series_per_chunk=50K1, min_series_per_chunk=5K1, #chunk size
	107	sep=",", #ASCII input separator
4bcfdbee	108	nbytes=4, endian=.Platform$endian, #serialization (write,read)
492cd9e7	109	verbose=FALSE, parll=TRUE)
ac1d4231	110	{
0e2dce80	111	# Check/transform arguments
492cd9e7 BA	112	if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
	113	&& !is.function(getSeries)
	114	&& !methods::is(getSeries,"connection") && !is.character(getSeries))
0e2dce80	115	{
492cd9e7	116	stop("'getSeries': [big]matrix, function, file or valid connection (no NA)")
5c652979	117	}
56857861 BA	118	K1 = .toInteger(K1, function(x) x>=2)
	119	K2 = .toInteger(K2, function(x) x>=2)
	120	if (!is.logical(random))
	121	stop("'random': logical")
	122	tryCatch(
4bcfdbee	123	{ignored <- wavelets::wt.filter(wf)},
56857861	124	error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter"))
7f0781b7 BA	125	if (WER!="end" && WER!="mix")
7f0781b7 BA	126	stop("WER takes values in {'end','mix'}")
56857861 BA	127	ntasks = .toInteger(ntasks, function(x) x>=1)
	128	ncores_tasks = .toInteger(ncores_tasks, function(x) x>=1)
	129	ncores_clust = .toInteger(ncores_clust, function(x) x>=1)
	130	nb_series_per_chunk = .toInteger(nb_series_per_chunk, function(x) x>=K1)
	131	min_series_per_chunk = .toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk)
	132	if (!is.character(sep))
	133	stop("'sep': character")
	134	nbytes = .toInteger(nbytes, function(x) x==4 \|\| x==8)
	135
	136	# Serialize series if required, to always use a function
dc646a97	137	bin_dir = ".epclust_bin/"
56857861 BA	138	dir.create(bin_dir, showWarnings=FALSE, mode="0755")
	139	if (!is.function(getSeries))
	140	{
4bcfdbee BA	141	if (verbose)
4bcfdbee BA	142	cat("...Serialize time-series\n")
56857861	143	series_file = paste(bin_dir,"data",sep="") ; unlink(series_file)
4bcfdbee BA	144	binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
4bcfdbee BA	145	getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
56857861	146	}
ac1d4231	147
95b5c2e6	148	# Serialize all computed wavelets contributions into a file
4bcfdbee	149	contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file)
7f0781b7	150	index = 1
cea14f3a	151	nb_curves = 0
4bcfdbee BA	152	if (verbose)
4bcfdbee BA	153	cat("...Compute contributions and serialize them\n")
492cd9e7 BA	154	nb_curves = binarizeTransform(getSeries,
	155	function(series) curvesToContribs(series, wf, ctype),
	156	contribs_file, nb_series_per_chunk, nbytes, endian)
4bcfdbee	157	getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
8e6accca	158
5c652979 BA	159	if (nb_curves < min_series_per_chunk)
	160	stop("Not enough data: less rows than min_series_per_chunk!")
	161	nb_series_per_task = round(nb_curves / ntasks)
	162	if (nb_series_per_task < min_series_per_chunk)
	163	stop("Too many tasks: less series in one task than min_series_per_chunk!")
ac1d4231	164
492cd9e7 BA	165	runTwoStepClustering = function(inds)
492cd9e7 BA	166	{
bf5c0844	167	if (parll && ntasks>1)
492cd9e7 BA	168	require("epclust", quietly=TRUE)
	169	indices_medoids = clusteringTask1(
	170	inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll)
56857861 BA	171	if (WER=="mix")
56857861 BA	172	{
bf5c0844 BA	173	medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
bf5c0844 BA	174	medoids2 = clusteringTask2(medoids1,
492cd9e7	175	K2, getSeries, nb_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
4bcfdbee	176	binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian)
56857861 BA	177	return (vector("integer",0))
	178	}
	179	indices_medoids
492cd9e7 BA	180	}
492cd9e7 BA	181
c45fd663 BA	182	# Cluster contributions in parallel (by nb_series_per_chunk)
	183	indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
	184	indices_tasks = lapply(seq_len(ntasks), function(i) {
	185	upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
	186	indices_all[((i-1)*nb_series_per_task+1):upper_bound]
	187	})
	188	if (verbose)
e161499b BA	189	{
	190	message = paste("...Run ",ntasks," x stage 1", sep="")
	191	if (WER=="mix")
	192	message = paste(message," + stage 2", sep="")
	193	cat(paste(message,"\n", sep=""))
	194	}
c45fd663 BA	195	if (WER=="mix")
c45fd663 BA	196	{synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)}
bf5c0844	197	if (parll && ntasks>1)
c45fd663 BA	198	{
	199	cl = parallel::makeCluster(ncores_tasks)
	200	varlist = c("getSeries","getContribs","K1","K2","verbose","parll",
bf5c0844	201	"nb_series_per_chunk","ntasks","ncores_clust","sep","nbytes","endian")
c45fd663 BA	202	if (WER=="mix")
	203	varlist = c(varlist, "synchrones_file")
	204	parallel::clusterExport(cl, varlist=varlist, envir = environment())
	205	}
	206
492cd9e7	207	# 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file
bf5c0844	208	if (parll && ntasks>1)
492cd9e7 BA	209	indices = unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
	210	else
	211	indices = unlist( lapply(indices_tasks, runTwoStepClustering) )
bf5c0844	212	if (parll && ntasks>1)
492cd9e7	213	parallel::stopCluster(cl)
3465b246	214
8702eb86	215	getRefSeries = getSeries
e205f218 BA	216	if (WER=="mix")
	217	{
	218	indices = seq_len(ntasks*K2)
	219	#Now series must be retrieved from synchrones_file
56857861	220	getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian)
4bcfdbee BA	221	#Contributions must be re-computed
4bcfdbee BA	222	unlink(contribs_file)
e205f218	223	index = 1
4bcfdbee BA	224	if (verbose)
4bcfdbee BA	225	cat("...Serialize contributions computed on synchrones\n")
492cd9e7 BA	226	ignored = binarizeTransform(getSeries,
	227	function(series) curvesToContribs(series, wf, ctype),
	228	contribs_file, nb_series_per_chunk, nbytes, endian)
e205f218	229	}
0e2dce80 BA	230
0e2dce80 BA	231	# Run step2 on resulting indices or series (from file)
4bcfdbee BA	232	if (verbose)
4bcfdbee BA	233	cat("...Run final // stage 1 + stage 2\n")
492cd9e7	234	indices_medoids = clusteringTask1(
af3ea947	235	indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
bf5c0844	236	medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
e161499b	237	medoids2 = clusteringTask2(medoids1, K2,
af3ea947	238	getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
4bcfdbee BA	239
	240	# Cleanup
	241	unlink(bin_dir, recursive=TRUE)
	242
bf5c0844	243	medoids2
56857861 BA	244	}
56857861 BA	245
4bcfdbee BA	246	#' curvesToContribs
	247	#'
	248	#' Compute the discrete wavelet coefficients for each series, and aggregate them in
	249	#' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2
	250	#'
	251	#' @param series Matrix of series (in rows), of size n x L
	252	#' @inheritParams claws
	253	#'
	254	#' @return A matrix of size n x log(L) containing contributions in rows
	255	#'
	256	#' @export
	257	curvesToContribs = function(series, wf, ctype)
56857861 BA	258	{
	259	L = length(series[1,])
	260	D = ceiling( log2(L) )
	261	nb_sample_points = 2^D
4bcfdbee BA	262	cont_types = c("relative","absolute")
4bcfdbee BA	263	ctype = cont_types[ pmatch(ctype,cont_types) ]
8702eb86	264	t( apply(series, 1, function(x) {
56857861 BA	265	interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
56857861 BA	266	W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
4bcfdbee BA	267	nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
4bcfdbee BA	268	if (ctype=="relative") nrj / sum(nrj) else nrj
8702eb86	269	}) )
56857861 BA	270	}
56857861 BA	271
492cd9e7	272	# Check integer arguments with functional conditions
56857861 BA	273	.toInteger <- function(x, condition)
	274	{
	275	if (!is.integer(x))
	276	tryCatch(
	277	{x = as.integer(x)[1]},
	278	error = function(e) paste("Cannot convert argument",substitute(x),"to integer")
	279	)
	280	if (!condition(x))
	281	stop(paste("Argument",substitute(x),"does not verify condition",body(condition)))
	282	x
cea14f3a	283	}