'update'

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

#' CLAWS: CLustering with wAvelets and Wer distanceS
#'
#' Cluster electricity power curves (or any series of similar nature) by applying a
#' two stage procedure in parallel (see details).
#' Input series must be sampled on the same time grid, no missing values.
#'
#' Summary of the function execution flow:
#' \enumerate{
#'   \item Compute and serialize all contributions, obtained through discrete wavelet
#'     decomposition (see Antoniadis & al. [2013])
#'   \item Divide series into \code{ntasks} groups to process in parallel. In each task:
#'   \enumerate{
#'     \item iterate the first clustering algorithm on its aggregated outputs,
#'       on inputs of size \code{nb_series_per_chunk}
#'     \item optionally, if WER=="mix":
#'       a) compute the K1 synchrones curves,
#'       a) compute WER distances (K1xK1 matrix) between medoids and
#'       b) apply the second clustering algorithm (output: K2 indices)
#'   }
#'   \item Launch a final task on the aggregated outputs of all previous tasks:
#'     ntasks*K1 if WER=="end", ntasks*K2 otherwise
#'   \item Compute synchrones (sum of series within each final group)
#' }
#' \cr
#' The main argument -- \code{series} -- has a quite misleading name, since it can be
#' either a [big.]matrix, a CSV file, a connection or a user function to retrieve series.
#' When \code{series} is given as a function, it must take a single argument,
#' 'indices', integer vector equal to the indices of the curves to retrieve;
#' see SQLite example.
#' WARNING: the return value must be a matrix (in columns), or NULL if no matches.
#' \cr
#' Note: Since we don't make assumptions on initial data, there is a possibility that
#' even when serialized, contributions do not fit in RAM. For example,
#' 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore,
#' it's safer to place these in (binary) files; that's what we do.
#'
#' @param series Access to the (time-)series, which can be of one of the three
#'   following types:
#'   \itemize{
#'     \item [big.]matrix: each column contains the (time-ordered) values of one time-serie
#'     \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 SQLite example
#'   }
#' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series])
#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
#' @param nb_series_per_chunk (Maximum) number of series to retrieve in one batch;
#'   this value is also used for the (maximum) number of series to cluster at a time
#' @param algoClust1 Clustering algorithm for stage 1. A function which takes (data, K)
#'   as argument where data is a matrix in columns and K the desired number of clusters,
#'   and outputs K medoids ranks. Default: PAM. In our method, this function is called
#'   on iterated medoids during stage 1
#' @param algoClust2 Clustering algorithm for stage 2. A function which takes (dists, K)
#'   as argument where dists is a matrix of distances and K the desired number of clusters,
#'   and outputs K medoids ranks. Default: PAM.  In our method, this function is called
#'   on a matrix of K1 x K1 (WER) distances computed between medoids after algorithm 1
#' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter
#' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (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 nvoice Number of voices within each octave for CWT computations
#' @param random TRUE (default) for random chunks repartition
#' @param ntasks Number of tasks (parallel iterations to obtain K1 [if WER=="end"]
#'   or K2 [if WER=="mix"] medoids); default: 1.
#'   Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks
#' @param ncores_tasks Number of parallel tasks (1 to disable: sequential tasks)
#' @param ncores_clust Number of parallel clusterings in one task (3 should be a minimum)
#' @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 for (de)serialization ("little" or "big")
#' @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 list with
#' \itemize{
#'   medoids: a matrix of the final K2 medoids curves, in columns
#'   ranks: corresponding indices in the dataset
#'   synchrones: a matrix of the K2 sum of series within each final group
#' }
#'
#' @references Clustering functional data using Wavelets [2013];
#'   A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi.
#'   Inter. J. of Wavelets, Multiresolution and Information Procesing,
#'   vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033
#'
#' @examples
#' \dontrun{
#' # WER distances computations are 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)), ncol=6 )
#' library(wmtsa)
#' series = do.call( cbind, lapply( 1:6, function(i)
#'   do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=400)) ) )
#' #dim(series) #c(2400,10001)
#' res_ascii = claws(series, K1=60, K2=6, 200, verbose=TRUE)
#'
#' # Same example, from CSV file
#' csv_file = "/tmp/epclust_series.csv"
#' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
#' res_csv = claws(csv_file, K1=60, K2=6, 200)
#'
#' # Same example, from binary file
#' bin_file <- "/tmp/epclust_series.bin"
#' nbytes <- 8
#' endian <- "little"
#' binarize(csv_file, bin_file, 500, nbytes, endian)
#' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian)
#' res_bin <- claws(getSeries, K1=60, K2=6, 200)
#' 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"] )
#' serie_length <- as.integer( dbGetQuery(series_db,
#'   paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) )
#' getSeries <- function(indices) {
#'   request <- "SELECT id,value FROM times_values WHERE id in ("
#'   for (i in indices)
#'     request <- paste(request, indexToID_inDB[i], ",", sep="")
#'   request <- paste(request, ")", sep="")
#'   df_series <- dbGetQuery(series_db, request)
#'   if (length(df_series) >= 1)
#'     as.matrix(df_series[,"value"], nrow=serie_length)
#'   else
#'     NULL
#' }
#' res_db = claws(getSeries, K1=60, K2=6, 200))
#' dbDisconnect(series_db)
#'
#' # All results should be the same:
#' library(digest)
#' digest::sha1(res_ascii)
#' digest::sha1(res_csv)
#' digest::sha1(res_bin)
#' digest::sha1(res_db)
#' }
#' @export
claws <- function(getSeries, K1, K2, nb_series_per_chunk,
	algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE,pamonce=1)$id.med,
	algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE,pamonce=1)$id.med,
	wav_filt="d8", contrib_type="absolute", WER="end", nvoice=4, random=TRUE,
	ntasks=1, ncores_tasks=1, ncores_clust=4, sep=",", nbytes=4,
	endian=.Platform$endian, verbose=FALSE, parll=TRUE)
{
	# Check/transform arguments
	if (!is.matrix(series) && !bigmemory::is.big.matrix(series)
		&& !is.function(series)
		&& !methods::is(series,"connection") && !is.character(series))
	{
		stop("'series': [big]matrix, function, file or valid connection (no NA)")
	}
	K1 <- .toInteger(K1, function(x) x>=2)
	K2 <- .toInteger(K2, function(x) x>=2)
	nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1)
	# K1 (number of clusters at step 1) cannot exceed nb_series_per_chunk, because we will need
	# to load K1 series in memory for clustering stage 2.
	if (K1 > nb_series_per_chunk)
		stop("'K1' cannot exceed 'nb_series_per_chunk'")
	random <- .toLogical(random)
	tryCatch( {ignored <- wavelets::wt.filter(wav_filt)},
		error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") )
	ctypes = c("relative","absolute","logit")
	contrib_type = ctypes[ pmatch(contrib_type,ctypes) ]
	if (is.na(contrib_type))
		stop("'contrib_type' in {'relative','absolute','logit'}")
	if (WER!="end" && WER!="mix")
		stop("'WER': in {'end','mix'}")
	random <- .toLogical(random)
	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)
	if (!is.character(sep))
		stop("'sep': character")
	nbytes <- .toInteger(nbytes, function(x) x==4 || x==8)
	verbose <- .toLogical(verbose)
	parll <- .toLogical(parll)

	# Binarize series if it is not a function; the aim is to always use a function,
	# to uniformize treatments. An equally good alternative would be to use a file-backed
	# bigmemory::big.matrix, but it would break the "all-is-function" pattern.
	if (!is.function(series))
	{
		if (verbose)
			cat("...Serialize time-series (or retrieve past binary file)\n")
		series_file = ".series.epclust.bin"
		if (!file.exists(series_file))
			binarize(series, series_file, nb_series_per_chunk, sep, nbytes, endian)
		getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
	}
	else
		getSeries = series

	# Serialize all computed wavelets contributions into a file
	contribs_file = ".contribs.epclust.bin"
	index = 1
	nb_curves = 0
	if (verbose)
		cat("...Compute contributions and serialize them (or retrieve past binary file)\n")
	if (!file.exists(contribs_file))
	{
		nb_curves = binarizeTransform(getSeries,
			function(curves) curvesToContribs(curves, wav_filt, contrib_type),
			contribs_file, nb_series_per_chunk, nbytes, endian)
	}
	else
	{
		# TODO: duplicate from getDataInFile() in de_serialize.R
		contribs_size = file.info(contribs_file)$size #number of bytes in the file
		contrib_length = readBin(contribs_file, "integer", n=1, size=8, endian=endian)
		nb_curves = (contribs_size-8) / (nbytes*contrib_length)
	}
	getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)

	# A few sanity checks: do not continue if too few data available.
	if (nb_curves < K2)
		stop("Not enough data: less series than final number of clusters")
	nb_series_per_task = round(nb_curves / ntasks)
	if (nb_series_per_task < K2)
		stop("Too many tasks: less series in one task than final number of clusters")

	# Generate a random permutation of 1:N (if random==TRUE);
	# otherwise just use arrival (storage) order.
	indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
	# Split (all) indices into ntasks groups of ~same size
	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 (parll && ntasks>1)
	{
		# Initialize parallel runs: outfile="" allow to output verbose traces in the console
		# under Linux. All necessary variables are passed to the workers.
		cl = parallel::makeCluster(ncores_tasks, outfile="")
		parallel::clusterExport(cl, envir = environment(),
			varlist = c("getSeries","getContribs","K1","K2","algoClust1","algoClust2",
			"nb_series_per_chunk","ncores_clust","nvoice","nbytes","endian","verbose","parll"))
	}

	# This function achieves one complete clustering task, divided in stage 1 + stage 2.
	# stage 1: n indices  --> clusteringTask1(...) --> K1 medoids
	# stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids,
	# where n = N / ntasks, N being the total number of curves.
	runTwoStepClustering = function(inds)
	{
		# When running in parallel, the environment is blank: we need to load the required
		# packages, and pass useful variables.
		if (parll && ntasks>1)
			require("epclust", quietly=TRUE)
		indices_medoids = clusteringTask1(inds, getContribs, K1, algoClust1,
			nb_series_per_chunk, ncores_clust, verbose, parll)
		if (WER=="mix")
		{
			indices_medoids = clusteringTask2(indices_medoids, getSeries, K2, algoClust2,
				nb_series_per_chunk, nvoice, nbytes, endian, ncores_clust, verbose, parll)
		}
		indices_medoids
	}

	if (verbose)
	{
		message = paste("...Run ",ntasks," x stage 1", sep="")
		if (WER=="mix")
			message = paste(message," + stage 2", sep="")
		cat(paste(message,"\n", sep=""))
	}

	# As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"],
	# or nothing (empty vector) if WER=="mix"; in this case, synchrones are stored in a file.
	indices_medoids_all <-
		if (parll && ntasks>1)
			unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
		else
			unlist( lapply(indices_tasks, runTwoStepClustering) )

	if (parll && ntasks>1)
		parallel::stopCluster(cl)

	# Right before the final stage, input data still is the initial set of curves, referenced
	# by the ntasks*[K1 or K2] medoids indices.

	# Run last clustering tasks to obtain only K2 medoids indices, from ntasks*[K1 or K2]
	# indices, depending wether WER=="end" or WER=="mix"
	if (verbose)
		cat("...Run final // stage 1 + stage 2\n")
	indices_medoids = clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1,
		nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
	indices_medoids = clusteringTask2(indices_medoids, getContribs, K2, algoClust2,
		nb_series_per_chunk, nvoice, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)

	# Compute synchrones
	medoids = getSeries(indices_medoids)
	synchrones = computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk,
		ncores_tasks*ncores_clust, verbose, parll)

	# NOTE: no need to use big.matrix here, since there are only K2 << K1 << N remaining curves
	list("medoids"=medoids, "ranks"=indices_medoids, "synchrones"=synchrones)
}