-#' @title Cluster power curves with PAM in parallel
+#' CLAWS: CLustering with wAvelets and Wer distanceS
#'
-#' @description 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}
+#' 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 data Access to the data, which can be of one of the three following types:
-#' \itemize{
-#' \item data.frame: each line contains its ID in the first cell, and all values after
-#' \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 two arguments: the start index
-#' (start) and number of curves (n); see example in package vignette.
-#' }
+#' @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 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 wf Wavelet transform filter; see ?wt.filter. Default: haar
-#' @param WER "end" to apply stage 2 after stage 1 has iterated and finished, or "mix"
-#' to apply it after every stage 1
#' @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 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 data.frame of the final medoids curves (identifiers + values)
+#' @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,
-#' "LIMIT ", n, " ORDER BY date", sep=""))
-#' return (df)
+#' \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)
#' }
-#' #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)
+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)
{
- #0) check arguments
- if (!is.data.frame(data) && !is.function(data))
+ # Check/transform arguments
+ if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
+ && !is.function(getSeries)
+ && !methods::is(getSeries,"connection") && !is.character(getSeries))
{
- tryCatch(
- {
- if (is.character(data))
- data_con = file(data, open="r")
- else if (!isOpen(data))
- {
- open(data)
- data_con = data
- }
- },
- error=function(e) "data should be a data.frame, a function or a valid connection"
- )
+ 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)
- ntasks = toInteger(ntasks)
- 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)
- ncores_tasks = toInteger(ncores_tasks, function(x) x>=1)
- ncores_clust = toInteger(ncores_clust, function(x) x>=1)
+ 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)
- #1) Serialize all wavelets coefficients (+ IDs) onto a file
- coeffs_file = ".coeffs"
- index = 1
- nb_curves = 0
- nb_coeffs = NA
- repeat
+ # 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))
{
- coeffs_chunk = computeCoeffs(data, index, nb_series_per_chunk, wf)
- if (is.null(coeffs_chunk))
- break
- serialized_coeffs = serialize(coeffs_chunk)
- appendBinary(coeffs_file, serialized_coeffs)
- index = index + nb_series_per_chunk
- nb_curves = nb_curves + nrow(coeffs_chunk)
- if (is.na(nb_coeffs))
- nb_coeffs = ncol(coeffs_chunk)-1
+ 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)
}
-# finalizeSerialization(coeffs_file) ........, nb_curves, )
-#TODO: is it really useful ?! we will always have these informations (nb_curves, nb_coeffs)
+ # 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!")
if (nb_series_per_task < min_series_per_chunk)
stop("Too many tasks: less series in one task than min_series_per_chunk!")
- #2) Cluster coefficients in parallel (by nb_series_per_chunk)
- # All indices, relative to complete dataset
- indices = if (random) sample(nb_curves) else seq_len(nb_curves)
- # Indices to be processed in each task
- indices_tasks = list()
- for (i in seq_len(ntasks))
+ 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_task[[i]] = indices[((i-1)*nb_series_per_task+1):upper_bound]
+ 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)
}
- library(parallel, quietly=TRUE)
- cl_tasks = parallel::makeCluster(ncores_tasks)
- parallel::clusterExport(cl_tasks, ..........ncores_clust, indices_tasks, nb_series_per_chunk, processChunk, K1,
- K2, WER, )
- ranks = parallel::parSapply(cl_tasks, seq_along(indices_tasks), oneIteration)
- parallel::stopCluster(cl_tasks)
-
- #3) Run step1+2 step on resulting ranks
- ranks = oneIteration(.........)
- return (list("ranks"=ranks, "medoids"=getSeries(data, ranks)))
+
+ # 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
}
projects / epclust.git / blobdiff