#' obtaind by \code{getSeries(indices)}
#'
#' @param indices Range of series indices to cluster
+#' @param getSeries Function to retrieve series (argument: 'indices', integer vector),
+#' as columns of a matrix
+#' @param ncores Number of cores for parallel runs
#' @inheritParams claws
-#' @inheritParams computeSynchrones
#'
#' @return A distances matrix of size K x K where K == length(indices)
#'
#' @export
-computeWerDists <- function(indices, getSeries, nb_series_per_chunk, smooth_lvl, nvoice,
- nbytes, endian, ncores_clust=3, verbose=FALSE, parll=TRUE)
+computeWerDists <- function(indices, getSeries, nb_series_per_chunk, smooth_lvl=3, nvoice=4,
+ nbytes=4, endian=.Platform$endian, ncores=3, verbose=FALSE)
{
n <- length(indices)
L <- length(getSeries(1)) #TODO: not very neat way to get L
cwt_file <- tempfile(pattern="epclust_cwt.bin_")
# Compute the getSeries(indices) CWT, and store the results in the binary file
- computeSaveCWT <- function(indices)
+ computeSaveCWT <- function(inds)
{
- if (parll)
- {
- # parallel workers start with an empty environment
- require("epclust", quietly=TRUE)
- }
+ if (verbose)
+ cat(" Compute save CWT on ",length(inds)," indices\n", sep="")
# Obtain CWT as big vectors of real part + imaginary part (concatenate)
- ts_cwt <- sapply(indices, function(i) {
+ ts_cwt <- sapply(inds, function(i) {
ts <- scale(ts(getSeries(i)), center=TRUE, scale=FALSE)
ts_cwt <- Rwave::cwt(ts, noctave, nvoice, w0=2*pi, twoD=TRUE, plot=FALSE)
c( as.double(Re(ts_cwt)),as.double(Im(ts_cwt)) )
re_part + 1i * im_part
}
- # Compute distance between columns i and j for j>i
+ # Compute distances between columns i and j for j>i
computeDistances <- function(i)
{
if (parll)
Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
}
- if (verbose && !parll)
+ if (verbose)
cat(paste(" Distances from ",i," to ",i+1,"...",n,"\n", sep=""))
# Get CWT of column i, and run computations for columns j>i
Xwer_dist[i,i] <- 0.
}
+ if (verbose)
+ cat(paste("--- Precompute and serialize synchrones CWT\n", sep=""))
+
+ # Split indices by packets of length at most nb_cwt_per_chunk
+ indices_cwt <- .splitIndices(indices, nb_cwt_per_chunk)
+ # NOTE: next loop could potentially be run in //. Indices would be permuted (by
+ # serialization order), and synchronicity would be required because of concurrent
+ # writes. Probably not worth the effort - but possible.
+ for (inds in indices_cwt)
+ computeSaveCWT(inds)
+
+ parll <- (ncores > 1)
if (parll)
{
# outfile=="" to see stderr/stdout on terminal
cl <-
if (verbose)
- parallel::makeCluster(ncores_clust, outfile="")
+ parallel::makeCluster(ncores, outfile="")
else
- parallel::makeCluster(ncores_clust)
+ parallel::makeCluster(ncores)
Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
- parallel::clusterExport(cl, varlist=c("parll","nb_cwt_per_chunk","n","L",
- "Xwer_dist_desc","noctave","nvoice","getCWT"), envir=environment())
+ parallel::clusterExport(cl, envir=environment(),
+ varlist=c("parll","n","L","Xwer_dist_desc","getCWT","verbose"))
}
- if (verbose)
- cat(paste("--- Precompute and serialize synchrones CWT\n", sep=""))
-
- # Split indices by packets of length at most nb_cwt_per_chunk
- indices_cwt <- .splitIndices(seq_len(n), nb_cwt_per_chunk)
- ignored <-
- if (parll)
- parallel::parLapply(cl, indices_cwt, computeSaveCWT)
- else
- lapply(indices_cwt, computeSaveCWT)
-
if (verbose)
cat(paste("--- Compute WER distances\n", sep=""))