X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fmain.R;h=f6662678f9db2ae812054979a4173728ca08efd3;hp=bcc650abb8feee40cfc246ef3f95d27b13e478c4;hb=a52836b23adb4bfa6722642ec6426fb7b5f39650;hpb=d9bb53c5e1392018bf67f92140edb10137f3423c

diff --git a/epclust/R/main.R b/epclust/R/main.R
index bcc650a..f666267 100644
--- a/epclust/R/main.R
+++ b/epclust/R/main.R
@@ -27,7 +27,8 @@
 #' series; the name was chosen because all types of arguments are converted to a function.
 #' When \code{getSeries} 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. The nature and role of other arguments should be clear
+#' see SQLite example. The nature and role of other arguments should be clear.
+#' 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 or synchrones do not fit in RAM. For example,
@@ -61,6 +62,7 @@
 #' @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.
@@ -90,7 +92,7 @@
 #' 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)) ) )
+#'   do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=400)) ) )
 #' #dim(series) #c(2400,10001)
 #' medoids_ascii = claws(series, K1=60, K2=6, 200, verbose=TRUE)
 #'
@@ -130,7 +132,10 @@
 #'     request <- paste(request, indexToID_inDB[i], ",", sep="")
 #'   request <- paste(request, ")", sep="")
 #'   df_series <- dbGetQuery(series_db, request)
-#'   as.matrix(df_series[,"value"], nrow=serie_length)
+#'   if (length(df_series) >= 1)
+#'     as.matrix(df_series[,"value"], nrow=serie_length)
+#'   else
+#'     NULL
 #' }
 #' medoids_db = claws(getSeries, K1=60, K2=6, 200))
 #' dbDisconnect(series_db)
@@ -145,7 +150,7 @@
 claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1,
 	algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE)$id.med,
 	algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE)$id.med,
-	wav_filt="d8", contrib_type="absolute", WER="end", random=TRUE,
+	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)
 {
@@ -189,21 +194,32 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1,
 	if (!is.function(getSeries))
 	{
 		if (verbose)
-			cat("...Serialize time-series\n")
-		series_file = ".series.bin" ; unlink(series_file)
-		binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
+			cat("...Serialize time-series (or retrieve past binary file)\n")
+		series_file = ".series.bin"
+		if (!file.exists(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 = ".contribs.bin" ; unlink(contribs_file)
+	contribs_file = ".contribs.bin"
 	index = 1
 	nb_curves = 0
 	if (verbose)
-		cat("...Compute contributions and serialize them\n")
-	nb_curves = binarizeTransform(getSeries,
-		function(series) curvesToContribs(series, wav_filt, contrib_type),
-		contribs_file, nb_series_per_chunk, nbytes, endian)
+		cat("...Compute contributions and serialize them (or retrieve past binary file)\n")
+	if (!file.exists(contribs_file))
+	{
+		nb_curves = binarizeTransform(getSeries,
+			function(series) curvesToContribs(series, 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.
@@ -229,7 +245,7 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1,
 		cl = parallel::makeCluster(ncores_tasks, outfile="")
 		varlist = c("getSeries","getContribs","K1","K2","algoClust1","algoClust2",
 			"nb_series_per_chunk","nb_items_clust1","ncores_clust",
-			"sep","nbytes","endian","verbose","parll")
+			"nvoice","sep","nbytes","endian","verbose","parll")
 		if (WER=="mix" && ntasks>1)
 			varlist = c(varlist, "medoids_file")
 		parallel::clusterExport(cl, varlist, envir = environment())
@@ -253,7 +269,7 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1,
 				require("bigmemory", quietly=TRUE)
 			medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
 			medoids2 = clusteringTask2(medoids1, K2, algoClust2, getSeries, nb_curves,
-				nb_series_per_chunk, nbytes, endian, ncores_clust, verbose, parll)
+				nb_series_per_chunk, nvoice, nbytes, endian, ncores_clust, verbose, parll)
 			binarize(medoids2, medoids_file, nb_series_per_chunk, sep, nbytes, endian)
 			return (vector("integer",0))
 		}
@@ -314,7 +330,7 @@ claws <- function(getSeries, K1, K2, nb_series_per_chunk, nb_items_clust1=7*K1,
 		nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
 	medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
 	medoids2 = clusteringTask2(medoids1, K2, algoClust2, getRefSeries, nb_curves,
-		nb_series_per_chunk, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
+		nb_series_per_chunk, nvoice, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
 
 	# Cleanup: remove temporary binary files
 	tryCatch(