X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=epclust%2FR%2Futils.R;h=1e4ea30f9a8297031724386e168bfd5083902602;hb=282342bafdc9ff65c5df98c6e2304d63b33b9fb2;hp=8f7da383c43b818a50a85839a13a314856d4b563;hpb=5c6529795907ba1b34d4552cbfd0e0cbb77cac0f;p=epclust.git

diff --git a/epclust/R/utils.R b/epclust/R/utils.R
index 8f7da38..1e4ea30 100644
--- a/epclust/R/utils.R
+++ b/epclust/R/utils.R
@@ -1,44 +1,139 @@
-toInteger <- function(x, condition)
+# Check integer arguments with functional conditions
+.toInteger <- function(x, condition)
 {
+	errWarn <- function(ignored)
+		paste("Cannot convert argument' ",substitute(x),"' to integer", sep="")
 	if (!is.integer(x))
-		tryCatch(
-			{x = as.integer(x)[1]},
-			error = function(e) paste("cannot convert argument",substitute(x),"to integer")
-		)
+		tryCatch({x <- as.integer(x)[1]; if (is.na(x)) stop()},
+			warning=errWarn, error=errWarn)
 	if (!condition(x))
-		stop(paste("argument",substitute(x),"does not verify condition",body(condition)))
+	{
+		stop(paste("Argument '",substitute(x),
+			"' does not verify condition ",body(condition), sep=""))
+	}
 	x
 }
 
-#TODO: merge these 2 next ?!
-serialize = function(coeffs)
+# Check logical arguments
+.toLogical <- function(x)
 {
-	#.........
-	#C function (from data.frame, type of IDs ??! force integers ? [yes])
-	#return raw vector
+	errWarn <- function(ignored)
+		paste("Cannot convert argument' ",substitute(x),"' to logical", sep="")
+	if (!is.logical(x))
+		tryCatch({x <- as.logical(x)[1]; if (is.na(x)) stop()},
+			warning=errWarn, error=errWarn)
+	x
 }
-appendBinary = function(.......)
+
+#' 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 curves [big.]matrix of series (in columns), of size L x n
+#' @inheritParams claws
+#'
+#' @return A matrix of size log(L) x n containing contributions in columns
+#'
+#' @export
+curvesToContribs <- function(series, wav_filt, contrib_type)
 {
-	#take raw vector, append it (binary mode) to a file
+	series <- as.matrix(series)
+	L <- nrow(series)
+	D <- ceiling( log2(L) )
+	# Series are interpolated to all have length 2^D
+	nb_sample_points <- 2^D
+	apply(series, 2, function(x) {
+		interpolated_curve <- spline(1:L, x, n=nb_sample_points)$y
+		W <- wavelets::dwt(interpolated_curve, filter=wav_filt, D)@W
+		# Compute the sum of squared discrete wavelet coefficients, for each scale
+		nrj <- rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
+		if (contrib_type!="absolute")
+			nrj <- nrj / sum(nrj)
+		if (contrib_type=="logit")
+			nrj <- - log(1 - nrj)
+		unname( nrj )
+	})
 }
 
-#finalizeSerialization = function(...)
-#{
-#	#write number of series, and length of each...
-#}
-
-deserialize = function(coeffs, range)
+# Helper function to divide indices into balanced sets.
+# Ensure that all indices sets have at least min_size elements.
+.splitIndices <- function(indices, nb_per_set, min_size=1)
 {
-	#......
-	#C function (from file name)
+	L <- length(indices)
+	nb_workers <- floor( L / nb_per_set )
+	rem <- L %% nb_per_set
+	if (nb_workers == 0 || (nb_workers==1 && rem==0))
+	{
+		# L <= nb_per_set, simple case
+		return (list(indices))
+	}
+
+	indices_workers <- lapply( seq_len(nb_workers), function(i)
+		indices[(nb_per_set*(i-1)+1):(nb_per_set*i)] )
+
+	rem <- L %% nb_per_set #number of remaining unassigned items
+	if (rem == 0)
+		return (indices_workers)
+
+	rem <- (L-rem+1):L
+	# If remainder is smaller than min_size, feed it with indices from other sets
+	# until either its size exceed min_size (success) or other sets' size
+	# get lower min_size (failure).
+	while (length(rem) < min_size)
+	{
+		index <- length(rem) %% nb_workers + 1
+		if (length(indices_workers[[index]]) <= min_size)
+		{
+			stop("Impossible to split indices properly for clustering.
+				Try increasing nb_items_clust or decreasing K1")
+		}
+		rem <- c(rem, tail(indices_workers[[index]],1))
+		indices_workers[[index]] <- head( indices_workers[[index]], -1)
+	}
+	return ( c(indices_workers, list(rem) ) )
 }
 
-getSeries(data, rank=NULL, id=NULL)
+#' assignMedoids
+#'
+#' Find the closest medoid for each curve in input (by-columns matrix)
+#'
+#' @param curves (Chunk) of series whose medoids indices must be found
+#' @param medoids Matrix of medoids (in columns)
+#'
+#' @return The vector of integer assignments
+#' @export
+assignMedoids <- function(curves, medoids)
 {
-	#TODO:
+	nb_series <- ncol(curves)
+	mi <- rep(NA,nb_series)
+	for (i in seq_len(nb_series))
+		mi[i] <- which.min( colSums( sweep(medoids, 1, curves[,i], '-')^2 ) )
+	mi
 }
 
-getCoeffs(.....) #FROM BINARY FILE !!!
-{
+#' filterMA
+#'
+#' Filter [time-]series by replacing all values by the moving average of values
+#' centered around current one. Border values are averaged with available data.
+#'
+#' @param M_ A real matrix of size LxD
+#' @param w_ The (odd) number of values to average
+#'
+#' @return The filtered matrix (in columns), of same size as the input
+#' @export
+filterMA <- function(M_, w_)
+	.Call("filterMA", M_, w_, PACKAGE="epclust")
 
+#' cleanBin
+#'
+#' Remove binary files to re-generate them at next run of \code{claws()}.
+#' Note: run it in the folder where the computations occurred (or no effect).
+#'
+#' @export
+cleanBin <- function()
+{
+	bin_files <- list.files(pattern="*.epclust.bin", all.files=TRUE)
+	for (file in bin_files)
+		unlink(file)
 }