errWarn <- function(ignored)
paste("Cannot convert argument' ",substitute(x),"' to integer", sep="")
if (!is.integer(x))
- tryCatch({x = as.integer(x)[1]; if (is.na(x)) stop()},
- warning = errWarn, error = errWarn)
+ tryCatch({x <- as.integer(x)[1]; if (is.na(x)) stop()},
+ warning=errWarn, error=errWarn)
if (!condition(x))
{
stop(paste("Argument '",substitute(x),
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)
+ tryCatch({x <- as.logical(x)[1]; if (is.na(x)) stop()},
+ warning=errWarn, error=errWarn)
x
}
#' 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 [big.]matrix of series (in columns), of size L x n
+#' @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, coin=FALSE)
+curvesToContribs <- function(curves, wav_filt, contrib_type)
{
- L = nrow(series)
- D = ceiling( log2(L) )
+ series <- as.matrix(curves)
+ L <- nrow(series)
+ D <- ceiling( log2(L) )
# Series are interpolated to all have length 2^D
- nb_sample_points = 2^D
+ nb_sample_points <- 2^D
apply(series, 2, function(x) {
- interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
- W = wavelets::dwt(interpolated_curve, filter=wav_filt, D)@W
+ interpolated_curve <- spline(1:L, x, n=nb_sample_points)$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) ) ) ) )
+ nrj <- rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
if (contrib_type!="absolute")
- nrj = nrj / sum(nrj)
+ nrj <- nrj / sum(nrj)
if (contrib_type=="logit")
- nrj = - log(1 - nrj)
- nrj
+ nrj <- - log(1 - nrj)
+ unname( nrj )
})
}
-# Helper function to divide indices into balanced sets
-# If max == TRUE, sets sizes cannot exceed nb_per_set
-.splitIndices = function(indices, nb_per_set, max=FALSE)
+# 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)
{
- L = length(indices)
- nb_workers = floor( L / nb_per_set )
- rem = L %% nb_per_set
+ 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
- indices_workers = list(indices)
+ return (list(indices))
}
- else
- {
- indices_workers = lapply( seq_len(nb_workers), function(i)
- indices[(nb_per_set*(i-1)+1):(nb_per_set*i)] )
- if (max)
- {
- # Sets are not so well balanced, but size is supposed to be critical
- return ( c( indices_workers, if (rem>0) list((L-rem+1):L) else NULL ) )
- }
+ indices_workers <- lapply( seq_len(nb_workers), function(i)
+ indices[(nb_per_set*(i-1)+1):(nb_per_set*i)] )
- # Spread the remaining load among the workers
- rem = L %% nb_per_set
- while (rem > 0)
+ 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)
{
- index = rem%%nb_workers + 1
- indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
- rem = rem - 1
+ 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)
}
- indices_workers
+ return ( c(indices_workers, list(rem) ) )
+}
+
+#' assignMedoids
+#'
+#' Find the closest medoid for each curve in input
+#'
+#' @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)
+{
+ 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
}
#' filterMA
#' @param M_ A real matrix of size LxD
#' @param w_ The (odd) number of values to average
#'
-#' @return The filtered matrix, of same size as the input
+#' @return The filtered matrix (in columns), of same size as the input
#' @export
-filterMA = function(M_, w_)
+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).
+#' To be run in the folder where computations occurred (or no effect).
#'
#' @export
cleanBin <- function()
{
- bin_files = list.files(pattern = "*.epclust.bin", all.files=TRUE)
+ bin_files <- list.files(pattern="*.epclust.bin", all.files=TRUE)
for (file in bin_files)
unlink(file)
}