'update'

[epclust.git] / epclust / R / computeWerDists.R

diff --git a/epclust/R/computeWerDists.R b/epclust/R/computeWerDists.R
new file mode 100644 (file)
index 0000000..aae1cc1
--- /dev/null
+++ b/epclust/R/computeWerDists.R
@@ -0,0 +1,141 @@
+#' computeWerDists
+#'
+#' Compute the WER distances between the synchrones curves (in columns), which are
+#' returned (e.g.) by \code{computeSynchrones()}
+#'
+#' @param synchrones A big.matrix of synchrones, in columns. The series have same
+#'   length as the series in the initial dataset
+#' @inheritParams claws
+#'
+#' @return A distances matrix of size K1 x K1
+#'
+#' @export
+computeWerDists = function(synchrones, nvoice, nbytes,endian,ncores_clust=1,
+       verbose=FALSE,parll=TRUE)
+{
+       n <- ncol(synchrones)
+       L <- nrow(synchrones)
+       noctave = ceiling(log2(L)) #min power of 2 to cover serie range
+
+       # Initialize result as a square big.matrix of size 'number of synchrones'
+       Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
+
+       # Generate n(n-1)/2 pairs for WER distances computations
+       pairs = list()
+       V = seq_len(n)
+       for (i in 1:n)
+       {
+               V = V[-1]
+               pairs = c(pairs, lapply(V, function(v) c(i,v)))
+       }
+
+       cwt_file = ".cwt.bin"
+       # Compute the synchrones[,indices] CWT, and store the results in the binary file
+       computeSaveCWT = function(indices)
+       {
+               if (parll)
+               {
+                       require("bigmemory", quietly=TRUE)
+                       require("Rwave", quietly=TRUE)
+                       require("epclust", quietly=TRUE)
+                       synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
+               }
+
+               # Obtain CWT as big vectors of real part + imaginary part (concatenate)
+               ts_cwt <- sapply(indices, function(i) {
+                       ts <- scale(ts(synchrones[,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)) )
+               })
+
+               # Serialization
+               binarize(ts_cwt, cwt_file, 1, ",", nbytes, endian)
+       }
+
+       if (parll)
+       {
+               cl = parallel::makeCluster(ncores_clust)
+               synchrones_desc <- bigmemory::describe(synchrones)
+               Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
+               parallel::clusterExport(cl, varlist=c("parll","synchrones_desc","Xwer_dist_desc",
+                       "noctave","nvoice","verbose","getCWT"), envir=environment())
+       }
+
+       if (verbose)
+               cat(paste("--- Precompute and serialize synchrones CWT\n", sep=""))
+
+       ignored <-
+               if (parll)
+                       parallel::parLapply(cl, 1:n, computeSaveCWT)
+               else
+                       lapply(1:n, computeSaveCWT)
+
+       # Function to retrieve a synchrone CWT from (binary) file
+       getSynchroneCWT = function(index, L)
+       {
+               flat_cwt <- getDataInFile(index, cwt_file, nbytes, endian)
+               cwt_length = length(flat_cwt) / 2
+               re_part = as.matrix(flat_cwt[1:cwt_length], nrow=L)
+               im_part = as.matrix(flat_cwt[(cwt_length+1):(2*cwt_length)], nrow=L)
+               re_part + 1i * im_part
+       }
+
+
+
+
+#TODO: better repartition here, 
+       #better code in .splitIndices :: never exceed nb_per_chunk; arg: min_per_chunk (default: 1)
+###TODO: reintroduire nb_items_clust ======> l'autre est typiquement + grand !!! (pas de relation !)
+
+
+
+       # Compute distance between columns i and j in synchrones
+       computeDistanceIJ = function(pair)
+       {
+               if (parll)
+               {
+                       # parallel workers start with an empty environment
+                       require("bigmemory", quietly=TRUE)
+                       require("epclust", quietly=TRUE)
+                       synchrones <- bigmemory::attach.big.matrix(synchrones_desc)
+                       Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
+               }
+
+               i = pair[1] ; j = pair[2]
+               if (verbose && j==i+1 && !parll)
+                       cat(paste("   Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
+
+               # Compute CWT of columns i and j in synchrones
+               L = nrow(synchrones)
+               cwt_i <- getSynchroneCWT(i, L)
+               cwt_j <- getSynchroneCWT(j, L)
+
+               # Compute the ratio of integrals formula 5.6 for WER^2
+               # in https://arxiv.org/abs/1101.4744v2 §5.3
+               num <- filterMA(Mod(cwt_i * Conj(cwt_j)))
+               WX  <- filterMA(Mod(cwt_i * Conj(cwt_i)))
+               WY <- filterMA(Mod(cwt_j * Conj(cwt_j)))
+               wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
+
+               Xwer_dist[i,j] <- sqrt(L * ncol(cwt_i) * (1 - wer2))
+               Xwer_dist[j,i] <- Xwer_dist[i,j]
+               Xwer_dist[i,i] <- 0.
+       }
+
+       if (verbose)
+               cat(paste("--- Compute WER distances\n", sep=""))
+
+       ignored <-
+               if (parll)
+                       parallel::parLapply(cl, pairs, computeDistanceIJ)
+               else
+                       lapply(pairs, computeDistanceIJ)
+
+       if (parll)
+               parallel::stopCluster(cl)
+
+       unlink(cwt_file)
+
+       Xwer_dist[n,n] = 0.
+       Xwer_dist[,] #~small matrix K1 x K1
+}