epclust/R/computeWerDists.R

   1 #' computeWerDists
   2 #'
   3 #' Compute the WER distances between the series at specified indices, which are
   4 #' obtaind by \code{getSeries(indices)}
   5 #'
   6 #' @param indices Range of series indices to cluster
   7 #' @inheritParams claws
   8 #' @inheritParams computeSynchrones
   9 #'
  10 #' @return A distances matrix of size K x K where K == length(indices)
  11 #'
  12 #' @export
  13 computeWerDists <- function(indices, getSeries, nb_series_per_chunk, smooth_lvl, nvoice,
  14     nbytes, endian, ncores_clust=3, verbose=FALSE, parll=TRUE)
  15 {
  16     n <- length(indices)
  17     L <- length(getSeries(1)) #TODO: not very neat way to get L
  18     noctave <- ceiling(log2(L)) #min power of 2 to cover serie range
  19     # Since a CWT contains noctave*nvoice complex series, we deduce the number of CWT to
  20     # retrieve/put in one chunk.
  21     nb_cwt_per_chunk <- max(1, floor(nb_series_per_chunk / (nvoice*noctave*2)))
  22
  23     # Initialize result as a square big.matrix of size 'number of medoids'
  24     Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
  25
  26     cwt_file <- tempfile(pattern="epclust_cwt.bin_")
  27     # Compute the getSeries(indices) CWT, and store the results in the binary file
  28     computeSaveCWT <- function(indices)
  29     {
  30         if (parll)
  31         {
  32             # parallel workers start with an empty environment
  33             require("epclust", quietly=TRUE)
  34         }
  35
  36         # Obtain CWT as big vectors of real part + imaginary part (concatenate)
  37         ts_cwt <- sapply(indices, function(i) {
  38             ts <- scale(ts(getSeries(i)), center=TRUE, scale=FALSE)
  39             ts_cwt <- Rwave::cwt(ts, noctave, nvoice, w0=2*pi, twoD=TRUE, plot=FALSE)
  40             c( as.double(Re(ts_cwt)),as.double(Im(ts_cwt)) )
  41         })
  42
  43         # Serialization
  44         binarize(ts_cwt, cwt_file, nb_cwt_per_chunk, ",", nbytes, endian)
  45     }
  46
  47     # Function to retrieve a synchrone CWT from (binary) file
  48     getCWT <- function(index, L)
  49     {
  50         flat_cwt <- getDataInFile(index, cwt_file, nbytes, endian)
  51         cwt_length <- length(flat_cwt) / 2
  52         re_part <- as.matrix(flat_cwt[1:cwt_length], nrow=L)
  53         im_part <- as.matrix(flat_cwt[(cwt_length+1):(2*cwt_length)], nrow=L)
  54         re_part + 1i * im_part
  55     }
  56
  57     # Compute distance between columns i and j for j>i
  58     computeDistances <- function(i)
  59     {
  60         if (parll)
  61         {
  62             # parallel workers start with an empty environment
  63             require("epclust", quietly=TRUE)
  64             Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
  65         }
  66
  67         if (verbose && !parll)
  68             cat(paste("   Distances from ",i," to ",i+1,"...",n,"\n", sep=""))
  69
  70         # Get CWT of column i, and run computations for columns j>i
  71         cwt_i <- getCWT(i, L)
  72         WX  <- filterMA(Mod(cwt_i * Conj(cwt_i)), smooth_lvl)
  73
  74         for (j in (i+1):n)
  75         {
  76             cwt_j <- getCWT(j, L)
  77
  78             # Compute the ratio of integrals formula 5.6 for WER^2
  79             # in https://arxiv.org/abs/1101.4744v2 paragraph 5.3
  80             num <- filterMA(Mod(cwt_i * Conj(cwt_j)), smooth_lvl)
  81             WY <- filterMA(Mod(cwt_j * Conj(cwt_j)), smooth_lvl)
  82             wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
  83
  84             Xwer_dist[i,j] <- sqrt(L * ncol(cwt_i) * (1 - wer2))
  85             Xwer_dist[j,i] <- Xwer_dist[i,j]
  86         }
  87         Xwer_dist[i,i] <- 0.
  88     }
  89
  90     if (parll)
  91     {
  92         # outfile=="" to see stderr/stdout on terminal
  93         cl <-
  94             if (verbose)
  95                 parallel::makeCluster(ncores_clust, outfile="")
  96             else
  97                 parallel::makeCluster(ncores_clust)
  98         Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
  99         parallel::clusterExport(cl, varlist=c("parll","nb_cwt_per_chunk","n","L",
 100             "Xwer_dist_desc","noctave","nvoice","getCWT"), envir=environment())
 101     }
 102
 103     if (verbose)
 104         cat(paste("--- Precompute and serialize synchrones CWT\n", sep=""))
 105
 106     # Split indices by packets of length at most nb_cwt_per_chunk
 107     indices_cwt <- .splitIndices(seq_len(n), nb_cwt_per_chunk)
 108     ignored <-
 109         if (parll)
 110             parallel::parLapply(cl, indices_cwt, computeSaveCWT)
 111         else
 112             lapply(indices_cwt, computeSaveCWT)
 113
 114     if (verbose)
 115         cat(paste("--- Compute WER distances\n", sep=""))
 116
 117     ignored <-
 118         if (parll)
 119             parallel::parLapply(cl, seq_len(n-1), computeDistances)
 120         else
 121             lapply(seq_len(n-1), computeDistances)
 122     Xwer_dist[n,n] <- 0.
 123
 124     if (parll)
 125         parallel::stopCluster(cl)
 126
 127     unlink(cwt_file) #remove binary file
 128
 129     Xwer_dist[,] #~small matrix K1 x K1
 130 }