old_C_code/stage2_UNFINISHED/src/05_cluster2stepWER.r

   1 ## File : 05_cluster2stepWER.r
   2 ## Description :
   3
   4 rm(list = ls())
   5
   6 setwd("~/ownCloud/projects/2014_EDF-Orsay-Lyon2/codes/")
   7
   8 library(Rwave)       # CWT
   9 library(cluster)     # pam
  10 #library(flexclust)   # kcca
  11 source("aux.r")               # auxiliary clustering functions
  12
  13 #TODO: [plus tard] alternative à sowa (package disparu) : cwt..
  14 source("sowas-superseded.r")  # auxiliary CWT functions
  15
  16 ## 1. Read auxiliar data files ####
  17
  18 identifiants <- read.table("identifs.txt")[ ,1]
  19 dates0       <- read.table("datesall.txt")[, 1]
  20 dates        <- as.character(dates0[grep("2009", dates0)])
  21 rm(dates0)
  22
  23 n     <- length(identifiants)
  24 p <- delta <- length(dates)
  25
  26 synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200RC.txt")))
  27 #synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200-random.txt")))
  28
  29 nas <- which(is.na(synchros09)[, 1]) # some 1/1/2009 are missing
  30 synchros09[nas, 1] <- rowMeans(synchros09[nas, 2:4]) #valeurs après 1er janvier
  31
  32 #moyenne pondérée pour compléter deux demi-heures manquantes
  33 imput09 <- synchros09[, 4180:4181] %*% matrix(c(2/3, 1/3, 1/3, 2/3), 2)
  34 synchros09 <- cbind(synchros09[, 1:4180], imput09, synchros09[, 4181:17518])
  35
  36 conso <- synchros09[-201, ];  # series must be on rows
  37 n     <- nrow(conso)
  38 delta <- ncol(conso)
  39
  40 rm(synchros09, nas)
  41
  42 ## 2. Compute WER distance matrix ####
  43
  44 ## _.a CWT -- Filtering the lowest freqs (>6m) ####
  45 nvoice   <- 4
  46 # # noctave4 = 2^13 = 8192 half hours ~ 180 days
  47 noctave4 <- adjust.noctave(N = delta, dt = 1, s0 = 2,
  48                            tw = 0, noctave = 13)
  49 # # 4 here represent 2^5 = 32 half-hours ~ 1 day
  50 scalevector4  <- 2^(4:(noctave4 * nvoice) / nvoice) * 2
  51 lscvect4      <- length(scalevector4)
  52 lscvect <- lscvect4  # i should clean my code: werFam demands a lscvect
  53
  54
  55 #(Benjamin)
  56 #à partir de là, "conso" == courbes synchrones
  57 n     <- nrow(conso)
  58 delta <- ncol(conso)
  59
  60
  61 #17000 colonnes coeff 1, puis 17000 coeff 2... [non : dans chaque tranche du cube]
  62
  63 #TODO: une fonction qui fait lignes 59 à 91
  64
  65 #cube:
  66 # Xcwt4   <- toCWT(conso, noctave = noctave4, dt = 1,
  67 #                 scalevector = scalevector4,
  68 #                 lt = delta, smooth = FALSE,
  69 #                 nvoice = nvoice)      # observations node with CWT
  70 #
  71 # #matrix:
  72 # ############Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect)
  73 # #Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1]))))
  74 #
  75 # #NOTE: delta et lscvect pourraient etre gardés à part (communs)
  76 # for(i in 1:n)
  77 #  Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) )
  78 #
  79 # #rm(conso, Xcwt4); gc()
  80 #
  81 # ## _.b WER^2 distances  ########
  82 # Xwer_dist    <- matrix(0.0, n, n)
  83 # for(i in 1:(n - 1)){
  84 #  mat1   <- vect2mat(Xcwt2[i,])
  85 #  for(j in (i + 1):n){
  86 #     mat2 <- vect2mat(Xcwt2[j,])
  87 #     num     <- Mod(mat1 * Conj(mat2))
  88 #     WX      <- Mod(mat1 * Conj(mat1))
  89 #     WY      <- Mod(mat2 * Conj(mat2))
  90 #     smsmnum <- smCWT(num, scalevector = scalevector4)
  91 #     smsmWX  <- smCWT(WX,  scalevector = scalevector4)
  92 #     smsmWY  <- smCWT(WY,  scalevector = scalevector4)
  93 #     wer2    <- sum(colSums(smsmnum)^2)  /
  94 #       sum( sum(colSums(smsmWX) * colSums(smsmWY)) )
  95 #     Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2))
  96 #     Xwer_dist[j, i] <- Xwer_dist[i, j]
  97 #   }
  98 # }
  99 # diag(Xwer_dist) <- numeric(n)
 100 #
 101 # save(Xwer_dist, file = "../res/2009_synchros200WER.Rdata")
 102 # save(Xwer_dist, file = "../res/2009_synchros200-randomWER.Rdata")
 103
 104
 105
 106 #lignes 59 à 91 "dépliées" :
 107 Xcwt4   <- toCWT(conso, noctave = noctave4, dt = 1,
 108                  scalevector = scalevector4,
 109                  lt = delta, smooth = FALSE,
 110                  nvoice = nvoice)      # observations node with CWT
 111
 112  #matrix:
 113  ############Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect)
 114  Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1]))))
 115
 116  #NOTE: delta et lscvect pourraient etre gardés à part (communs)
 117  for(i in 1:n)
 118     Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) )
 119
 120  #rm(conso, Xcwt4); gc()
 121
 122  ## _.b WER^2 distances  ########
 123  Xwer_dist    <- matrix(0.0, n, n)
 124  for(i in 1:(n - 1)){
 125   mat1   <- vect2mat(Xcwt2[i,])
 126
 127  #NOTE: vect2mat = as.matrix ?! (dans aux.R)
 128   vect2mat <- function(vect){
 129                  vect <- as.vector(vect)
 130                  matrix(vect[-(1:2)], delta, lscvect)
 131                }
 132
 133  for(j in (i + 1):n){
 134      mat2 <- vect2mat(Xcwt2[j,])
 135      num     <- Mod(mat1 * Conj(mat2))
 136      WX      <- Mod(mat1 * Conj(mat1))
 137      WY      <- Mod(mat2 * Conj(mat2))
 138      smsmnum <- smCWT(num, scalevector = scalevector4)
 139      smsmWX  <- smCWT(WX,  scalevector = scalevector4)
 140      smsmWY  <- smCWT(WY,  scalevector = scalevector4)
 141      wer2    <- sum(colSums(smsmnum)^2)  /
 142        sum( sum(colSums(smsmWX) * colSums(smsmWY)) )
 143      Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2))
 144      Xwer_dist[j, i] <- Xwer_dist[i, j]
 145    }
 146  }
 147  diag(Xwer_dist) <- numeric(n)
 148
 149 #fonction smCWT (dans aux.R)
 150   smCWT <- function(CWT, sw=  0,  tw=  0, swabs= 0,
 151                        nvoice= 12, noctave= 2, s0= 2, w0= 2*pi,
 152                        lt= 24, dt= 0.5, scalevector )
 153          {
 154 #         noctave  <- adjust.noctave(lt, dt, s0, tw, noctave)
 155 #         scalevector  <- 2^(0:(noctave * nvoice) / nvoice) * s0
 156          wsp     <- Mod(CWT)
 157          smwsp   <- smooth.matrix(wsp, swabs)
 158          smsmwsp <- smooth.time(smwsp, tw, dt, scalevector)
 159          smsmwsp
 160        }
 161
 162  #dans sowas.R
 163 smooth.matrix <- function(wt,swabs){
 164
 165   if (swabs != 0)
 166     smwt <- t(filter(t(wt),rep(1,2*swabs+1)/(2*swabs+1)))
 167   else
 168     smwt <- wt
 169
 170   smwt
 171
 172 }
 173 smooth.time <- function(wt,tw,dt,scalevector){
 174
 175   smwt <- wt
 176
 177   if (tw != 0){
 178     for (i in 1:length(scalevector)){
 179
 180       twi <- as.integer(scalevector[i]*tw/dt)
 181       smwt[,i] <- filter(wt[,i],rep(1,2*twi+1)/(2*twi+1))
 182
 183     }
 184   }
 185   smwt
 186 }
 187
 188 #et filter() est dans stats::
 189
 190 #cf. filters en C dans : https://svn.r-project.org/R/trunk/src/library/stats/src/filter.c
 191
 192
 193
 194 load("../res/2009_synchros200WER.Rdata")
 195 #load("../res/2009_synchros200-randomWER.Rdata")
 196
 197 ## 3. Cluster using WER distance matrix ####
 198
 199 #hc    <- hclust(as.dist(Xwer_dist), method = "ward.D")
 200 #plot(hc)
 201 #
 202 # #clust <- cutree(hc, 2)
 203 #
 204 for(K in 2:30){
 205   #K <- 3
 206   #pamfit <- pam(tdata[-201, ci$selectv], k = K)
 207   pamfit <- pam(as.dist(Xwer_dist), k = K, diss = TRUE)
 208
 209   #table(pamfit$clustering)
 210
 211   SC <- matrix(0, ncol = p, nrow = K)
 212
 213   clustfactor <- pamfit$clustering
 214 #  for(k in 1:K){
 215 #    clustk <- which(clustfactor == k)
 216 #  if(length(clustk) > 0) {
 217 #    if(length(clustk) > 1) {
 218 #      SCk <- colSums(synchros09[which(clustfactor == k), ])
 219 #      } else {
 220 #        SCk <- synchros09[which(clustfactor == k), ]
 221 #      }
 222 #      SC[k, ] <- SC[k, ] + SCk
 223 #      rm(SCk)
 224 #  }
 225 #}
 226
 227 #write.table(clustfactor, file = paste0("~/tmp/clustfactorRC", K, ".txt"))
 228 #write.table(clustfactor, file = "~/tmp/clustfactor3.txt")
 229 #write.table(clustfactor, file = paste0("~/tmp/clustfactorWER", K, ".txt"))
 230 write.table(clustfactor, file = paste0("~/tmp/clustfactor-randomWER", K, ".txt"))
 231 }
 232 #
 233 # # Plots
 234 # layout(1)
 235 # matplot(t(SC)[48*10 + 1:(48*30), ],  type = 'l', ylab = '',col = 1:3, lty = 1)
 236 # matplot(t(SC)[48*100 + 1:(48*30), ], type = 'l', ylab = '', col = 1:3, lty = 1)
 237 #
 238 #
 239 #