## File : 05_cluster2stepWER.r
## Description : 

rm(list = ls())

if(Sys.info()[4] ==  "mojarrita"){ 
  setwd("~/Documents/projects/2014_EDF-Orsay-Lyon2/codes/")
} else {
  setwd("~/ownCloud/projects/2014_EDF-Orsay-Lyon2/codes/")
}
  
library(Rwave)       # CWT
library(cluster)     # pam
#library(flexclust)   # kcca
source("aux.r")               # auxiliary clustering functions 
source("sowas-superseded.r")  # auxiliary CWT functions

## 1. Read auxiliar data files ####

identifiants <- read.table("identifs.txt")[ ,1]
dates0       <- read.table("datesall.txt")[, 1]
dates        <- as.character(dates0[grep("2009", dates0)])
rm(dates0)

#n <- length(identifiants)
#p <- length(dates)

load('~/tmp/2009synchrosdf200WER')
#load('../res/2009_synchros200WER.Rdata')
synchros09 <- synchros
load('~/tmp/2010synchrosdf200WER')
synchros10 <- synchros; rm(synchros)

conso <- lapply(synchros09, function(ll) { 
                nas <- which(is.na(ll)[, 1]) # some 1/1/2009 are missing
                ll[nas, 1] <- rowMeans(ll[nas, 2:4])
                imput <- ll[, 4180:4181] %*% matrix(c(2/3, 1/3, 1/3, 2/3), 2)
                cbind(ll[, 1:4180], imput, ll[, 4181:17518]) } )

n     <- nrow(conso[[1]])
delta <- ncol(conso[[1]])
rm(synchros09)


## 2. Compute WER distance matrix ####

## _.a CWT -- Filtering the lowest freqs (>6m) ####
nvoice   <- 4
# noctave4 = 2^13 = 8192 half hours ~ 180 days
noctave4 <- adjust.noctave(N = delta, dt = 1, s0 = 2,
                           tw = 0, noctave = 13)
# 4 here represent 2^5 = 32 half-hours ~ 1 day
scalevector4  <- 2^(4:(noctave4 * nvoice) / nvoice) * 2
lscvect4      <- length(scalevector4)
lscvect <- lscvect4  # i should clean my code: werFam demands a lscvect

Xcwt4 <- lapply(conso, function(ll)
  toCWT(ll, noctave = noctave4, dt = 1,
        scalevector = scalevector4,
        lt = delta, smooth = FALSE, 
        nvoice = nvoice)      # observations node with CWT
  )

rm(conso)

Xcwt4 <- lapply(conso, function(ll) {
  aux <- toCWT(ll, noctave = noctave4, dt = 1,
               scalevector = scalevector4,
               lt = delta, smooth = FALSE, 
               nvoice = nvoice)      # observations node with CWT
  res <- matrix(NA_complex_, nrow = n, ncol= 2 + length((c(aux[,,1]))))
  for(i in 1:n) 
    res[i, ] <- c(delta, lscvect, res[,,i] / max(Mod(res[,,i])) ) 
  res })

rm(conso)


#Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect)
#Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1]))))

#for(i in 1:n) 
#  Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) ) 

#rm(conso, Xcwt4); gc()

## _.b WER^2 distances  ########
#Xwer_dist    <- matrix(0.0, n, n)
#for(i in 1:(n - 1)){
#  mat1   <- vect2mat(Xcwt2[i,])
#  for(j in (i + 1):n){
#     mat2 <- vect2mat(Xcwt2[j,])
#     num     <- Mod(mat1 * Conj(mat2))
#     WX      <- Mod(mat1 * Conj(mat1))
#     WY      <- Mod(mat2 * Conj(mat2))
#     smsmnum <- smCWT(num, scalevector = scalevector4)
#     smsmWX  <- smCWT(WX,  scalevector = scalevector4)
#     smsmWY  <- smCWT(WY,  scalevector = scalevector4)
#     wer2    <- sum(colSums(smsmnum)^2)  /
#       sum( sum(colSums(smsmWX) * colSums(smsmWY)) )
#     Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2))
#     Xwer_dist[j, i] <- Xwer_dist[i, j]
#   }
# }
# diag(Xwer_dist) <- numeric(n)
# 
# save(Xwer_dist, file = "../res/2009_synchros200WER.Rdata")

load("../res/2009_synchros200WER.Rdata")


## 3. Cluster using WER distance matrix ####
 
#hc    <- hclust(as.dist(Xwer_dist), method = "ward.D")
#plot(hc)
# 
# #clust <- cutree(hc, 2)
# 
for(K in 2:30){ 
  #K <- 3
  #pamfit <- pam(tdata[-201, ci$selectv], k = K)
  pamfit <- pam(as.dist(Xwer_dist), k = K, diss = TRUE)
  
  #table(pamfit$clustering)

  SC <- matrix(0, ncol = p, nrow = K)

  clustfactor <- pamfit$clustering
#  for(k in 1:K){ 
#    clustk <- which(clustfactor == k)
#  if(length(clustk) > 0) {
#    if(length(clustk) > 1) {
#      SCk <- colSums(synchros09[which(clustfactor == k), ])
#      } else {
#        SCk <- synchros09[which(clustfactor == k), ]
#      }
#      SC[k, ] <- SC[k, ] + SCk
#      rm(SCk)
#  }
#}

#write.table(clustfactor, file = paste0("~/tmp/clustfactorRC", K, ".txt"))
#write.table(clustfactor, file = "~/tmp/clustfactor3.txt")
write.table(clustfactor, file = paste0("~/tmp/clustfactorWER", K, ".txt"))
}
# 
# # Plots
# layout(1)
# matplot(t(SC)[48*10 + 1:(48*30), ],  type = 'l', ylab = '',col = 1:3, lty = 1)
# matplot(t(SC)[48*100 + 1:(48*30), ], type = 'l', ylab = '', col = 1:3, lty = 1)
# 
# 
#