## File : ireland-data.r
## Description : 

rm(list = ls())
setwd("~/ownCloud/projects/2014_EDF-Orsay-Lyon2/codes/")
library(Rwave)       # CWT
library(cluster)     # pam

## 1. Read auxiliar data files ####
source("aux.r")               # auxiliary clustering functions 
source("sowas-superseded.r")  # auxiliary CWT functions
load("~/data/Irlande/Data_CER_clean/SME.RData")
SME <- as.matrix(SME)

nbdays   <- nrow(SME) / 48
nb_clust <- nbdays - 365 # last year to forecast

id_clust <- 1:(48 * nb_clust)

## 2. Compute WER distance matrix ####
conso  <- t(SME[id_clust, ]) # ts are in lines
N      <- delta <- ncol(conso) # length of one ts
n      <- nrow(conso) # number of ts

# # _.a CWT -- Filtering the lowest freqs (>6m) ####
# nvoice   <- 4
# # noctave4 = 2^12 = 4096 half hours ~ 90 days
# noctave4 <- adjust.noctave(N = N, 
#                            dt = 1, s0 = 2,
#                            tw = 0, noctave = 12)
# # 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   <- toCWT(conso, noctave = noctave4, dt = 1,
#                 scalevector = scalevector4,
#                 lt = N, smooth = FALSE, 
#                 nvoice = nvoice)      # observations node with CWT
# 
# 
# Xcwt2 <- matrix(NA_complex_, nrow = n, ncol= 2 + length((c(Xcwt4[,,1]))))
# 
# for(i in 1:n) 
#  Xcwt2[i,] <- c(N, 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(N * lscvect * (1 - wer2))
#     Xwer_dist[j, i] <- Xwer_dist[i, j]
#   }
# }
# diag(Xwer_dist) <- numeric(n)
# 
# save(Xwer_dist, file = "~/werdist-irlanda.Rdata")

load("~/werdist-irlanda.Rdata")
hc <- hclust(as.dist(Xwer_dist))

plot(hc)


Ks <- c(2:10, 15, 20, 25, 30)
for(k in seq_along(Ks)){ 
  K      <- Ks[k]
  pamfit <- pam(as.dist(Xwer_dist), k = K, diss = TRUE)
  
  fname <- paste0("clustfactor", K)
  write.table(pamfit$clustering, 
              file = paste0("~/tmp/clustfactorSME-", K, ".txt")) 
}


#dir(path = '~/tmp/', pattern = 'clustfac-
K <- 2
fname <- paste0("~/tmp/clustfactorSME-", K, ".txt")
clustfactor <- read.table(fname)$x # pamfit$clustering
 for(k in 1:K){ 
   clustk <- which(clustfactor == k)
 if(length(clustk) > 0) {
   if(length(clustk) > 1) {
     SCk <- colSums(SME[, which(clustfactor == k)])
     } else {
       SCk <- synchros09[which(clustfactor == k), ]
     }
     SC[k, ] <- SC[k, ] + SCk
     rm(SCk)
 }
 }