'update'

[epclust.git] / code / stage2 / src / 05_cluster2stepWER.r

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

rm(list = ls())

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source("sowas-superseded.r")  # auxiliary CWT functions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 <- delta <- length(dates)

synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200RC.txt")))
#synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200-random.txt")))

nas <- which(is.na(synchros09)[, 1]) # some 1/1/2009 are missing
synchros09[nas, 1] <- rowMeans(synchros09[nas, 2:4])

imput09 <- synchros09[, 4180:4181] %*% matrix(c(2/3, 1/3, 1/3, 2/3), 2)
synchros09 <- cbind(synchros09[, 1:4180], imput09, synchros09[, 4181:17518])

conso <- synchros09[-201, ];  # series must be on rows 
n     <- nrow(conso)
delta <- ncol(conso)

rm(synchros09, nas)

## 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   <- toCWT(conso, noctave = noctave4, dt = 1,
#                 scalevector = scalevector4,
#                 lt = delta, smooth = FALSE, 
#                 nvoice = nvoice)      # observations node with CWT
# 
# #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")
# save(Xwer_dist, file = "../res/2009_synchros200-randomWER.Rdata")

load("../res/2009_synchros200WER.Rdata")
#load("../res/2009_synchros200-randomWER.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"))
write.table(clustfactor, file = paste0("~/tmp/clustfactor-randomWER", 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)
# 
# 
#