complete first draft of package

[epclust.git] / old_C_code / stage2_UNFINISHED / src / unused / 00_plots-energycon.r

## File : 00_plots-energycon.r
## Description : Using the full data matrix, we extract handy features to
##               cluster.

rm(list = ls())

library(Rwave)       # CWT
#library(cluster)     # pam
#library(flexclust)   # kcca
source("aux.r")               # auxiliary clustering functions 
source("sowas-superseded.r")  # auxiliary CWT functions
source('http://eric.univ-lyon2.fr/~jcugliari/codes/functional-clustering.r')
setwd("~/recherche/03_projects/2014_EDF-Orsay-Lyon2/codes/")


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

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

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

#blocks <- c(rep(6500, 3), 5511)  

# table( substr(dates, 11, 15) ) # Sunlight time saving produces an 
# unbalanced number of time points
# per time stepa across the year


## 2. Process the large file ####

# if(exists("con")) close(con)
# con <- file("~/tmp/2009_full.txt")  # Establish a connection to the file
# open(con, "r")                      # Open the connection
# 
# nb <- 4
# actual <- readLines(con = con, n = nb )[-3]
# auxmat <- matrix(unlist(strsplit(actual, " ")), ncol = p + 1, byrow = TRUE)
# rm(actual)
#   
# datamat <- t(apply(auxmat[, -1], 1, as.numeric))
# rownames(datamat) <- substr(auxmat[, 1], 2, 7)
# rm(auxmat)
# 
# datamat <- datamat[, 1:(48 * 14)]
# p <- ncol(datamat)
# 
# auxDWT <- t(apply(datamat, 1, toDWT))
# matcontrib <- t(apply(auxDWT,  1, contrib))
# rm(auxDWT)
# 
# close(con); rm(con)                    # close connection to the file


load("~/data/Irlande/Data_CER_clean/SME.RData")

smp <- c(4, 79, 126)

datamat <- t(SME[1:(48 * 7), smp])
p <- ncol(datamat)

auxDWT <- t(apply(datamat, 1, toDWT))
matcontrib <- t(apply(auxDWT,  1, contrib))
rm(auxDWT)

matplot(t(datamat), type = "l", lty = 1, 
        col = 1:8, lwd = 2)

pdf("~/courbes.pdf")
#par(mai = c(1, 1, 0.8, 0.6), mfcol = c(4, 2), cex  = 2)
for(courbe in 1:ncol(SME)) {
  plot(SME[1:(48 * 7), courbe], main = paste(courbe),
       xlab = "", ylab = "", type = "l")
}
dev.off()




## Plots for ENERGYCON full article ####
op <- par()

col <- c("grey", "black", "black")
## Curves
pdf('~/curves.pdf', width = 12)
par(mai = c(1.3, 1.3, 0.1, 0.1), cex  = 1.2)
matplot(t(datamat), type = "l", lty = c(1, 1, 2), 
        lwd = 2, col = col, # c(1, 2, 4),
        ylab = "Load", xlab = "Time (1/2 hours)")
legend("top", c("Cust. A", "Cust. B", "Cust. C"),
       col = col, lty = c(1, 1, 2), ncol = 3, lwd = 2)
# matplot(scale(t(datamat), scale = F), 
#         type = "l", lty = 1, col = c(1, 2, 4), lwd = 2, 
#         ylab = "Load", xlab = "Time (1/2 hours)")
dev.off()

normi <- function(x) x / max(x)
normi2 <- function(x) (x - min(x)) / (max(x) - min(x))

matplot(apply(datamat, 1, normi2),
        type = "l", lty = 1, col = c(1, 2, 4), lwd = 2, 
        ylab = "Load", xlab = "Time (1/2 hours)")


cont_dist <- dist(scale(matcontrib)) 
cont_dist <- cont_dist / max(cont_dist)


delta <- p
n     <- nrow(datamat)

## _.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 = 10)
# 10 here represent 2^10 = 1024 half-hours ~ 2 weeks day
scalevector4  <- 2^(4:(noctave4 * nvoice) / nvoice) * 2
lscvect4      <- length(scalevector4)
lscvect <- lscvect4  # i should clean my code: werFam demands a lscvect
Xcwt4   <- toCWT(datamat, noctave = noctave4, dt = 1,
                 scalevector = scalevector4,
                 lt = delta, 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(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) ) 

rm(conso, Xcwt4); gc()

lscvect <- 41 ## very very nasty: toCWT changes scalevector to 41 (instead of
              ## the original length--37--)
## _.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)


Xwer_dist <- Xwer_dist / max(Xwer_dist)


pdf("~/cmdscale.pdf", width = 14)
#layout(matrix(1:2, 1, 2))
par(mai = c(1, 1, 0.8, 0.6), mfcol = c(1, 2), cex  = 2)
plot(cmdscale(cont_dist), pch = c("A", "B", "C"),#c(15, 17, 19), 
     main = "RC based distance",
     #col = c(1, 2, 4), 
     xlim = c(-1, 1), ylim = c(-1, 1), 
     xlab = "", ylab = "", asp = 1)
abline(h= 0, lwd = 2); abline(v = 0, lwd = 2); grid(lty = 1)

plot(cmdscale(Xwer_dist), pch = c("A", "B", "C"),#c(15, 17, 19),
     main = "WER distance",
     #col = c(1, 2, 4), 
     xlim = c(-1, 1), ylim = c(-1, 1), 
     xlab = "", ylab = "", asp = 1)
abline(h= 0, lwd = 2); abline(v = 0, lwd = 2); grid(lty = 1)
dev.off()



## Effectives distribution
#load('../res/clfit500.Rdata')
pdf("~/distro500.pdf", width = 12)
plot(sort(table(clfit$clustering), decreasing = TRUE), 
     type ="s", ylab = "Effectives", xlab = "Class", lwd = 2)
abline(v = 200)
#dev.off()