## File : 01_extract-features_2009.r
## Description : Using the full data matrix, we extract handy features to
##               cluster.

rm(list = ls())

#source('http://eric.univ-lyon2.fr/~jcugliari/codes/functional-clustering.r')
setwd("~/Documents/projects/2014_EDF-Orsay-Lyon2/codes/")
source('aux2.r')

## 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 ####

close(con)
con <- file("~/tmp/2009_full.txt")  # Establish a connection to the file
open(con, "r")                      # Open the connection

for(b in seq_along(blocks)){        # Reading loop
  nb <- blocks[b]
  actual <- readLines(con = con, n = nb )
  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)

  nas <- which(is.na(datamat)[, 1]) # some 1/1/2009 are missing
  if(length(nas)>0) datamat[nas, 1] <- rowMeans(datamat[nas, 2:4])
  
  imput   <- datamat[, 4180:4181] %*% matrix(c(2/3, 1/3, 1/3, 2/3), 2)
  datamat <- cbind(datamat[, 1:4180], imput, datamat[, 4181:17518])
  
  dayimp   <- t(apply(datamat, 1, dayimpact))
  nightimp <- t(apply(datamat, 1, nightimpact))
  lunchimp <- t(apply(datamat, 1, lunchimpact))
  
  auxfeat  <- cbind(dayimp, nightimp, lunchimp)
  
  if(b == 1) {
    matfeat <- auxfeat 
  } else {
    matfeat <- rbind(matfeat, auxfeat)
  }
  
}

close(con)                      # close connection to the file

write.table(matfeat, file = "~/tmp/2009_impacts.txt")