Commit | Line | Data |
---|---|---|
ad642dc6 BA |
1 | ## File : 01_extract-features_2009.r |
2 | ## Description : Using the full data matrix, we extract handy features to | |
3 | ## cluster. | |
4 | ||
5 | rm(list = ls()) | |
6 | ||
7 | source('http://eric.univ-lyon2.fr/~jcugliari/codes/functional-clustering.r') | |
8 | setwd("~/ownCloud/projects/2014_EDF-Orsay-Lyon2/codes/") | |
9 | ||
10 | ## 1. Read auxiliar data files #### | |
11 | ||
12 | identifiants <- read.table("identifs.txt")[ ,1] | |
13 | dates0 <- read.table("datesall.txt")[, 1] | |
14 | dates <- dates0[grep("2009", dates0)] | |
15 | rm(dates0) | |
16 | ||
17 | n <- length(identifiants) | |
18 | p <- length(dates) | |
19 | ||
20 | blocks <- c(rep(6500, 3), 5511) | |
21 | ||
22 | # table( substr(dates, 11, 15) ) # Sunlight time saving produces an | |
23 | # unbalanced number of time points | |
24 | # per time stepa across the year | |
25 | ||
26 | ||
27 | ## 2. Process the large file #### | |
28 | ||
29 | close(con) | |
30 | con <- file("~/tmp/2009_full.txt") # Establish a connection to the file | |
31 | open(con, "r") # Open the connection | |
32 | ||
33 | for(b in seq_along(blocks)){ # Reading loop | |
34 | nb <- blocks[b] | |
35 | actual <- readLines(con = con, n = nb ) | |
36 | auxmat <- matrix(unlist(strsplit(actual, " ")), ncol = p + 1, byrow = TRUE) | |
37 | rm(actual) | |
38 | ||
39 | datamat <- t(apply(auxmat[, -1], 1, as.numeric)) | |
40 | rownames(datamat) <- substr(auxmat[, 1], 2, 7) | |
41 | rm(auxmat) | |
42 | ||
43 | auxDWT <- t(apply(datamat, 1, toDWT)) | |
44 | auxcontrib <- t(apply(auxDWT, 1, contrib)) | |
45 | rm(auxDWT) | |
46 | ||
47 | if(b == 1) { | |
48 | matcontrib <- auxcontrib | |
49 | } else { | |
50 | matcontrib <- rbind(matcontrib, auxcontrib) | |
51 | } | |
52 | ||
53 | } | |
54 | ||
55 | close(con) # close connection to the file | |
56 | ||
57 | write.table(matcontrib, file = "~/tmp/2009_contrib.txt") | |
58 |