firx error in slave.c

[epclust.git] / old_C_code / stage2_UNFINISHED / src / 01_extract-features_2009.r

diff --git a/old_C_code/stage2_UNFINISHED/src/01_extract-features_2009.r b/old_C_code/stage2_UNFINISHED/src/01_extract-features_2009.r
new file mode 100644 (file)
index 0000000..99ab8c5
--- /dev/null
+++ b/old_C_code/stage2_UNFINISHED/src/01_extract-features_2009.r
@@ -0,0 +1,58 @@
+## 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("~/ownCloud/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 ####
+
+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)
+
+  auxDWT <- t(apply(datamat, 1, toDWT))
+  auxcontrib <- t(apply(auxDWT,  1, contrib))
+  rm(auxDWT)
+  
+  if(b == 1) {
+    matcontrib <- auxcontrib
+  } else {
+    matcontrib <- rbind(matcontrib, auxcontrib)
+  }
+  
+}
+
+close(con)                      # close connection to the file
+
+write.table(matcontrib, file = "~/tmp/2009_contrib.txt")
+