| 1 | ## File : 05_cluster2stepWER.r |
| 2 | ## Description : |
| 3 | |
| 4 | rm(list = ls()) |
| 5 | |
| 6 | setwd("~/ownCloud/projects/2014_EDF-Orsay-Lyon2/codes/") |
| 7 | |
| 8 | library(Rwave) # CWT |
| 9 | library(cluster) # pam |
| 10 | #library(flexclust) # kcca |
| 11 | source("aux.r") # auxiliary clustering functions |
| 12 | |
| 13 | #TODO: [plus tard] alternative à sowa (package disparu) : cwt.. |
| 14 | source("sowas-superseded.r") # auxiliary CWT functions |
| 15 | |
| 16 | ## 1. Read auxiliar data files #### |
| 17 | |
| 18 | identifiants <- read.table("identifs.txt")[ ,1] |
| 19 | dates0 <- read.table("datesall.txt")[, 1] |
| 20 | dates <- as.character(dates0[grep("2009", dates0)]) |
| 21 | rm(dates0) |
| 22 | |
| 23 | n <- length(identifiants) |
| 24 | p <- delta <- length(dates) |
| 25 | |
| 26 | synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200RC.txt"))) |
| 27 | #synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200-random.txt"))) |
| 28 | |
| 29 | nas <- which(is.na(synchros09)[, 1]) # some 1/1/2009 are missing |
| 30 | synchros09[nas, 1] <- rowMeans(synchros09[nas, 2:4]) #valeurs après 1er janvier |
| 31 | |
| 32 | #moyenne pondérée pour compléter deux demi-heures manquantes |
| 33 | imput09 <- synchros09[, 4180:4181] %*% matrix(c(2/3, 1/3, 1/3, 2/3), 2) |
| 34 | synchros09 <- cbind(synchros09[, 1:4180], imput09, synchros09[, 4181:17518]) |
| 35 | |
| 36 | conso <- synchros09[-201, ]; # series must be on rows |
| 37 | n <- nrow(conso) |
| 38 | delta <- ncol(conso) |
| 39 | |
| 40 | rm(synchros09, nas) |
| 41 | |
| 42 | ## 2. Compute WER distance matrix #### |
| 43 | |
| 44 | ## _.a CWT -- Filtering the lowest freqs (>6m) #### |
| 45 | # nvoice <- 4 |
| 46 | # # noctave4 = 2^13 = 8192 half hours ~ 180 days |
| 47 | # noctave4 <- adjust.noctave(N = delta, dt = 1, s0 = 2, |
| 48 | # tw = 0, noctave = 13) |
| 49 | # # 4 here represent 2^5 = 32 half-hours ~ 1 day |
| 50 | # scalevector4 <- 2^(4:(noctave4 * nvoice) / nvoice) * 2 |
| 51 | # lscvect4 <- length(scalevector4) |
| 52 | # lscvect <- lscvect4 # i should clean my code: werFam demands a lscvect |
| 53 | |
| 54 | |
| 55 | #17000 colonnes coeff 1, puis 17000 coeff 2... [non : dans chaque tranche du cube] |
| 56 | |
| 57 | #TODO: une fonction qui fait lignes 59 à 91 |
| 58 | |
| 59 | #cube: |
| 60 | # Xcwt4 <- toCWT(conso, noctave = noctave4, dt = 1, |
| 61 | # scalevector = scalevector4, |
| 62 | # lt = delta, smooth = FALSE, |
| 63 | # nvoice = nvoice) # observations node with CWT |
| 64 | # |
| 65 | # #matrix: |
| 66 | # ############Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect) |
| 67 | # #Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1])))) |
| 68 | # |
| 69 | # #NOTE: delta et lscvect pourraient etre gardés à part (communs) |
| 70 | # for(i in 1:n) |
| 71 | # Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) ) |
| 72 | # |
| 73 | # #rm(conso, Xcwt4); gc() |
| 74 | # |
| 75 | # ## _.b WER^2 distances ######## |
| 76 | # Xwer_dist <- matrix(0.0, n, n) |
| 77 | # for(i in 1:(n - 1)){ |
| 78 | # mat1 <- vect2mat(Xcwt2[i,]) |
| 79 | # for(j in (i + 1):n){ |
| 80 | # mat2 <- vect2mat(Xcwt2[j,]) |
| 81 | # num <- Mod(mat1 * Conj(mat2)) |
| 82 | # WX <- Mod(mat1 * Conj(mat1)) |
| 83 | # WY <- Mod(mat2 * Conj(mat2)) |
| 84 | # smsmnum <- smCWT(num, scalevector = scalevector4) |
| 85 | # smsmWX <- smCWT(WX, scalevector = scalevector4) |
| 86 | # smsmWY <- smCWT(WY, scalevector = scalevector4) |
| 87 | # wer2 <- sum(colSums(smsmnum)^2) / |
| 88 | # sum( sum(colSums(smsmWX) * colSums(smsmWY)) ) |
| 89 | # Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2)) |
| 90 | # Xwer_dist[j, i] <- Xwer_dist[i, j] |
| 91 | # } |
| 92 | # } |
| 93 | # diag(Xwer_dist) <- numeric(n) |
| 94 | # |
| 95 | # save(Xwer_dist, file = "../res/2009_synchros200WER.Rdata") |
| 96 | # save(Xwer_dist, file = "../res/2009_synchros200-randomWER.Rdata") |
| 97 | |
| 98 | load("../res/2009_synchros200WER.Rdata") |
| 99 | #load("../res/2009_synchros200-randomWER.Rdata") |
| 100 | |
| 101 | ## 3. Cluster using WER distance matrix #### |
| 102 | |
| 103 | #hc <- hclust(as.dist(Xwer_dist), method = "ward.D") |
| 104 | #plot(hc) |
| 105 | # |
| 106 | # #clust <- cutree(hc, 2) |
| 107 | # |
| 108 | for(K in 2:30){ |
| 109 | #K <- 3 |
| 110 | #pamfit <- pam(tdata[-201, ci$selectv], k = K) |
| 111 | pamfit <- pam(as.dist(Xwer_dist), k = K, diss = TRUE) |
| 112 | |
| 113 | #table(pamfit$clustering) |
| 114 | |
| 115 | SC <- matrix(0, ncol = p, nrow = K) |
| 116 | |
| 117 | clustfactor <- pamfit$clustering |
| 118 | # for(k in 1:K){ |
| 119 | # clustk <- which(clustfactor == k) |
| 120 | # if(length(clustk) > 0) { |
| 121 | # if(length(clustk) > 1) { |
| 122 | # SCk <- colSums(synchros09[which(clustfactor == k), ]) |
| 123 | # } else { |
| 124 | # SCk <- synchros09[which(clustfactor == k), ] |
| 125 | # } |
| 126 | # SC[k, ] <- SC[k, ] + SCk |
| 127 | # rm(SCk) |
| 128 | # } |
| 129 | #} |
| 130 | |
| 131 | #write.table(clustfactor, file = paste0("~/tmp/clustfactorRC", K, ".txt")) |
| 132 | #write.table(clustfactor, file = "~/tmp/clustfactor3.txt") |
| 133 | #write.table(clustfactor, file = paste0("~/tmp/clustfactorWER", K, ".txt")) |
| 134 | write.table(clustfactor, file = paste0("~/tmp/clustfactor-randomWER", K, ".txt")) |
| 135 | } |
| 136 | # |
| 137 | # # Plots |
| 138 | # layout(1) |
| 139 | # matplot(t(SC)[48*10 + 1:(48*30), ], type = 'l', ylab = '',col = 1:3, lty = 1) |
| 140 | # matplot(t(SC)[48*100 + 1:(48*30), ], type = 'l', ylab = '', col = 1:3, lty = 1) |
| 141 | # |
| 142 | # |
| 143 | # |