Commit | Line | Data |
---|---|---|
ad642dc6 BA |
1 | ## File : 05_cluster2stepWER.r |
2 | ## Description : | |
3 | ||
4 | rm(list = ls()) | |
5 | ||
6 | if(Sys.info()[4] == "mojarrita"){ | |
7 | setwd("~/Documents/projects/2014_EDF-Orsay-Lyon2/codes/") | |
8 | } else { | |
9 | setwd("~/2014_EDF-Orsay-Lyon2/codes/") | |
10 | } | |
11 | ||
12 | library(Rwave) # CWT | |
13 | library(cluster) # pam | |
14 | #library(flexclust) # kcca | |
15 | source("aux.r") # auxiliary clustering functions | |
16 | source("sowas-superseded.r") # auxiliary CWT functions | |
17 | ||
18 | ## 1. Read auxiliar data files #### | |
19 | ||
20 | identifiants <- read.table("identifs.txt")[ ,1] | |
21 | dates0 <- read.table("datesall.txt")[, 1] | |
22 | dates <- as.character(dates0[grep("2009", dates0)]) | |
23 | rm(dates0) | |
24 | ||
25 | n <- length(identifiants) | |
26 | p <- delta <- length(dates) | |
27 | ||
28 | load("~/tmp/2009_synchros200RND") | |
29 | synchros09 <- synchros[[1]] | |
30 | #synchros09 <- as.matrix(read.table("~/tmp/2009_synchros200RANDOM.txt")) | |
31 | #synchros09 <- t(as.matrix(read.table("~/tmp/2009_synchros200RANDOM.txt"))) | |
32 | nas <- which(is.na(synchros09)[, 1]) # some 1/1/2009 are missing | |
33 | synchros09[nas, 1] <- rowMeans(synchros09[nas, 2:4]) | |
34 | ||
35 | imput09 <- synchros09[, 4180:4181] %*% matrix(c(2/3, 1/3, 1/3, 2/3), 2) | |
36 | synchros09 <- cbind(synchros09[, 1:4180], imput09, synchros09[, 4181:17518]) | |
37 | ||
38 | conso <- (synchros09)[-201, ]; # series must be on rows | |
39 | n <- nrow(conso) | |
40 | delta <- ncol(conso) | |
41 | ||
42 | rm(synchros09, nas) | |
43 | ||
44 | ## 2. Compute WER distance matrix #### | |
45 | ||
46 | ## _.a CWT -- Filtering the lowest freqs (>6m) #### | |
47 | nvoice <- 4 | |
48 | # noctave4 = 2^13 = 8192 half hours ~ 180 days | |
49 | noctave4 <- adjust.noctave(N = delta, dt = 1, s0 = 2, | |
50 | tw = 0, noctave = 13) | |
51 | # 4 here represent 2^5 = 32 half-hours ~ 1 day | |
52 | scalevector4 <- 2^(4:(noctave4 * nvoice) / nvoice) * 2 | |
53 | lscvect4 <- length(scalevector4) | |
54 | lscvect <- lscvect4 # i should clean my code: werFam demands a lscvect | |
55 | Xcwt4 <- toCWT(conso, noctave = noctave4, dt = 1, | |
56 | scalevector = scalevector4, | |
57 | lt = delta, smooth = FALSE, | |
58 | nvoice = nvoice) # observations node with CWT | |
59 | ||
60 | Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect) | |
61 | Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1])))) | |
62 | ||
63 | for(i in 1:n) | |
64 | Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) ) | |
65 | ||
66 | rm(conso, Xcwt4); gc() | |
67 | ||
68 | ## _.b WER^2 distances ######## | |
69 | Xwer_dist <- matrix(0.0, n, n) | |
70 | for(i in 1:(n - 1)){ | |
71 | cat(sprintf('\nIter: , %i', i)) | |
72 | mat1 <- vect2mat(Xcwt2[i,]) | |
73 | for(j in (i + 1):n){ | |
74 | mat2 <- vect2mat(Xcwt2[j,]) | |
75 | num <- Mod(mat1 * Conj(mat2)) | |
76 | WX <- Mod(mat1 * Conj(mat1)) | |
77 | WY <- Mod(mat2 * Conj(mat2)) | |
78 | smsmnum <- smCWT(num, scalevector = scalevector4) | |
79 | smsmWX <- smCWT(WX, scalevector = scalevector4) | |
80 | smsmWY <- smCWT(WY, scalevector = scalevector4) | |
81 | wer2 <- sum(colSums(smsmnum)^2) / | |
82 | sum( sum(colSums(smsmWX) * colSums(smsmWY)) ) | |
83 | Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2)) | |
84 | Xwer_dist[j, i] <- Xwer_dist[i, j] | |
85 | } | |
86 | } | |
87 | diag(Xwer_dist) <- numeric(n) | |
88 | ||
89 | save(Xwer_dist, file = "../res/2009_synchros200RANDOM-WER.Rdata") | |
90 | ||
91 | #load("../res/2009_synchros200WER.Rdata") | |
92 | ||
93 | ||
94 | ## 3. Cluster using WER distance matrix #### | |
95 | ||
96 | #hc <- hclust(as.dist(Xwer_dist), method = "ward.D") | |
97 | #plot(hc) | |
98 | # | |
99 | # #clust <- cutree(hc, 2) | |
100 | # | |
101 | for(K in 2:30){ | |
102 | #K <- 3 | |
103 | #pamfit <- pam(tdata[-201, ci$selectv], k = K) | |
104 | pamfit <- pam(as.dist(Xwer_dist), k = K, diss = TRUE) | |
105 | ||
106 | #table(pamfit$clustering) | |
107 | ||
108 | SC <- matrix(0, ncol = p, nrow = K) | |
109 | ||
110 | clustfactor <- pamfit$clustering | |
111 | # for(k in 1:K){ | |
112 | # clustk <- which(clustfactor == k) | |
113 | # if(length(clustk) > 0) { | |
114 | # if(length(clustk) > 1) { | |
115 | # SCk <- colSums(synchros09[which(clustfactor == k), ]) | |
116 | # } else { | |
117 | # SCk <- synchros09[which(clustfactor == k), ] | |
118 | # } | |
119 | # SC[k, ] <- SC[k, ] + SCk | |
120 | # rm(SCk) | |
121 | # } | |
122 | #} | |
123 | ||
124 | # #write.table(clustfactor, file = paste0("~/tmp/clustfactorRC", K, ".txt")) | |
125 | # #write.table(clustfactor, file = "~/tmp/clustfactor3.txt") | |
126 | write.table(clustfactor, file = paste0("~/tmp/clustfactorRANDOM", K, ".txt")) | |
127 | } | |
128 | # | |
129 | # # Plots | |
130 | # layout(1) | |
131 | # matplot(t(SC)[48*10 + 1:(48*30), ], type = 'l', ylab = '',col = 1:3, lty = 1) | |
132 | # matplot(t(SC)[48*100 + 1:(48*30), ], type = 'l', ylab = '', col = 1:3, lty = 1) | |
133 | # | |
134 | # | |
135 | # |