finish simplifications on stage2.R
[epclust.git] / epclust / R / clustering.R
1 oneIteration = function(..........)
2 {
3 cl_clust = parallel::makeCluster(ncores_clust)
4 parallel::clusterExport(cl_clust, .............., envir=........)
5 indices_clust = indices_task[[i]]
6 repeat
7 {
8 nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
9 indices_workers = list()
10 #indices[[i]] == (start_index,number_of_elements)
11 for (i in 1:nb_workers)
12 {
13 upper_bound = ifelse( i<nb_workers,
14 min(nb_series_per_chunk*i,length(indices_clust)), length(indices_clust) )
15 indices_workers[[i]] = indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
16 }
17 indices_clust = parallel::parSapply(cl, indices_workers, processChunk, K1, K2*(WER=="mix"))
18 if ( (WER=="end" && length(indices_clust) == K1) ||
19 (WER=="mix" && length(indices_clust) == K2) )
20 {
21 break
22 }
23 }
24 parallel::stopCluster(cl_clust)
25 res_clust
26 }
27
28 processChunk = function(indices, K1, K2)
29 {
30 #1) retrieve data (coeffs)
31 coeffs = getCoeffs(indices)
32 #2) cluster
33 cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1)
34 #3) WER (optional)
35 if (K2 > 0)
36 {
37 curves = computeSynchrones(cl)
38 dists = computeWerDists(curves)
39 cl = computeClusters(dists, K2)
40 }
41 cl
42 }
43
44 computeClusters = function(data, K)
45 {
46 library(cluster)
47 pam_output = cluster::pam(data, K)
48 return ( list( clusts=pam_output$clustering, medoids=pam_output$medoids,
49 ranks=pam_output$id.med ) )
50 }
51
52 #TODO: appendCoeffs() en C --> serialize et append to file
53
54 computeSynchrones = function(...)
55 {
56
57 }
58
59 #Entrée : courbes synchrones, soit après étape 1 itérée, soit après chaqure étape 1
60 computeWerDist = function(conso)
61 {
62 if (!require("Rwave", quietly=TRUE))
63 stop("Unable to load Rwave library")
64 n <- nrow(conso)
65 delta <- ncol(conso)
66 #TODO: automatic tune of all these parameters ? (for other users)
67 nvoice <- 4
68 # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(conso))
69 noctave = 13
70 # 4 here represent 2^5 = 32 half-hours ~ 1 day
71 #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
72 scalevector <- 2^(4:(noctave * nvoice) / nvoice) * 2
73 #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
74 s0=2
75 w0=2*pi
76 scaled=FALSE
77 s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
78 totnoct = noctave + as.integer(s0log/nvoice) + 1
79
80 # (normalized) observations node with CWT
81 Xcwt4 <- lapply(seq_len(n), function(i) {
82 ts <- scale(ts(conso[i,]), center=TRUE, scale=scaled)
83 totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
84 ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
85 #Normalization
86 sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
87 sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
88 sqres / max(Mod(sqres))
89 })
90
91 Xwer_dist <- matrix(0., n, n)
92 fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
93 for (i in 1:(n-1))
94 {
95 for (j in (i+1):n)
96 {
97 #TODO: later, compute CWT here (because not enough storage space for 32M series)
98 # 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
99 num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
100 WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
101 WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
102 wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
103 Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
104 Xwer_dist[j,i] <- Xwer_dist[i,j]
105 }
106 }
107 diag(Xwer_dist) <- numeric(n)
108 Xwer_dist
109 }