578b2f399035023eb68b0b004be10f18d87cac84
[epclust.git] / epclust / R / clustering.R
1 # Cluster one full task (nb_curves / ntasks series)
2 clusteringTask = function(indices_clust)
3 {
4 cl_clust = parallel::makeCluster(ncores_clust)
5 parallel::clusterExport(cl_clust,
6 varlist=c("K1","K2","WER"),
7 envir=environment())
8 repeat
9 {
10 nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
11 indices_workers = lapply(seq_len(nb_workers), function(i) {
12 upper_bound = ifelse( i<nb_workers,
13 min(nb_series_per_chunk*i,length(indices_clust)), length(indices_clust) )
14 indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
15 })
16 indices_clust = parallel::parLapply(cl, indices_workers, clusterChunk)
17 # TODO: soft condition between K2 and K1, before applying final WER step
18 if ((WER=="end" && length(indices_clust)==K1) || (WER=="mix" && length(indices_clust)==K2))
19 break
20 }
21 parallel::stopCluster(cl_clust)
22 unlist(indices_clust)
23 }
24
25 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
26 clusterChunk = function(indices_chunk)
27 {
28 coeffs = readCoeffs(indices_chunk)
29 cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE)
30 if (WER=="mix" > 0)
31 {
32 curves = computeSynchrones(cl)
33 dists = computeWerDists(curves)
34 cl = computeClusters(dists, K2, diss=TRUE)
35 }
36 indices_chunk[cl]
37 }
38
39 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
40 computeClusters = function(md, K, diss)
41 {
42 if (!require(cluster, quietly=TRUE))
43 stop("Unable to load cluster library")
44 cluster::pam(md, K, diss=diss)$id.med
45 }
46
47 # Compute the synchrones curves (sum of clusters elements) from a clustering result
48 computeSynchrones = function(indices)
49 {
50 colSums( getData(indices) )
51 }
52
53 # Compute the WER distance between the synchrones curves
54 computeWerDist = function(curves)
55 {
56 if (!require("Rwave", quietly=TRUE))
57 stop("Unable to load Rwave library")
58 n <- nrow(curves)
59 delta <- ncol(curves)
60 #TODO: automatic tune of all these parameters ? (for other users)
61 nvoice <- 4
62 # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(curves))
63 noctave = 13
64 # 4 here represent 2^5 = 32 half-hours ~ 1 day
65 #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
66 scalevector <- 2^(4:(noctave * nvoice) / nvoice) * 2
67 #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
68 s0=2
69 w0=2*pi
70 scaled=FALSE
71 s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
72 totnoct = noctave + as.integer(s0log/nvoice) + 1
73
74 # (normalized) observations node with CWT
75 Xcwt4 <- lapply(seq_len(n), function(i) {
76 ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
77 totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
78 ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
79 #Normalization
80 sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
81 sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
82 sqres / max(Mod(sqres))
83 })
84
85 Xwer_dist <- matrix(0., n, n)
86 fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
87 for (i in 1:(n-1))
88 {
89 for (j in (i+1):n)
90 {
91 #TODO: later, compute CWT here (because not enough storage space for 32M series)
92 # 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
93 num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
94 WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
95 WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
96 wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
97 Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
98 Xwer_dist[j,i] <- Xwer_dist[i,j]
99 }
100 }
101 diag(Xwer_dist) <- numeric(n)
102 Xwer_dist
103 }