3 #' @aliases clusteringTask1 computeClusters1 computeClusters2
5 #' @title Two-stage clustering, withing one task (see \code{claws()})
7 #' @description \code{clusteringTask1()} runs one full stage-1 task, which consists in
8 #' iterated stage 1 clustering (on nb_curves / ntasks energy contributions, computed
9 #' through discrete wavelets coefficients). \code{computeClusters1()} and
10 #' \code{computeClusters2()} correspond to the atomic clustering procedures respectively
11 #' for stage 1 and 2. The former applies the clustering algorithm (PAM) on a
12 #' contributions matrix, while the latter clusters a chunk of series inside one task
13 #' (~max nb_series_per_chunk)
15 #' @param indices Range of series indices to cluster in parallel (initial data)
16 #' @param getContribs Function to retrieve contributions from initial series indices:
17 #' \code{getContribs(indices)} outpus a contributions matrix
18 #' @param contribs matrix of contributions (e.g. output of \code{curvesToContribs()})
19 #' @inheritParams computeSynchrones
20 #' @inheritParams claws
22 #' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the
23 #' computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus
24 #' \code{computeClusters2()} outputs a matrix of medoids
25 #' (of size limited by nb_series_per_chunk)
30 clusteringTask1 = function(
31 indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
34 cat(paste("*** Clustering task on ",length(indices)," lines\n", sep=""))
36 wrapComputeClusters1 = function(inds) {
38 require("epclust", quietly=TRUE)
40 cat(paste(" computeClusters1() on ",length(inds)," lines\n", sep=""))
41 inds[ computeClusters1(getContribs(inds), K1) ]
46 cl = parallel::makeCluster(ncores_clust)
47 parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
49 while (length(indices) > K1)
51 indices_workers = .spreadIndices(indices, nb_series_per_chunk)
53 indices = unlist( parallel::parLapply(cl, indices_workers, wrapComputeClusters1) )
55 indices = unlist( lapply(indices_workers, wrapComputeClusters1) )
58 parallel::stopCluster(cl)
65 computeClusters1 = function(contribs, K1)
66 cluster::pam(contribs, K1, diss=FALSE)$id.med
70 computeClusters2 = function(medoids, K2,
71 getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
73 synchrones = computeSynchrones(medoids,
74 getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
75 distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
76 medoids[ cluster::pam(distances, K2, diss=TRUE)$medoids , ]
81 #' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
82 #' using L2 distances.
84 #' @param medoids Matrix of medoids (curves of same legnth as initial series)
85 #' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
86 #' have been replaced by stage-1 medoids)
87 #' @param nb_ref_curves How many reference series? (This number is known at this stage)
88 #' @inheritParams claws
91 computeSynchrones = function(medoids, getRefSeries,
92 nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
94 computeSynchronesChunk = function(indices)
96 ref_series = getRefSeries(indices)
97 #get medoids indices for this chunk of series
98 for (i in seq_len(nrow(ref_series)))
100 j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
102 synchronicity::lock(m)
103 synchrones[j,] = synchrones[j,] + ref_series[i,]
104 counts[j,1] = counts[j,1] + 1
106 synchronicity::unlock(m)
111 # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
112 synchrones = bigmemory::big.matrix(nrow=K,ncol=ncol(medoids),type="double",init=0.)
113 counts = bigmemory::big.matrix(nrow=K,ncol=1,type="double",init=0)
114 # Fork (// run) only on Linux & MacOS; on Windows: run sequentially
115 parll = (requireNamespace("synchronicity",quietly=TRUE)
116 && parll && Sys.info()['sysname'] != "Windows")
118 m <- synchronicity::boost.mutex()
120 indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
121 for (inds in indices_workers)
125 cat(paste("--- Compute synchrones for indices range ",
126 min(inds)," -> ",max(inds),"\n", sep=""))
129 ignored <- parallel::mcparallel(computeSynchronesChunk(inds))
131 computeSynchronesChunk(inds)
134 parallel::mccollect()
136 mat_syncs = matrix(nrow=K, ncol=ncol(medoids))
137 vec_count = rep(NA, K)
138 #TODO: can we avoid this loop?
139 for (i in seq_len(K))
141 mat_syncs[i,] = synchrones[i,]
142 vec_count[i] = counts[i,1]
144 #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
145 # ...maybe; but let's hope resulting K1' be still quite bigger than K2
146 mat_syncs = sweep(mat_syncs, 1, vec_count, '/')
147 mat_syncs[ sapply(seq_len(K), function(i) all(!is.nan(mat_syncs[i,]))) , ]
152 #' Compute the WER distances between the synchrones curves (in rows), which are
153 #' returned (e.g.) by \code{computeSynchrones()}
155 #' @param synchrones A matrix of synchrones, in rows. The series have same length as the
156 #' series in the initial dataset
157 #' @inheritParams claws
160 computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
162 n <- nrow(synchrones)
163 delta <- ncol(synchrones)
164 #TODO: automatic tune of all these parameters ? (for other users)
166 # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
168 # 4 here represent 2^5 = 32 half-hours ~ 1 day
169 #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
170 scalevector <- 2^(4:(noctave * nvoice) / nvoice) * 2
171 #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
175 s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
176 totnoct = noctave + as.integer(s0log/nvoice) + 1
178 computeCWT = function(i)
181 cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep=""))
182 ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
183 totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
184 ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
186 sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
187 sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
188 sqres / max(Mod(sqres))
193 cl = parallel::makeCluster(ncores_clust)
194 parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
197 # (normalized) observations node with CWT
200 parallel::parLapply(cl, seq_len(n), computeCWT)
202 lapply(seq_len(n), computeCWT)
205 parallel::stopCluster(cl)
207 Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
208 fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
210 cat("*** Compute WER distances from CWT\n")
212 computeDistancesLineI = function(i)
215 cat(paste(" Line ",i,"\n", sep=""))
218 #TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
219 num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
220 WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
221 WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
222 wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
224 synchronicity::lock(m)
225 Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
226 Xwer_dist[j,i] <- Xwer_dist[i,j]
228 synchronicity::unlock(m)
233 parll = (requireNamespace("synchronicity",quietly=TRUE)
234 && parll && Sys.info()['sysname'] != "Windows")
236 m <- synchronicity::boost.mutex()
241 ignored <- parallel::mcparallel(computeDistancesLineI(i))
243 computeDistancesLineI(i)
248 parallel::mccollect()
250 mat_dists = matrix(nrow=n, ncol=n)
251 #TODO: avoid this loop?
253 mat_dists[i,] = Xwer_dist[i,]
257 # Helper function to divide indices into balanced sets
258 .spreadIndices = function(indices, nb_per_chunk)
261 nb_workers = floor( L / nb_per_chunk )
264 # L < nb_series_per_chunk, simple case
265 indices_workers = list(indices)
269 indices_workers = lapply( seq_len(nb_workers), function(i)
270 indices[(nb_per_chunk*(i-1)+1):(nb_per_chunk*i)] )
271 # Spread the remaining load among the workers
272 rem = L %% nb_per_chunk
275 index = rem%%nb_workers + 1
276 indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])