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).
10 #' \code{clusteringTask2()} runs a full stage-2 task, which consists in synchrones
11 #' and then WER distances computations, before applying the clustering algorithm.
12 #' \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic
13 #' clustering procedures respectively for stage 1 and 2. The former applies the
14 #' clustering algorithm (PAM) on a contributions matrix, while the latter clusters
15 #' a chunk of series inside one task (~max nb_series_per_chunk)
17 #' @param indices Range of series indices to cluster in parallel (initial data)
18 #' @param getContribs Function to retrieve contributions from initial series indices:
19 #' \code{getContribs(indices)} outpus a contributions matrix
20 #' @param contribs matrix of contributions (e.g. output of \code{curvesToContribs()})
21 #' @inheritParams computeSynchrones
22 #' @inheritParams claws
24 #' @return For \code{clusteringTask1()} and \code{computeClusters1()}, the indices of the
25 #' computed (K1) medoids. Indices are irrelevant for stage 2 clustering, thus
26 #' \code{computeClusters2()} outputs a big.matrix of medoids
27 #' (of size limited by nb_series_per_chunk)
32 clusteringTask1 = function(
33 indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
36 cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
40 cl = parallel::makeCluster(ncores_clust)
41 parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
43 while (length(indices) > K1)
45 indices_workers = .spreadIndices(indices, nb_series_per_chunk)
49 unlist( parallel::parLapply(cl, indices_workers, function(inds) {
50 require("epclust", quietly=TRUE)
51 inds[ computeClusters1(getContribs(inds), K1, verbose) ]
56 unlist( lapply(indices_workers, function(inds)
57 inds[ computeClusters1(getContribs(inds), K1, verbose) ]
62 parallel::stopCluster(cl)
69 clusteringTask2 = function(medoids, K2,
70 getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
73 cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))
75 if (nrow(medoids) <= K2)
77 synchrones = computeSynchrones(medoids,
78 getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
79 distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
80 # PAM in package 'cluster' cannot take big.matrix in input: need to cast it
81 medoids[ computeClusters2(distances[,],K2,verbose), ]
86 computeClusters1 = function(contribs, K1, verbose=FALSE)
89 cat(paste(" computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
90 cluster::pam(contribs, K1, diss=FALSE)$id.med
95 computeClusters2 = function(distances, K2, verbose=FALSE)
98 cat(paste(" computeClusters2() on ",nrow(distances)," lines\n", sep=""))
99 cluster::pam(distances, K2, diss=TRUE)$id.med
104 #' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
105 #' using L2 distances.
107 #' @param medoids big.matrix of medoids (curves of same length as initial series)
108 #' @param getRefSeries Function to retrieve initial series (e.g. in stage 2 after series
109 #' have been replaced by stage-1 medoids)
110 #' @param nb_ref_curves How many reference series? (This number is known at this stage)
111 #' @inheritParams claws
113 #' @return A big.matrix of size K1 x L where L = data_length
116 computeSynchrones = function(medoids, getRefSeries,
117 nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
120 cat(paste("--- Compute synchrones\n", sep=""))
122 computeSynchronesChunk = function(indices)
124 ref_series = getRefSeries(indices)
125 nb_series = nrow(ref_series)
126 #get medoids indices for this chunk of series
128 #TODO: debug this (address is OK but values are garbage: why?)
129 # mi = .Call("computeMedoidsIndices", medoids@address, ref_series, PACKAGE="epclust")
131 #R-equivalent, requiring a matrix (thus potentially breaking "fit-in-memory" hope)
132 mat_meds = medoids[,]
133 mi = rep(NA,nb_series)
134 for (i in 1:nb_series)
135 mi[i] <- which.min( rowSums( sweep(mat_meds, 2, ref_series[i,], '-')^2 ) )
138 for (i in seq_len(nb_series))
141 synchronicity::lock(m)
142 synchrones[mi[i],] = synchrones[mi[i],] + ref_series[i,]
143 counts[mi[i],1] = counts[mi[i],1] + 1
145 synchronicity::unlock(m)
149 K = nrow(medoids) ; L = ncol(medoids)
150 # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
151 # TODO: if size > RAM (not our case), use file-backed big.matrix
152 synchrones = bigmemory::big.matrix(nrow=K, ncol=L, type="double", init=0.)
153 counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
154 # synchronicity is only for Linux & MacOS; on Windows: run sequentially
155 parll = (requireNamespace("synchronicity",quietly=TRUE)
156 && parll && Sys.info()['sysname'] != "Windows")
158 m <- synchronicity::boost.mutex()
162 cl = parallel::makeCluster(ncores_clust)
163 parallel::clusterExport(cl,
164 varlist=c("synchrones","counts","verbose","medoids","getRefSeries"),
168 indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
172 parallel::parLapply(cl, indices_workers, computeSynchronesChunk)
174 lapply(indices_workers, computeSynchronesChunk)
177 parallel::stopCluster(cl)
179 #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
180 for (i in seq_len(K))
181 synchrones[i,] = synchrones[i,] / counts[i,1]
182 #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
183 # ...maybe; but let's hope resulting K1' be still quite bigger than K2
184 noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
187 # Else: some clusters are empty, need to slice synchrones
188 synchrones[noNA_rows,]
193 #' Compute the WER distances between the synchrones curves (in rows), which are
194 #' returned (e.g.) by \code{computeSynchrones()}
196 #' @param synchrones A big.matrix of synchrones, in rows. The series have same length
197 #' as the series in the initial dataset
198 #' @inheritParams claws
200 #' @return A big.matrix of size K1 x K1
203 computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
206 cat(paste("--- Compute WER dists\n", sep=""))
208 n <- nrow(synchrones)
209 delta <- ncol(synchrones)
210 #TODO: automatic tune of all these parameters ? (for other users)
212 # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
214 # 4 here represent 2^5 = 32 half-hours ~ 1 day
215 #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
216 scalevector <- 2^(4:(noctave * nvoice) / nvoice + 1)
217 #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
221 s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
222 totnoct = noctave + as.integer(s0log/nvoice) + 1
224 Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
225 fcoefs = rep(1/3, 3) #moving average on 3 values
227 # Generate n(n-1)/2 pairs for WER distances computations
233 pairs = c(pairs, lapply(V, function(v) c(i,v)))
236 computeCWT = function(i)
238 ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
239 totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
240 ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
242 sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
243 sqres <- sweep(ts.cwt,2,sqs,'*')
244 sqres / max(Mod(sqres))
247 computeDistancesIJ = function(pair)
249 i = pair[1] ; j = pair[2]
250 if (verbose && j==i+1)
251 cat(paste(" Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
252 cwt_i = computeCWT(i)
253 cwt_j = computeCWT(j)
254 num <- .Call("filter", Mod(cwt_i * Conj(cwt_j)), PACKAGE="epclust")
255 WX <- .Call("filter", Mod(cwt_i * Conj(cwt_i)), PACKAGE="epclust")
256 WY <- .Call("filter", Mod(cwt_j * Conj(cwt_j)), PACKAGE="epclust")
257 wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
258 Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * (1 - wer2))
259 Xwer_dist[j,i] <- Xwer_dist[i,j]
265 cl = parallel::makeCluster(ncores_clust)
266 parallel::clusterExport(cl,
267 varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
273 parallel::parLapply(cl, pairs, computeDistancesIJ)
275 lapply(pairs, computeDistancesIJ)
278 parallel::stopCluster(cl)
284 # Helper function to divide indices into balanced sets
285 .spreadIndices = function(indices, nb_per_chunk)
288 nb_workers = floor( L / nb_per_chunk )
291 # L < nb_series_per_chunk, simple case
292 indices_workers = list(indices)
296 indices_workers = lapply( seq_len(nb_workers), function(i)
297 indices[(nb_per_chunk*(i-1)+1):(nb_per_chunk*i)] )
298 # Spread the remaining load among the workers
299 rem = L %% nb_per_chunk
302 index = rem%%nb_workers + 1
303 indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])