parallel version running; TODO: check==sequential, plotting routines, parser; check...
[epclust.git] / epclust / R / clustering.R
1 #' @name clustering
2 #' @rdname clustering
3 #' @aliases clusteringTask1 computeClusters1 computeClusters2
4 #'
5 #' @title Two-stage clustering, withing one task (see \code{claws()})
6 #'
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)
14 #'
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
21 #'
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)
26 NULL
27
28 #' @rdname clustering
29 #' @export
30 clusteringTask1 = function(
31 indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
32 {
33 if (verbose)
34 cat(paste("*** Clustering task on ",length(indices)," lines\n", sep=""))
35
36 wrapComputeClusters1 = function(inds) {
37 if (parll)
38 require("epclust", quietly=TRUE)
39 if (verbose)
40 cat(paste(" computeClusters1() on ",length(inds)," lines\n", sep=""))
41 inds[ computeClusters1(getContribs(inds), K1) ]
42 }
43
44 if (parll)
45 {
46 cl = parallel::makeCluster(ncores_clust)
47 parallel::clusterExport(cl, varlist=c("getContribs","K1","verbose"), envir=environment())
48 }
49 while (length(indices) > K1)
50 {
51 indices_workers = .spreadIndices(indices, nb_series_per_chunk)
52 if (parll)
53 indices = unlist( parallel::parLapply(cl, indices_workers, wrapComputeClusters1) )
54 else
55 indices = unlist( lapply(indices_workers, wrapComputeClusters1) )
56 }
57 if (parll)
58 parallel::stopCluster(cl)
59
60 indices #medoids
61 }
62
63 #' @rdname clustering
64 #' @export
65 computeClusters1 = function(contribs, K1)
66 cluster::pam(contribs, K1, diss=FALSE)$id.med
67
68 #' @rdname clustering
69 #' @export
70 computeClusters2 = function(medoids, K2,
71 getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
72 {
73 synchrones = computeSynchrones(medoids,
74 getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
75 distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
76 medoids[ cluster::pam(distances, K2, diss=TRUE)$medoids , ]
77 }
78
79 #' computeSynchrones
80 #'
81 #' Compute the synchrones curves (sum of clusters elements) from a matrix of medoids,
82 #' using L2 distances.
83 #'
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
89 #'
90 #' @export
91 computeSynchrones = function(medoids, getRefSeries,
92 nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
93 {
94 computeSynchronesChunk = function(indices)
95 {
96 if (verbose)
97 cat(paste("--- Compute synchrones for ",length(indices)," lines\n", sep=""))
98 ref_series = getRefSeries(indices)
99 #get medoids indices for this chunk of series
100 for (i in seq_len(nrow(ref_series)))
101 {
102 j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
103 if (parll)
104 synchronicity::lock(m)
105 synchrones[j,] = synchrones[j,] + ref_series[i,]
106 counts[j,1] = counts[j,1] + 1
107 if (parll)
108 synchronicity::unlock(m)
109 }
110 }
111
112 K = nrow(medoids)
113 # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
114 synchrones = bigmemory::big.matrix(nrow=K,ncol=ncol(medoids),type="double",init=0.)
115 counts = bigmemory::big.matrix(nrow=K,ncol=1,type="double",init=0)
116 # Fork (// run) only on Linux & MacOS; on Windows: run sequentially
117 parll = (requireNamespace("synchronicity",quietly=TRUE)
118 && parll && Sys.info()['sysname'] != "Windows")
119 if (parll)
120 m <- synchronicity::boost.mutex()
121
122 indices_workers = .spreadIndices(seq_len(nb_ref_curves), nb_series_per_chunk)
123 ignored <-
124 if (parll)
125 {
126 parallel::mclapply(indices_workers, computeSynchronesChunk,
127 mc.cores=ncores_clust, mc.allow.recursive=FALSE)
128 }
129 else
130 lapply(indices_workers, computeSynchronesChunk)
131
132 mat_syncs = matrix(nrow=K, ncol=ncol(medoids))
133 vec_count = rep(NA, K)
134 #TODO: can we avoid this loop?
135 for (i in seq_len(K))
136 {
137 mat_syncs[i,] = synchrones[i,]
138 vec_count[i] = counts[i,1]
139 }
140 #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
141 # ...maybe; but let's hope resulting K1' be still quite bigger than K2
142 mat_syncs = sweep(mat_syncs, 1, vec_count, '/')
143 mat_syncs[ sapply(seq_len(K), function(i) all(!is.nan(mat_syncs[i,]))) , ]
144 }
145
146 #' computeWerDists
147 #'
148 #' Compute the WER distances between the synchrones curves (in rows), which are
149 #' returned (e.g.) by \code{computeSynchrones()}
150 #'
151 #' @param synchrones A matrix of synchrones, in rows. The series have same length as the
152 #' series in the initial dataset
153 #' @inheritParams claws
154 #'
155 #' @export
156 computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
157 {
158 n <- nrow(synchrones)
159 delta <- ncol(synchrones)
160 #TODO: automatic tune of all these parameters ? (for other users)
161 nvoice <- 4
162 # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(synchrones))
163 noctave = 13
164 # 4 here represent 2^5 = 32 half-hours ~ 1 day
165 #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
166 scalevector <- 2^(4:(noctave * nvoice) / nvoice) * 2
167 #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
168 s0=2
169 w0=2*pi
170 scaled=FALSE
171 s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
172 totnoct = noctave + as.integer(s0log/nvoice) + 1
173
174 computeCWT = function(i)
175 {
176 if (verbose)
177 cat(paste("+++ Compute Rwave::cwt() on serie ",i,"\n", sep=""))
178 ts <- scale(ts(synchrones[i,]), center=TRUE, scale=scaled)
179 totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
180 ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
181 #Normalization
182 sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
183 sqres <- sweep(ts.cwt,2,sqs,'*')
184 sqres / max(Mod(sqres))
185 }
186
187 if (parll)
188 {
189 cl = parallel::makeCluster(ncores_clust)
190 parallel::clusterExport(cl,
191 varlist=c("synchrones","totnoct","nvoice","w0","s0log","noctave","s0","verbose"),
192 envir=environment())
193 }
194
195 # (normalized) observations node with CWT
196 Xcwt4 <-
197 if (parll)
198 parallel::parLapply(cl, seq_len(n), computeCWT)
199 else
200 lapply(seq_len(n), computeCWT)
201
202 if (parll)
203 parallel::stopCluster(cl)
204
205 Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
206 fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
207 if (verbose)
208 cat("*** Compute WER distances from CWT\n")
209
210 computeDistancesLineI = function(i)
211 {
212 if (verbose)
213 cat(paste(" Line ",i,"\n", sep=""))
214 for (j in (i+1):n)
215 {
216 #TODO: 'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
217 num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
218 WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
219 WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
220 wer2 <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
221 if (parll)
222 synchronicity::lock(m)
223 Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
224 Xwer_dist[j,i] <- Xwer_dist[i,j]
225 if (parll)
226 synchronicity::unlock(m)
227 }
228 Xwer_dist[i,i] = 0.
229 }
230
231 parll = (requireNamespace("synchronicity",quietly=TRUE)
232 && parll && Sys.info()['sysname'] != "Windows")
233 if (parll)
234 m <- synchronicity::boost.mutex()
235
236 ignored <-
237 if (parll)
238 {
239 parallel::mclapply(seq_len(n-1), computeDistancesLineI,
240 mc.cores=ncores_clust, mc.allow.recursive=FALSE)
241 }
242 else
243 lapply(seq_len(n-1), computeDistancesLineI)
244 Xwer_dist[n,n] = 0.
245
246 mat_dists = matrix(nrow=n, ncol=n)
247 #TODO: avoid this loop?
248 for (i in 1:n)
249 mat_dists[i,] = Xwer_dist[i,]
250 mat_dists
251 }
252
253 # Helper function to divide indices into balanced sets
254 .spreadIndices = function(indices, nb_per_chunk)
255 {
256 L = length(indices)
257 nb_workers = floor( L / nb_per_chunk )
258 if (nb_workers == 0)
259 {
260 # L < nb_series_per_chunk, simple case
261 indices_workers = list(indices)
262 }
263 else
264 {
265 indices_workers = lapply( seq_len(nb_workers), function(i)
266 indices[(nb_per_chunk*(i-1)+1):(nb_per_chunk*i)] )
267 # Spread the remaining load among the workers
268 rem = L %% nb_per_chunk
269 while (rem > 0)
270 {
271 index = rem%%nb_workers + 1
272 indices_workers[[index]] = c(indices_workers[[index]], indices[L-rem+1])
273 rem = rem - 1
274 }
275 }
276 indices_workers
277 }