Commit | Line | Data |
---|---|---|
8702eb86 | 1 | #' CLAWS: CLustering with wAvelets and Wer distanceS |
7f0781b7 | 2 | #' |
eef6f6c9 BA |
3 | #' Cluster electricity power curves (or any series of similar nature) by applying a |
4 | #' two stage procedure in parallel (see details). | |
5 | #' Input series must be sampled on the same time grid, no missing values. | |
6 | #' | |
d9bb53c5 BA |
7 | #' Summary of the function execution flow: |
8 | #' \enumerate{ | |
9 | #' \item Compute and serialize all contributions, obtained through discrete wavelet | |
10 | #' decomposition (see Antoniadis & al. [2013]) | |
11 | #' \item Divide series into \code{ntasks} groups to process in parallel. In each task: | |
eef6f6c9 | 12 | #' \enumerate{ |
d9bb53c5 | 13 | #' \item iterate the first clustering algorithm on its aggregated outputs, |
3fb6e823 BA |
14 | #' on inputs of size \code{nb_items_clust}\cr |
15 | #' -> K1 medoids indices | |
16 | #' \item optionally, if WER=="mix":\cr | |
17 | #' a. compute WER distances (K1xK1) between medoids\cr | |
18 | #' b. apply the 2nd clustering algorithm\cr | |
19 | #' -> K2 medoids indices | |
eef6f6c9 | 20 | #' } |
d9bb53c5 | 21 | #' \item Launch a final task on the aggregated outputs of all previous tasks: |
40f12a2f BA |
22 | #' ntasks*K1 if WER=="end", ntasks*K2 otherwise |
23 | #' \item Compute synchrones (sum of series within each final group) | |
d9bb53c5 | 24 | #' } |
3fb6e823 | 25 | #' |
40f12a2f BA |
26 | #' The main argument -- \code{series} -- has a quite misleading name, since it can be |
27 | #' either a [big.]matrix, a CSV file, a connection or a user function to retrieve series. | |
3fb6e823 BA |
28 | #' When \code{series} is given as a function it must take a single argument, |
29 | #' 'indices': integer vector equal to the indices of the curves to retrieve; | |
40f12a2f | 30 | #' see SQLite example. |
a52836b2 | 31 | #' WARNING: the return value must be a matrix (in columns), or NULL if no matches. |
3fb6e823 | 32 | #' |
d9bb53c5 | 33 | #' Note: Since we don't make assumptions on initial data, there is a possibility that |
40f12a2f | 34 | #' even when serialized, contributions do not fit in RAM. For example, |
d9bb53c5 BA |
35 | #' 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore, |
36 | #' it's safer to place these in (binary) files; that's what we do. | |
7f0781b7 | 37 | #' |
3fb6e823 | 38 | #' @param series Access to the N (time-)series, which can be of one of the four |
8702eb86 BA |
39 | #' following types: |
40 | #' \itemize{ | |
eef6f6c9 | 41 | #' \item [big.]matrix: each column contains the (time-ordered) values of one time-serie |
bf5c0844 BA |
42 | #' \item connection: any R connection object providing lines as described above |
43 | #' \item character: name of a CSV file containing series in rows (no header) | |
8702eb86 | 44 | #' \item function: a custom way to retrieve the curves; it has only one argument: |
eef6f6c9 | 45 | #' the indices of the series to be retrieved. See SQLite example |
8702eb86 | 46 | #' } |
3fb6e823 | 47 | #' @param K1 Number of clusters to be found after stage 1 (K1 << N) |
1c6f223e | 48 | #' @param K2 Number of clusters to be found after stage 2 (K2 << K1) |
3fb6e823 BA |
49 | #' @param nb_series_per_chunk Number of series to retrieve in one batch |
50 | #' @param nb_items_clust Number of items in 1st clustering algorithm input | |
0486fbad | 51 | #' @param algoClust1 Clustering algorithm for stage 1. A function which takes (data, K) |
2b9f5356 | 52 | #' as argument where data is a matrix in columns and K the desired number of clusters, |
3fb6e823 | 53 | #' and outputs K medoids ranks. Default: PAM. |
0486fbad | 54 | #' @param algoClust2 Clustering algorithm for stage 2. A function which takes (dists, K) |
2b9f5356 | 55 | #' as argument where dists is a matrix of distances and K the desired number of clusters, |
3fb6e823 | 56 | #' and outputs K medoids ranks. Default: PAM. |
eef6f6c9 BA |
57 | #' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter |
58 | #' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix) | |
59 | #' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply | |
60 | #' stage 2 at the end of each task | |
3fb6e823 | 61 | #' @param smooth_lvl Smoothing level: odd integer, 1 == no smoothing. |
a52836b2 | 62 | #' @param nvoice Number of voices within each octave for CWT computations |
4bcfdbee | 63 | #' @param random TRUE (default) for random chunks repartition |
eef6f6c9 BA |
64 | #' @param ntasks Number of tasks (parallel iterations to obtain K1 [if WER=="end"] |
65 | #' or K2 [if WER=="mix"] medoids); default: 1. | |
66 | #' Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks | |
3fb6e823 BA |
67 | #' @param ncores_tasks Number of parallel tasks ('1' == sequential tasks) |
68 | #' @param ncores_clust Number of parallel clusterings in one task | |
4bcfdbee | 69 | #' @param sep Separator in CSV input file (if any provided) |
3fb6e823 BA |
70 | #' @param nbytes Number of bytes to serialize a floating-point number: 4 or 8 |
71 | #' @param endian Endianness for (de)serialization: "little" or "big" | |
72 | #' @param verbose FALSE: nothing printed; TRUE: some execution traces | |
73 | #' @param parll TRUE: run in parallel. FALSE: run sequentially | |
dc86eb0c | 74 | #' @param reuse_bin Re-use previously stored binary series and contributions |
7f0781b7 | 75 | #' |
3fb6e823 | 76 | #' @return A list: |
40f12a2f | 77 | #' \itemize{ |
3fb6e823 BA |
78 | #' \item medoids: matrix of the final K2 medoids curves |
79 | #' \item ranks: corresponding indices in the dataset | |
80 | #' \item synchrones: sum of series within each final group | |
40f12a2f | 81 | #' } |
eef6f6c9 BA |
82 | #' |
83 | #' @references Clustering functional data using Wavelets [2013]; | |
84 | #' A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi. | |
85 | #' Inter. J. of Wavelets, Multiresolution and Information Procesing, | |
86 | #' vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033 | |
1c6f223e BA |
87 | #' |
88 | #' @examples | |
4efef8cc | 89 | #' \dontrun{ |
eef6f6c9 | 90 | #' # WER distances computations are too long for CRAN (for now) |
4efef8cc BA |
91 | #' |
92 | #' # Random series around cos(x,2x,3x)/sin(x,2x,3x) | |
3fb6e823 BA |
93 | #' x <- seq(0,50,0.05) |
94 | #' L <- length(x) #1001 | |
282342ba | 95 | #' ref_series <- matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 ) |
4efef8cc | 96 | #' library(wmtsa) |
282342ba | 97 | #' series <- do.call( cbind, lapply( 1:6, function(i) |
3fb6e823 | 98 | #' do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=40)) ) ) |
dc86eb0c BA |
99 | #' # Mix series so that all groups are evenly spread |
100 | #' permut <- (0:239)%%6 * 40 + (0:239)%/%6 + 1 | |
101 | #' series = series[,permut] | |
3fb6e823 | 102 | #' #dim(series) #c(240,1001) |
dc86eb0c | 103 | #' res_ascii <- claws(series, K1=30, K2=6, 100, random=FALSE, verbose=TRUE) |
4efef8cc BA |
104 | #' |
105 | #' # Same example, from CSV file | |
3fb6e823 BA |
106 | #' csv_file <- tempfile(pattern="epclust_series.csv_") |
107 | #' write.table(t(series), csv_file, sep=",", row.names=FALSE, col.names=FALSE) | |
dc86eb0c | 108 | #' res_csv <- claws(csv_file, K1=30, K2=6, 100, random=FALSE) |
4efef8cc BA |
109 | #' |
110 | #' # Same example, from binary file | |
3fb6e823 | 111 | #' bin_file <- tempfile(pattern="epclust_series.bin_") |
eef6f6c9 BA |
112 | #' nbytes <- 8 |
113 | #' endian <- "little" | |
dc86eb0c | 114 | #' binarize(csv_file, bin_file, 500, ",", nbytes, endian) |
eef6f6c9 | 115 | #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian) |
dc86eb0c | 116 | #' res_bin <- claws(getSeries, K1=30, K2=6, 100, random=FALSE) |
4efef8cc BA |
117 | #' unlink(csv_file) |
118 | #' unlink(bin_file) | |
119 | #' | |
120 | #' # Same example, from SQLite database | |
121 | #' library(DBI) | |
122 | #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:") | |
123 | #' # Prepare data.frame in DB-format | |
dc86eb0c BA |
124 | #' n <- ncol(series) |
125 | #' times_values <- data.frame( | |
126 | #' id = rep(1:n,each=L), | |
127 | #' time = rep( as.POSIXct(1800*(1:L),"GMT",origin="2001-01-01"), n ), | |
128 | #' value = as.double(series) ) | |
4efef8cc | 129 | #' dbWriteTable(series_db, "times_values", times_values) |
4bcfdbee BA |
130 | #' # Fill associative array, map index to identifier |
131 | #' indexToID_inDB <- as.character( | |
dc86eb0c | 132 | #' dbGetQuery(series_db, 'SELECT DISTINCT id FROM times_values')[,"id"] ) |
eef6f6c9 | 133 | #' serie_length <- as.integer( dbGetQuery(series_db, |
dc86eb0c | 134 | #' paste("SELECT COUNT(*) FROM times_values WHERE id == ",indexToID_inDB[1],sep="")) ) |
eef6f6c9 BA |
135 | #' getSeries <- function(indices) { |
136 | #' request <- "SELECT id,value FROM times_values WHERE id in (" | |
dc86eb0c BA |
137 | #' for (i in seq_along(indices)) { |
138 | #' request <- paste(request, indexToID_inDB[ indices[i] ], sep="") | |
139 | #' if (i < length(indices)) | |
140 | #' request <- paste(request, ",", sep="") | |
141 | #' } | |
eef6f6c9 BA |
142 | #' request <- paste(request, ")", sep="") |
143 | #' df_series <- dbGetQuery(series_db, request) | |
dc86eb0c BA |
144 | #' if (nrow(df_series) >= 1) |
145 | #' matrix(df_series[,"value"], nrow=serie_length) | |
a52836b2 BA |
146 | #' else |
147 | #' NULL | |
4efef8cc | 148 | #' } |
dc86eb0c BA |
149 | #' # reuse_bin==FALSE: DB do not garantee ordering |
150 | #' res_db <- claws(getSeries, K1=30, K2=6, 100, random=FALSE, reuse_bin=FALSE) | |
4bcfdbee BA |
151 | #' dbDisconnect(series_db) |
152 | #' | |
dc86eb0c BA |
153 | #' # All results should be equal: |
154 | #' all(res_ascii$ranks == res_csv$ranks | |
155 | #' & res_ascii$ranks == res_bin$ranks | |
156 | #' & res_ascii$ranks == res_db$ranks) | |
1c6f223e | 157 | #' } |
1c6f223e | 158 | #' @export |
3c5a4b08 | 159 | claws <- function(series, K1, K2, nb_series_per_chunk, nb_items_clust=7*K1, |
40f12a2f BA |
160 | algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE,pamonce=1)$id.med, |
161 | algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE,pamonce=1)$id.med, | |
282342ba BA |
162 | wav_filt="d8", contrib_type="absolute", WER="end", smooth_lvl=3, nvoice=4, |
163 | random=TRUE, ntasks=1, ncores_tasks=1, ncores_clust=3, sep=",", nbytes=4, | |
dc86eb0c | 164 | endian=.Platform$endian, verbose=FALSE, parll=TRUE, reuse_bin=TRUE) |
ac1d4231 | 165 | { |
dc86eb0c BA |
166 | |
167 | ||
168 | #TODO: comprendre differences.......... debuguer getSeries for DB | |
169 | ||
170 | ||
0e2dce80 | 171 | # Check/transform arguments |
40f12a2f BA |
172 | if (!is.matrix(series) && !bigmemory::is.big.matrix(series) |
173 | && !is.function(series) | |
174 | && !methods::is(series,"connection") && !is.character(series)) | |
0e2dce80 | 175 | { |
40f12a2f | 176 | stop("'series': [big]matrix, function, file or valid connection (no NA)") |
5c652979 | 177 | } |
eef6f6c9 BA |
178 | K1 <- .toInteger(K1, function(x) x>=2) |
179 | K2 <- .toInteger(K2, function(x) x>=2) | |
37c82bba | 180 | nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1) |
3c5a4b08 | 181 | nb_items_clust <- .toInteger(nb_items_clust, function(x) x>K1) |
eef6f6c9 | 182 | random <- .toLogical(random) |
282342ba BA |
183 | tryCatch({ignored <- wavelets::wt.filter(wav_filt)}, |
184 | error=function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") ) | |
185 | ctypes <- c("relative","absolute","logit") | |
186 | contrib_type <- ctypes[ pmatch(contrib_type,ctypes) ] | |
eef6f6c9 BA |
187 | if (is.na(contrib_type)) |
188 | stop("'contrib_type' in {'relative','absolute','logit'}") | |
7f0781b7 | 189 | if (WER!="end" && WER!="mix") |
eef6f6c9 BA |
190 | stop("'WER': in {'end','mix'}") |
191 | random <- .toLogical(random) | |
192 | ntasks <- .toInteger(ntasks, function(x) x>=1) | |
193 | ncores_tasks <- .toInteger(ncores_tasks, function(x) x>=1) | |
194 | ncores_clust <- .toInteger(ncores_clust, function(x) x>=1) | |
56857861 BA |
195 | if (!is.character(sep)) |
196 | stop("'sep': character") | |
eef6f6c9 BA |
197 | nbytes <- .toInteger(nbytes, function(x) x==4 || x==8) |
198 | verbose <- .toLogical(verbose) | |
199 | parll <- .toLogical(parll) | |
56857861 | 200 | |
40f12a2f | 201 | # Binarize series if it is not a function; the aim is to always use a function, |
2b9f5356 | 202 | # to uniformize treatments. An equally good alternative would be to use a file-backed |
d9bb53c5 | 203 | # bigmemory::big.matrix, but it would break the "all-is-function" pattern. |
40f12a2f | 204 | if (!is.function(series)) |
56857861 | 205 | { |
4bcfdbee | 206 | if (verbose) |
a52836b2 | 207 | cat("...Serialize time-series (or retrieve past binary file)\n") |
282342ba | 208 | series_file <- ".series.epclust.bin" |
dc86eb0c BA |
209 | if (!file.exists(series_file) || !reuse_bin) |
210 | { | |
211 | unlink(series_file,) | |
40f12a2f | 212 | binarize(series, series_file, nb_series_per_chunk, sep, nbytes, endian) |
dc86eb0c | 213 | } |
282342ba | 214 | getSeries <- function(inds) getDataInFile(inds, series_file, nbytes, endian) |
56857861 | 215 | } |
40f12a2f | 216 | else |
282342ba | 217 | getSeries <- series |
ac1d4231 | 218 | |
95b5c2e6 | 219 | # Serialize all computed wavelets contributions into a file |
282342ba | 220 | contribs_file <- ".contribs.epclust.bin" |
4bcfdbee | 221 | if (verbose) |
a52836b2 | 222 | cat("...Compute contributions and serialize them (or retrieve past binary file)\n") |
dc86eb0c | 223 | if (!file.exists(contribs_file) || !reuse_bin) |
a52836b2 | 224 | { |
dc86eb0c | 225 | unlink(contribs_file,) |
282342ba | 226 | nb_curves <- binarizeTransform(getSeries, |
40f12a2f | 227 | function(curves) curvesToContribs(curves, wav_filt, contrib_type), |
a52836b2 BA |
228 | contribs_file, nb_series_per_chunk, nbytes, endian) |
229 | } | |
230 | else | |
231 | { | |
232 | # TODO: duplicate from getDataInFile() in de_serialize.R | |
282342ba BA |
233 | contribs_size <- file.info(contribs_file)$size #number of bytes in the file |
234 | contrib_length <- readBin(contribs_file, "integer", n=1, size=8, endian=endian) | |
235 | nb_curves <- (contribs_size-8) / (nbytes*contrib_length) | |
a52836b2 | 236 | } |
282342ba | 237 | getContribs <- function(indices) getDataInFile(indices, contribs_file, nbytes, endian) |
8e6accca | 238 | |
2b9f5356 | 239 | # A few sanity checks: do not continue if too few data available. |
eef6f6c9 BA |
240 | if (nb_curves < K2) |
241 | stop("Not enough data: less series than final number of clusters") | |
282342ba | 242 | nb_series_per_task <- round(nb_curves / ntasks) |
eef6f6c9 BA |
243 | if (nb_series_per_task < K2) |
244 | stop("Too many tasks: less series in one task than final number of clusters") | |
ac1d4231 | 245 | |
d9bb53c5 BA |
246 | # Generate a random permutation of 1:N (if random==TRUE); |
247 | # otherwise just use arrival (storage) order. | |
282342ba | 248 | indices_all <- if (random) sample(nb_curves) else seq_len(nb_curves) |
2b9f5356 | 249 | # Split (all) indices into ntasks groups of ~same size |
282342ba BA |
250 | indices_tasks <- lapply(seq_len(ntasks), function(i) { |
251 | upper_bound <- ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves ) | |
2b9f5356 BA |
252 | indices_all[((i-1)*nb_series_per_task+1):upper_bound] |
253 | }) | |
254 | ||
255 | if (parll && ntasks>1) | |
256 | { | |
257 | # Initialize parallel runs: outfile="" allow to output verbose traces in the console | |
258 | # under Linux. All necessary variables are passed to the workers. | |
3fb6e823 BA |
259 | cl <- |
260 | if (verbose) | |
261 | parallel::makeCluster(ncores_tasks, outfile="") | |
262 | else | |
263 | parallel::makeCluster(ncores_tasks) | |
282342ba | 264 | varlist <- c("ncores_clust","verbose","parll", #task 1 & 2 |
3c5a4b08 BA |
265 | "K1","getContribs","algoClust1","nb_items_clust") #task 1 |
266 | if (WER=="mix") | |
267 | { | |
268 | # Add variables for task 2 | |
282342ba BA |
269 | varlist <- c(varlist, "K2","getSeries","algoClust2","nb_series_per_chunk", |
270 | "smooth_lvl","nvoice","nbytes","endian") | |
3c5a4b08 | 271 | } |
282342ba | 272 | parallel::clusterExport(cl, varlist, envir <- environment()) |
2b9f5356 BA |
273 | } |
274 | ||
275 | # This function achieves one complete clustering task, divided in stage 1 + stage 2. | |
3c5a4b08 BA |
276 | # stage 1: n indices --> clusteringTask1(...) --> K1 medoids (indices) |
277 | # stage 2: K1 indices --> K1xK1 WER distances --> clusteringTask2(...) --> K2 medoids, | |
282342ba BA |
278 | # where n == N / ntasks, N being the total number of curves. |
279 | runTwoStepClustering <- function(inds) | |
492cd9e7 | 280 | { |
d9bb53c5 | 281 | # When running in parallel, the environment is blank: we need to load the required |
2b9f5356 | 282 | # packages, and pass useful variables. |
bf5c0844 | 283 | if (parll && ntasks>1) |
492cd9e7 | 284 | require("epclust", quietly=TRUE) |
282342ba | 285 | indices_medoids <- clusteringTask1(inds, getContribs, K1, algoClust1, |
3c5a4b08 | 286 | nb_items_clust, ncores_clust, verbose, parll) |
40f12a2f | 287 | if (WER=="mix") |
56857861 | 288 | { |
282342ba BA |
289 | indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, |
290 | nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_clust,verbose,parll) | |
56857861 BA |
291 | } |
292 | indices_medoids | |
492cd9e7 BA |
293 | } |
294 | ||
c45fd663 | 295 | if (verbose) |
e161499b | 296 | { |
282342ba | 297 | message <- paste("...Run ",ntasks," x stage 1", sep="") |
e161499b | 298 | if (WER=="mix") |
282342ba | 299 | message <- paste(message," + stage 2", sep="") |
e161499b BA |
300 | cat(paste(message,"\n", sep="")) |
301 | } | |
c45fd663 | 302 | |
3c5a4b08 BA |
303 | # As explained above, we obtain after all runs ntasks*[K1 or K2] medoids indices, |
304 | # depending wether WER=="end" or "mix", respectively. | |
40f12a2f | 305 | indices_medoids_all <- |
eef6f6c9 BA |
306 | if (parll && ntasks>1) |
307 | unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) ) | |
308 | else | |
309 | unlist( lapply(indices_tasks, runTwoStepClustering) ) | |
40f12a2f | 310 | |
bf5c0844 | 311 | if (parll && ntasks>1) |
492cd9e7 | 312 | parallel::stopCluster(cl) |
3465b246 | 313 | |
3c5a4b08 BA |
314 | # For the last stage, ncores_tasks*(ncores_clusts+1) cores should be available: |
315 | # - ntasks for level 1 parallelism | |
316 | # - ntasks*ncores_clust for level 2 parallelism, | |
317 | # but since an extension MPI <--> tasks / OpenMP <--> sub-tasks is on the way, | |
318 | # it's better to just re-use ncores_clust | |
319 | ncores_last_stage <- ncores_clust | |
0e2dce80 | 320 | |
3c5a4b08 | 321 | # Run last clustering tasks to obtain only K2 medoids indices |
4bcfdbee BA |
322 | if (verbose) |
323 | cat("...Run final // stage 1 + stage 2\n") | |
282342ba | 324 | indices_medoids <- clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1, |
3c5a4b08 | 325 | nb_items_clust, ncores_tasks*ncores_clust, verbose, parll) |
dc86eb0c BA |
326 | |
327 | indices_medoids <- clusteringTask2(indices_medoids, getSeries, K2, algoClust2, | |
282342ba | 328 | nb_series_per_chunk,smooth_lvl,nvoice,nbytes,endian,ncores_last_stage,verbose,parll) |
4bcfdbee | 329 | |
3c5a4b08 BA |
330 | # Compute synchrones, that is to say the cumulated power consumptions for each of the K2 |
331 | # final groups. | |
282342ba BA |
332 | medoids <- getSeries(indices_medoids) |
333 | synchrones <- computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk, | |
3c5a4b08 | 334 | ncores_last_stage, verbose, parll) |
4bcfdbee | 335 | |
40f12a2f BA |
336 | # NOTE: no need to use big.matrix here, since there are only K2 << K1 << N remaining curves |
337 | list("medoids"=medoids, "ranks"=indices_medoids, "synchrones"=synchrones) | |
cea14f3a | 338 | } |