Add comments to easily read code
[epclust.git] / epclust / R / main.R
... / ...
CommitLineData
1#' CLAWS: CLustering with wAvelets and Wer distanceS
2#'
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#'
7#' @details 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:
12#' \enumerate{
13#' \item iterate the first clustering algorithm on its aggregated outputs,
14#' on inputs of size \code{nb_items_clust}
15#' \item optionally, if WER=="mix":
16#' a) compute the K1 synchrones curves,
17#' b) compute WER distances (K1xK1 matrix) between synchrones and
18#' c) apply the second clustering algorithm
19#' }
20#' \item Launch a final task on the aggregated outputs of all previous tasks:
21#' in the case WER=="end" this task takes indices in input, otherwise
22#' (medoid) curves
23#' }
24#' The main argument -- \code{getSeries} -- has a quite misleading name, since it can be
25#' either a [big.]matrix, a CSV file, a connection or a user function to retrieve
26#' series; the name was chosen because all types of arguments are converted to a function.
27#' When \code{getSeries} is given as a function, it must take a single argument,
28#' 'indices', integer vector equal to the indices of the curves to retrieve;
29#' see SQLite example. The nature and role of other arguments should be clear
30#'
31#' @param getSeries Access to the (time-)series, which can be of one of the three
32#' following types:
33#' \itemize{
34#' \item [big.]matrix: each column contains the (time-ordered) values of one time-serie
35#' \item connection: any R connection object providing lines as described above
36#' \item character: name of a CSV file containing series in rows (no header)
37#' \item function: a custom way to retrieve the curves; it has only one argument:
38#' the indices of the series to be retrieved. See SQLite example
39#' }
40#' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series])
41#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
42#' @param nb_per_chunk (Maximum) number of items to retrieve in one batch, for both types of
43#' retrieval: resp. series and contribution; in a vector of size 2
44#' @param algo_clust1 Clustering algorithm for stage 1. A function which takes (data, K)
45#' as argument where data is a matrix in columns and K the desired number of clusters,
46#' and outputs K medoids ranks. Default: PAM
47#' @param algo_clust2 Clustering algorithm for stage 2. A function which takes (dists, K)
48#' as argument where dists is a matrix of distances and K the desired number of clusters,
49#' and outputs K clusters representatives (curves). Default: k-means
50#' @param nb_items_clust1 (Maximum) number of items in input of the clustering algorithm
51#' for stage 1
52#' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter
53#' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix)
54#' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply
55#' stage 2 at the end of each task
56#' @param random TRUE (default) for random chunks repartition
57#' @param ntasks Number of tasks (parallel iterations to obtain K1 [if WER=="end"]
58#' or K2 [if WER=="mix"] medoids); default: 1.
59#' Note: ntasks << N (number of series), so that N is "roughly divisible" by ntasks
60#' @param ncores_tasks Number of parallel tasks (1 to disable: sequential tasks)
61#' @param ncores_clust Number of parallel clusterings in one task (4 should be a minimum)
62#' @param sep Separator in CSV input file (if any provided)
63#' @param nbytes Number of bytes to serialize a floating-point number; 4 or 8
64#' @param endian Endianness for (de)serialization ("little" or "big")
65#' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
66#' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
67#'
68#' @return A matrix of the final K2 medoids curves, in columns
69#'
70#' @references Clustering functional data using Wavelets [2013];
71#' A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi.
72#' Inter. J. of Wavelets, Multiresolution and Information Procesing,
73#' vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033
74#'
75#' @examples
76#' \dontrun{
77#' # WER distances computations are too long for CRAN (for now)
78#'
79#' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
80#' x = seq(0,500,0.05)
81#' L = length(x) #10001
82#' ref_series = matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 )
83#' library(wmtsa)
84#' series = do.call( cbind, lapply( 1:6, function(i)
85#' do.call(cbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
86#' #dim(series) #c(2400,10001)
87#' medoids_ascii = claws(series, K1=60, K2=6, nb_per_chunk=c(200,500), verbose=TRUE)
88#'
89#' # Same example, from CSV file
90#' csv_file = "/tmp/epclust_series.csv"
91#' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
92#' medoids_csv = claws(csv_file, K1=60, K2=6, nb_per_chunk=c(200,500))
93#'
94#' # Same example, from binary file
95#' bin_file <- "/tmp/epclust_series.bin"
96#' nbytes <- 8
97#' endian <- "little"
98#' binarize(csv_file, bin_file, 500, nbytes, endian)
99#' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian)
100#' medoids_bin <- claws(getSeries, K1=60, K2=6, nb_per_chunk=c(200,500))
101#' unlink(csv_file)
102#' unlink(bin_file)
103#'
104#' # Same example, from SQLite database
105#' library(DBI)
106#' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
107#' # Prepare data.frame in DB-format
108#' n <- nrow(series)
109#' time_values <- data.frame(
110#' id = rep(1:n,each=L),
111#' time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
112#' value = as.double(t(series)) )
113#' dbWriteTable(series_db, "times_values", times_values)
114#' # Fill associative array, map index to identifier
115#' indexToID_inDB <- as.character(
116#' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
117#' serie_length <- as.integer( dbGetQuery(series_db,
118#' paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) )
119#' getSeries <- function(indices) {
120#' request <- "SELECT id,value FROM times_values WHERE id in ("
121#' for (i in indices)
122#' request <- paste(request, indexToID_inDB[i], ",", sep="")
123#' request <- paste(request, ")", sep="")
124#' df_series <- dbGetQuery(series_db, request)
125#' as.matrix(df_series[,"value"], nrow=serie_length)
126#' }
127#' medoids_db = claws(getSeries, K1=60, K2=6, nb_per_chunk=c(200,500))
128#' dbDisconnect(series_db)
129#'
130#' # All computed medoids should be the same:
131#' digest::sha1(medoids_ascii)
132#' digest::sha1(medoids_csv)
133#' digest::sha1(medoids_bin)
134#' digest::sha1(medoids_db)
135#' }
136#' @export
137claws <- function(getSeries, K1, K2, nb_per_chunk,
138 nb_items_clust1=7*K1,
139 algo_clust1=function(data,K) cluster::pam(data,K,diss=FALSE),
140 algo_clust2=function(dists,K) stats::kmeans(dists,K,iter.max=50,nstart=3),
141 wav_filt="d8",contrib_type="absolute",
142 WER="end",
143 random=TRUE,
144 ntasks=1, ncores_tasks=1, ncores_clust=4,
145 sep=",",
146 nbytes=4, endian=.Platform$endian,
147 verbose=FALSE, parll=TRUE)
148{
149 # Check/transform arguments
150 if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
151 && !is.function(getSeries)
152 && !methods::is(getSeries,"connection") && !is.character(getSeries))
153 {
154 stop("'getSeries': [big]matrix, function, file or valid connection (no NA)")
155 }
156 K1 <- .toInteger(K1, function(x) x>=2)
157 K2 <- .toInteger(K2, function(x) x>=2)
158 if (!is.numeric(nb_per_chunk) || length(nb_per_chunk)!=2)
159 stop("'nb_per_chunk': numeric, size 2")
160 nb_per_chunk[1] <- .toInteger(nb_per_chunk[1], function(x) x>=1)
161 # A batch of contributions should have at least as many elements as a batch of series,
162 # because it always contains much less values
163 nb_per_chunk[2] <- max(.toInteger(nb_per_chunk[2],function(x) x>=1), nb_per_chunk[1])
164 nb_items_clust1 <- .toInteger(nb_items_clust1, function(x) x>K1)
165 random <- .toLogical(random)
166 tryCatch
167 (
168 {ignored <- wavelets::wt.filter(wav_filt)},
169 error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter")
170 )
171 ctypes = c("relative","absolute","logit")
172 contrib_type = ctypes[ pmatch(contrib_type,ctypes) ]
173 if (is.na(contrib_type))
174 stop("'contrib_type' in {'relative','absolute','logit'}")
175 if (WER!="end" && WER!="mix")
176 stop("'WER': in {'end','mix'}")
177 random <- .toLogical(random)
178 ntasks <- .toInteger(ntasks, function(x) x>=1)
179 ncores_tasks <- .toInteger(ncores_tasks, function(x) x>=1)
180 ncores_clust <- .toInteger(ncores_clust, function(x) x>=1)
181 if (!is.character(sep))
182 stop("'sep': character")
183 nbytes <- .toInteger(nbytes, function(x) x==4 || x==8)
184 verbose <- .toLogical(verbose)
185 parll <- .toLogical(parll)
186
187 # Since we don't make assumptions on initial data, there is a possibility that even
188 # when serialized, contributions or synchrones do not fit in RAM. For example,
189 # 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore,
190 # it's safer to place these in (binary) files, located in the following folder.
191 bin_dir <- ".epclust_bin/"
192 dir.create(bin_dir, showWarnings=FALSE, mode="0755")
193
194 # Binarize series if getSeries is not a function; the aim is to always use a function,
195 # to uniformize treatments. An equally good alternative would be to use a file-backed
196 # bigmemory::big.matrix, but it would break the uniformity.
197 if (!is.function(getSeries))
198 {
199 if (verbose)
200 cat("...Serialize time-series\n")
201 series_file = paste(bin_dir,"data",sep="") ; unlink(series_file)
202 binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
203 getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
204 }
205
206 # Serialize all computed wavelets contributions into a file
207 contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file)
208 index = 1
209 nb_curves = 0
210 if (verbose)
211 cat("...Compute contributions and serialize them\n")
212 nb_curves = binarizeTransform(getSeries,
213 function(series) curvesToContribs(series, wf, ctype),
214 contribs_file, nb_series_per_chunk, nbytes, endian)
215 getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
216
217 # A few sanity checks: do not continue if too few data available.
218 if (nb_curves < K2)
219 stop("Not enough data: less series than final number of clusters")
220 nb_series_per_task = round(nb_curves / ntasks)
221 if (nb_series_per_task < K2)
222 stop("Too many tasks: less series in one task than final number of clusters")
223
224 # Generate a random permutation of 1:N (if random==TRUE); otherwise just use arrival
225 # (storage) order.
226 indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
227 # Split (all) indices into ntasks groups of ~same size
228 indices_tasks = lapply(seq_len(ntasks), function(i) {
229 upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
230 indices_all[((i-1)*nb_series_per_task+1):upper_bound]
231 })
232
233 if (parll && ntasks>1)
234 {
235 # Initialize parallel runs: outfile="" allow to output verbose traces in the console
236 # under Linux. All necessary variables are passed to the workers.
237 cl = parallel::makeCluster(ncores_tasks, outfile="")
238 varlist = c("getSeries","getContribs","K1","K2","algo_clust1","algo_clust2",
239 "nb_per_chunk","nb_items_clust","ncores_clust","sep","nbytes","endian",
240 "verbose","parll")
241 if (WER=="mix")
242 varlist = c(varlist, "medoids_file")
243 parallel::clusterExport(cl, varlist, envir = environment())
244 }
245
246 # This function achieves one complete clustering task, divided in stage 1 + stage 2.
247 # stage 1: n indices --> clusteringTask1(...) --> K1 medoids
248 # stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids,
249 # where n = N / ntasks, N being the total number of curves.
250 runTwoStepClustering = function(inds)
251 {
252 # When running in parallel, the environment is blank: we need to load required
253 # packages, and pass useful variables.
254 if (parll && ntasks>1)
255 require("epclust", quietly=TRUE)
256 indices_medoids = clusteringTask1(
257 inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll)
258 if (WER=="mix")
259 {
260 if (parll && ntasks>1)
261 require("bigmemory", quietly=TRUE)
262 medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
263 medoids2 = clusteringTask2(medoids1, K2, getSeries, nb_curves, nb_series_per_chunk,
264 nbytes, endian, ncores_clust, verbose, parll)
265 binarize(medoids2, medoids_file, nb_series_per_chunk, sep, nbytes, endian)
266 return (vector("integer",0))
267 }
268 indices_medoids
269 }
270
271 # Synchrones (medoids) need to be stored only if WER=="mix"; indeed in this case, every
272 # task output is a set of new (medoids) curves. If WER=="end" however, output is just a
273 # set of indices, representing some initial series.
274 if (WER=="mix")
275 {medoids_file = paste(bin_dir,"medoids",sep="") ; unlink(medoids_file)}
276
277 if (verbose)
278 {
279 message = paste("...Run ",ntasks," x stage 1", sep="")
280 if (WER=="mix")
281 message = paste(message," + stage 2", sep="")
282 cat(paste(message,"\n", sep=""))
283 }
284
285 # As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"],
286 # or nothing (empty vector) if WER=="mix"; in this case, medoids (synchrones) are stored
287 # in a file.
288 indices <-
289 if (parll && ntasks>1)
290 unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
291 else
292 unlist( lapply(indices_tasks, runTwoStepClustering) )
293 if (parll && ntasks>1)
294 parallel::stopCluster(cl)
295
296 # Right before the final stage, two situations are possible:
297 # a. data to be processed now sit in binary format in medoids_file (if WER=="mix")
298 # b. data still is the initial set of curves, referenced by the ntasks*K1 indices
299 # So, the function getSeries() will potentially change. However, computeSynchrones()
300 # requires a function retrieving the initial series. Thus, the next line saves future
301 # conditional instructions.
302 getRefSeries = getSeries
303
304 if (WER=="mix")
305 {
306 indices = seq_len(ntasks*K2)
307 # Now series must be retrieved from synchrones_file
308 getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian)
309 # Contributions must be re-computed
310 unlink(contribs_file)
311 index = 1
312 if (verbose)
313 cat("...Serialize contributions computed on synchrones\n")
314 ignored = binarizeTransform(getSeries,
315 function(series) curvesToContribs(series, wf, ctype),
316 contribs_file, nb_series_per_chunk, nbytes, endian)
317 }
318
319 # Run step2 on resulting indices or series (from file)
320 if (verbose)
321 cat("...Run final // stage 1 + stage 2\n")
322 indices_medoids = clusteringTask1(
323 indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
324 medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
325 medoids2 = clusteringTask2(medoids1, K2, getRefSeries, nb_curves, nb_series_per_chunk,
326 nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
327
328 # Cleanup: remove temporary binary files and their folder
329 unlink(bin_dir, recursive=TRUE)
330
331 # Return medoids as a standard matrix, since K2 series have to fit in RAM
332 # (clustering algorithm 1 takes K1 > K2 of them as input)
333 medoids2[,]
334}
335
336#' curvesToContribs
337#'
338#' Compute the discrete wavelet coefficients for each series, and aggregate them in
339#' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2
340#'
341#' @param series [big.]matrix of series (in columns), of size L x n
342#' @inheritParams claws
343#'
344#' @return A [big.]matrix of size log(L) x n containing contributions in columns
345#'
346#' @export
347curvesToContribs = function(series, wav_filt, contrib_type)
348{
349 L = nrow(series)
350 D = ceiling( log2(L) )
351 nb_sample_points = 2^D
352 apply(series, 2, function(x) {
353 interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
354 W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
355 nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
356 if (contrib_type!="absolute")
357 nrj = nrj / sum(nrj)
358 if (contrib_type=="logit")
359 nrj = - log(1 - nrj)
360 nrj
361 })
362}
363
364# Check integer arguments with functional conditions
365.toInteger <- function(x, condition)
366{
367 errWarn <- function(ignored)
368 paste("Cannot convert argument' ",substitute(x),"' to integer", sep="")
369 if (!is.integer(x))
370 tryCatch({x = as.integer(x)[1]; if (is.na(x)) stop()},
371 warning = errWarn, error = errWarn)
372 if (!condition(x))
373 {
374 stop(paste("Argument '",substitute(x),
375 "' does not verify condition ",body(condition), sep=""))
376 }
377 x
378}
379
380# Check logical arguments
381.toLogical <- function(x)
382{
383 errWarn <- function(ignored)
384 paste("Cannot convert argument' ",substitute(x),"' to logical", sep="")
385 if (!is.logical(x))
386 tryCatch({x = as.logical(x)[1]; if (is.na(x)) stop()},
387 warning = errWarn, error = errWarn)
388 x
389}