'update'
[epclust.git] / epclust / R / main.R
1 #' CLAWS: CLustering with wAvelets and Wer distanceS
2 #'
3 #' Groups electricity power curves (or any series of similar nature) by applying PAM
4 #' algorithm in parallel to chunks of size \code{nb_series_per_chunk}. Input series
5 #' must be sampled on the same time grid, no missing values.
6 #'
7 #' @param getSeries Access to the (time-)series, which can be of one of the three
8 #' following types:
9 #' \itemize{
10 #' \item [big.]matrix: each line contains all the values for one time-serie, ordered by time
11 #' \item connection: any R connection object providing lines as described above
12 #' \item character: name of a CSV file containing series in rows (no header)
13 #' \item function: a custom way to retrieve the curves; it has only one argument:
14 #' the indices of the series to be retrieved. See examples
15 #' }
16 #' @inheritParams clustering
17 #' @param K1 Number of super-consumers to be found after stage 1 (K1 << N)
18 #' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
19 #' @param wf Wavelet transform filter; see ?wavelets::wt.filter
20 #' @param ctype Type of contribution: "relative" or "absolute" (or any prefix)
21 #' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply stage 2
22 #' at the end of each task
23 #' @param random TRUE (default) for random chunks repartition
24 #' @param ntasks Number of tasks (parallel iterations to obtain K1 medoids); default: 1.
25 #' Note: ntasks << N, so that N is "roughly divisible" by N (number of series)
26 #' @param ncores_tasks "MPI" number of parallel tasks (1 to disable: sequential tasks)
27 #' @param ncores_clust "OpenMP" number of parallel clusterings in one task
28 #' @param nb_series_per_chunk (~Maximum) number of series in each group, inside a task
29 #' @param min_series_per_chunk Minimum number of series in each group
30 #' @param sep Separator in CSV input file (if any provided)
31 #' @param nbytes Number of bytes to serialize a floating-point number; 4 or 8
32 #' @param endian Endianness to use for (de)serialization. Use "little" or "big" for portability
33 #' @param verbose Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
34 #' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
35 #'
36 #' @return A big.matrix of the final medoids curves (K2) in rows
37 #'
38 #' @examples
39 #' \dontrun{
40 #' # WER distances computations are a bit too long for CRAN (for now)
41 #'
42 #' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
43 #' x = seq(0,500,0.05)
44 #' L = length(x) #10001
45 #' ref_series = matrix( c(cos(x), cos(2*x), cos(3*x), sin(x), sin(2*x), sin(3*x)),
46 #' byrow=TRUE, ncol=L )
47 #' library(wmtsa)
48 #' series = do.call( rbind, lapply( 1:6, function(i)
49 #' do.call(rbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
50 #' #dim(series) #c(2400,10001)
51 #' medoids_ascii = claws(series, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
52 #'
53 #' # Same example, from CSV file
54 #' csv_file = "/tmp/epclust_series.csv"
55 #' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
56 #' medoids_csv = claws(csv_file, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
57 #'
58 #' # Same example, from binary file
59 #' bin_file = "/tmp/epclust_series.bin"
60 #' nbytes = 8
61 #' endian = "little"
62 #' epclust::binarize(csv_file, bin_file, 500, nbytes, endian)
63 #' getSeries = function(indices) getDataInFile(indices, bin_file, nbytes, endian)
64 #' medoids_bin = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
65 #' unlink(csv_file)
66 #' unlink(bin_file)
67 #'
68 #' # Same example, from SQLite database
69 #' library(DBI)
70 #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
71 #' # Prepare data.frame in DB-format
72 #' n = nrow(series)
73 #' time_values = data.frame(
74 #' id = rep(1:n,each=L),
75 #' time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
76 #' value = as.double(t(series)) )
77 #' dbWriteTable(series_db, "times_values", times_values)
78 #' # Fill associative array, map index to identifier
79 #' indexToID_inDB <- as.character(
80 #' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
81 #' getSeries = function(indices) {
82 #' request = "SELECT id,value FROM times_values WHERE id in ("
83 #' for (i in indices)
84 #' request = paste(request, i, ",", sep="")
85 #' request = paste(request, ")", sep="")
86 #' df_series = dbGetQuery(series_db, request)
87 #' # Assume that all series share same length at this stage
88 #' ts_length = sum(df_series[,"id"] == df_series[1,"id"])
89 #' t( as.matrix(df_series[,"value"], nrow=ts_length) )
90 #' }
91 #' medoids_db = claws(getSeries, K1=60, K2=6, "d8", "rel", nb_series_per_chunk=500)
92 #' dbDisconnect(series_db)
93 #'
94 #' # All computed medoids should be the same:
95 #' digest::sha1(medoids_ascii)
96 #' digest::sha1(medoids_csv)
97 #' digest::sha1(medoids_bin)
98 #' digest::sha1(medoids_db)
99 #' }
100 #' @export
101 claws = function(getSeries, K1, K2,
102 wf,ctype, #stage 1
103 WER="end", #stage 2
104 random=TRUE, #randomize series order?
105 ntasks=1, ncores_tasks=1, ncores_clust=4, #control parallelism
106 nb_series_per_chunk=50*K1, min_series_per_chunk=5*K1, #chunk size
107 sep=",", #ASCII input separator
108 nbytes=4, endian=.Platform$endian, #serialization (write,read)
109 verbose=FALSE, parll=TRUE)
110 {
111 # Check/transform arguments
112 if (!is.matrix(getSeries) && !bigmemory::is.big.matrix(getSeries)
113 && !is.function(getSeries)
114 && !methods::is(getSeries,"connection") && !is.character(getSeries))
115 {
116 stop("'getSeries': [big]matrix, function, file or valid connection (no NA)")
117 }
118 K1 = .toInteger(K1, function(x) x>=2)
119 K2 = .toInteger(K2, function(x) x>=2)
120 if (!is.logical(random))
121 stop("'random': logical")
122 tryCatch(
123 {ignored <- wavelets::wt.filter(wf)},
124 error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter"))
125 if (WER!="end" && WER!="mix")
126 stop("WER takes values in {'end','mix'}")
127 ntasks = .toInteger(ntasks, function(x) x>=1)
128 ncores_tasks = .toInteger(ncores_tasks, function(x) x>=1)
129 ncores_clust = .toInteger(ncores_clust, function(x) x>=1)
130 nb_series_per_chunk = .toInteger(nb_series_per_chunk, function(x) x>=K1)
131 min_series_per_chunk = .toInteger(K1, function(x) x>=K1 && x<=nb_series_per_chunk)
132 if (!is.character(sep))
133 stop("'sep': character")
134 nbytes = .toInteger(nbytes, function(x) x==4 || x==8)
135
136 # Serialize series if required, to always use a function
137 bin_dir = ".epclust_bin/"
138 dir.create(bin_dir, showWarnings=FALSE, mode="0755")
139 if (!is.function(getSeries))
140 {
141 if (verbose)
142 cat("...Serialize time-series\n")
143 series_file = paste(bin_dir,"data",sep="") ; unlink(series_file)
144 binarize(getSeries, series_file, nb_series_per_chunk, sep, nbytes, endian)
145 getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
146 }
147
148 # Serialize all computed wavelets contributions into a file
149 contribs_file = paste(bin_dir,"contribs",sep="") ; unlink(contribs_file)
150 index = 1
151 nb_curves = 0
152 if (verbose)
153 cat("...Compute contributions and serialize them\n")
154 nb_curves = binarizeTransform(getSeries,
155 function(series) curvesToContribs(series, wf, ctype),
156 contribs_file, nb_series_per_chunk, nbytes, endian)
157 getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
158
159 if (nb_curves < min_series_per_chunk)
160 stop("Not enough data: less rows than min_series_per_chunk!")
161 nb_series_per_task = round(nb_curves / ntasks)
162 if (nb_series_per_task < min_series_per_chunk)
163 stop("Too many tasks: less series in one task than min_series_per_chunk!")
164
165 runTwoStepClustering = function(inds)
166 {
167 if (parll && ntasks>1)
168 require("epclust", quietly=TRUE)
169 indices_medoids = clusteringTask1(
170 inds, getContribs, K1, nb_series_per_chunk, ncores_clust, verbose, parll)
171 if (WER=="mix")
172 {
173 medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
174 medoids2 = clusteringTask2(medoids1,
175 K2, getSeries, nb_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
176 binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian)
177 return (vector("integer",0))
178 }
179 indices_medoids
180 }
181
182 # Cluster contributions in parallel (by nb_series_per_chunk)
183 indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
184 indices_tasks = lapply(seq_len(ntasks), function(i) {
185 upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
186 indices_all[((i-1)*nb_series_per_task+1):upper_bound]
187 })
188 if (verbose)
189 cat(paste("...Run ",ntasks," x stage 1 in parallel\n",sep=""))
190 if (WER=="mix")
191 {synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)}
192 if (parll && ntasks>1)
193 {
194 cl = parallel::makeCluster(ncores_tasks)
195 varlist = c("getSeries","getContribs","K1","K2","verbose","parll",
196 "nb_series_per_chunk","ntasks","ncores_clust","sep","nbytes","endian")
197 if (WER=="mix")
198 varlist = c(varlist, "synchrones_file")
199 parallel::clusterExport(cl, varlist=varlist, envir = environment())
200 }
201
202 # 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file
203 if (parll && ntasks>1)
204 indices = unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
205 else
206 indices = unlist( lapply(indices_tasks, runTwoStepClustering) )
207 if (parll && ntasks>1)
208 parallel::stopCluster(cl)
209
210 getRefSeries = getSeries
211 if (WER=="mix")
212 {
213 indices = seq_len(ntasks*K2)
214 #Now series must be retrieved from synchrones_file
215 getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian)
216 #Contributions must be re-computed
217 unlink(contribs_file)
218 index = 1
219 if (verbose)
220 cat("...Serialize contributions computed on synchrones\n")
221 ignored = binarizeTransform(getSeries,
222 function(series) curvesToContribs(series, wf, ctype),
223 contribs_file, nb_series_per_chunk, nbytes, endian)
224 }
225
226 # Run step2 on resulting indices or series (from file)
227 if (verbose)
228 cat("...Run final // stage 1 + stage 2\n")
229 indices_medoids = clusteringTask1(
230 indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
231 medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
232 medoids2 = computeClusters2(medoids1, K2,
233 getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
234
235 # Cleanup
236 unlink(bin_dir, recursive=TRUE)
237
238 medoids2
239 }
240
241 #' curvesToContribs
242 #'
243 #' Compute the discrete wavelet coefficients for each series, and aggregate them in
244 #' energy contribution across scales as described in https://arxiv.org/abs/1101.4744v2
245 #'
246 #' @param series Matrix of series (in rows), of size n x L
247 #' @inheritParams claws
248 #'
249 #' @return A matrix of size n x log(L) containing contributions in rows
250 #'
251 #' @export
252 curvesToContribs = function(series, wf, ctype)
253 {
254 L = length(series[1,])
255 D = ceiling( log2(L) )
256 nb_sample_points = 2^D
257 cont_types = c("relative","absolute")
258 ctype = cont_types[ pmatch(ctype,cont_types) ]
259 t( apply(series, 1, function(x) {
260 interpolated_curve = spline(1:L, x, n=nb_sample_points)$y
261 W = wavelets::dwt(interpolated_curve, filter=wf, D)@W
262 nrj = rev( sapply( W, function(v) ( sqrt( sum(v^2) ) ) ) )
263 if (ctype=="relative") nrj / sum(nrj) else nrj
264 }) )
265 }
266
267 # Check integer arguments with functional conditions
268 .toInteger <- function(x, condition)
269 {
270 if (!is.integer(x))
271 tryCatch(
272 {x = as.integer(x)[1]},
273 error = function(e) paste("Cannot convert argument",substitute(x),"to integer")
274 )
275 if (!condition(x))
276 stop(paste("Argument",substitute(x),"does not verify condition",body(condition)))
277 x
278 }