603f7bfbbec05e2c71db48bcc75a7132507eb2f4
[epclust.git] / epclust / R / main.R
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 #' 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_series_per_chunk}
15 #' \item optionally, if WER=="mix":
16 #' a) compute the K1 synchrones curves,
17 #' a) compute WER distances (K1xK1 matrix) between medoids and
18 #' b) apply the second clustering algorithm (output: K2 indices)
19 #' }
20 #' \item Launch a final task on the aggregated outputs of all previous tasks:
21 #' ntasks*K1 if WER=="end", ntasks*K2 otherwise
22 #' \item Compute synchrones (sum of series within each final group)
23 #' }
24 #' \cr
25 #' The main argument -- \code{series} -- has a quite misleading name, since it can be
26 #' either a [big.]matrix, a CSV file, a connection or a user function to retrieve series.
27 #' When \code{series} 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.
30 #' WARNING: the return value must be a matrix (in columns), or NULL if no matches.
31 #' \cr
32 #' Note: Since we don't make assumptions on initial data, there is a possibility that
33 #' even when serialized, contributions do not fit in RAM. For example,
34 #' 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore,
35 #' it's safer to place these in (binary) files; that's what we do.
36 #'
37 #' @param series Access to the (time-)series, which can be of one of the three
38 #' following types:
39 #' \itemize{
40 #' \item [big.]matrix: each column contains the (time-ordered) values of one time-serie
41 #' \item connection: any R connection object providing lines as described above
42 #' \item character: name of a CSV file containing series in rows (no header)
43 #' \item function: a custom way to retrieve the curves; it has only one argument:
44 #' the indices of the series to be retrieved. See SQLite example
45 #' }
46 #' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series])
47 #' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
48 #' @param nb_series_per_chunk (Maximum) number of series to retrieve in one batch;
49 #' this value is also used for the (maximum) number of series to cluster at a time
50 #' @param algoClust1 Clustering algorithm for stage 1. A function which takes (data, K)
51 #' as argument where data is a matrix in columns and K the desired number of clusters,
52 #' and outputs K medoids ranks. Default: PAM. In our method, this function is called
53 #' on iterated medoids during stage 1
54 #' @param algoClust2 Clustering algorithm for stage 2. A function which takes (dists, K)
55 #' as argument where dists is a matrix of distances and K the desired number of clusters,
56 #' and outputs K medoids ranks. Default: PAM. In our method, this function is called
57 #' on a matrix of K1 x K1 (WER) distances computed between medoids after algorithm 1
58 #' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter
59 #' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix)
60 #' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply
61 #' stage 2 at the end of each task
62 #' @param nvoice Number of voices within each octave for CWT computations
63 #' @param random TRUE (default) for random chunks repartition
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
67 #' @param ncores_tasks Number of parallel tasks (1 to disable: sequential tasks)
68 #' @param ncores_clust Number of parallel clusterings in one task (3 should be a minimum)
69 #' @param sep Separator in CSV input file (if any provided)
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 Level of verbosity (0/FALSE for nothing or 1/TRUE for all; devel stage)
73 #' @param parll TRUE to fully parallelize; otherwise run sequentially (debug, comparison)
74 #'
75 #' @return A list with
76 #' \itemize{
77 #' medoids: a matrix of the final K2 medoids curves, in columns
78 #' ranks: corresponding indices in the dataset
79 #' synchrones: a matrix of the K2 sum of series within each final group
80 #' }
81 #'
82 #' @references Clustering functional data using Wavelets [2013];
83 #' A. Antoniadis, X. Brossat, J. Cugliari & J.-M. Poggi.
84 #' Inter. J. of Wavelets, Multiresolution and Information Procesing,
85 #' vol. 11, No 1, pp.1-30. doi:10.1142/S0219691313500033
86 #'
87 #' @examples
88 #' \dontrun{
89 #' # WER distances computations are too long for CRAN (for now)
90 #'
91 #' # Random series around cos(x,2x,3x)/sin(x,2x,3x)
92 #' x = seq(0,500,0.05)
93 #' L = length(x) #10001
94 #' ref_series = matrix( c(cos(x),cos(2*x),cos(3*x),sin(x),sin(2*x),sin(3*x)), ncol=6 )
95 #' library(wmtsa)
96 #' series = do.call( cbind, lapply( 1:6, function(i)
97 #' do.call(cbind, wmtsa::wavBootstrap(ref_series[,i], n.realization=400)) ) )
98 #' #dim(series) #c(2400,10001)
99 #' res_ascii = claws(series, K1=60, K2=6, 200, verbose=TRUE)
100 #'
101 #' # Same example, from CSV file
102 #' csv_file = "/tmp/epclust_series.csv"
103 #' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
104 #' res_csv = claws(csv_file, K1=60, K2=6, 200)
105 #'
106 #' # Same example, from binary file
107 #' bin_file <- "/tmp/epclust_series.bin"
108 #' nbytes <- 8
109 #' endian <- "little"
110 #' binarize(csv_file, bin_file, 500, nbytes, endian)
111 #' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian)
112 #' res_bin <- claws(getSeries, K1=60, K2=6, 200)
113 #' unlink(csv_file)
114 #' unlink(bin_file)
115 #'
116 #' # Same example, from SQLite database
117 #' library(DBI)
118 #' series_db <- dbConnect(RSQLite::SQLite(), "file::memory:")
119 #' # Prepare data.frame in DB-format
120 #' n <- nrow(series)
121 #' time_values <- data.frame(
122 #' id = rep(1:n,each=L),
123 #' time = rep( as.POSIXct(1800*(0:n),"GMT",origin="2001-01-01"), L ),
124 #' value = as.double(t(series)) )
125 #' dbWriteTable(series_db, "times_values", times_values)
126 #' # Fill associative array, map index to identifier
127 #' indexToID_inDB <- as.character(
128 #' dbGetQuery(series_db, 'SELECT DISTINCT id FROM time_values')[,"id"] )
129 #' serie_length <- as.integer( dbGetQuery(series_db,
130 #' paste("SELECT COUNT * FROM time_values WHERE id == ",indexToID_inDB[1],sep="")) )
131 #' getSeries <- function(indices) {
132 #' request <- "SELECT id,value FROM times_values WHERE id in ("
133 #' for (i in indices)
134 #' request <- paste(request, indexToID_inDB[i], ",", sep="")
135 #' request <- paste(request, ")", sep="")
136 #' df_series <- dbGetQuery(series_db, request)
137 #' if (length(df_series) >= 1)
138 #' as.matrix(df_series[,"value"], nrow=serie_length)
139 #' else
140 #' NULL
141 #' }
142 #' res_db = claws(getSeries, K1=60, K2=6, 200))
143 #' dbDisconnect(series_db)
144 #'
145 #' # All results should be the same:
146 #' library(digest)
147 #' digest::sha1(res_ascii)
148 #' digest::sha1(res_csv)
149 #' digest::sha1(res_bin)
150 #' digest::sha1(res_db)
151 #' }
152 #' @export
153 claws <- function(getSeries, K1, K2, nb_series_per_chunk,
154 algoClust1=function(data,K) cluster::pam(t(data),K,diss=FALSE,pamonce=1)$id.med,
155 algoClust2=function(dists,K) cluster::pam(dists,K,diss=TRUE,pamonce=1)$id.med,
156 wav_filt="d8", contrib_type="absolute", WER="end", nvoice=4, random=TRUE,
157 ntasks=1, ncores_tasks=1, ncores_clust=4, sep=",", nbytes=4,
158 endian=.Platform$endian, verbose=FALSE, parll=TRUE)
159 {
160 # Check/transform arguments
161 if (!is.matrix(series) && !bigmemory::is.big.matrix(series)
162 && !is.function(series)
163 && !methods::is(series,"connection") && !is.character(series))
164 {
165 stop("'series': [big]matrix, function, file or valid connection (no NA)")
166 }
167 K1 <- .toInteger(K1, function(x) x>=2)
168 K2 <- .toInteger(K2, function(x) x>=2)
169 nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1)
170 # K1 (number of clusters at step 1) cannot exceed nb_series_per_chunk, because we will need
171 # to load K1 series in memory for clustering stage 2.
172 if (K1 > nb_series_per_chunk)
173 stop("'K1' cannot exceed 'nb_series_per_chunk'")
174 random <- .toLogical(random)
175 tryCatch( {ignored <- wavelets::wt.filter(wav_filt)},
176 error = function(e) stop("Invalid wavelet filter; see ?wavelets::wt.filter") )
177 ctypes = c("relative","absolute","logit")
178 contrib_type = ctypes[ pmatch(contrib_type,ctypes) ]
179 if (is.na(contrib_type))
180 stop("'contrib_type' in {'relative','absolute','logit'}")
181 if (WER!="end" && WER!="mix")
182 stop("'WER': in {'end','mix'}")
183 random <- .toLogical(random)
184 ntasks <- .toInteger(ntasks, function(x) x>=1)
185 ncores_tasks <- .toInteger(ncores_tasks, function(x) x>=1)
186 ncores_clust <- .toInteger(ncores_clust, function(x) x>=1)
187 if (!is.character(sep))
188 stop("'sep': character")
189 nbytes <- .toInteger(nbytes, function(x) x==4 || x==8)
190 verbose <- .toLogical(verbose)
191 parll <- .toLogical(parll)
192
193 # Binarize series if it is not a function; the aim is to always use a function,
194 # to uniformize treatments. An equally good alternative would be to use a file-backed
195 # bigmemory::big.matrix, but it would break the "all-is-function" pattern.
196 if (!is.function(series))
197 {
198 if (verbose)
199 cat("...Serialize time-series (or retrieve past binary file)\n")
200 series_file = ".series.epclust.bin"
201 if (!file.exists(series_file))
202 binarize(series, series_file, nb_series_per_chunk, sep, nbytes, endian)
203 getSeries = function(inds) getDataInFile(inds, series_file, nbytes, endian)
204 }
205 else
206 getSeries = series
207
208 # Serialize all computed wavelets contributions into a file
209 contribs_file = ".contribs.epclust.bin"
210 index = 1
211 nb_curves = 0
212 if (verbose)
213 cat("...Compute contributions and serialize them (or retrieve past binary file)\n")
214 if (!file.exists(contribs_file))
215 {
216 nb_curves = binarizeTransform(getSeries,
217 function(curves) curvesToContribs(curves, wav_filt, contrib_type),
218 contribs_file, nb_series_per_chunk, nbytes, endian)
219 }
220 else
221 {
222 # TODO: duplicate from getDataInFile() in de_serialize.R
223 contribs_size = file.info(contribs_file)$size #number of bytes in the file
224 contrib_length = readBin(contribs_file, "integer", n=1, size=8, endian=endian)
225 nb_curves = (contribs_size-8) / (nbytes*contrib_length)
226 }
227 getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
228
229 # A few sanity checks: do not continue if too few data available.
230 if (nb_curves < K2)
231 stop("Not enough data: less series than final number of clusters")
232 nb_series_per_task = round(nb_curves / ntasks)
233 if (nb_series_per_task < K2)
234 stop("Too many tasks: less series in one task than final number of clusters")
235
236 # Generate a random permutation of 1:N (if random==TRUE);
237 # otherwise just use arrival (storage) order.
238 indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
239 # Split (all) indices into ntasks groups of ~same size
240 indices_tasks = lapply(seq_len(ntasks), function(i) {
241 upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
242 indices_all[((i-1)*nb_series_per_task+1):upper_bound]
243 })
244
245 if (parll && ntasks>1)
246 {
247 # Initialize parallel runs: outfile="" allow to output verbose traces in the console
248 # under Linux. All necessary variables are passed to the workers.
249 cl = parallel::makeCluster(ncores_tasks, outfile="")
250 parallel::clusterExport(cl, envir = environment(),
251 varlist = c("getSeries","getContribs","K1","K2","algoClust1","algoClust2",
252 "nb_series_per_chunk","ncores_clust","nvoice","nbytes","endian","verbose","parll"))
253 }
254
255 # This function achieves one complete clustering task, divided in stage 1 + stage 2.
256 # stage 1: n indices --> clusteringTask1(...) --> K1 medoids
257 # stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids,
258 # where n = N / ntasks, N being the total number of curves.
259 runTwoStepClustering = function(inds)
260 {
261 # When running in parallel, the environment is blank: we need to load the required
262 # packages, and pass useful variables.
263 if (parll && ntasks>1)
264 require("epclust", quietly=TRUE)
265 indices_medoids = clusteringTask1(inds, getContribs, K1, algoClust1,
266 nb_series_per_chunk, ncores_clust, verbose, parll)
267 if (WER=="mix")
268 {
269 indices_medoids = clusteringTask2(indices_medoids, getSeries, K2, algoClust2,
270 nb_series_per_chunk, nvoice, nbytes, endian, ncores_clust, verbose, parll)
271 }
272 indices_medoids
273 }
274
275 if (verbose)
276 {
277 message = paste("...Run ",ntasks," x stage 1", sep="")
278 if (WER=="mix")
279 message = paste(message," + stage 2", sep="")
280 cat(paste(message,"\n", sep=""))
281 }
282
283 # As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"],
284 # or nothing (empty vector) if WER=="mix"; in this case, synchrones are stored in a file.
285 indices_medoids_all <-
286 if (parll && ntasks>1)
287 unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
288 else
289 unlist( lapply(indices_tasks, runTwoStepClustering) )
290
291 if (parll && ntasks>1)
292 parallel::stopCluster(cl)
293
294 # Right before the final stage, input data still is the initial set of curves, referenced
295 # by the ntasks*[K1 or K2] medoids indices.
296
297 # Run last clustering tasks to obtain only K2 medoids indices, from ntasks*[K1 or K2]
298 # indices, depending wether WER=="end" or WER=="mix"
299 if (verbose)
300 cat("...Run final // stage 1 + stage 2\n")
301 indices_medoids = clusteringTask1(indices_medoids_all, getContribs, K1, algoClust1,
302 nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
303 indices_medoids = clusteringTask2(indices_medoids, getContribs, K2, algoClust2,
304 nb_series_per_chunk, nvoice, nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
305
306 # Compute synchrones
307 medoids = getSeries(indices_medoids)
308 synchrones = computeSynchrones(medoids, getSeries, nb_curves, nb_series_per_chunk,
309 ncores_tasks*ncores_clust, verbose, parll)
310
311 # NOTE: no need to use big.matrix here, since there are only K2 << K1 << N remaining curves
312 list("medoids"=medoids, "ranks"=indices_medoids, "synchrones"=synchrones)
313 }