#' }
#' @param K1 Number of clusters to be found after stage 1 (K1 << N [number of series])
#' @param K2 Number of clusters to be found after stage 2 (K2 << K1)
-#' @param nb_per_chunk (Maximum) number of items to retrieve in one batch, for both types of
-#' retrieval: resp. series and contribution; in a vector of size 2
-#' @param nb_items_clust1 (Maximum) number of items in input of the clustering algorithm
-#' for stage 1
+#' @param nb_series_per_chunk (Maximum) number of series to retrieve in one batch
+#' @param algo_clust1 Clustering algorithm for stage 1. A function which takes (data, K)
+#' as argument where data is a matrix in columns and K the desired number of clusters,
+#' and outputs K medoids ranks. Default: PAM
+#' @param algo_clust2 Clustering algorithm for stage 2. A function which takes (dists, K)
+#' as argument where dists is a matrix of distances and K the desired number of clusters,
+#' and outputs K clusters representatives (curves). Default: k-means
+#' @param nb_items_clust1 (~Maximum) number of items in input of the clustering algorithm
+#' for stage 1. At worst, a clustering algorithm might be called with ~2*nb_items_clust1
+#' items; but this could only happen at the last few iterations.
#' @param wav_filt Wavelet transform filter; see ?wavelets::wt.filter
#' @param contrib_type Type of contribution: "relative", "logit" or "absolute" (any prefix)
#' @param WER "end" to apply stage 2 after stage 1 has fully iterated, or "mix" to apply
#' series = do.call( cbind, lapply( 1:6, function(i)
#' do.call(cbind, wmtsa::wavBootstrap(ref_series[i,], n.realization=400)) ) )
#' #dim(series) #c(2400,10001)
-#' medoids_ascii = claws(series, K1=60, K2=6, nb_per_chunk=c(200,500), verbose=TRUE)
+#' medoids_ascii = claws(series, K1=60, K2=6, 200, verbose=TRUE)
#'
#' # Same example, from CSV file
#' csv_file = "/tmp/epclust_series.csv"
#' write.table(series, csv_file, sep=",", row.names=FALSE, col.names=FALSE)
-#' medoids_csv = claws(csv_file, K1=60, K2=6, nb_per_chunk=c(200,500))
+#' medoids_csv = claws(csv_file, K1=60, K2=6, 200)
#'
#' # Same example, from binary file
#' bin_file <- "/tmp/epclust_series.bin"
#' endian <- "little"
#' binarize(csv_file, bin_file, 500, nbytes, endian)
#' getSeries <- function(indices) getDataInFile(indices, bin_file, nbytes, endian)
-#' medoids_bin <- claws(getSeries, K1=60, K2=6, nb_per_chunk=c(200,500))
+#' medoids_bin <- claws(getSeries, K1=60, K2=6, 200)
#' unlink(csv_file)
#' unlink(bin_file)
#'
#' df_series <- dbGetQuery(series_db, request)
#' as.matrix(df_series[,"value"], nrow=serie_length)
#' }
-#' medoids_db = claws(getSeries, K1=60, K2=6, nb_per_chunk=c(200,500))
+#' medoids_db = claws(getSeries, K1=60, K2=6, 200))
#' dbDisconnect(series_db)
#'
#' # All computed medoids should be the same:
#' digest::sha1(medoids_db)
#' }
#' @export
-claws <- function(getSeries, K1, K2,
- nb_per_chunk,nb_items_clust1=7*K1 #volumes of data
- wav_filt="d8",contrib_type="absolute", #stage 1
- WER="end", #stage 2
- random=TRUE, #randomize series order?
- ntasks=1, ncores_tasks=1, ncores_clust=4, #parallelism
- sep=",", #ASCII input separator
- nbytes=4, endian=.Platform$endian, #serialization (write,read)
+claws <- function(getSeries, K1, K2, nb_series_per_chunk,
+ nb_items_clust1=7*K1,
+ algo_clust1=function(data,K) cluster::pam(data,K,diss=FALSE),
+ algo_clust2=function(dists,K) stats::kmeans(dists,K,iter.max=50,nstart=3),
+ wav_filt="d8", contrib_type="absolute",
+ WER="end",
+ random=TRUE,
+ ntasks=1, ncores_tasks=1, ncores_clust=4,
+ sep=",",
+ nbytes=4, endian=.Platform$endian,
verbose=FALSE, parll=TRUE)
{
# Check/transform arguments
}
K1 <- .toInteger(K1, function(x) x>=2)
K2 <- .toInteger(K2, function(x) x>=2)
- if (!is.numeric(nb_per_chunk) || length(nb_per_chunk)!=2)
- stop("'nb_per_chunk': numeric, size 2")
- nb_per_chunk[1] <- .toInteger(nb_per_chunk[1], function(x) x>=1)
- # A batch of contributions should have at least as many elements as a batch of series,
- # because it always contains much less values
- nb_per_chunk[2] <- max(.toInteger(nb_per_chunk[2],function(x) x>=1), nb_per_chunk[1])
+ nb_series_per_chunk <- .toInteger(nb_series_per_chunk, function(x) x>=1)
+ # K1 (number of clusters at step 1) cannot exceed nb_series_per_chunk, because we will need
+ # to load K1 series in memory for clustering stage 2.
+ if (K1 > nb_series_per_chunk)
+ stop("'K1' cannot exceed 'nb_series_per_chunk'")
nb_items_clust1 <- .toInteger(nb_items_clust1, function(x) x>K1)
random <- .toLogical(random)
tryCatch
verbose <- .toLogical(verbose)
parll <- .toLogical(parll)
- # Serialize series if required, to always use a function
+ # Since we don't make assumptions on initial data, there is a possibility that even
+ # when serialized, contributions or synchrones do not fit in RAM. For example,
+ # 30e6 series of length 100,000 would lead to a +4Go contribution matrix. Therefore,
+ # it's safer to place these in (binary) files, located in the following folder.
bin_dir <- ".epclust_bin/"
dir.create(bin_dir, showWarnings=FALSE, mode="0755")
+
+ # Binarize series if getSeries is not a function; the aim is to always use a function,
+ # to uniformize treatments. An equally good alternative would be to use a file-backed
+ # bigmemory::big.matrix, but it would break the uniformity.
if (!is.function(getSeries))
{
if (verbose)
contribs_file, nb_series_per_chunk, nbytes, endian)
getContribs = function(indices) getDataInFile(indices, contribs_file, nbytes, endian)
+ # A few sanity checks: do not continue if too few data available.
if (nb_curves < K2)
stop("Not enough data: less series than final number of clusters")
nb_series_per_task = round(nb_curves / ntasks)
if (nb_series_per_task < K2)
stop("Too many tasks: less series in one task than final number of clusters")
+ # Generate a random permutation of 1:N (if random==TRUE); otherwise just use arrival
+ # (storage) order.
+ indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
+ # Split (all) indices into ntasks groups of ~same size
+ indices_tasks = lapply(seq_len(ntasks), function(i) {
+ upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
+ indices_all[((i-1)*nb_series_per_task+1):upper_bound]
+ })
+
+ if (parll && ntasks>1)
+ {
+ # Initialize parallel runs: outfile="" allow to output verbose traces in the console
+ # under Linux. All necessary variables are passed to the workers.
+ cl = parallel::makeCluster(ncores_tasks, outfile="")
+ varlist = c("getSeries","getContribs","K1","K2","algo_clust1","algo_clust2",
+ "nb_series_per_chunk","nb_items_clust","ncores_clust","sep",
+ "nbytes","endian","verbose","parll")
+ if (WER=="mix")
+ varlist = c(varlist, "medoids_file")
+ parallel::clusterExport(cl, varlist, envir = environment())
+ }
+
+ # This function achieves one complete clustering task, divided in stage 1 + stage 2.
+ # stage 1: n indices --> clusteringTask1(...) --> K1 medoids
+ # stage 2: K1 medoids --> clusteringTask2(...) --> K2 medoids,
+ # where n = N / ntasks, N being the total number of curves.
runTwoStepClustering = function(inds)
{
+ # When running in parallel, the environment is blank: we need to load required
+ # packages, and pass useful variables.
if (parll && ntasks>1)
require("epclust", quietly=TRUE)
indices_medoids = clusteringTask1(
medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
medoids2 = clusteringTask2(medoids1, K2, getSeries, nb_curves, nb_series_per_chunk,
nbytes, endian, ncores_clust, verbose, parll)
- binarize(medoids2, synchrones_file, nb_series_per_chunk, sep, nbytes, endian)
+ binarize(medoids2, medoids_file, nb_series_per_chunk, sep, nbytes, endian)
return (vector("integer",0))
}
indices_medoids
}
- # Cluster contributions in parallel (by nb_series_per_chunk)
- indices_all = if (random) sample(nb_curves) else seq_len(nb_curves)
- indices_tasks = lapply(seq_len(ntasks), function(i) {
- upper_bound = ifelse( i<ntasks, min(nb_series_per_task*i,nb_curves), nb_curves )
- indices_all[((i-1)*nb_series_per_task+1):upper_bound]
- })
+ # Synchrones (medoids) need to be stored only if WER=="mix"; indeed in this case, every
+ # task output is a set of new (medoids) curves. If WER=="end" however, output is just a
+ # set of indices, representing some initial series.
+ if (WER=="mix")
+ {medoids_file = paste(bin_dir,"medoids",sep="") ; unlink(medoids_file)}
+
if (verbose)
{
message = paste("...Run ",ntasks," x stage 1", sep="")
message = paste(message," + stage 2", sep="")
cat(paste(message,"\n", sep=""))
}
- if (WER=="mix")
- {synchrones_file = paste(bin_dir,"synchrones",sep="") ; unlink(synchrones_file)}
- if (parll && ntasks>1)
- {
- cl = parallel::makeCluster(ncores_tasks, outfile="")
- varlist = c("getSeries","getContribs","K1","K2","verbose","parll",
- "nb_series_per_chunk","ntasks","ncores_clust","sep","nbytes","endian")
- if (WER=="mix")
- varlist = c(varlist, "synchrones_file")
- parallel::clusterExport(cl, varlist=varlist, envir = environment())
- }
- # 1000*K1 indices [if WER=="end"], or empty vector [if WER=="mix"] --> series on file
+ # As explained above, indices will be assigned to ntasks*K1 medoids indices [if WER=="end"],
+ # or nothing (empty vector) if WER=="mix"; in this case, medoids (synchrones) are stored
+ # in a file.
indices <-
if (parll && ntasks>1)
unlist( parallel::parLapply(cl, indices_tasks, runTwoStepClustering) )
if (parll && ntasks>1)
parallel::stopCluster(cl)
+ # Right before the final stage, two situations are possible:
+ # a. data to be processed now sit in binary format in medoids_file (if WER=="mix")
+ # b. data still is the initial set of curves, referenced by the ntasks*K1 indices
+ # So, the function getSeries() will potentially change. However, computeSynchrones()
+ # requires a function retrieving the initial series. Thus, the next line saves future
+ # conditional instructions.
getRefSeries = getSeries
+
if (WER=="mix")
{
indices = seq_len(ntasks*K2)
- #Now series must be retrieved from synchrones_file
- getSeries = function(inds) getDataInFile(inds, synchrones_file, nbytes, endian)
- #Contributions must be re-computed
+ # Now series (synchrones) must be retrieved from medoids_file
+ getSeries = function(inds) getDataInFile(inds, medoids_file, nbytes, endian)
+ # Contributions must be re-computed
unlink(contribs_file)
index = 1
if (verbose)
contribs_file, nb_series_per_chunk, nbytes, endian)
}
+#TODO: check THAT
+
+
# Run step2 on resulting indices or series (from file)
if (verbose)
cat("...Run final // stage 1 + stage 2\n")
medoids2 = clusteringTask2(medoids1, K2, getRefSeries, nb_curves, nb_series_per_chunk,
nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
- # Cleanup
+ # Cleanup: remove temporary binary files and their folder
unlink(bin_dir, recursive=TRUE)
+ # Return medoids as a standard matrix, since K2 series have to fit in RAM
+ # (clustering algorithm 1 takes K1 > K2 of them as input)
medoids2[,]
}
projects / epclust.git / blobdiff