Add comments to easily read code

[epclust.git] / epclust / R / clustering.R

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index a4c273a..70d263e 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,6 +1,6 @@
 #' @name clustering
 #' @rdname clustering
-#' @aliases clusteringTask1 computeClusters1 computeClusters2
+#' @aliases clusteringTask1 clusteringTask2 computeClusters1 computeClusters2
 #'
 #' @title Two-stage clustering, withing one task (see \code{claws()})
 #'
@@ -11,8 +11,8 @@
 #'   and then WER distances computations, before applying the clustering algorithm.
 #'   \code{computeClusters1()} and \code{computeClusters2()} correspond to the atomic
 #'   clustering procedures respectively for stage 1 and 2. The former applies the
-#'   clustering algorithm (PAM) on a contributions matrix, while the latter clusters
-#'   a chunk of series inside one task (~max nb_series_per_chunk)
+#'   first clustering algorithm on a contributions matrix, while the latter clusters
+#'   a set of series inside one task (~nb_items_clust)
 #'
 #' @param indices Range of series indices to cluster in parallel (initial data)
 #' @param getContribs Function to retrieve contributions from initial series indices:
@@ -31,11 +31,23 @@ NULL
 #' @rdname clustering
 #' @export
 clusteringTask1 = function(
-       indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
+       indices, getContribs, K1, nb_per_chunk, nb_items_clust, ncores_clust=1,
+       verbose=FALSE, parll=TRUE)
 {
        if (verbose)
                cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
 
+
+
+
+
+
+##TODO: reviser le spreadIndices, tenant compte de nb_items_clust
+
+       ##TODO: reviser / harmoniser avec getContribs qui en récupère pt'et + pt'et - !!
+
+
+
        if (parll)
        {
                cl = parallel::makeCluster(ncores_clust)
@@ -87,7 +99,7 @@ computeClusters1 = function(contribs, K1, verbose=FALSE)
 {
        if (verbose)
                cat(paste("   computeClusters1() on ",nrow(contribs)," lines\n", sep=""))
-       cluster::pam(contribs, K1, diss=FALSE)$id.med
+       cluster::pam(        t(contribs)       , K1, diss=FALSE)$id.med
 }
 
 #' @rdname clustering
@@ -96,7 +108,7 @@ computeClusters2 = function(distances, K2, verbose=FALSE)
 {
        if (verbose)
                cat(paste("   computeClusters2() on ",nrow(distances)," lines\n", sep=""))
-       cluster::pam(distances, K2, diss=TRUE)$id.med
+       cluster::pam(       distances        , K2, diss=TRUE)$id.med
 }
 
 #' computeSynchrones
@@ -110,7 +122,7 @@ computeClusters2 = function(distances, K2, verbose=FALSE)
 #' @param nb_ref_curves How many reference series? (This number is known at this stage)
 #' @inheritParams claws
 #'
-#' @return A big.matrix of size K1 x L where L = data_length
+#' @return A big.matrix of size L x K1 where L = length of a serie
 #'
 #' @export
 computeSynchrones = function(medoids, getRefSeries,
@@ -142,8 +154,8 @@ computeSynchrones = function(medoids, getRefSeries,
                {
                        if (parll)
                                synchronicity::lock(m)
-                       synchrones[ mi[i], ] = synchrones[ mi[i], ] + ref_series[i,]
-                       counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts?
+                       synchrones[, mi[i] ] = synchrones[, mi[i] ] + ref_series[,i]
+                       counts[ mi[i] ] = counts[ mi[i] ] + 1 #TODO: remove counts? ...or as arg?!
                        if (parll)
                                synchronicity::unlock(m)
                }
@@ -152,7 +164,7 @@ computeSynchrones = function(medoids, getRefSeries,
        K = nrow(medoids) ; L = ncol(medoids)
        # Use bigmemory (shared==TRUE by default) + synchronicity to fill synchrones in //
        # TODO: if size > RAM (not our case), use file-backed big.matrix
-       synchrones = bigmemory::big.matrix(nrow=K, ncol=L, type="double", init=0.)
+       synchrones = bigmemory::big.matrix(nrow=L, ncol=K, type="double", init=0.)
        counts = bigmemory::big.matrix(nrow=K, ncol=1, type="double", init=0)
        # synchronicity is only for Linux & MacOS; on Windows: run sequentially
        parll = (requireNamespace("synchronicity",quietly=TRUE)
@@ -181,14 +193,14 @@ computeSynchrones = function(medoids, getRefSeries,
 
        #TODO: can we avoid this loop? ( synchrones = sweep(synchrones, 1, counts, '/') )
        for (i in seq_len(K))
-               synchrones[i,] = synchrones[i,] / counts[i,1]
+               synchrones[,i] = synchrones[,i] / counts[i]
        #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
        #      ...maybe; but let's hope resulting K1' be still quite bigger than K2
-       noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,])))
+       noNA_rows = sapply(seq_len(K), function(i) all(!is.nan(synchrones[,i])))
        if (all(noNA_rows))
                return (synchrones)
        # Else: some clusters are empty, need to slice synchrones
-       synchrones[noNA_rows,]
+       bigmemory::as.big.matrix(synchrones[,noNA_rows])
 }
 
 #' computeWerDists
@@ -272,7 +284,7 @@ computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALS
        {
                #from cwt_file ...
                res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian)
-       ###############TODO:    
+       ###############TODO:
        }
 
        # Distance between rows i and j