TODO: args, et finir tests; relancer

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

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 4519f44..14915ab 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()})
 #'
@@ -31,7 +31,7 @@ NULL
 #' @rdname clustering
 #' @export
 clusteringTask1 = function(
-       indices, getContribs, K1, nb_series_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
+       indices, getContribs, K1, nb_items_per_chunk, ncores_clust=1, verbose=FALSE, parll=TRUE)
 {
        if (verbose)
                cat(paste("*** Clustering task 1 on ",length(indices)," lines\n", sep=""))
@@ -67,8 +67,8 @@ clusteringTask1 = function(
 
 #' @rdname clustering
 #' @export
-clusteringTask2 = function(medoids, K2,
-       getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust=1,verbose=FALSE,parll=TRUE)
+clusteringTask2 = function(medoids, K2, getRefSeries, nb_ref_curves,
+       nb_series_per_chunk, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
        if (verbose)
                cat(paste("*** Clustering task 2 on ",nrow(medoids)," lines\n", sep=""))
@@ -77,7 +77,7 @@ clusteringTask2 = function(medoids, K2,
                return (medoids)
        synchrones = computeSynchrones(medoids,
                getRefSeries, nb_ref_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
-       distances = computeWerDists(synchrones, ncores_clust, verbose, parll)
+       distances = computeWerDists(synchrones, nbytes, endian, ncores_clust, verbose, parll)
        medoids[ computeClusters2(distances,K2,verbose), ]
 }
 
@@ -87,7 +87,7 @@ 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 +96,7 @@ 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 +110,7 @@ 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 +142,8 @@ 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 +152,7 @@ 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 +181,14 @@ 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
@@ -203,7 +203,7 @@ computeSynchrones = function(medoids, getRefSeries,
 #' @return A matrix of size K1 x K1
 #'
 #' @export
-computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
+computeWerDists = function(synchrones, nbytes,endian,ncores_clust=1,verbose=FALSE,parll=TRUE)
 {
        if (verbose)
                cat(paste("--- Compute WER dists\n", sep=""))
@@ -218,8 +218,8 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
        #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
        scalevector  <- 2^(4:(noctave * nvoice) / nvoice + 1)
        #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
-       s0=2
-       w0=2*pi
+       s0 = 2
+       w0 = 2*pi
        scaled=FALSE
        s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
        totnoct = noctave + as.integer(s0log/nvoice) + 1
@@ -237,7 +237,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
                V = V[-1]
                pairs = c(pairs, lapply(V, function(v) c(i,v)))
        }
-       
+
        computeSaveCWT = function(index)
        {
                ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled)
@@ -249,7 +249,7 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
                res <- sqres / max(Mod(sqres))
                #TODO: serializer les CWT, les récupérer via getDataInFile ;
                #--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
-               binarize(res, cwt_file, 100, ",", nbytes, endian)
+               binarize(c(as.double(Re(res)),as.double(Im(res))), cwt_file, ncol(res), ",", nbytes, endian)
        }
 
        if (parll)
@@ -271,6 +271,8 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
        getCWT = function(index)
        {
                #from cwt_file ...
+               res <- getDataInFile(c(2*index-1,2*index), cwt_file, nbytes, endian)
+       ###############TODO:
        }
 
        # Distance between rows i and j