draft final form of current package

diff --git a/TODO b/TODO
index 52b139d..53b4c97 100644 (file)
--- a/TODO
+++ b/TODO
@@ -65,3 +65,5 @@ réduire taille 17519 trop long ?
 synchrone : sum
 cwt : trim R part
 // : clever by rows retenir cwt...
+
+Stockage matrices : en colonnes systématiquement ?

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 4519f44..a4c273a 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -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), ]
 }
 
@@ -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

diff --git a/epclust/R/main.R b/epclust/R/main.R
index 9ba23ae..28217c3 100644 (file)
--- a/epclust/R/main.R
+++ b/epclust/R/main.R
@@ -172,8 +172,8 @@ claws = function(getSeries, K1, K2,
                {
                        require("bigmemory", quietly=TRUE)
                        medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
-                       medoids2 = clusteringTask2(medoids1,
-                               K2, getSeries, nb_curves, nb_series_per_chunk, ncores_clust, verbose, parll)
+                       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)
                        return (vector("integer",0))
                }
@@ -235,8 +235,8 @@ claws = function(getSeries, K1, K2,
        indices_medoids = clusteringTask1(
                indices, getContribs, K1, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
        medoids1 = bigmemory::as.big.matrix( getSeries(indices_medoids) )
-       medoids2 = clusteringTask2(medoids1, K2,
-               getRefSeries, nb_curves, nb_series_per_chunk, ncores_tasks*ncores_clust, verbose, parll)
+       medoids2 = clusteringTask2(medoids1, K2, getRefSeries, nb_curves, nb_series_per_chunk,
+               nbytes, endian, ncores_tasks*ncores_clust, verbose, parll)
 
        # Cleanup
        unlink(bin_dir, recursive=TRUE)