before computeSynchrones

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

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 6090517..c8bad66 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,57 +1,60 @@
 # Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices, ncores)
+clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_file,
+       getCoefs,K1,K2,nb_series_per_chunk,ncores,to_file)
 {
        cl = parallel::makeCluster(ncores)
-       parallel::clusterExport(cl,
-               varlist=c("K1","getCoefs"),
-               envir=environment())
        repeat
        {
-               nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
+               nb_workers = max( 1, round( length(indices) / nb_series_per_chunk ) )
                indices_workers = lapply(seq_len(nb_workers), function(i) {
                        upper_bound = ifelse( i<nb_workers,
-                               min(nb_series_per_chunk*i,length(indices_clust)), length(indices_clust) )
-                       indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
+                               min(nb_series_per_chunk*i,length(indices)), length(indices) )
+                       indices[(nb_series_per_chunk*(i-1)+1):upper_bound]
                })
-               indices_clust = unlist( parallel::parLapply(cl, indices_workers, function(indices)
-                       computeClusters1(indices, getCoefs, K1)) )
+               indices = unlist( parallel::parLapply(cl, indices_workers, function(inds)
+                       computeClusters1(inds, getCoefs, K1)) )
                if (length(indices_clust) == K1)
                        break
        }
-       parallel::stopCluster(cl_clust)
-       if (WER == "end")
-               return (indices_clust)
-       #WER=="mix"
-       computeClusters2(indices_clust, K2, getSeries, to_file=TRUE)
+       parallel::stopCluster(cl)
+       if (K2 == 0)
+               return (indices)
+       computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file)
+       vector("integer",0)
 }
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
 computeClusters1 = function(indices, getCoefs, K1)
-       indices[ cluster::pam(getCoefs(indices), K1, diss=FALSE)$id.med ]
+{
+       coefs = getCoefs(indices)
+       indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
+}
 
 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-computeClusters2 = function(indices, K2, getSeries, to_file)
+computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file)
 {
-       if (is.null(indices))
-       {
-               #get series from file
-       }
-#Puis K-means après WER...
-       if (WER=="mix" > 0)
+       curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones)
+       dists = computeWerDists(curves)
+       medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
+       if (to_file)
        {
-               curves = computeSynchrones(indices)
-               dists = computeWerDists(curves)
-               indices = computeClusters(dists, K2, diss=TRUE)
+               serialize(medoids, synchrones_file)
+               return (NULL)
        }
-       if (to_file)
-               #write results to file (JUST series ; no possible ID here)
+       medoids
 }
 
 # Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(inds)
-       sapply(seq_along(inds), colMeans(getSeries(inds[[i]]$indices,inds[[i]]$ids)))
+computeSynchrones = function(indices, getSeries, getSeriesForSynchrones)
+{
+       #les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les
+       #courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ?
+       series = getSeries(indices)
+       #...........
+       #sapply(seq_along(inds), colMeans(getSeries(inds[[i]]$indices,inds[[i]]$ids)))
+}
 
-# Compute the WER distance between the synchrones curves (in columns)
+# Compute the WER distance between the synchrones curves (in rows)
 computeWerDist = function(curves)
 {
        if (!require("Rwave", quietly=TRUE))
@@ -74,7 +77,7 @@ computeWerDist = function(curves)
 
        # (normalized) observations node with CWT
        Xcwt4 <- lapply(seq_len(n), function(i) {
-               ts <- scale(ts(curves[,i]), center=TRUE, scale=scaled)
+               ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
                totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
                ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
                #Normalization