before computeSynchrones

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

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 077becf..c8bad66 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,56 +1,60 @@
 # Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(K1, K2, WER, nb_series_per_chunk, indices_tasks, ncores_clust)
+clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_file,
+       getCoefs,K1,K2,nb_series_per_chunk,ncores,to_file)
 {
-       cl_clust = parallel::makeCluster(ncores_clust)
-       #parallel::clusterExport(cl=cl_clust, varlist=c("fonctions_du_package"), envir=environment())
-       indices_clust = indices_task[[i]]
+       cl = parallel::makeCluster(ncores)
        repeat
        {
-               nb_workers = max( 1, round( length(indices_clust) / nb_series_per_chunk ) )
-               indices_workers = list()
-               for (i in 1:nb_workers)
-               {
+               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_workers[[i]] = indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
-               }
-               indices_clust = parallel::parLapply(cl, indices_workers, clusterChunk, K1, K2*(WER=="mix"))
-               if ((WER=="end" && length(indices_clust)==K1) || (WER=="mix" && length(indices_clust)==K2))
+                               min(nb_series_per_chunk*i,length(indices)), length(indices) )
+                       indices[(nb_series_per_chunk*(i-1)+1):upper_bound]
+               })
+               indices = unlist( parallel::parLapply(cl, indices_workers, function(inds)
+                       computeClusters1(inds, getCoefs, K1)) )
+               if (length(indices_clust) == K1)
                        break
        }
-       parallel::stopCluster(cl_clust)
-       unlist(indices_clust)
+       parallel::stopCluster(cl)
+       if (K2 == 0)
+               return (indices)
+       computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file)
+       vector("integer",0)
 }
 
-# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-clusterChunk = function(indices, K1, K2)
+# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
+computeClusters1 = function(indices, getCoefs, K1)
 {
-       coeffs = getCoeffs(indices)
-       cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE)
-       if (K2 > 0)
-       {
-               curves = computeSynchrones(cl)
-               dists = computeWerDists(curves)
-               cl = computeClusters(dists, K2, diss=TRUE)
-       }
-       indices[cl]
+       coefs = getCoefs(indices)
+       indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
 }
 
-# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters = function(md, K, diss)
+# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
+computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file)
 {
-       if (!require(cluster, quietly=TRUE))
-               stop("Unable to load cluster library")
-       cluster::pam(md, K, diss=diss)$id.med
+       curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones)
+       dists = computeWerDists(curves)
+       medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
+       if (to_file)
+       {
+               serialize(medoids, synchrones_file)
+               return (NULL)
+       }
+       medoids
 }
 
 # Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices)
+computeSynchrones = function(indices, getSeries, getSeriesForSynchrones)
 {
-       colSums( getData(indices) )
+       #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
+# Compute the WER distance between the synchrones curves (in rows)
 computeWerDist = function(curves)
 {
        if (!require("Rwave", quietly=TRUE))
@@ -88,7 +92,7 @@ computeWerDist = function(curves)
        {
                for (j in (i+1):n)
                {
-                       #TODO: later, compute CWT here (because not enough storage space for 32M series)
+                       #TODO: later, compute CWT here (because not enough storage space for 200k series)
                        #      'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
                        num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
                        WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)