with parallel::export

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

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 578b2f3..6090517 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,9 +1,9 @@
 # Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices_clust)
+clusteringTask = function(indices, ncores)
 {
-       cl_clust = parallel::makeCluster(ncores_clust)
-       parallel::clusterExport(cl_clust,
-               varlist=c("K1","K2","WER"),
+       cl = parallel::makeCluster(ncores)
+       parallel::clusterExport(cl,
+               varlist=c("K1","getCoefs"),
                envir=environment())
        repeat
        {
@@ -13,44 +13,45 @@ clusteringTask = function(indices_clust)
                                min(nb_series_per_chunk*i,length(indices_clust)), length(indices_clust) )
                        indices_clust[(nb_series_per_chunk*(i-1)+1):upper_bound]
                })
-               indices_clust = parallel::parLapply(cl, indices_workers, clusterChunk)
-               # TODO: soft condition between K2 and K1, before applying final WER step
-               if ((WER=="end" && length(indices_clust)==K1) || (WER=="mix" && length(indices_clust)==K2))
+               indices_clust = unlist( parallel::parLapply(cl, indices_workers, function(indices)
+                       computeClusters1(indices, getCoefs, K1)) )
+               if (length(indices_clust) == K1)
                        break
        }
        parallel::stopCluster(cl_clust)
-       unlist(indices_clust)
+       if (WER == "end")
+               return (indices_clust)
+       #WER=="mix"
+       computeClusters2(indices_clust, K2, getSeries, to_file=TRUE)
 }
 
+# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
+computeClusters1 = function(indices, getCoefs, K1)
+       indices[ cluster::pam(getCoefs(indices), K1, diss=FALSE)$id.med ]
+
 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-clusterChunk = function(indices_chunk)
+computeClusters2 = function(indices, K2, getSeries, to_file)
 {
-       coeffs = readCoeffs(indices_chunk)
-       cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE)
+       if (is.null(indices))
+       {
+               #get series from file
+       }
+#Puis K-means après WER...
        if (WER=="mix" > 0)
        {
-               curves = computeSynchrones(cl)
+               curves = computeSynchrones(indices)
                dists = computeWerDists(curves)
-               cl = computeClusters(dists, K2, diss=TRUE)
+               indices = computeClusters(dists, K2, diss=TRUE)
        }
-       indices_chunk[cl]
-}
-
-# Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters = function(md, K, diss)
-{
-       if (!require(cluster, quietly=TRUE))
-               stop("Unable to load cluster library")
-       cluster::pam(md, K, diss=diss)$id.med
+       if (to_file)
+               #write results to file (JUST series ; no possible ID here)
 }
 
 # Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices)
-{
-       colSums( getData(indices) )
-}
+computeSynchrones = function(inds)
+       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 columns)
 computeWerDist = function(curves)
 {
        if (!require("Rwave", quietly=TRUE))
@@ -73,7 +74,7 @@ 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
@@ -88,7 +89,7 @@ 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)