de_serialize works. Variables names improved. Code beautified. TODO: clustering tests

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

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 6090517..fce1b1c 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,57 +1,64 @@
-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices, ncores)
+# Cluster one full task (nb_curves / ntasks series); only step 1
+clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores)
 {
        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)) )
-               if (length(indices_clust) == K1)
+               indices = unlist( parallel::parLapply(cl, indices_workers, function(inds)
+                       computeClusters1(getCoefs(inds), K1)) )
+               if (length(indices) == 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)
+       indices #medoids
 }
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters1 = function(indices, getCoefs, K1)
-       indices[ cluster::pam(getCoefs(indices), K1, diss=FALSE)$id.med ]
+computeClusters1 = function(coefs, K1)
+       indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
 
 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-computeClusters2 = function(indices, K2, getSeries, to_file)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
 {
-       if (is.null(indices))
-       {
-               #get series from file
-       }
-#Puis K-means après WER...
-       if (WER=="mix" > 0)
-       {
-               curves = computeSynchrones(indices)
-               dists = computeWerDists(curves)
-               indices = computeClusters(dists, K2, diss=TRUE)
-       }
-       if (to_file)
-               #write results to file (JUST series ; no possible ID here)
+       synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
+       cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$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(medoids, getRefSeries, nb_series_per_chunk)
+{
+       #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 ?
+       K = nrow(medoids)
+       synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
+       counts = rep(0,K)
+       index = 1
+       repeat
+       {
+               range = (index-1) + seq_len(nb_series_per_chunk)
+               ref_series = getRefSeries(range)
+               if (is.null(ref_series))
+                       break
+               #get medoids indices for this chunk of series
+               for (i in seq_len(nrow(ref_series)))
+               {
+                       j = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) )
+                       synchrones[j,] = synchrones[j,] + series[i,]
+                       counts[j] = counts[j] + 1
+               }
+               index = index + nb_series_per_chunk
+       }
+       #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
+       sweep(synchrones, 1, counts, '/')
+}
 
-# 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 +81,7 @@ 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