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 578b2f3..fce1b1c 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,56 +1,64 @@
-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices_clust)
+# Cluster one full task (nb_curves / ntasks series); only step 1
+clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores)
 {
-       cl_clust = parallel::makeCluster(ncores_clust)
-       parallel::clusterExport(cl_clust,
-               varlist=c("K1","K2","WER"),
-               envir=environment())
+       cl = parallel::makeCluster(ncores)
        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 = 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 = unlist( parallel::parLapply(cl, indices_workers, function(inds)
+                       computeClusters1(getCoefs(inds), K1)) )
+               if (length(indices) == K1)
                        break
        }
-       parallel::stopCluster(cl_clust)
-       unlist(indices_clust)
-}
-
-# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-clusterChunk = function(indices_chunk)
-{
-       coeffs = readCoeffs(indices_chunk)
-       cl = computeClusters(as.matrix(coeffs[,2:ncol(coeffs)]), K1, diss=FALSE)
-       if (WER=="mix" > 0)
-       {
-               curves = computeSynchrones(cl)
-               dists = computeWerDists(curves)
-               cl = computeClusters(dists, K2, diss=TRUE)
-       }
-       indices_chunk[cl]
+       parallel::stopCluster(cl)
+       indices #medoids
 }
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters = function(md, K, diss)
+computeClusters1 = function(coefs, K1)
+       indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
+
+# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
 {
-       if (!require(cluster, quietly=TRUE))
-               stop("Unable to load cluster library")
-       cluster::pam(md, K, diss=diss)$id.med
+       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(indices)
+computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
 {
-       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 ?
+       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
+# Compute the WER distance between the synchrones curves (in rows)
 computeWerDist = function(curves)
 {
        if (!require("Rwave", quietly=TRUE))
@@ -88,7 +96,7 @@ 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)