X-Git-Url: https://git.auder.net/?p=epclust.git;a=blobdiff_plain;f=epclust%2FR%2Fclustering.R;h=fce1b1c695f4b6094580375e28a6cd5cd0f1e805;hp=87a5f914e137cb3f509443b58a1e59b80505b011;hb=56857861dc15088cf58e7438968fe5714b22168e;hpb=62deb4244895a20a35397dfb062f0b9fe94c5012

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index 87a5f91..fce1b1c 100644
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -1,6 +1,5 @@
-# Cluster one full task (nb_curves / ntasks series)
-clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_file,
-	getCoefs,K1,K2,nb_series_per_chunk,ncores,to_file,ftype)
+# 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)
 	repeat
@@ -12,62 +11,51 @@ clusteringTask = function(indices,getSeries,getSeriesForSynchrones,synchrones_fi
 			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)
+			computeClusters1(getCoefs(inds), K1)) )
+		if (length(indices) == K1)
 			break
 	}
 	parallel::stopCluster(cl)
-	if (K2 == 0)
-		return (indices)
-	computeClusters2(indices, K2, getSeries, getSeriesForSynchrones, to_file,
-									 nb_series_per_chunk,ftype)
-	vector("integer",0)
+	indices #medoids
 }
 
 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
-computeClusters1 = function(indices, getCoefs, K1)
-{
-	coefs = getCoefs(indices)
+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, getSeriesForSynchrones, to_file,
-														nb_series_per_chunk, ftype)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
 {
-	curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk)
-	dists = computeWerDists(curves)
-	medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
-	if (to_file)
-	{
-		serialize(medoids, synchrones_file, ftype, nb_series_per_chunk)
-		return (NULL)
-	}
-	medoids
+	synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
+	cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids
 }
 
 # Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices, getSeries, getSeriesForSynchrones, nb_series_per_chunk)
+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 ?
-	medoids = getSeries(indices)
 	K = nrow(medoids)
 	synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
 	counts = rep(0,K)
 	index = 1
 	repeat
 	{
-		series = getSeriesForSynchrones((index-1)+seq_len(nb_series_per_chunk))
-		if (is.null(series))
+		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
-		index = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) )
-		synchrones[index,] = synchrones[index,] + series[i,]
-		counts[index] = counts[index] + 1
+		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)
-	synchrones = sweep(synchrones, 1, counts, '/')
+	sweep(synchrones, 1, counts, '/')
 }
 
 # Compute the WER distance between the synchrones curves (in rows)