-# 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)
+# 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
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)
- 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)$id.med ]
-}
# Cluster a chunk of series inside one task (~max nb_series_per_chunk)
-computeClusters2 = function(indices, K2, getSeries, getSeriesForSynchrones, to_file)
+computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
{
- curves = computeSynchrones(indices, getSeries, getSeriesForSynchrones)
- dists = computeWerDists(curves)
- medoids = cluster::pam(dists, K2, diss=TRUE)$medoids
- if (to_file)
- {
- serialize(medoids, synchrones_file)
- return (NULL)
- }
- medoids
+ synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
+ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids
}
# Compute the synchrones curves (sum of clusters elements) from a clustering result
-computeSynchrones = function(indices, getSeries, getSeriesForSynchrones)
+computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
{
#les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les
#courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ?
- series = getSeries(indices)
- #...........
- #sapply(seq_along(inds), colMeans(getSeries(inds[[i]]$indices,inds[[i]]$ids)))
+ 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 rows)