add submodule enercast

diff --git a/.enercast b/.enercast
new file mode 160000 (submodule)
index 0000000..35da9ea
--- /dev/null
+++ b/.enercast
@@ -0,0 +1 @@
+Subproject commit 35da9ea4a4caaac6124c0807fb8fcbd8d5e1c7ca

diff --git a/.gitmodules b/.gitmodules
index 16826ed..2b8ef9a 100644 (file)
--- a/.gitmodules
+++ b/.gitmodules
@@ -4,3 +4,6 @@
 [submodule ".nbstripout"]
        path = .nbstripout
        url = https://github.com/kynan/nbstripout.git
+[submodule ".enercast"]
+       path = .enercast
+       url = https://github.com/cugliari/enercast.git

diff --git a/epclust/R/clustering.R b/epclust/R/clustering.R
index c226786..4519f44 100644 (file)
--- a/epclust/R/clustering.R
+++ b/epclust/R/clustering.R
@@ -208,15 +208,6 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
        if (verbose)
                cat(paste("--- Compute WER dists\n", sep=""))
 
-
-
-
-#TODO: serializer les CWT, les récupérer via getDataInFile 
-#--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
-
-
-
-
        n <- nrow(synchrones)
        delta <- ncol(synchrones)
        #TODO: automatic tune of all these parameters ? (for other users)
@@ -235,24 +226,52 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
 
        Xwer_dist <- bigmemory::big.matrix(nrow=n, ncol=n, type="double")
 
+       cwt_file = ".epclust_bin/cwt"
+       #TODO: args, nb_per_chunk, nbytes, endian
+
        # Generate n(n-1)/2 pairs for WER distances computations
-#      pairs = list()
-#      V = seq_len(n)
-#      for (i in 1:n)
-#      {
-#              V = V[-1]
-#              pairs = c(pairs, lapply(V, function(v) c(i,v)))
-#      }
-       # Generate "smart" pairs for WER distances computations
        pairs = list()
-       F = floor(2*n/3)
-       for (i in 1:F)
-               pairs = c(pairs, lapply((i+1):n, function(v) c(i,v)))
-       V = (F+1):n
-       for (i in (F+1):(n-1))
+       V = seq_len(n)
+       for (i in 1:n)
        {
                V = V[-1]
-               pairs = c(pairs, 
+               pairs = c(pairs, lapply(V, function(v) c(i,v)))
+       }
+       
+       computeSaveCWT = function(index)
+       {
+               ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled)
+               totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
+               ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
+               #Normalization
+               sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
+               sqres <- sweep(ts.cwt,2,sqs,'*')
+               res <- sqres / max(Mod(sqres))
+               #TODO: serializer les CWT, les récupérer via getDataInFile ;
+               #--> OK, faut juste stocker comme séries simples de taille delta*ncol (53*17519)
+               binarize(res, cwt_file, 100, ",", nbytes, endian)
+       }
+
+       if (parll)
+       {
+               cl = parallel::makeCluster(ncores_clust)
+               synchrones_desc <- bigmemory::describe(synchrones)
+               Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
+               parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
+                       "nvoice","w0","s0log","noctave","s0","verbose","getCWT"), envir=environment())
+       }
+
+       #precompute and serialize all CWT
+       ignored <-
+               if (parll)
+                       parallel::parLapply(cl, 1:n, computeSaveCWT)
+               else
+                       lapply(1:n, computeSaveCWT)
+
+       getCWT = function(index)
+       {
+               #from cwt_file ...
+       }
 
        # Distance between rows i and j
        computeDistancesIJ = function(pair)
@@ -265,44 +284,21 @@ computeWerDists = function(synchrones, ncores_clust=1,verbose=FALSE,parll=TRUE)
                        Xwer_dist <- bigmemory::attach.big.matrix(Xwer_dist_desc)
                }
 
-               computeCWT = function(index)
-               {
-                       ts <- scale(ts(synchrones[index,]), center=TRUE, scale=scaled)
-                       totts.cwt = Rwave::cwt(ts, totnoct, nvoice, w0, plot=FALSE)
-                       ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
-                       #Normalization
-                       sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
-                       sqres <- sweep(ts.cwt,2,sqs,'*')
-                       sqres / max(Mod(sqres))
-               }
-
                i = pair[1] ; j = pair[2]
                if (verbose && j==i+1)
                        cat(paste("   Distances (",i,",",j,"), (",i,",",j+1,") ...\n", sep=""))
-               cwt_i <- computeCWT(i)
-               cwt_j <- computeCWT(j)
+               cwt_i <- getCWT(i)
+               cwt_j <- getCWT(j)
 
-#print(system.time( {
                num <- epclustFilter(Mod(cwt_i * Conj(cwt_j)))
                WX  <- epclustFilter(Mod(cwt_i * Conj(cwt_i)))
-               WY  <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
+               WY <- epclustFilter(Mod(cwt_j * Conj(cwt_j)))
                wer2 <- sum(colSums(num)^2) / sum(colSums(WX) * colSums(WY))
                Xwer_dist[i,j] <- sqrt(delta * ncol(cwt_i) * max(1 - wer2, 0.)) #FIXME: wer2 should be < 1
                Xwer_dist[j,i] <- Xwer_dist[i,j]
-#} ) )
                Xwer_dist[i,i] = 0.
        }
 
-       if (parll)
-       {
-               cl = parallel::makeCluster(ncores_clust)
-               synchrones_desc <- bigmemory::describe(synchrones)
-               Xwer_dist_desc <- bigmemory::describe(Xwer_dist)
-
-               parallel::clusterExport(cl, varlist=c("synchrones_desc","Xwer_dist_desc","totnoct",
-                       "nvoice","w0","s0log","noctave","s0","verbose"), envir=environment())
-       }
-
        ignored <-
                if (parll)
                        parallel::parLapply(cl, pairs, computeDistancesIJ)