epclust/R/clustering.R

   1 # Cluster one full task (nb_curves / ntasks series); only step 1
   2 clusteringTask = function(indices, getCoefs, K1, nb_series_per_chunk, ncores)
   3 {
   4     cl = parallel::makeCluster(ncores)
   5     repeat
   6     {
   7         nb_workers = max( 1, round( length(indices) / nb_series_per_chunk ) )
   8         indices_workers = lapply(seq_len(nb_workers), function(i) {
   9             upper_bound = ifelse( i<nb_workers,
  10                 min(nb_series_per_chunk*i,length(indices)), length(indices) )
  11             indices[(nb_series_per_chunk*(i-1)+1):upper_bound]
  12         })
  13         indices = unlist( parallel::parLapply(cl, indices_workers, function(inds)
  14             computeClusters1(getCoefs(inds), K1)) )
  15         if (length(indices) == K1)
  16             break
  17     }
  18     parallel::stopCluster(cl)
  19     indices #medoids
  20 }
  21
  22 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
  23 computeClusters1 = function(coefs, K1)
  24     indices[ cluster::pam(coefs, K1, diss=FALSE)$id.med ]
  25
  26 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
  27 computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
  28 {
  29     synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
  30     cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids
  31 }
  32
  33 # Compute the synchrones curves (sum of clusters elements) from a clustering result
  34 computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
  35 {
  36     #les getSeries(indices) sont les medoides --> init vect nul pour chacun, puis incr avec les
  37     #courbes (getSeriesForSynchrones) les plus proches... --> au sens de la norme L2 ?
  38     K = nrow(medoids)
  39     synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
  40     counts = rep(0,K)
  41     index = 1
  42     repeat
  43     {
  44         range = (index-1) + seq_len(nb_series_per_chunk)
  45         ref_series = getRefSeries(range)
  46         if (is.null(ref_series))
  47             break
  48         #get medoids indices for this chunk of series
  49         for (i in seq_len(nrow(ref_series)))
  50         {
  51             j = which.min( rowSums( sweep(medoids, 2, series[i,], '-')^2 ) )
  52             synchrones[j,] = synchrones[j,] + series[i,]
  53             counts[j] = counts[j] + 1
  54         }
  55         index = index + nb_series_per_chunk
  56     }
  57     #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
  58     sweep(synchrones, 1, counts, '/')
  59 }
  60
  61 # Compute the WER distance between the synchrones curves (in rows)
  62 computeWerDist = function(curves)
  63 {
  64     if (!require("Rwave", quietly=TRUE))
  65         stop("Unable to load Rwave library")
  66     n <- nrow(curves)
  67     delta <- ncol(curves)
  68     #TODO: automatic tune of all these parameters ? (for other users)
  69     nvoice   <- 4
  70     # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(curves))
  71     noctave = 13
  72     # 4 here represent 2^5 = 32 half-hours ~ 1 day
  73     #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
  74     scalevector  <- 2^(4:(noctave * nvoice) / nvoice) * 2
  75     #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
  76     s0=2
  77     w0=2*pi
  78     scaled=FALSE
  79     s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
  80     totnoct = noctave + as.integer(s0log/nvoice) + 1
  81
  82     # (normalized) observations node with CWT
  83     Xcwt4 <- lapply(seq_len(n), function(i) {
  84         ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
  85         totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
  86         ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
  87         #Normalization
  88         sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
  89         sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
  90         sqres / max(Mod(sqres))
  91     })
  92
  93     Xwer_dist <- matrix(0., n, n)
  94     fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
  95     for (i in 1:(n-1))
  96     {
  97         for (j in (i+1):n)
  98         {
  99             #TODO: later, compute CWT here (because not enough storage space for 200k series)
 100             #      'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
 101             num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
 102             WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
 103             WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
 104             wer2    <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
 105             Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
 106             Xwer_dist[j,i] <- Xwer_dist[i,j]
 107         }
 108     }
 109     diag(Xwer_dist) <- numeric(n)
 110     Xwer_dist
 111 }