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     parallel::clusterExport(cl, varlist=c("getCoefs","K1"), envir=environment())
   6     repeat
   7     {
   8         nb_workers = max( 1, floor( length(indices) / nb_series_per_chunk ) )
   9         indices_workers = lapply( seq_len(nb_workers), function(i)
  10             indices[(nb_series_per_chunk*(i-1)+1):(nb_series_per_chunk*i)] )
  11         # Spread the remaining load among the workers
  12         rem = length(indices) %% nb_series_per_chunk
  13         while (rem > 0)
  14         {
  15             index = rem%%nb_workers + 1
  16             indices_workers[[index]] = c(indices_workers[[index]], tail(indices,rem))
  17             rem = rem - 1
  18         }
  19         indices = unlist( parallel::parLapply( cl, indices_workers, function(inds) {
  20             require("epclust", quietly=TRUE)
  21             inds[ computeClusters1(getCoefs(inds), K1) ]
  22         } ) )
  23         if (length(indices) == K1)
  24             break
  25     }
  26     parallel::stopCluster(cl)
  27     indices #medoids
  28 }
  29
  30 # Apply the clustering algorithm (PAM) on a coeffs or distances matrix
  31 computeClusters1 = function(coefs, K1)
  32     cluster::pam(coefs, K1, diss=FALSE)$id.med
  33
  34 # Cluster a chunk of series inside one task (~max nb_series_per_chunk)
  35 computeClusters2 = function(medoids, K2, getRefSeries, nb_series_per_chunk)
  36 {
  37     synchrones = computeSynchrones(medoids, getRefSeries, nb_series_per_chunk)
  38     medoids[ cluster::pam(computeWerDists(synchrones), K2, diss=TRUE)$medoids , ]
  39 }
  40
  41 # Compute the synchrones curves (sum of clusters elements) from a clustering result
  42 computeSynchrones = function(medoids, getRefSeries, nb_series_per_chunk)
  43 {
  44     K = nrow(medoids)
  45     synchrones = matrix(0, nrow=K, ncol=ncol(medoids))
  46     counts = rep(0,K)
  47     index = 1
  48     repeat
  49     {
  50         range = (index-1) + seq_len(nb_series_per_chunk)
  51         ref_series = getRefSeries(range)
  52         if (is.null(ref_series))
  53             break
  54         #get medoids indices for this chunk of series
  55         for (i in seq_len(nrow(ref_series)))
  56         {
  57             j = which.min( rowSums( sweep(medoids, 2, ref_series[i,], '-')^2 ) )
  58             synchrones[j,] = synchrones[j,] + ref_series[i,]
  59             counts[j] = counts[j] + 1
  60         }
  61         index = index + nb_series_per_chunk
  62     }
  63     #NOTE: odds for some clusters to be empty? (when series already come from stage 2)
  64     #      ...maybe; but let's hope resulting K1' be still quite bigger than K2
  65     synchrones = sweep(synchrones, 1, counts, '/')
  66     synchrones[ sapply(seq_len(K), function(i) all(!is.nan(synchrones[i,]))) , ]
  67 }
  68
  69 # Compute the WER distance between the synchrones curves (in rows)
  70 computeWerDists = function(curves)
  71 {
  72     if (!require("Rwave", quietly=TRUE))
  73         stop("Unable to load Rwave library")
  74     n <- nrow(curves)
  75     delta <- ncol(curves)
  76     #TODO: automatic tune of all these parameters ? (for other users)
  77     nvoice   <- 4
  78     # noctave = 2^13 = 8192 half hours ~ 180 days ; ~log2(ncol(curves))
  79     noctave = 13
  80     # 4 here represent 2^5 = 32 half-hours ~ 1 day
  81     #NOTE: default scalevector == 2^(0:(noctave * nvoice) / nvoice) * s0 (?)
  82     scalevector  <- 2^(4:(noctave * nvoice) / nvoice) * 2
  83     #condition: ( log2(s0*w0/(2*pi)) - 1 ) * nvoice + 1.5 >= 1
  84     s0=2
  85     w0=2*pi
  86     scaled=FALSE
  87     s0log = as.integer( (log2( s0*w0/(2*pi) ) - 1) * nvoice + 1.5 )
  88     totnoct = noctave + as.integer(s0log/nvoice) + 1
  89
  90     # (normalized) observations node with CWT
  91     Xcwt4 <- lapply(seq_len(n), function(i) {
  92         ts <- scale(ts(curves[i,]), center=TRUE, scale=scaled)
  93         totts.cwt = Rwave::cwt(ts,totnoct,nvoice,w0,plot=0)
  94         ts.cwt = totts.cwt[,s0log:(s0log+noctave*nvoice)]
  95         #Normalization
  96         sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0)
  97         sqres <- sweep(ts.cwt,MARGIN=2,sqs,'*')
  98         sqres / max(Mod(sqres))
  99     })
 100
 101     Xwer_dist <- matrix(0., n, n)
 102     fcoefs = rep(1/3, 3) #moving average on 3 values (TODO: very slow! correct?!)
 103     for (i in 1:(n-1))
 104     {
 105         for (j in (i+1):n)
 106         {
 107             #TODO: later, compute CWT here (because not enough storage space for 200k series)
 108             #      'circular=TRUE' is wrong, should just take values on the sides; to rewrite in C
 109             num <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
 110             WX <- filter(Mod(Xcwt4[[i]] * Conj(Xcwt4[[i]])), fcoefs, circular=TRUE)
 111             WY <- filter(Mod(Xcwt4[[j]] * Conj(Xcwt4[[j]])), fcoefs, circular=TRUE)
 112             wer2    <- sum(colSums(num)^2) / sum( sum(colSums(WX) * colSums(WY)) )
 113             Xwer_dist[i,j] <- sqrt(delta * ncol(Xcwt4[[1]]) * (1 - wer2))
 114             Xwer_dist[j,i] <- Xwer_dist[i,j]
 115         }
 116     }
 117     diag(Xwer_dist) <- numeric(n)
 118     Xwer_dist
 119 }