####################################################################
##
## File:        aux.r
##
## Description: Miscelaneous functions for clustering with kcca
##
## Modified:    june 2010
##
####################################################################


  #######################################################

  # Transforms a matrix of data (one observation by row)
  #     into an array where position[ , , i] gives
  #     the smoothed modulus of the i-th cwt observation 

  ########################################################


##NOTE: renvoie une matrice 3D
  toCWT  <- function(X, sw=  0,  tw=  0, swabs= 0,
                       nvoice= 12, noctave= 5, 
                       s0= 2, w0= 2*pi, lt= 24, dt= 0.5,
                       spectra = FALSE, smooth = TRUE,
                       scaled  = FALSE,
                     scalevector)
     { noctave  <- adjust.noctave(lt, dt, s0, tw, noctave)
       if(missing(scalevector)) 
          scalevector  <- 2^(0:(noctave * nvoice) / nvoice) * s0
       res <- lapply(1:nrow(X), function(n)
           { tsX         <- ts( X[n,] )
             tsCent      <- tsX - mean(tsX)
             if(scaled)  tsCent <- ts(scale(tsCent))           
             tsCent.cwt  <- cwt.ts(tsCent, s0, noctave, nvoice, w0)
             tsCent.cwt
           } )
	   if( spectra ) res <- lapply(res, function(l) Mod(l)^2 )
	   if( smooth  ) res <- lapply(res, smCWT, swabs = swabs,
	                               tw = tw, dt = dt, 
	                               scalevector = scalevector)
       resArray <- array(NA, c(nrow(res[[1]]), ncol(res[[1]]),
                               length(res)))
       for( l in 1:length(res) ) resArray[ , , l] <- res[[l]]
       resArray
     }


  # ===============================================================

  smCWT <- function(CWT, sw=  0,  tw=  0, swabs= 0,
                       nvoice= 12, noctave= 2, s0= 2, w0= 2*pi, 
					   lt= 24, dt= 0.5, scalevector )
		 {
#         noctave  <- adjust.noctave(lt, dt, s0, tw, noctave)
#         scalevector  <- 2^(0:(noctave * nvoice) / nvoice) * s0
         wsp     <- Mod(CWT)  
         smwsp   <- smooth.matrix(wsp, swabs)
         smsmwsp <- smooth.time(smwsp, tw, dt, scalevector)
         smsmwsp
       }


  # ===============================================================

  toDWT <- function(x, filter.number = 6, family = "DaubLeAsymm")
{ x2   <- spline(x, n = 2^ceiling( log(length(x), 2) ),
            method = 'natural')$y
  Dx2 <- wd(x2, family = family, filter.number = filter.number)$D
		Dx2
}

  # ===============================================================

  contrib <- function(x) 
      { J   <- log( length(x)+1, 2)
        nrj <- numeric(J)
        t0  <- 1
        t1  <- 0
        for( j in 1:J ) {
          t1     <- t1 + 2^(J-j)
          nrj[j] <- sqrt( sum( x[t0:t1]^2 ) )
          t0     <- t1 + 1
        }
        return(nrj)  
	  }


    # ========================================= distance for coh ===

  coherence <- function( x, y)
       { J <- log(length(x) + 1, 2)
	     t0 <- 1
		 sg2_x <- 0
		 sg2_y <- 0
		 sg_xy <- 0
	     for(j in 0:(J - 1))
		 {  t1 <- t0 + 2^(J - j)/2  - 1
		    tt <- t0:t1
		    sg2_x <- sg2_x + mean(x[t0:t1]^2)
			sg2_y <- sg2_y + mean(y[t0:t1]^2)
			sg_xy <- sg_xy + mean(x[t0:t1] * y[t0:t1])
            t0 <- t1 + 1
		 }
		res <- sg_xy^2 / sg2_x / sg2_y
		res
	   }


  vect2mat <- function(vect){
                 vect <- as.vector(vect)
                 matrix(vect[-(1:2)], delta, lscvect)
               }


  # =========================================  # myimg for graphics 
  jet.colors <- colorRampPalette(c("#00007F", "blue", "#007FFF", 
                                "cyan", "#7FFF7F", "yellow", 
                                "#FF7F00", "red", "#7F0000"))

  myimg <- function(MAT, x = 1:nrow(MAT), y = 1:col(MAT), ... )
              filled.contour(  x = x, y = y, z = MAT, 
			       xlab= 'Time', ylab= 'scale',
			       color.palette = jet.colors,
			       ... )