From: Benjamin Auder Date: Tue, 31 Jan 2017 10:55:51 +0000 (+0100) Subject: prepared step2.R for first tests (old code, reindented, all in one file) X-Git-Url: https://git.auder.net/images/assets/doc/html/current/git-logo.png?a=commitdiff_plain;h=d03c0621a8f298b19659ebc20a86099ba56d8ff7;p=epclust.git prepared step2.R for first tests (old code, reindented, all in one file) --- diff --git a/epclust/R/stage2.R b/epclust/R/stage2.R index da84035..ebb44d9 100644 --- a/epclust/R/stage2.R +++ b/epclust/R/stage2.R @@ -1,297 +1,170 @@ +#point avec Jairo: +#rentrer dans code C cwt continue Rwave +#passer partie sowas à C +#fct qui pour deux series (ID, medoides) renvoie distance WER (Rwave ou à moi) +#transformee croisee , smoothing lissage 3 composantes , + calcul pour WER +#attention : code fait pour des series temps desynchronisees ! (deltat, dt == 1,2 ...) +#determiner nvoice noctave (entre octave + petit et + grand) + library("Rwave") #Entrée : courbes synchrones, soit après étape 1 itérée, soit après chaqure étape 1 #TODO: bout de code qui calcule les courbes synchrones après étapes 1+2 à partir des ID médoïdes -#(Benjamin) -#à partir de là, "conso" == courbes synchrones -n <- nrow(conso) -delta <- ncol(conso) - -#17000 colonnes coeff 1, puis 17000 coeff 2... [non : dans chaque tranche du cube] -# #NOTE: delta et lscvect pourraient etre gardés à part (communs) - -#lignes 59 à 91 "dépliées" : -Xcwt4 <- toCWT(conso, noctave = noctave4, dt = 1, - scalevector = scalevector4, - lt = delta, smooth = FALSE, - nvoice = nvoice) # observations node with CWT - #toCWT: (aux) ##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 - } - -#from sowas -cwt.ts <- function(ts,s0,noctave=5,nvoice=10,w0=2*pi){ - - if (class(ts)!="ts"){ - - cat("# This function needs a time series object as input. You may construct this by using the function ts(data,start,deltat). Try '?ts' for help.\n") - - } - else{ - - t=time(ts) - dt=t[2]-t[1] - - s0unit=s0/dt*w0/(2*pi) - s0log=as.integer((log2(s0unit)-1)*nvoice+1.5) - - if (s0log<1){ - cat(paste("# s0unit = ",s0unit,"\n",sep="")) - cat(paste("# s0log = ",s0log,"\n",sep="")) - cat("# s0 too small for w0! \n") - } - totnoct=noctave+as.integer(s0log/nvoice)+1 - - #cwt from package Rwave - totts.cwt=cwt(ts,totnoct,nvoice,w0,plot=0) - - ts.cwt=totts.cwt[,s0log:(s0log+noctave*nvoice)] - - #Normalization - sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0) - smat <- matrix(rep(sqs,length(t)),nrow=length(t),byrow=TRUE) - - ts.cwt*smat - - } - +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 } - #matrix: - ############Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect) - Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1])))) - - #NOTE: delta et lscvect pourraient etre gardés à part (communs) - for(i in 1:n) - Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) ) - - #rm(conso, Xcwt4); gc() - - ## _.b WER^2 distances ######## - Xwer_dist <- matrix(0.0, n, n) - for(i in 1:(n - 1)){ - mat1 <- vect2mat(Xcwt2[i,]) +#from sowas +cwt.ts <- function(ts,s0,noctave=5,nvoice=10,w0=2*pi) +{ + if (class(ts)!="ts") + stop("# This function needs a time series object as input. You may construct this by using the function ts(data,start,deltat). Try '?ts' for help.\n") + + t=time(ts) + dt=t[2]-t[1] + s0unit=s0/dt*w0/(2*pi) + s0log=as.integer((log2(s0unit)-1)*nvoice+1.5) + if (s0log<1) + { + cat(paste("# s0unit = ",s0unit,"\n",sep="")) + cat(paste("# s0log = ",s0log,"\n",sep="")) + cat("# s0 too small for w0! \n") + } + totnoct=noctave+as.integer(s0log/nvoice)+1 - #NOTE: vect2mat = as.matrix ?! (dans aux.R) - vect2mat <- function(vect){ - vect <- as.vector(vect) - matrix(vect[-(1:2)], delta, lscvect) - } - - for(j in (i + 1):n){ - mat2 <- vect2mat(Xcwt2[j,]) - num <- Mod(mat1 * Conj(mat2)) - WX <- Mod(mat1 * Conj(mat1)) - WY <- Mod(mat2 * Conj(mat2)) - smsmnum <- smCWT(num, scalevector = scalevector4) - smsmWX <- smCWT(WX, scalevector = scalevector4) - smsmWY <- smCWT(WY, scalevector = scalevector4) - wer2 <- sum(colSums(smsmnum)^2) / - sum( sum(colSums(smsmWX) * colSums(smsmWY)) ) - Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2)) - Xwer_dist[j, i] <- Xwer_dist[i, j] - } - } - diag(Xwer_dist) <- numeric(n) + #cwt from package Rwave + totts.cwt=cwt(ts,totnoct,nvoice,w0,plot=0) + ts.cwt=totts.cwt[,s0log:(s0log+noctave*nvoice)] -#fonction smCWT (dans aux.R) - 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 - } + #Normalization + sqs <- sqrt(2^(0:(noctave*nvoice)/nvoice)*s0) + smat <- matrix(rep(sqs,length(t)),nrow=length(t),byrow=TRUE) - #dans sowas.R (...donc on ne lisse pas à ce niveau ?) -smooth.matrix <- function(wt,swabs){ - - if (swabs != 0) - smwt <- t(filter(t(wt),rep(1,2*swabs+1)/(2*swabs+1))) - else - smwt <- wt - - smwt - -} -smooth.time <- function(wt,tw,dt,scalevector){ - - smwt <- wt - - if (tw != 0){ - for (i in 1:length(scalevector)){ - - twi <- as.integer(scalevector[i]*tw/dt) - smwt[,i] <- filter(wt[,i],rep(1,2*twi+1)/(2*twi+1)) - - } - } - smwt + ts.cwt*smat } -#et filter() est dans stats:: -> filter -function (x, filter, method = c("convolution", "recursive"), - sides = 2L, circular = FALSE, init = NULL) +#NOTE: vect2mat = as.matrix ?! (dans aux.R) +vect2mat <- function(vect) { - method <- match.arg(method) - x <- as.ts(x) - storage.mode(x) <- "double" - xtsp <- tsp(x) - n <- as.integer(NROW(x)) - if (is.na(n)) - stop("invalid value of nrow(x)", domain = NA) - nser <- NCOL(x) - filter <- as.double(filter) - nfilt <- as.integer(length(filter)) - if (is.na(n)) - stop("invalid value of length(filter)", domain = NA) - if (anyNA(filter)) - stop("missing values in 'filter'") - if (method == "convolution") { - if (nfilt > n) - stop("'filter' is longer than time series") - sides <- as.integer(sides) - if (is.na(sides) || (sides != 1L && sides != 2L)) - stop("argument 'sides' must be 1 or 2") - circular <- as.logical(circular) - if (is.na(circular)) - stop("'circular' must be logical and not NA") - if (is.matrix(x)) { - y <- matrix(NA, n, nser) - for (i in seq_len(nser)) y[, i] <- .Call(C_cfilter, - x[, i], filter, sides, circular) - } - else y <- .Call(C_cfilter, x, filter, sides, circular) - } - else { - if (missing(init)) { - init <- matrix(0, nfilt, nser) - } - else { - ni <- NROW(init) - if (ni != nfilt) - stop("length of 'init' must equal length of 'filter'") - if (NCOL(init) != 1L && NCOL(init) != nser) { - stop(sprintf(ngettext(nser, "'init' must have %d column", - "'init' must have 1 or %d columns", domain = "R-stats"), - nser), domain = NA) - } - if (!is.matrix(init)) - dim(init) <- c(nfilt, nser) - } - ind <- seq_len(nfilt) - if (is.matrix(x)) { - y <- matrix(NA, n, nser) - for (i in seq_len(nser)) y[, i] <- .Call(C_rfilter, - x[, i], filter, c(rev(init[, i]), double(n)))[-ind] - } - else y <- .Call(C_rfilter, x, filter, c(rev(init[, 1L]), - double(n)))[-ind] - } - tsp(y) <- xtsp - class(y) <- if (nser > 1L) - c("mts", "ts") - else "ts" - y + vect <- as.vector(vect) + matrix(vect[-(1:2)], delta, lscvect) } - - - - -#cf. filters en C dans : https://svn.r-project.org/R/trunk/src/library/stats/src/filter.c -#ifdef HAVE_CONFIG_H -# include -#endif - -#include -#include "ts.h" -#ifndef min -#define min(a, b) ((a < b)?(a):(b)) -#define max(a, b) ((a < b)?(b):(a)) -#endif - -// currently ISNAN includes NAs -#define my_isok(x) (!ISNA(x) & !ISNAN(x)) - -#Pour method=="convolution" dans filter() (fonction R) -SEXP cfilter(SEXP sx, SEXP sfilter, SEXP ssides, SEXP scircular) +#fonction smCWT (dans aux.R) +smCWT <- function(CWT, sw= 0, tw= 0, swabs= 0, nvoice= 12, noctave= 2, s0= 2, w0= 2*pi, + lt= 24, dt= 0.5, scalevector ) { - if (TYPEOF(sx) != REALSXP || TYPEOF(sfilter) != REALSXP) - error("invalid input"); - R_xlen_t nx = XLENGTH(sx), nf = XLENGTH(sfilter); - int sides = asInteger(ssides), circular = asLogical(scircular); - if(sides == NA_INTEGER || circular == NA_LOGICAL) error("invalid input"); - - SEXP ans = allocVector(REALSXP, nx); +#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 +} - R_xlen_t i, j, nshift; - double z, tmp, *x = REAL(sx), *filter = REAL(sfilter), *out = REAL(ans); +#dans sowas.R (...donc on ne lisse pas à ce niveau ?) +smooth.matrix <- function(wt,swabs) +{ + if (swabs != 0) + { + smwt <- t(filter(t(wt),rep(1,2*swabs+1)/(2*swabs+1))) + } else + { + smwt <- wt + } + smwt +} - if(sides == 2) nshift = nf /2; else nshift = 0; - if(!circular) { - for(i = 0; i < nx; i++) { - z = 0; - if(i + nshift - (nf - 1) < 0 || i + nshift >= nx) { - out[i] = NA_REAL; - continue; - } - for(j = max(0, nshift + i - nx); j < min(nf, i + nshift + 1) ; j++) { - tmp = x[i + nshift - j]; - if(my_isok(tmp)) z += filter[j] * tmp; - else { out[i] = NA_REAL; goto bad; } - } - out[i] = z; - bad: - continue; +smooth.time <- function(wt,tw,dt,scalevector) +{ + smwt <- wt + if (tw != 0) + { + for (i in 1:length(scalevector)) + { + twi <- as.integer(scalevector[i]*tw/dt) + smwt[,i] <- filter(wt[,i],rep(1,2*twi+1)/(2*twi+1)) + } } - } else { /* circular */ - for(i = 0; i < nx; i++) + smwt +} + +step2 = function(conso) +{ + #(Benjamin) + #à partir de là, "conso" == courbes synchrones + n <- nrow(conso) + delta <- ncol(conso) + + #17000 colonnes coeff 1, puis 17000 coeff 2... [non : dans chaque tranche du cube] + # #NOTE: delta et lscvect pourraient etre gardés à part (communs) + + #TODO: automatic tune of these parameters ? (for other users) + nvoice <- 4 + # # noctave4 = 2^13 = 8192 half hours ~ 180 days + noctave4 <- adjust.noctave(N = delta, dt = 1, s0 = 2, tw = 0, noctave = 13) + # # 4 here represent 2^5 = 32 half-hours ~ 1 day + scalevector4 <- 2^(4:(noctave4 * nvoice) / nvoice) * 2 + lscvect4 <- length(scalevector4) + lscvect <- lscvect4 # i should clean my code: werFam demands a lscvect + + # observations node with CWT + Xcwt4 <- toCWT(conso, noctave = noctave4, dt = 1, scalevector = scalevector4, lt = delta, + smooth = FALSE, nvoice = nvoice) + + #matrix: + ############Xcwt2 <- matrix(0.0, nrow= n, ncol= 2 + delta * lscvect) + Xcwt2 <- matrix(NA_complex_, nrow= n, ncol= 2 + length((c(Xcwt4[,,1])))) + + #NOTE: delta et lscvect pourraient etre gardés à part (communs) + for(i in 1:n) + Xcwt2[i,] <- c(delta, lscvect, Xcwt4[,,i] / max(Mod(Xcwt4[,,i])) ) + #rm(conso, Xcwt4); gc() + + ## _.b WER^2 distances ######## + Xwer_dist <- matrix(0.0, n, n) + for(i in 1:(n - 1)) { - z = 0; - for(j = 0; j < nf; j++) { - R_xlen_t ii = i + nshift - j; - if(ii < 0) ii += nx; - if(ii >= nx) ii -= nx; - tmp = x[ii]; - if(my_isok(tmp)) z += filter[j] * tmp; - else { out[i] = NA_REAL; goto bad2; } - } - out[i] = z; - bad2: - continue; + mat1 <- vect2mat(Xcwt2[i,]) + + for(j in (i + 1):n) + { + mat2 <- vect2mat(Xcwt2[j,]) + num <- Mod(mat1 * Conj(mat2)) + WX <- Mod(mat1 * Conj(mat1)) + WY <- Mod(mat2 * Conj(mat2)) + smsmnum <- smCWT(num, scalevector = scalevector4) + smsmWX <- smCWT(WX, scalevector = scalevector4) + smsmWY <- smCWT(WY, scalevector = scalevector4) + wer2 <- sum(colSums(smsmnum)^2) / + sum( sum(colSums(smsmWX) * colSums(smsmWY)) ) + Xwer_dist[i, j] <- sqrt(delta * lscvect * (1 - wer2)) + Xwer_dist[j, i] <- Xwer_dist[i, j] + } } - } - return ans; + diag(Xwer_dist) <- numeric(n) + Wwer_dist }