fdays = getNoNA2(data, max(today-memory,1), today-1)
# Get optional args
+ simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
if (hasArg(h_window))
{
return ( private$.predictShapeAux(data,
- fdays, today, horizon, list(...)$h_window, kernel, TRUE) )
+ fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
}
-
- # Indices of similar days for cross-validation; TODO: 45 = magic number
- # TODO: ici faut une sorte de "same_season==TRUE" --> mois similaires epandage
- sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
-
+ # Indices of similar days for cross-validation; TODO: 20 = magic number
+ cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, days_in=fdays)
# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
- errorOnLastNdays = function(h, kernel)
+ errorOnLastNdays = function(h, kernel, simtype)
{
error = 0
nb_jours = 0
- for (i in intersect(fdays,sdays))
+ for (i in seq_along(cv_days))
{
# mix_strategy is never used here (simtype != "mix"), therefore left blank
- prediction = private$.predictShapeAux(data, fdays, i, horizon, h, kernel, FALSE)
+ prediction = private$.predictShapeAux(data,
+ fdays, cv_days[i], horizon, h, kernel, simtype, FALSE)
if (!is.na(prediction[1]))
{
nb_jours = nb_jours + 1
- error = error +
- mean((data$getSerie(i+1)[1:horizon] - prediction)^2)
+ error = error + mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
}
}
return (error / nb_jours)
}
- # h :: only for endo in this variation
- h_best_endo = optimize(errorOnLastNdays, c(0,10), kernel=kernel)$minimum
+ if (simtype != "endo")
+ {
+ h_best_exo = optimize(
+ errorOnLastNdays, c(0,7), kernel=kernel, simtype="exo")$minimum
+ }
+ if (simtype != "exo")
+ {
+ h_best_endo = optimize(
+ errorOnLastNdays, c(0,7), kernel=kernel, simtype="endo")$minimum
+ }
- return (private$.predictShapeAux(data, fdays, today, horizon, h_best, kernel, TRUE))
+ if (simtype == "endo")
+ {
+ return (private$.predictShapeAux(data,
+ fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
+ }
+ if (simtype == "exo")
+ {
+ return (private$.predictShapeAux(data,
+ fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
+ }
+ if (simtype == "mix")
+ {
+ h_best_mix = c(h_best_endo,h_best_exo)
+ return(private$.predictShapeAux(data,
+ fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
+ }
}
),
private = list(
# Precondition: "today" is full (no NAs)
- .predictShapeAux = function(data, fdays, today, horizon, h, kernel, final_call)
+ .predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
{
- fdays = fdays[ fdays < today ]
+ fdays_cut = fdays[ fdays < today ]
# TODO: 3 = magic number
- if (length(fdays) < 3)
+ if (length(fdays_cut) < 3)
return (NA)
- # ENDO:: Distances from last observed day to days in the past
- distances2 = rep(NA, length(fdays))
- for (i in seq_along(fdays))
+ # Neighbors: days in "same season"; TODO: 60 == magic number...
+ fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE, days_in=fdays_cut)
+ if (length(fdays) <= 1)
+ return (NA)
+ levelToday = data$getLevel(today)
+ distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
+ #TODO: 2, 3, 5, 10 magic numbers here...
+ dist_thresh = 2
+ min_neighbs = min(3,length(fdays))
+ repeat
{
- delta = data$getSerie(today) - data$getSerie(fdays[i])
- # Require at least half of non-NA common values to compute the distance
- if ( !any( is.na(delta) ) )
- distances2[i] = mean(delta^2)
+ same_pollution = (distances <= dist_thresh)
+ nb_neighbs = sum(same_pollution)
+ if (nb_neighbs >= min_neighbs) #will eventually happen
+ break
+ dist_thresh = dist_thresh + 3
}
-
- sd_dist = sd(distances2)
- if (sd_dist < .Machine$double.eps)
+ fdays = fdays[same_pollution]
+ max_neighbs = 10
+ if (nb_neighbs > max_neighbs)
{
-# warning("All computed distances are very close: stdev too small")
- sd_dist = 1 #mostly for tests... FIXME:
+ # Keep only max_neighbs closest neighbors
+ fdays = fdays[ sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
}
- simils_endo =
- if (kernel=="Gauss")
- exp(-distances2/(sd_dist*h_endo^2))
- else
+ if (length(fdays) == 1) #the other extreme...
+ {
+ if (final_call)
{
- # Epanechnikov
- u = 1 - distances2/(sd_dist*h_endo^2)
- u[abs(u)>1] = 0.
- u
+ private$.params$weights <- 1
+ private$.params$indices <- fdays
+ private$.params$window <- 1
}
+ return ( data$getSerie(fdays[1])[1:horizon] ) #what else?!
+ }
- # EXOGENS: distances computations are enough
- # TODO: search among similar concentrations....... at this stage ?!
- M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
- M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
- for (i in seq_along(fdays))
- M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
+ if (simtype != "exo")
+ {
+ h_endo = ifelse(simtype=="mix", h[1], h)
- sigma = cov(M) #NOTE: robust covariance is way too slow
- sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
+ # Distances from last observed day to days in the past
+ serieToday = data$getSerie(today)
+ distances2 = sapply(fdays, function(i) {
+ delta = serieToday - data$getSerie(i)
+ mean(delta^2)
+ })
- # Distances from last observed day to days in the past
- distances2 = rep(NA, nrow(M)-1)
- for (i in 2:nrow(M))
- {
- delta = M[1,] - M[i,]
- distances2[i-1] = delta %*% sigma_inv %*% delta
+ sd_dist = sd(distances2)
+ if (sd_dist < .Machine$double.eps)
+ {
+# warning("All computed distances are very close: stdev too small")
+ sd_dist = 1 #mostly for tests... FIXME:
+ }
+ simils_endo =
+ if (kernel=="Gauss")
+ exp(-distances2/(sd_dist*h_endo^2))
+ else
+ {
+ # Epanechnikov
+ u = 1 - distances2/(sd_dist*h_endo^2)
+ u[abs(u)>1] = 0.
+ u
+ }
}
- ppv <- sort(distances2, index.return=TRUE)$ix[1:10] #..............
-#PPV pour endo ?
+ if (simtype != "endo")
+ {
+ h_exo = ifelse(simtype=="mix", h[2], h)
+
+ M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
+ M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
+ for (i in seq_along(fdays))
+ M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
+
+ sigma = cov(M) #NOTE: robust covariance is way too slow
+ # TODO: 10 == magic number; more robust way == det, or always ginv()
+ sigma_inv =
+ if (length(fdays) > 10)
+ solve(sigma)
+ else
+ MASS::ginv(sigma)
+
+ # Distances from last observed day to days in the past
+ distances2 = sapply(seq_along(fdays), function(i) {
+ delta = M[1,] - M[i+1,]
+ delta %*% sigma_inv %*% delta
+ })
+
+ sd_dist = sd(distances2)
+ if (sd_dist < .25 * sqrt(.Machine$double.eps))
+ {
+# warning("All computed distances are very close: stdev too small")
+ sd_dist = 1 #mostly for tests... FIXME:
+ }
+ simils_exo =
+ if (kernel=="Gauss")
+ exp(-distances2/(sd_dist*h_exo^2))
+ else
+ {
+ # Epanechnikov
+ u = 1 - distances2/(sd_dist*h_exo^2)
+ u[abs(u)>1] = 0.
+ u
+ }
+ }
similarities =
if (simtype == "exo")
simils_endo
else #mix
simils_endo * simils_exo
+ similarities = similarities / sum(similarities)
prediction = rep(0, horizon)
for (i in seq_along(fdays))
prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
- prediction = prediction / sum(similarities, na.rm=TRUE)
if (final_call)
{
+ prediction = prediction - mean(prediction) #predict centered serie (artificial...)
private$.params$weights <- similarities
private$.params$indices <- fdays
private$.params$window <-