fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
}
- # Indices of similar days for cross-validation; TODO: 45 = magic number
- sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
+ # Indices of similar days for cross-validation; TODO: 20 = magic number
+ cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, days_in=fdays)
# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
errorOnLastNdays = function(h, kernel, simtype)
{
error = 0
nb_jours = 0
- for (i in intersect(fdays,sdays))
+ for (i in seq_along(cv_days))
{
# mix_strategy is never used here (simtype != "mix"), therefore left blank
prediction = private$.predictShapeAux(data,
- fdays, i, horizon, h, kernel, simtype, FALSE)
+ fdays, cv_days[i], horizon, h, kernel, simtype, FALSE)
if (!is.na(prediction[1]))
{
nb_jours = nb_jours + 1
error = error +
- mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2)
+ mean((data$getCenteredSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
}
}
return (error / nb_jours)
if (simtype != "endo")
{
h_best_exo = optimize(
- errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
+ errorOnLastNdays, c(0,7), kernel=kernel, simtype="exo")$minimum
}
if (simtype != "exo")
{
h_best_endo = optimize(
- errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
+ errorOnLastNdays, c(0,7), kernel=kernel, simtype="endo")$minimum
}
if (simtype == "endo")
h_endo = ifelse(simtype=="mix", h[1], h)
# Distances from last observed day to days in the past
- distances2 = rep(NA, length(fdays))
- for (i in seq_along(fdays))
- {
- delta = data$getCenteredSerie(today) - data$getCenteredSerie(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)
- }
+ serieToday = data$getSerie(today)
+ distances2 = sapply(fdays, function(i) {
+ delta = serieToday - data$getSerie(i)
+ mean(delta^2)
+ })
sd_dist = sd(distances2)
if (sd_dist < .Machine$double.eps)
M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
sigma = cov(M) #NOTE: robust covariance is way too slow
- sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
+ # TODO: 10 == magic number; more robust way == det, or always ginv()
+ sigma_inv =
+ if (length(fdays) > 10)
+ solve(sigma)
+ else
+ MASS::ginv(sigma)
# Distances from last observed day to days in the past
- distances2 = rep(NA, nrow(M)-1)
- for (i in 2:nrow(M))
- {
- delta = M[1,] - M[i,]
- distances2[i-1] = delta %*% sigma_inv %*% delta
- }
+ distances2 = sapply(seq_along(fdays), function(i) {
+ delta = M[1,] - M[i+1,]
+ delta %*% sigma_inv %*% delta
+ })
sd_dist = sd(distances2)
- if (sd_dist < .Machine$double.eps)
+ if (sd_dist < .25 * sqrt(.Machine$double.eps))
{
# warning("All computed distances are very close: stdev too small")
sd_dist = 1 #mostly for tests... FIXME:
simils_endo
else #mix
simils_endo * simils_exo
+ similarities = similarities / sum(similarities)
prediction = rep(0, horizon)
for (i in seq_along(fdays))
- prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
- prediction = prediction / sum(similarities, na.rm=TRUE)
+ prediction = prediction + similarities[i] * data$getCenteredSerie(fdays[i]+1)[1:horizon]
if (final_call)
{