inherit = Forecaster,
public = list(
- predictSerie = function(data, today, memory, horizon, ...)
- {
- # Parameters (potentially) computed during shape prediction stage
- predicted_shape = self$predictShape(data, today, memory, horizon, ...)
-# predicted_delta = private$.pjump(data,today,memory,horizon,private$.params,...)
- # Predicted shape is aligned it on the end of current day + jump
-# predicted_shape+tail(data$getSerie(today),1)-predicted_shape[1]+predicted_delta
- predicted_shape
- },
predictShape = function(data, today, memory, horizon, ...)
{
# (re)initialize computed parameters
fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
}
- # Indices of similar days for cross-validation; TODO: 45 = magic number
- sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
-
- cv_days = intersect(fdays,sdays)
- # Limit to 20 most recent matching days (TODO: 20 == magic number)
- cv_days = sort(cv_days,decreasing=TRUE)[1:min(20,length(cv_days))]
+ # Indices of similar days for cross-validation; TODO: 20 = magic number
+ cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, days_in=fdays)
# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
errorOnLastNdays = function(h, kernel, simtype)
if (!is.na(prediction[1]))
{
nb_jours = nb_jours + 1
- error = error +
- mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
+ error = error + mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
}
}
return (error / nb_jours)
if (simtype != "endo")
{
h_best_exo = optimize(
- errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$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")$minimum
}
if (simtype == "endo")
# Precondition: "today" is full (no NAs)
.predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
{
- fdays = fdays[ fdays < today ]
+ fdays_cut = fdays[ fdays < today ]
# TODO: 3 = magic number
- if (length(fdays) < 3)
+ if (length(fdays_cut) < 3)
return (NA)
- # Neighbors: days in "same season"
- sdays = getSimilarDaysIndices(today, limit=45, same_season=TRUE, data)
- indices = intersect(fdays,sdays)
+ # Neighbors: days in "same season"; TODO: 60 == magic number...
+ fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE, days_in=fdays_cut)
+ if (length(fdays) <= 1)
+ return (NA)
levelToday = data$getLevel(today)
- distances = sapply(indices, function(i) abs(data$getLevel(i)-levelToday))
- same_pollution = (distances <= 2)
- if (sum(same_pollution) < 3) #TODO: 3 == magic number
+ distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
+ #TODO: 2, 3, 5, 10 magic numbers here...
+ dist_thresh = 2
+ min_neighbs = min(3,length(fdays))
+ repeat
{
- same_pollution = (distances <= 5)
- if (sum(same_pollution) < 3)
- return (NA)
+ same_pollution = (distances <= dist_thresh)
+ nb_neighbs = sum(same_pollution)
+ if (nb_neighbs >= min_neighbs) #will eventually happen
+ break
+ dist_thresh = dist_thresh + 3
+ }
+ fdays = fdays[same_pollution]
+ max_neighbs = 10
+ if (nb_neighbs > max_neighbs)
+ {
+ # Keep only max_neighbs closest neighbors
+ fdays = fdays[ sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
+ }
+ if (length(fdays) == 1) #the other extreme...
+ {
+ if (final_call)
+ {
+ private$.params$weights <- 1
+ private$.params$indices <- fdays
+ private$.params$window <- 1
+ }
+ return ( data$getSerie(fdays[1])[1:horizon] ) #what else?!
}
- indices = indices[same_pollution]
if (simtype != "exo")
{
# Distances from last observed day to days in the past
serieToday = data$getSerie(today)
- distances2 = sapply(indices, function(i) {
+ distances2 = sapply(fdays, function(i) {
delta = serieToday - data$getSerie(i)
mean(delta^2)
})
{
h_exo = ifelse(simtype=="mix", h[2], h)
- M = matrix( nrow=1+length(indices), ncol=1+length(data$getExo(today)) )
+ M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
- for (i in seq_along(indices))
- M[i+1,] = c( data$getLevel(indices[i]), as.double(data$getExo(indices[i])) )
+ 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
-# sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
- sigma_inv = MASS::ginv(sigma)
-#if (final_call) browser()
+ # 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(indices), function(i) {
+ distances2 = sapply(seq_along(fdays), function(i) {
delta = M[1,] - M[i+1,]
delta %*% sigma_inv %*% delta
})
simils_endo
else #mix
simils_endo * simils_exo
+ similarities = similarities / sum(similarities)
prediction = rep(0, horizon)
- for (i in seq_along(indices))
- prediction = prediction + similarities[i] * data$getSerie(indices[i]+1)[1:horizon]
- prediction = prediction / sum(similarities, na.rm=TRUE)
+ for (i in seq_along(fdays))
+ prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
if (final_call)
{
+ prediction = prediction - mean(prediction) #predict centered serie (artificial...)
private$.params$weights <- similarities
private$.params$indices <- fdays
private$.params$window <-
projects / talweg.git / blobdiff