+++ /dev/null
-#' @include Forecaster.R
-#'
-#' @title Neighbors Forecaster
-#'
-#' @description Predict tomorrow as a weighted combination of "futures of the past" days.
-#' Inherits \code{\link{Forecaster}}
-NeighborsForecaster = setRefClass(
- Class = "NeighborsForecaster",
- contains = "Forecaster",
-
- methods = list(
- initialize = function(...)
- {
- callSuper(...)
- },
- predictShape = function(today, memory, horizon, ...)
- {
- # (re)initialize computed parameters
- params <<- list("weights"=NA, "indices"=NA, "window"=NA)
-
- # 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 (.predictShapeAux(fdays,today,horizon,list(...)$h_window,kernel,simtype,TRUE))
-
- # HACK for test reports: complete some days with a few NAs, for nicer graphics
- nas_in_serie = is.na(data$getSerie(today))
- if (any(nas_in_serie))
- {
- if (sum(nas_in_serie) >= length(nas_in_serie) / 2)
- return (NA)
- for (i in seq_along(nas_in_serie))
- {
- if (nas_in_serie[i])
- {
- #look left
- left = i-1
- while (left>=1 && nas_in_serie[left])
- left = left-1
- #look right
- right = i+1
- while (right<=length(nas_in_serie) && nas_in_serie[right])
- right = right+1
- #HACK: modify by-reference Data object...
- data$data[[today]]$serie[i] <<-
- if (left==0) data$data[[today]]$serie[right]
- else if (right==0) data$data[[today]]$serie[left]
- else (data$data[[today]]$serie[left] + data$data[[today]]$serie[right]) / 2.
- }
- }
- }
-
- # Determine indices of no-NAs days followed by no-NAs tomorrows
- first_day = max(today - memory, 1)
- fdays = (first_day:(today-1))[ sapply(first_day:(today-1), function(i) {
- !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1)))
- }) ]
-
- # Indices of similar days for cross-validation; TODO: 45 = magic number
- sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
-
- # 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))
- {
- # mix_strategy is never used here (simtype != "mix"), therefore left blank
- prediction = .predictShapeAux(fdays, i, horizon, h, kernel, simtype, FALSE)
- if (!is.na(prediction[1]))
- {
- nb_jours = nb_jours + 1
- error = error + mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2)
- }
- }
- return (error / nb_jours)
- }
-
- if (simtype != "endo")
- h_best_exo = optimize(errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
- if (simtype != "exo")
- h_best_endo = optimize(errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
-
- if (simtype == "endo")
- return (.predictShapeAux(fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
- if (simtype == "exo")
- return (.predictShapeAux(fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
- if (simtype == "mix")
- {
- h_best_mix = c(h_best_endo,h_best_exo)
- return (.predictShapeAux(fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
- }
- },
- # Precondition: "today" is full (no NAs)
- .predictShapeAux = function(fdays, today, horizon, h, kernel, simtype, final_call)
- {
- dat = data$data #HACK: faster this way...
-
- fdays = fdays[ fdays < today ]
- # TODO: 3 = magic number
- if (length(fdays) < 3)
- return (NA)
-
- if (simtype != "exo")
- {
- 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 = dat[[today]]$serie - dat[[ fdays[i] ]]$serie
- # Require at least half of non-NA common values to compute the distance
- if (sum(is.na(delta)) <= 0) #length(delta)/2)
- distances2[i] = mean(delta^2) #, na.rm=TRUE)
- }
-
- sd_dist = sd(distances2)
- if (sd_dist < .Machine$double.eps)
- sd_dist = 1 #mostly for tests... FIXME:
- simils_endo =
- if (kernel=="Gauss")
- exp(-distances2/(sd_dist*h_endo^2))
- else { #Epanechnikov
- u = 1 - distances2/(sd_dist*h_endo^2)
- u[abs(u)>1] = 0.
- u
- }
- }
-
- if (simtype != "endo")
- {
- h_exo = ifelse(simtype=="mix", h[2], h)
-
- M = matrix( nrow=1+length(fdays), ncol=1+length(dat[[today]]$exo) )
- M[1,] = c( dat[[today]]$level, as.double(dat[[today]]$exo) )
- for (i in seq_along(fdays))
- M[i+1,] = c( dat[[ fdays[i] ]]$level, as.double(dat[[ fdays[i] ]]$exo) )
-
- 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
- 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)
- 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_exo
- else if (simtype == "endo")
- simils_endo
- else #mix
- simils_endo * simils_exo
-
- prediction = rep(0, horizon)
- for (i in seq_along(fdays_indices))
- prediction = prediction + similarities[i] * dat[[ fdays_indices[i]+1 ]]$serie[1:horizon]
- prediction = prediction / sum(similarities, na.rm=TRUE)
-
- if (final_call)
- {
- params$weights <<- similarities
- params$indices <<- fdays_indices
- params$window <<-
- if (simtype=="endo") {
- h_endo
- } else if (simtype=="exo") {
- h_exo
- } else { #mix
- c(h_endo,h_exo)
- }
- }
-
- return (prediction)
- }
- )
-)