fdays = getNoNA2(data, max(today-memory,1), today-1)
# Get optional args
+ local = ifelse(hasArg("local"), list(...)$local, FALSE) #same level + season?
simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
- kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
- if (hasArg(h_window))
+ if (hasArg("window"))
{
return ( private$.predictShapeAux(data,
- fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
+ fdays, today, horizon, local, list(...)$window, simtype, TRUE) )
}
# Indices of similar days for cross-validation; TODO: 20 = magic number
- cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, days_in=fdays)
+ 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)
+ # Optimize h : h |--> sum of prediction errors on last 45 "similar" days
+ errorOnLastNdays = function(window, simtype)
{
error = 0
nb_jours = 0
for (i in seq_along(cv_days))
{
# mix_strategy is never used here (simtype != "mix"), therefore left blank
- prediction = private$.predictShapeAux(data,
- fdays, cv_days[i], horizon, h, kernel, simtype, FALSE)
+ prediction = private$.predictShapeAux(data, fdays, cv_days[i], horizon, local,
+ window, simtype, FALSE)
if (!is.na(prediction[1]))
{
nb_jours = nb_jours + 1
error = error +
- mean((data$getCenteredSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
+ mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
}
}
return (error / nb_jours)
if (simtype != "endo")
{
- h_best_exo = optimize(
- errorOnLastNdays, c(0,7), kernel=kernel, simtype="exo")$minimum
+ best_window_exo = optimize(
+ errorOnLastNdays, c(0,7), simtype="exo")$minimum
}
if (simtype != "exo")
{
- h_best_endo = optimize(
- errorOnLastNdays, c(0,7), kernel=kernel, simtype="endo")$minimum
+ best_window_endo = optimize(
+ errorOnLastNdays, c(0,7), simtype="endo")$minimum
}
if (simtype == "endo")
{
- return (private$.predictShapeAux(data,
- fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
+ return (private$.predictShapeAux(data, fdays, today, horizon, local,
+ best_window_endo, "endo", TRUE))
}
if (simtype == "exo")
{
- return (private$.predictShapeAux(data,
- fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
+ return (private$.predictShapeAux(data, fdays, today, horizon, local,
+ best_window_exo, "exo", TRUE))
}
if (simtype == "mix")
{
- h_best_mix = c(h_best_endo,h_best_exo)
- return(private$.predictShapeAux(data,
- fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
+ return(private$.predictShapeAux(data, fdays, today, horizon, local,
+ c(best_window_endo,best_window_exo), "mix", TRUE))
}
}
),
private = list(
# Precondition: "today" is full (no NAs)
- .predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
+ .predictShapeAux = function(data, fdays, today, horizon, local, window, simtype,
+ final_call)
{
- fdays = fdays[ fdays < today ]
- # TODO: 3 = magic number
- if (length(fdays) < 3)
+ fdays_cut = fdays[ fdays < today ]
+ if (length(fdays_cut) <= 1)
return (NA)
+ if (local)
+ {
+ # 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
+ {
+ 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?!
+ }
+ }
+ else
+ fdays = fdays_cut #no conditioning
+
if (simtype != "exo")
{
- h_endo = ifelse(simtype=="mix", h[1], h)
+ # Compute endogen similarities using given window
+ window_endo = ifelse(simtype=="mix", window[1], window)
# Distances from last observed day to days in the past
serieToday = data$getSerie(today)
})
sd_dist = sd(distances2)
- if (sd_dist < .Machine$double.eps)
+ if (sd_dist < .25 * sqrt(.Machine$double.eps))
{
# warning("All computed distances are very close: stdev too small")
sd_dist = 1 #mostly for tests... FIXME:
}
- simils_endo =
- if (kernel=="Gauss")
- exp(-distances2/(sd_dist*h_endo^2))
- else
- {
- # Epanechnikov
- u = 1 - distances2/(sd_dist*h_endo^2)
- u[abs(u)>1] = 0.
- u
- }
+ simils_endo = exp(-distances2/(sd_dist*window_endo^2))
}
if (simtype != "endo")
{
- h_exo = ifelse(simtype=="mix", h[2], h)
+ # Compute exogen similarities using given window
+ h_exo = ifelse(simtype=="mix", window[2], window)
M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
# 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
- }
+ simils_exo = exp(-distances2/(sd_dist*window_exo^2))
}
similarities =
prediction = rep(0, horizon)
for (i in seq_along(fdays))
- prediction = prediction + similarities[i] * data$getCenteredSerie(fdays[i]+1)[1:horizon]
+ prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
if (final_call)
{
private$.params$indices <- fdays
private$.params$window <-
if (simtype=="endo")
- h_endo
+ window_endo
else if (simtype=="exo")
- h_exo
+ window_exo
else #mix
- c(h_endo,h_exo)
+ c(window_endo,window_exo)
}
return (prediction)
+++ /dev/null
-#' @include Forecaster.R
-#'
-#' Neighbors2 Forecaster
-#'
-#' Predict tomorrow as a weighted combination of "futures of the past" days.
-#' Inherits \code{\link{Forecaster}}
-#'
-Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
- inherit = Forecaster,
-
- public = list(
- predictShape = function(data, today, memory, horizon, ...)
- {
- # (re)initialize computed parameters
- private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
-
- # Do not forecast on days with NAs (TODO: softer condition...)
- if (any(is.na(data$getCenteredSerie(today))))
- return (NA)
-
- # Determine indices of no-NAs days followed by no-NAs tomorrows
- 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, simtype, TRUE) )
- }
-
- # 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 seq_along(cv_days))
- {
- # mix_strategy is never used here (simtype != "mix"), therefore left blank
- 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(cv_days[i]+1)[1:horizon] - prediction)^2)
- }
- }
- return (error / nb_jours)
- }
-
- 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
- }
-
- 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$.predictShapeAux(data,
- fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
- }
- }
- ),
- private = list(
- # Precondition: "today" is full (no NAs)
- .predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
- {
- fdays_cut = fdays[ fdays < today ]
- # TODO: 3 = magic number
- if (length(fdays_cut) < 3)
- return (NA)
-
- # Neighbors: days in "same season"; TODO: 60 == magic number...
- fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE, days_in=fdays_cut)
- if (length(fdays) <= 1)
- return (NA)
- levelToday = data$getLevel(today)
- distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
- #TODO: 2, 3, 5, 10 magic numbers here...
- dist_thresh = 2
- min_neighbs = min(3,length(fdays))
- repeat
- {
- same_pollution = (distances <= dist_thresh)
- nb_neighbs = sum(same_pollution)
- if (nb_neighbs >= min_neighbs) #will eventually happen
- break
- dist_thresh = dist_thresh + 3
- }
- fdays = fdays[same_pollution]
- max_neighbs = 10
- if (nb_neighbs > max_neighbs)
- {
- # Keep only max_neighbs closest neighbors
- fdays = fdays[ sort(distances[same_pollution],index.return=TRUE)$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$getSerie(fdays[1])[1:horizon] ) #what else?!
- }
-
- if (simtype != "exo")
- {
- h_endo = ifelse(simtype=="mix", h[1], h)
-
- # Distances from last observed day to days in the past
- serieToday = data$getSerie(today)
- distances2 = sapply(fdays, function(i) {
- delta = serieToday - data$getSerie(i)
- mean(delta^2)
- })
-
- sd_dist = sd(distances2)
- if (sd_dist < .Machine$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
- }
- }
-
- 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_exo
- else if (simtype == "endo")
- 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$getSerie(fdays[i]+1)[1:horizon]
-
- if (final_call)
- {
- prediction = prediction - mean(prediction) #predict centered serie (artificial...)
- private$.params$weights <- similarities
- private$.params$indices <- fdays
- private$.params$window <-
- if (simtype=="endo")
- h_endo
- else if (simtype=="exo")
- h_exo
- else #mix
- c(h_endo,h_exo)
- }
-
- return (prediction)
- }
- )
-)
-----
<h2>Introduction</h2>
-J'ai fait quelques essais dans différentes configurations pour la méthode "Neighbors"
-(la seule dont on a parlé) et sa variante récente appelée pour l'instant "Neighbors2",
-avec simtype="mix" : deux types de similarités prises en compte, puis multiplication des poids.
-Pour Neighbors on prédit le saut (par la moyenne pondérée des sauts passés), et pour Neighbors2
-on n'effectue aucun raccordement (prévision directe).
+J'ai fait quelques essais dans deux configurations pour la méthode "Neighbors"
+(la seule dont on a parlé, incorporant désormais la "variante Bruno/Michel").
+
+ * avec simtype="mix" et raccordement simple ("Zero") dans le cas "non local", i.e. on va
+ chercher des voisins n'importe où du moment qu'ils correspondent à deux jours consécutifs sans
+ valeurs manquantes.
+ * avec simtype="endo" et raccordement "Neighbor" dans le cas "local" : voisins de même niveau de
+ pollution et même saison.
J'ai systématiquement comparé à une approche naïve : la moyenne des lendemains des jours
"similaires" dans tout le passé, ainsi qu'à la persistence -- reproduisant le jour courant ou
-----
<h2 style="color:blue;font-size:2em">${list_titles[i]}</h2>
-----r
-p_nn = computeForecast(data, ${list_indices[i]}, "Neighbors", "Neighbors", horizon=H)
-p_nn2 = computeForecast(data, ${list_indices[i]}, "Neighbors2", "Zero", horizon=H)
-p_az = computeForecast(data, ${list_indices[i]}, "Average", "Zero", horizon=H)
-p_pz = computeForecast(data, ${list_indices[i]}, "Persistence", "Zero", horizon=H, same_day=${'TRUE' if loop.index < 2 else 'FALSE'})
+p_n = computeForecast(data, ${list_indices[i]}, "Neighbors", "Zero", horizon=H,
+ simtype="mix", local=FALSE)
+p_l = computeForecast(data, ${list_indices[i]}, "Neighbors", "Neighbors", horizon=H,
+ simtype="endo", local=TRUE)
+p_a = computeForecast(data, ${list_indices[i]}, "Average", "Zero", horizon=H)
+p_p = computeForecast(data, ${list_indices[i]}, "Persistence", "Zero", horizon=H,
+ same_day=${'TRUE' if loop.index < 2 else 'FALSE'})
-----r
-e_nn = computeError(data, p_nn, H)
-e_nn2 = computeError(data, p_nn2, H)
-e_az = computeError(data, p_az, H)
-e_pz = computeError(data, p_pz, H)
+e_n = computeError(data, p_n, H)
+e_l = computeError(data, p_nl, H)
+e_a = computeError(data, p_a, H)
+e_p = computeError(data, p_p, H)
options(repr.plot.width=9, repr.plot.height=7)
-plotError(list(e_nn, e_pz, e_az, e_nn2), cols=c(1,2,colors()[258], 4))
+plotError(list(e_n, e_p, e_a, e_l), cols=c(1,2,colors()[258], 4))
-# Noir: Neighbors, bleu: Neighbors2, vert: moyenne, rouge: persistence
+# Noir: Neighbors non-local, bleu: Neighbors local, vert: moyenne, rouge: persistence
-i_np = which.min(e_nn$abs$indices)
-i_p = which.max(e_nn$abs$indices)
+i_np = which.min(e_n$abs$indices)
+i_p = which.max(e_n$abs$indices)
-----r
options(repr.plot.width=9, repr.plot.height=4)
par(mfrow=c(1,2))
-plotPredReal(data, p_nn, i_np); title(paste("PredReal nn day",i_np))
-plotPredReal(data, p_nn2, i_p); title(paste("PredReal nn day",i_p))
+plotPredReal(data, p_n, i_np); title(paste("PredReal non-loc day",i_np))
+plotPredReal(data, p_n, i_p); title(paste("PredReal non-loc day",i_p))
-plotPredReal(data, p_nn2, i_np); title(paste("PredReal nn2 day",i_np))
-plotPredReal(data, p_nn2, i_p); title(paste("PredReal nn2 day",i_p))
+plotPredReal(data, p_l, i_np); title(paste("PredReal loc day",i_np))
+plotPredReal(data, p_l, i_p); title(paste("PredReal loc day",i_p))
-plotPredReal(data, p_az, i_np); title(paste("PredReal az day",i_np))
-plotPredReal(data, p_az, i_p); title(paste("PredReal az day",i_p))
+plotPredReal(data, p_a, i_np); title(paste("PredReal avg day",i_np))
+plotPredReal(data, p_a, i_p); title(paste("PredReal avg day",i_p))
# Bleu: prévue, noir: réalisée
-----r
par(mfrow=c(1,2))
-f_np = computeFilaments(data, p_nn, i_np, plot=TRUE); title(paste("Filaments nn day",i_np))
-f_p = computeFilaments(data, p_nn, i_p, plot=TRUE); title(paste("Filaments nn day",i_p))
+f_np_n = computeFilaments(data, p_n, i_np, plot=TRUE); title(paste("Filaments non-loc day",i_np))
+f_p_n = computeFilaments(data, p_n, i_p, plot=TRUE); title(paste("Filaments non-loc day",i_p))
-f_np2 = computeFilaments(data, p_nn2, i_np, plot=TRUE); title(paste("Filaments nn2 day",i_np))
-f_p2 = computeFilaments(data, p_nn2, i_p, plot=TRUE); title(paste("Filaments nn2 day",i_p))
+f_np_l = computeFilaments(data, p_l, i_np, plot=TRUE); title(paste("Filaments loc day",i_np))
+f_p_l = computeFilaments(data, p_l, i_p, plot=TRUE); title(paste("Filaments loc day",i_p))
-----r
par(mfrow=c(1,2))
-plotFilamentsBox(data, f_np); title(paste("FilBox nn day",i_np))
-plotFilamentsBox(data, f_p); title(paste("FilBox nn day",i_p))
+plotFilamentsBox(data, f_np_n); title(paste("FilBox non-loc day",i_np))
+plotFilamentsBox(data, f_p_n); title(paste("FilBox non-loc day",i_p))
# Generally too few neighbors:
-#plotFilamentsBox(data, f_np2); title(paste("FilBox nn2 day",i_np))
-#plotFilamentsBox(data, f_p2); title(paste("FilBox nn2 day",i_p))
+#plotFilamentsBox(data, f_np_l); title(paste("FilBox loc day",i_np))
+#plotFilamentsBox(data, f_p_l); title(paste("FilBox loc day",i_p))
-----r
par(mfrow=c(1,2))
-plotRelVar(data, f_np); title(paste("StdDev nn day",i_np))
-plotRelVar(data, f_p); title(paste("StdDev nn day",i_p))
+plotRelVar(data, f_np_n); title(paste("StdDev non-loc day",i_np))
+plotRelVar(data, f_p_n); title(paste("StdDev non-loc day",i_p))
-plotRelVar(data, f_np2); title(paste("StdDev nn2 day",i_np))
-plotRelVar(data, f_p2); title(paste("StdDev nn2 day",i_p))
+plotRelVar(data, f_np_l); title(paste("StdDev loc day",i_np))
+plotRelVar(data, f_p_l); title(paste("StdDev loc day",i_p))
# Variabilité globale en rouge ; sur les 60 voisins (+ lendemains) en noir
-----r
par(mfrow=c(1,2))
-plotSimils(p_nn, i_np); title(paste("Weights nn day",i_np))
-plotSimils(p_nn, i_p); title(paste("Weights nn day",i_p))
+plotSimils(p_n, i_np); title(paste("Weights non-loc day",i_np))
+plotSimils(p_n, i_p); title(paste("Weights non-loc day",i_p))
-plotSimils(p_nn2, i_np); title(paste("Weights nn2 day",i_np))
-plotSimils(p_nn2, i_p); title(paste("Weights nn2 day",i_p))
+plotSimils(p_l, i_np); title(paste("Weights loc day",i_np))
+plotSimils(p_l, i_p); title(paste("Weights loc day",i_p))
# - pollué à gauche, + pollué à droite
-----r
-# Fenêtres sélectionnées dans ]0,7] / nn à gauche, nn2 à droite
-p_nn$getParams(i_np)$window
-p_nn$getParams(i_p)$window
+# Fenêtres sélectionnées dans ]0,7] / non-loc à gauche, loc à droite
+p_n$getParams(i_np)$window
+p_n$getParams(i_p)$window
-p_nn2$getParams(i_np)$window
-p_nn2$getParams(i_p)$window
+p_l$getParams(i_np)$window
+p_l$getParams(i_p)$window
% endfor
projects / talweg.git / commitdiff