projects
/
talweg.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
fix methods, update report generation
[talweg.git]
/
pkg
/
R
/
F_Neighbors.R
diff --git
a/pkg/R/F_Neighbors.R
b/pkg/R/F_Neighbors.R
index
a3d44a3
..
d889a34
100644
(file)
--- a/
pkg/R/F_Neighbors.R
+++ b/
pkg/R/F_Neighbors.R
@@
-31,23
+31,27
@@
NeighborsForecaster = R6::R6Class("NeighborsForecaster",
}
# Indices of similar days for cross-validation; TODO: 45 = magic number
}
# Indices of similar days for cross-validation; TODO: 45 = magic number
- sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
+ sdays = getSimilarDaysIndices(today, data, 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))]
# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
errorOnLastNdays = function(h, kernel, simtype)
{
error = 0
nb_jours = 0
# 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,s
days))
+ for (i in
seq_along(cv_
days))
{
# mix_strategy is never used here (simtype != "mix"), therefore left blank
prediction = private$.predictShapeAux(data,
{
# mix_strategy is never used here (simtype != "mix"), therefore left blank
prediction = private$.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 +
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)
}
}
return (error / nb_jours)
@@
-96,19
+100,16
@@
NeighborsForecaster = R6::R6Class("NeighborsForecaster",
h_endo = ifelse(simtype=="mix", h[1], h)
# Distances from last observed day to days in the past
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$double.eps)
{
sd_dist = sd(distances2)
if (sd_dist < .Machine$double.eps)
{
-
warning("All computed distances are very close: stdev too small")
+
#
warning("All computed distances are very close: stdev too small")
sd_dist = 1 #mostly for tests... FIXME:
}
simils_endo =
sd_dist = 1 #mostly for tests... FIXME:
}
simils_endo =
@@
-133,20
+134,23
@@
NeighborsForecaster = R6::R6Class("NeighborsForecaster",
M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
sigma = cov(M) #NOTE: robust covariance is way too slow
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
# 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)
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")
+
#
warning("All computed distances are very close: stdev too small")
sd_dist = 1 #mostly for tests... FIXME:
}
simils_exo =
sd_dist = 1 #mostly for tests... FIXME:
}
simils_exo =
@@
-171,7
+175,7
@@
NeighborsForecaster = R6::R6Class("NeighborsForecaster",
prediction = rep(0, horizon)
for (i in seq_along(fdays))
prediction = rep(0, horizon)
for (i in seq_along(fdays))
- prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
+ prediction = prediction + similarities[i] * data$get
Centered
Serie(fdays[i]+1)[1:horizon]
prediction = prediction / sum(similarities, na.rm=TRUE)
if (final_call)
prediction = prediction / sum(similarities, na.rm=TRUE)
if (final_call)