Commit | Line | Data |
---|---|---|
e030a6e3 | 1 | #' @include Forecaster.R |
3d69ff21 | 2 | #' |
25b75559 | 3 | #' Neighbors Forecaster |
3d69ff21 | 4 | #' |
25b75559 BA |
5 | #' Predict tomorrow as a weighted combination of "futures of the past" days. |
6 | #' Inherits \code{\link{Forecaster}} | |
7 | NeighborsForecaster = R6::R6Class("NeighborsForecaster", | |
8 | inherit = "Forecaster", | |
9 | ||
10 | public = list( | |
e030a6e3 | 11 | predictShape = function(today, memory, horizon, ...) |
3d69ff21 BA |
12 | { |
13 | # (re)initialize computed parameters | |
14 | params <<- list("weights"=NA, "indices"=NA, "window"=NA) | |
15 | ||
f17665c7 BA |
16 | # Get optional args |
17 | simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo" | |
18 | kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan" | |
19 | if (hasArg(h_window)) | |
20 | return (.predictShapeAux(fdays,today,horizon,list(...)$h_window,kernel,simtype,TRUE)) | |
3d69ff21 | 21 | |
3d69ff21 | 22 | # Determine indices of no-NAs days followed by no-NAs tomorrows |
f17665c7 BA |
23 | first_day = max(today - memory, 1) |
24 | fdays = (first_day:(today-1))[ sapply(first_day:(today-1), function(i) { | |
25 | !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) | |
26 | }) ] | |
3d69ff21 | 27 | |
f17665c7 BA |
28 | # Indices of similar days for cross-validation; TODO: 45 = magic number |
29 | sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE) | |
3d69ff21 BA |
30 | |
31 | # Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days | |
32 | errorOnLastNdays = function(h, kernel, simtype) | |
33 | { | |
34 | error = 0 | |
35 | nb_jours = 0 | |
f17665c7 | 36 | for (i in intersect(fdays,sdays)) |
3d69ff21 | 37 | { |
f17665c7 BA |
38 | # mix_strategy is never used here (simtype != "mix"), therefore left blank |
39 | prediction = .predictShapeAux(fdays, i, horizon, h, kernel, simtype, FALSE) | |
40 | if (!is.na(prediction[1])) | |
3d69ff21 BA |
41 | { |
42 | nb_jours = nb_jours + 1 | |
f17665c7 | 43 | error = error + mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2) |
3d69ff21 BA |
44 | } |
45 | } | |
46 | return (error / nb_jours) | |
47 | } | |
48 | ||
f17665c7 BA |
49 | if (simtype != "endo") |
50 | h_best_exo = optimize(errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum | |
3d69ff21 | 51 | if (simtype != "exo") |
f17665c7 | 52 | h_best_endo = optimize(errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum |
3d69ff21 BA |
53 | |
54 | if (simtype == "endo") | |
f17665c7 | 55 | return (.predictShapeAux(fdays, today, horizon, h_best_endo, kernel, "endo", TRUE)) |
3d69ff21 | 56 | if (simtype == "exo") |
f17665c7 | 57 | return (.predictShapeAux(fdays, today, horizon, h_best_exo, kernel, "exo", TRUE)) |
3d69ff21 BA |
58 | if (simtype == "mix") |
59 | { | |
f17665c7 BA |
60 | h_best_mix = c(h_best_endo,h_best_exo) |
61 | return (.predictShapeAux(fdays, today, horizon, h_best_mix, kernel, "mix", TRUE)) | |
3d69ff21 | 62 | } |
25b75559 BA |
63 | } |
64 | ), | |
65 | private = list( | |
3d69ff21 | 66 | # Precondition: "today" is full (no NAs) |
f17665c7 | 67 | .predictShapeAux = function(fdays, today, horizon, h, kernel, simtype, final_call) |
3d69ff21 | 68 | { |
f17665c7 | 69 | fdays = fdays[ fdays < today ] |
3d69ff21 | 70 | # TODO: 3 = magic number |
f17665c7 | 71 | if (length(fdays) < 3) |
3d69ff21 BA |
72 | return (NA) |
73 | ||
74 | if (simtype != "exo") | |
75 | { | |
76 | h_endo = ifelse(simtype=="mix", h[1], h) | |
77 | ||
78 | # Distances from last observed day to days in the past | |
f17665c7 BA |
79 | distances2 = rep(NA, length(fdays)) |
80 | for (i in seq_along(fdays)) | |
3d69ff21 | 81 | { |
25b75559 | 82 | delta = data$getCenteredSerie(today) - data$getCenteredSerie(fdays[i]) |
3d69ff21 BA |
83 | # Require at least half of non-NA common values to compute the distance |
84 | if (sum(is.na(delta)) <= 0) #length(delta)/2) | |
85 | distances2[i] = mean(delta^2) #, na.rm=TRUE) | |
86 | } | |
87 | ||
88 | sd_dist = sd(distances2) | |
99f83c9a BA |
89 | if (sd_dist < .Machine$double.eps) |
90 | sd_dist = 1 #mostly for tests... FIXME: | |
3d69ff21 | 91 | simils_endo = |
99f83c9a | 92 | if (kernel=="Gauss") |
3d69ff21 | 93 | exp(-distances2/(sd_dist*h_endo^2)) |
99f83c9a | 94 | else { #Epanechnikov |
3d69ff21 BA |
95 | u = 1 - distances2/(sd_dist*h_endo^2) |
96 | u[abs(u)>1] = 0. | |
97 | u | |
98 | } | |
99 | } | |
100 | ||
101 | if (simtype != "endo") | |
102 | { | |
103 | h_exo = ifelse(simtype=="mix", h[2], h) | |
104 | ||
25b75559 BA |
105 | M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) ) |
106 | M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) ) | |
f17665c7 | 107 | for (i in seq_along(fdays)) |
25b75559 | 108 | M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) ) |
3d69ff21 BA |
109 | |
110 | sigma = cov(M) #NOTE: robust covariance is way too slow | |
613a986f | 111 | sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed? |
3d69ff21 BA |
112 | |
113 | # Distances from last observed day to days in the past | |
114 | distances2 = rep(NA, nrow(M)-1) | |
115 | for (i in 2:nrow(M)) | |
116 | { | |
117 | delta = M[1,] - M[i,] | |
118 | distances2[i-1] = delta %*% sigma_inv %*% delta | |
119 | } | |
120 | ||
121 | sd_dist = sd(distances2) | |
122 | simils_exo = | |
f17665c7 | 123 | if (kernel=="Gauss") |
3d69ff21 | 124 | exp(-distances2/(sd_dist*h_exo^2)) |
f17665c7 | 125 | else { #Epanechnikov |
3d69ff21 BA |
126 | u = 1 - distances2/(sd_dist*h_exo^2) |
127 | u[abs(u)>1] = 0. | |
128 | u | |
129 | } | |
130 | } | |
131 | ||
3d69ff21 | 132 | similarities = |
f17665c7 | 133 | if (simtype == "exo") |
3d69ff21 | 134 | simils_exo |
f17665c7 BA |
135 | else if (simtype == "endo") |
136 | simils_endo | |
137 | else #mix | |
138 | simils_endo * simils_exo | |
3d69ff21 BA |
139 | |
140 | prediction = rep(0, horizon) | |
141 | for (i in seq_along(fdays_indices)) | |
25b75559 | 142 | prediction = prediction + similarities[i] * data$getSerie(fdays_indices[i]+1)[1:horizon] |
3d69ff21 | 143 | prediction = prediction / sum(similarities, na.rm=TRUE) |
99f83c9a | 144 | |
3d69ff21 BA |
145 | if (final_call) |
146 | { | |
147 | params$weights <<- similarities | |
148 | params$indices <<- fdays_indices | |
149 | params$window <<- | |
150 | if (simtype=="endo") { | |
151 | h_endo | |
152 | } else if (simtype=="exo") { | |
153 | h_exo | |
f17665c7 | 154 | } else { #mix |
3d69ff21 BA |
155 | c(h_endo,h_exo) |
156 | } | |
157 | } | |
99f83c9a | 158 | |
3d69ff21 BA |
159 | return (prediction) |
160 | } | |
161 | ) | |
162 | ) |