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", | |
a66a84b5 | 8 | inherit = Forecaster, |
25b75559 BA |
9 | |
10 | public = list( | |
98e958ca | 11 | predictShape = function(data, today, memory, horizon, ...) |
3d69ff21 BA |
12 | { |
13 | # (re)initialize computed parameters | |
a66a84b5 | 14 | private$.params <- list("weights"=NA, "indices"=NA, "window"=NA) |
3d69ff21 | 15 | |
af3b84f4 | 16 | # Determine indices of no-NAs days followed by no-NAs tomorrows |
98e958ca | 17 | fdays = getNoNA2(data, max(today-memory,1), today-1) |
af3b84f4 | 18 | |
f17665c7 BA |
19 | # Get optional args |
20 | simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo" | |
21 | kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan" | |
22 | if (hasArg(h_window)) | |
a66a84b5 | 23 | { |
98e958ca | 24 | return ( private$.predictShapeAux(data, |
a66a84b5 BA |
25 | fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) ) |
26 | } | |
3d69ff21 | 27 | |
f17665c7 BA |
28 | # Indices of similar days for cross-validation; TODO: 45 = magic number |
29 | sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE) | |
3d69ff21 BA |
30 | |
31 | # Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days | |
32 | errorOnLastNdays = function(h, kernel, simtype) | |
33 | { | |
34 | error = 0 | |
35 | nb_jours = 0 | |
f17665c7 | 36 | for (i in intersect(fdays,sdays)) |
3d69ff21 | 37 | { |
f17665c7 | 38 | # mix_strategy is never used here (simtype != "mix"), therefore left blank |
98e958ca BA |
39 | prediction = private$.predictShapeAux(data, |
40 | fdays, i, horizon, h, kernel, simtype, FALSE) | |
f17665c7 | 41 | if (!is.na(prediction[1])) |
3d69ff21 BA |
42 | { |
43 | nb_jours = nb_jours + 1 | |
af3b84f4 | 44 | error = error + |
98e958ca | 45 | mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2) |
3d69ff21 BA |
46 | } |
47 | } | |
48 | return (error / nb_jours) | |
49 | } | |
50 | ||
f17665c7 | 51 | if (simtype != "endo") |
af3b84f4 BA |
52 | { |
53 | h_best_exo = optimize( | |
54 | errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum | |
55 | } | |
3d69ff21 | 56 | if (simtype != "exo") |
af3b84f4 BA |
57 | { |
58 | h_best_endo = optimize( | |
59 | errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum | |
60 | } | |
3d69ff21 BA |
61 | |
62 | if (simtype == "endo") | |
af3b84f4 | 63 | { |
98e958ca | 64 | return (private$.predictShapeAux(data, |
af3b84f4 BA |
65 | fdays, today, horizon, h_best_endo, kernel, "endo", TRUE)) |
66 | } | |
3d69ff21 | 67 | if (simtype == "exo") |
af3b84f4 | 68 | { |
98e958ca | 69 | return (private$.predictShapeAux(data, |
af3b84f4 BA |
70 | fdays, today, horizon, h_best_exo, kernel, "exo", TRUE)) |
71 | } | |
3d69ff21 BA |
72 | if (simtype == "mix") |
73 | { | |
f17665c7 | 74 | h_best_mix = c(h_best_endo,h_best_exo) |
98e958ca | 75 | return(private$.predictShapeAux(data, |
af3b84f4 | 76 | fdays, today, horizon, h_best_mix, kernel, "mix", TRUE)) |
3d69ff21 | 77 | } |
25b75559 BA |
78 | } |
79 | ), | |
80 | private = list( | |
3d69ff21 | 81 | # Precondition: "today" is full (no NAs) |
98e958ca | 82 | .predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call) |
3d69ff21 | 83 | { |
f17665c7 | 84 | fdays = fdays[ fdays < today ] |
3d69ff21 | 85 | # TODO: 3 = magic number |
f17665c7 | 86 | if (length(fdays) < 3) |
3d69ff21 BA |
87 | return (NA) |
88 | ||
89 | if (simtype != "exo") | |
90 | { | |
91 | h_endo = ifelse(simtype=="mix", h[1], h) | |
92 | ||
93 | # Distances from last observed day to days in the past | |
f17665c7 BA |
94 | distances2 = rep(NA, length(fdays)) |
95 | for (i in seq_along(fdays)) | |
3d69ff21 | 96 | { |
25b75559 | 97 | delta = data$getCenteredSerie(today) - data$getCenteredSerie(fdays[i]) |
3d69ff21 BA |
98 | # Require at least half of non-NA common values to compute the distance |
99 | if (sum(is.na(delta)) <= 0) #length(delta)/2) | |
100 | distances2[i] = mean(delta^2) #, na.rm=TRUE) | |
101 | } | |
102 | ||
103 | sd_dist = sd(distances2) | |
99f83c9a BA |
104 | if (sd_dist < .Machine$double.eps) |
105 | sd_dist = 1 #mostly for tests... FIXME: | |
3d69ff21 | 106 | simils_endo = |
99f83c9a | 107 | if (kernel=="Gauss") |
3d69ff21 | 108 | exp(-distances2/(sd_dist*h_endo^2)) |
99f83c9a | 109 | else { #Epanechnikov |
3d69ff21 BA |
110 | u = 1 - distances2/(sd_dist*h_endo^2) |
111 | u[abs(u)>1] = 0. | |
112 | u | |
113 | } | |
114 | } | |
115 | ||
116 | if (simtype != "endo") | |
117 | { | |
118 | h_exo = ifelse(simtype=="mix", h[2], h) | |
119 | ||
25b75559 BA |
120 | M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) ) |
121 | M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) ) | |
f17665c7 | 122 | for (i in seq_along(fdays)) |
25b75559 | 123 | M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) ) |
3d69ff21 BA |
124 | |
125 | sigma = cov(M) #NOTE: robust covariance is way too slow | |
613a986f | 126 | sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed? |
3d69ff21 BA |
127 | |
128 | # Distances from last observed day to days in the past | |
129 | distances2 = rep(NA, nrow(M)-1) | |
130 | for (i in 2:nrow(M)) | |
131 | { | |
132 | delta = M[1,] - M[i,] | |
133 | distances2[i-1] = delta %*% sigma_inv %*% delta | |
134 | } | |
135 | ||
136 | sd_dist = sd(distances2) | |
137 | simils_exo = | |
f17665c7 | 138 | if (kernel=="Gauss") |
3d69ff21 | 139 | exp(-distances2/(sd_dist*h_exo^2)) |
f17665c7 | 140 | else { #Epanechnikov |
3d69ff21 BA |
141 | u = 1 - distances2/(sd_dist*h_exo^2) |
142 | u[abs(u)>1] = 0. | |
143 | u | |
144 | } | |
145 | } | |
146 | ||
3d69ff21 | 147 | similarities = |
f17665c7 | 148 | if (simtype == "exo") |
3d69ff21 | 149 | simils_exo |
f17665c7 BA |
150 | else if (simtype == "endo") |
151 | simils_endo | |
152 | else #mix | |
153 | simils_endo * simils_exo | |
3d69ff21 BA |
154 | |
155 | prediction = rep(0, horizon) | |
a66a84b5 BA |
156 | for (i in seq_along(fdays)) |
157 | prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon] | |
3d69ff21 | 158 | prediction = prediction / sum(similarities, na.rm=TRUE) |
99f83c9a | 159 | |
3d69ff21 BA |
160 | if (final_call) |
161 | { | |
a66a84b5 BA |
162 | private$.params$weights <- similarities |
163 | private$.params$indices <- fdays | |
164 | private$.params$window <- | |
3d69ff21 BA |
165 | if (simtype=="endo") { |
166 | h_endo | |
167 | } else if (simtype=="exo") { | |
168 | h_exo | |
f17665c7 | 169 | } else { #mix |
3d69ff21 BA |
170 | c(h_endo,h_exo) |
171 | } | |
172 | } | |
99f83c9a | 173 | |
3d69ff21 BA |
174 | return (prediction) |
175 | } | |
176 | ) | |
177 | ) |