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}} | |
546b0cb6 | 7 | #' |
25b75559 | 8 | NeighborsForecaster = R6::R6Class("NeighborsForecaster", |
a66a84b5 | 9 | inherit = Forecaster, |
25b75559 BA |
10 | |
11 | public = list( | |
98e958ca | 12 | predictShape = function(data, today, memory, horizon, ...) |
3d69ff21 BA |
13 | { |
14 | # (re)initialize computed parameters | |
a66a84b5 | 15 | private$.params <- list("weights"=NA, "indices"=NA, "window"=NA) |
3d69ff21 | 16 | |
a5a3a294 BA |
17 | # Do not forecast on days with NAs (TODO: softer condition...) |
18 | if (any(is.na(data$getCenteredSerie(today)))) | |
19 | return (NA) | |
20 | ||
af3b84f4 | 21 | # Determine indices of no-NAs days followed by no-NAs tomorrows |
98e958ca | 22 | fdays = getNoNA2(data, max(today-memory,1), today-1) |
af3b84f4 | 23 | |
f17665c7 | 24 | # Get optional args |
445e7bbc BA |
25 | local = ifelse(hasArg("local"), list(...)$local, TRUE) #same level + season? |
26 | simtype = ifelse(hasArg("simtype"), list(...)$simtype, "none") #or "endo", or "exo" | |
aa059de7 | 27 | if (hasArg("window")) |
a66a84b5 | 28 | { |
98e958ca | 29 | return ( private$.predictShapeAux(data, |
aa059de7 | 30 | fdays, today, horizon, local, list(...)$window, simtype, TRUE) ) |
a66a84b5 | 31 | } |
3d69ff21 | 32 | |
6774e53d | 33 | # Indices of similar days for cross-validation; TODO: 20 = magic number |
aa059de7 BA |
34 | cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, |
35 | days_in=fdays) | |
5e838b3e | 36 | |
445e7bbc | 37 | # Optimize h : h |--> sum of prediction errors on last N "similar" days |
aa059de7 | 38 | errorOnLastNdays = function(window, simtype) |
3d69ff21 BA |
39 | { |
40 | error = 0 | |
41 | nb_jours = 0 | |
5e838b3e | 42 | for (i in seq_along(cv_days)) |
3d69ff21 | 43 | { |
f17665c7 | 44 | # mix_strategy is never used here (simtype != "mix"), therefore left blank |
aa059de7 BA |
45 | prediction = private$.predictShapeAux(data, fdays, cv_days[i], horizon, local, |
46 | window, simtype, FALSE) | |
f17665c7 | 47 | if (!is.na(prediction[1])) |
3d69ff21 BA |
48 | { |
49 | nb_jours = nb_jours + 1 | |
af3b84f4 | 50 | error = error + |
aa059de7 | 51 | mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2) |
3d69ff21 BA |
52 | } |
53 | } | |
54 | return (error / nb_jours) | |
55 | } | |
56 | ||
445e7bbc | 57 | # TODO: 7 == magic number |
eef54517 | 58 | if (simtype=="endo" || simtype=="mix") |
af3b84f4 | 59 | { |
aa059de7 BA |
60 | best_window_endo = optimize( |
61 | errorOnLastNdays, c(0,7), simtype="endo")$minimum | |
af3b84f4 | 62 | } |
eef54517 | 63 | if (simtype=="exo" || simtype=="mix") |
af3b84f4 | 64 | { |
eef54517 BA |
65 | best_window_exo = optimize( |
66 | errorOnLastNdays, c(0,7), simtype="exo")$minimum | |
3d69ff21 | 67 | } |
eef54517 BA |
68 | |
69 | best_window = | |
70 | if (simtype == "endo") | |
71 | best_window_endo | |
72 | else if (simtype == "exo") | |
73 | best_window_exo | |
74 | else if (simtype == "mix") | |
75 | c(best_window_endo,best_window_exo) | |
76 | else #none: value doesn't matter | |
77 | 1 | |
78 | ||
79 | return(private$.predictShapeAux(data, fdays, today, horizon, local, | |
80 | best_window, simtype, TRUE)) | |
25b75559 BA |
81 | } |
82 | ), | |
83 | private = list( | |
3d69ff21 | 84 | # Precondition: "today" is full (no NAs) |
aa059de7 BA |
85 | .predictShapeAux = function(data, fdays, today, horizon, local, window, simtype, |
86 | final_call) | |
3d69ff21 | 87 | { |
aa059de7 BA |
88 | fdays_cut = fdays[ fdays < today ] |
89 | if (length(fdays_cut) <= 1) | |
3d69ff21 BA |
90 | return (NA) |
91 | ||
aa059de7 BA |
92 | if (local) |
93 | { | |
94 | # Neighbors: days in "same season"; TODO: 60 == magic number... | |
95 | fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE, | |
96 | days_in=fdays_cut) | |
97 | if (length(fdays) <= 1) | |
98 | return (NA) | |
99 | levelToday = data$getLevel(today) | |
100 | distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday)) | |
445e7bbc | 101 | #TODO: 2, 10, 3, 12 magic numbers here... |
aa059de7 | 102 | dist_thresh = 2 |
445e7bbc | 103 | min_neighbs = min(10,length(fdays)) |
aa059de7 BA |
104 | repeat |
105 | { | |
106 | same_pollution = (distances <= dist_thresh) | |
107 | nb_neighbs = sum(same_pollution) | |
108 | if (nb_neighbs >= min_neighbs) #will eventually happen | |
109 | break | |
110 | dist_thresh = dist_thresh + 3 | |
111 | } | |
112 | fdays = fdays[same_pollution] | |
445e7bbc | 113 | max_neighbs = 12 |
aa059de7 BA |
114 | if (nb_neighbs > max_neighbs) |
115 | { | |
116 | # Keep only max_neighbs closest neighbors | |
117 | fdays = fdays[ | |
118 | sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ] | |
119 | } | |
120 | if (length(fdays) == 1) #the other extreme... | |
121 | { | |
122 | if (final_call) | |
123 | { | |
124 | private$.params$weights <- 1 | |
125 | private$.params$indices <- fdays | |
126 | private$.params$window <- 1 | |
127 | } | |
128 | return ( data$getSerie(fdays[1])[1:horizon] ) #what else?! | |
129 | } | |
130 | } | |
131 | else | |
132 | fdays = fdays_cut #no conditioning | |
133 | ||
445e7bbc | 134 | if (simtype == "endo" || simtype == "mix") |
3d69ff21 | 135 | { |
aa059de7 BA |
136 | # Compute endogen similarities using given window |
137 | window_endo = ifelse(simtype=="mix", window[1], window) | |
3d69ff21 BA |
138 | |
139 | # Distances from last observed day to days in the past | |
5e838b3e BA |
140 | serieToday = data$getSerie(today) |
141 | distances2 = sapply(fdays, function(i) { | |
142 | delta = serieToday - data$getSerie(i) | |
143 | mean(delta^2) | |
144 | }) | |
3d69ff21 BA |
145 | |
146 | sd_dist = sd(distances2) | |
aa059de7 | 147 | if (sd_dist < .25 * sqrt(.Machine$double.eps)) |
546b0cb6 | 148 | { |
fa5b7bfc | 149 | # warning("All computed distances are very close: stdev too small") |
99f83c9a | 150 | sd_dist = 1 #mostly for tests... FIXME: |
546b0cb6 | 151 | } |
aa059de7 | 152 | simils_endo = exp(-distances2/(sd_dist*window_endo^2)) |
3d69ff21 BA |
153 | } |
154 | ||
445e7bbc | 155 | if (simtype == "exo" || simtype == "mix") |
3d69ff21 | 156 | { |
aa059de7 | 157 | # Compute exogen similarities using given window |
445e7bbc | 158 | window_exo = ifelse(simtype=="mix", window[2], window) |
3d69ff21 | 159 | |
25b75559 BA |
160 | M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) ) |
161 | M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) ) | |
f17665c7 | 162 | for (i in seq_along(fdays)) |
25b75559 | 163 | M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) ) |
3d69ff21 BA |
164 | |
165 | sigma = cov(M) #NOTE: robust covariance is way too slow | |
ee8b1b4e BA |
166 | # TODO: 10 == magic number; more robust way == det, or always ginv() |
167 | sigma_inv = | |
168 | if (length(fdays) > 10) | |
169 | solve(sigma) | |
170 | else | |
171 | MASS::ginv(sigma) | |
3d69ff21 BA |
172 | |
173 | # Distances from last observed day to days in the past | |
5e838b3e BA |
174 | distances2 = sapply(seq_along(fdays), function(i) { |
175 | delta = M[1,] - M[i+1,] | |
176 | delta %*% sigma_inv %*% delta | |
177 | }) | |
3d69ff21 BA |
178 | |
179 | sd_dist = sd(distances2) | |
ee8b1b4e | 180 | if (sd_dist < .25 * sqrt(.Machine$double.eps)) |
546b0cb6 | 181 | { |
fa5b7bfc | 182 | # warning("All computed distances are very close: stdev too small") |
546b0cb6 BA |
183 | sd_dist = 1 #mostly for tests... FIXME: |
184 | } | |
aa059de7 | 185 | simils_exo = exp(-distances2/(sd_dist*window_exo^2)) |
3d69ff21 BA |
186 | } |
187 | ||
3d69ff21 | 188 | similarities = |
f17665c7 | 189 | if (simtype == "exo") |
3d69ff21 | 190 | simils_exo |
f17665c7 BA |
191 | else if (simtype == "endo") |
192 | simils_endo | |
445e7bbc | 193 | else if (simtype == "mix") |
f17665c7 | 194 | simils_endo * simils_exo |
445e7bbc BA |
195 | else #none |
196 | rep(1, length(fdays)) | |
ea5c7e56 | 197 | similarities = similarities / sum(similarities) |
3d69ff21 BA |
198 | |
199 | prediction = rep(0, horizon) | |
a66a84b5 | 200 | for (i in seq_along(fdays)) |
aa059de7 | 201 | prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon] |
99f83c9a | 202 | |
3d69ff21 BA |
203 | if (final_call) |
204 | { | |
a66a84b5 BA |
205 | private$.params$weights <- similarities |
206 | private$.params$indices <- fdays | |
207 | private$.params$window <- | |
546b0cb6 | 208 | if (simtype=="endo") |
aa059de7 | 209 | window_endo |
546b0cb6 | 210 | else if (simtype=="exo") |
aa059de7 | 211 | window_exo |
eef54517 | 212 | else if (simtype=="mix") |
aa059de7 | 213 | c(window_endo,window_exo) |
eef54517 BA |
214 | else #none |
215 | 1 | |
3d69ff21 | 216 | } |
99f83c9a | 217 | |
3d69ff21 BA |
218 | return (prediction) |
219 | } | |
220 | ) | |
221 | ) |