c55291aa996838a2a02535725f72c4fb8709b922
[talweg.git] / pkg / R / F_Neighbors.R
1 #' @include Forecaster.R
2 #'
3 #' Neighbors Forecaster
4 #'
5 #' Predict tomorrow as a weighted combination of "futures of the past" days.
6 #' Inherits \code{\link{Forecaster}}
7 #'
8 NeighborsForecaster = R6::R6Class("NeighborsForecaster",
9 inherit = Forecaster,
10
11 public = list(
12 predictShape = function(data, today, memory, horizon, ...)
13 {
14 # (re)initialize computed parameters
15 private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
16
17 # Do not forecast on days with NAs (TODO: softer condition...)
18 if (any(is.na(data$getCenteredSerie(today))))
19 return (NA)
20
21 # Determine indices of no-NAs days followed by no-NAs tomorrows
22 fdays = getNoNA2(data, max(today-memory,1), today-1)
23
24 # Get optional args
25 local = ifelse(hasArg("local"), list(...)$local, FALSE) #same level + season?
26 simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
27 if (hasArg("window"))
28 {
29 return ( private$.predictShapeAux(data,
30 fdays, today, horizon, local, list(...)$window, simtype, TRUE) )
31 }
32
33 # Indices of similar days for cross-validation; TODO: 20 = magic number
34 cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
35 days_in=fdays)
36
37 # Optimize h : h |--> sum of prediction errors on last 45 "similar" days
38 errorOnLastNdays = function(window, simtype)
39 {
40 error = 0
41 nb_jours = 0
42 for (i in seq_along(cv_days))
43 {
44 # mix_strategy is never used here (simtype != "mix"), therefore left blank
45 prediction = private$.predictShapeAux(data, fdays, cv_days[i], horizon, local,
46 window, simtype, FALSE)
47 if (!is.na(prediction[1]))
48 {
49 nb_jours = nb_jours + 1
50 error = error +
51 mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
52 }
53 }
54 return (error / nb_jours)
55 }
56
57 if (simtype != "endo")
58 {
59 best_window_exo = optimize(
60 errorOnLastNdays, c(0,7), simtype="exo")$minimum
61 }
62 if (simtype != "exo")
63 {
64 best_window_endo = optimize(
65 errorOnLastNdays, c(0,7), simtype="endo")$minimum
66 }
67
68 if (simtype == "endo")
69 {
70 return (private$.predictShapeAux(data, fdays, today, horizon, local,
71 best_window_endo, "endo", TRUE))
72 }
73 if (simtype == "exo")
74 {
75 return (private$.predictShapeAux(data, fdays, today, horizon, local,
76 best_window_exo, "exo", TRUE))
77 }
78 if (simtype == "mix")
79 {
80 return(private$.predictShapeAux(data, fdays, today, horizon, local,
81 c(best_window_endo,best_window_exo), "mix", TRUE))
82 }
83 }
84 ),
85 private = list(
86 # Precondition: "today" is full (no NAs)
87 .predictShapeAux = function(data, fdays, today, horizon, local, window, simtype,
88 final_call)
89 {
90 fdays_cut = fdays[ fdays < today ]
91 if (length(fdays_cut) <= 1)
92 return (NA)
93
94 if (local)
95 {
96 # Neighbors: days in "same season"; TODO: 60 == magic number...
97 fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
98 days_in=fdays_cut)
99 if (length(fdays) <= 1)
100 return (NA)
101 levelToday = data$getLevel(today)
102 distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
103 #TODO: 2, 3, 5, 10 magic numbers here...
104 dist_thresh = 2
105 min_neighbs = min(3,length(fdays))
106 repeat
107 {
108 same_pollution = (distances <= dist_thresh)
109 nb_neighbs = sum(same_pollution)
110 if (nb_neighbs >= min_neighbs) #will eventually happen
111 break
112 dist_thresh = dist_thresh + 3
113 }
114 fdays = fdays[same_pollution]
115 max_neighbs = 10
116 if (nb_neighbs > max_neighbs)
117 {
118 # Keep only max_neighbs closest neighbors
119 fdays = fdays[
120 sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
121 }
122 if (length(fdays) == 1) #the other extreme...
123 {
124 if (final_call)
125 {
126 private$.params$weights <- 1
127 private$.params$indices <- fdays
128 private$.params$window <- 1
129 }
130 return ( data$getSerie(fdays[1])[1:horizon] ) #what else?!
131 }
132 }
133 else
134 fdays = fdays_cut #no conditioning
135
136 if (simtype != "exo")
137 {
138 # Compute endogen similarities using given window
139 window_endo = ifelse(simtype=="mix", window[1], window)
140
141 # Distances from last observed day to days in the past
142 serieToday = data$getSerie(today)
143 distances2 = sapply(fdays, function(i) {
144 delta = serieToday - data$getSerie(i)
145 mean(delta^2)
146 })
147
148 sd_dist = sd(distances2)
149 if (sd_dist < .25 * sqrt(.Machine$double.eps))
150 {
151 # warning("All computed distances are very close: stdev too small")
152 sd_dist = 1 #mostly for tests... FIXME:
153 }
154 simils_endo = exp(-distances2/(sd_dist*window_endo^2))
155 }
156
157 if (simtype != "endo")
158 {
159 # Compute exogen similarities using given window
160 h_exo = ifelse(simtype=="mix", window[2], window)
161
162 M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
163 M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
164 for (i in seq_along(fdays))
165 M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
166
167 sigma = cov(M) #NOTE: robust covariance is way too slow
168 # TODO: 10 == magic number; more robust way == det, or always ginv()
169 sigma_inv =
170 if (length(fdays) > 10)
171 solve(sigma)
172 else
173 MASS::ginv(sigma)
174
175 # Distances from last observed day to days in the past
176 distances2 = sapply(seq_along(fdays), function(i) {
177 delta = M[1,] - M[i+1,]
178 delta %*% sigma_inv %*% delta
179 })
180
181 sd_dist = sd(distances2)
182 if (sd_dist < .25 * sqrt(.Machine$double.eps))
183 {
184 # warning("All computed distances are very close: stdev too small")
185 sd_dist = 1 #mostly for tests... FIXME:
186 }
187 simils_exo = exp(-distances2/(sd_dist*window_exo^2))
188 }
189
190 similarities =
191 if (simtype == "exo")
192 simils_exo
193 else if (simtype == "endo")
194 simils_endo
195 else #mix
196 simils_endo * simils_exo
197 similarities = similarities / sum(similarities)
198
199 prediction = rep(0, horizon)
200 for (i in seq_along(fdays))
201 prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
202
203 if (final_call)
204 {
205 private$.params$weights <- similarities
206 private$.params$indices <- fdays
207 private$.params$window <-
208 if (simtype=="endo")
209 window_endo
210 else if (simtype=="exo")
211 window_exo
212 else #mix
213 c(window_endo,window_exo)
214 }
215
216 return (prediction)
217 }
218 )
219 )