attempt to fix Bruno code
[talweg.git] / pkg / R / F_Neighbors.R
... / ...
CommitLineData
1#' Neighbors Forecaster
2#'
3#' Predict next serie as a weighted combination of "futures of the past" days,
4#' where days in the past are chosen and weighted according to some similarity measures.
5#'
6#' The main method is \code{predictShape()}, taking arguments data, today, memory,
7#' predict_from, horizon respectively for the dataset (object output of
8#' \code{getData()}), the current index, the data depth (in days), the first predicted
9#' hour and the last predicted hour.
10#' In addition, optional arguments can be passed:
11#' \itemize{
12#' \item local : TRUE (default) to constrain neighbors to be "same days within same
13#' season"
14#' \item simtype : 'endo' for a similarity based on the series only,<cr>
15#' 'exo' for a similarity based on exogenous variables only,<cr>
16#' 'mix' for the product of 'endo' and 'exo',<cr>
17#' 'none' (default) to apply a simple average: no computed weights
18#' \item window : A window for similarities computations; override cross-validation
19#' window estimation.
20#' }
21#' The method is summarized as follows:
22#' \enumerate{
23#' \item Determine N (=20) recent days without missing values, and followed by a
24#' tomorrow also without missing values.
25#' \item Optimize the window parameters (if relevant) on the N chosen days.
26#' \item Considering the optimized window, compute the neighbors (with locality
27#' constraint or not), compute their similarities -- using a gaussian kernel if
28#' simtype != "none" -- and average accordingly the "tomorrows of neigbors" to
29#' obtain the final prediction.
30#' }
31#'
32#' @usage # NeighborsForecaster$new(pjump)
33#'
34#' @docType class
35#' @format R6 class, inherits Forecaster
36#' @aliases F_Neighbors
37#'
38NeighborsForecaster = R6::R6Class("NeighborsForecaster",
39 inherit = Forecaster,
40
41 public = list(
42 predictShape = function(data, today, memory, predict_from, horizon, ...)
43 {
44 # (re)initialize computed parameters
45 private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
46
47 # Do not forecast on days with NAs (TODO: softer condition...)
48 if (any(is.na(data$getSerie(today-1))) ||
49 (predict_from>=2 && any(is.na(data$getSerie(today)[1:(predict_from-1)]))))
50 {
51 return (NA)
52 }
53
54 # Get optional args
55 local = ifelse(hasArg("local"), list(...)$local, TRUE) #same level + season?
56 simtype = ifelse(hasArg("simtype"), list(...)$simtype, "none") #or "endo", or "exo"
57 opera = ifelse(hasArg("opera"), list(...)$opera, FALSE) #operational mode?
58
59 # Determine indices of no-NAs days preceded by no-NAs yerstedays
60 tdays = .getNoNA2(data, max(today-memory,2), ifelse(opera,today-1,data$getSize()))
61 if (!opera)
62 tdays = setdiff(tdays, today) #always exclude current day
63
64 # Shortcut if window is known
65 if (hasArg("window"))
66 {
67 return ( private$.predictShapeAux(data, tdays, today, predict_from, horizon,
68 local, list(...)$window, simtype, opera, TRUE) )
69 }
70
71 # Indices of similar days for cross-validation; TODO: 20 = magic number
72 cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
73 days_in=tdays, operational=opera)
74
75 # Optimize h : h |--> sum of prediction errors on last N "similar" days
76 errorOnLastNdays = function(window, simtype)
77 {
78 error = 0
79 nb_jours = 0
80 for (i in seq_along(cv_days))
81 {
82 # mix_strategy is never used here (simtype != "mix"), therefore left blank
83 prediction = private$.predictShapeAux(data, tdays, cv_days[i], predict_from,
84 horizon, local, window, simtype, opera, FALSE)
85 if (!is.na(prediction[1]))
86 {
87 nb_jours = nb_jours + 1
88 error = error +
89 mean((data$getSerie(cv_days[i])[predict_from:horizon] - prediction)^2)
90 }
91 }
92 return (error / nb_jours)
93 }
94
95 # TODO: 7 == magic number
96 if (simtype=="endo" || simtype=="mix")
97 {
98 best_window_endo = optimize(
99 errorOnLastNdays, c(0,7), simtype="endo")$minimum
100 }
101 if (simtype=="exo" || simtype=="mix")
102 {
103 best_window_exo = optimize(
104 errorOnLastNdays, c(0,7), simtype="exo")$minimum
105 }
106
107 best_window =
108 if (simtype == "endo")
109 best_window_endo
110 else if (simtype == "exo")
111 best_window_exo
112 else if (simtype == "mix")
113 c(best_window_endo,best_window_exo)
114 else #none: value doesn't matter
115 1
116
117 return( private$.predictShapeAux(data, tdays, today, predict_from, horizon, local,
118 best_window, simtype, opera, TRUE) )
119 }
120 ),
121 private = list(
122 # Precondition: "yersteday until predict_from-1" is full (no NAs)
123 .predictShapeAux = function(data, tdays, today, predict_from, horizon, local, window,
124 simtype, opera, final_call)
125 {
126 tdays_cut = tdays[ tdays != today ]
127 if (length(tdays_cut) == 0)
128 return (NA)
129
130 if (local)
131 {
132 # TODO: 60 == magic number
133 tdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
134 days_in=tdays_cut, operational=opera)
135# if (length(tdays) <= 1)
136# return (NA)
137 # TODO: 10 == magic number
138 tdays = .getConstrainedNeighbs(today, data, tdays, min_neighbs=10)
139 if (length(tdays) == 1)
140 {
141 if (final_call)
142 {
143 private$.params$weights <- 1
144 private$.params$indices <- tdays
145 private$.params$window <- 1
146 }
147 return ( data$getSerie(tdays[1])[predict_from:horizon] )
148 }
149 }
150 else
151 tdays = tdays_cut #no conditioning
152
153 if (simtype == "endo" || simtype == "mix")
154 {
155 # Compute endogen similarities using given window
156 window_endo = ifelse(simtype=="mix", window[1], window)
157
158 # Distances from last observed day to selected days in the past
159 distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
160
161 if (local)
162 {
163 max_neighbs = 12 #TODO: 12 = arbitrary number
164 if (length(distances2) > max_neighbs)
165 {
166 ordering <- order(distances2)
167 tdays <- tdays[ ordering[1:max_neighbs] ]
168 distances2 <- distances2[ ordering[1:max_neighbs] ]
169 }
170 }
171
172 simils_endo <- .computeSimils(distances2, window_endo)
173 }
174
175 if (simtype == "exo" || simtype == "mix")
176 {
177 # Compute exogen similarities using given window
178 window_exo = ifelse(simtype=="mix", window[2], window)
179
180 distances2 <- .computeDistsExo(data, today, tdays)
181
182 simils_exo <- .computeSimils(distances2, window_exo)
183 }
184
185 similarities =
186 if (simtype == "exo")
187 simils_exo
188 else if (simtype == "endo")
189 simils_endo
190 else if (simtype == "mix")
191 simils_endo * simils_exo
192 else #none
193 rep(1, length(tdays))
194 similarities = similarities / sum(similarities)
195
196 prediction = rep(0, horizon-predict_from+1)
197 for (i in seq_along(tdays))
198 {
199 prediction = prediction +
200 similarities[i] * data$getSerie(tdays[i])[predict_from:horizon]
201 }
202
203 if (final_call)
204 {
205 private$.params$weights <- similarities
206 private$.params$indices <- tdays
207 private$.params$window <-
208 if (simtype=="endo")
209 window_endo
210 else if (simtype=="exo")
211 window_exo
212 else if (simtype=="mix")
213 c(window_endo,window_exo)
214 else #none
215 1
216 }
217
218 return (prediction)
219 }
220 )
221)
222
223# getConstrainedNeighbs
224#
225# Get indices of neighbors of similar pollution level (among same season + day type).
226#
227# @param today Index of current day
228# @param data Object of class Data
229# @param tdays Current set of "second days" (no-NA pairs)
230# @param min_neighbs Minimum number of points in a neighborhood
231# @param max_neighbs Maximum number of points in a neighborhood
232#
233.getConstrainedNeighbs = function(today, data, tdays, min_neighbs=10)
234{
235 levelToday = data$getLevelHat(today)
236# levelYersteday = data$getLevel(today-1)
237 distances = sapply(tdays, function(i) {
238# sqrt((data$getLevel(i-1)-levelYersteday)^2 + (data$getLevel(i)-levelToday)^2)
239 abs(data$getLevel(i)-levelToday)
240 })
241 #TODO: 1, +1, +3 : magic numbers
242 dist_thresh = 1
243 min_neighbs = min(min_neighbs,length(tdays))
244 repeat
245 {
246 same_pollution = (distances <= dist_thresh)
247 nb_neighbs = sum(same_pollution)
248 if (nb_neighbs >= min_neighbs) #will eventually happen
249 break
250 dist_thresh = dist_thresh + ifelse(dist_thresh>1,3,1)
251 }
252 tdays = tdays[same_pollution]
253# max_neighbs = 12
254# if (nb_neighbs > max_neighbs)
255# {
256# # Keep only max_neighbs closest neighbors
257# tdays = tdays[ order(distances[same_pollution])[1:max_neighbs] ]
258# }
259 tdays
260}
261
262# compute similarities
263#
264# Apply the gaussian kernel on computed squared distances.
265#
266# @param distances2 Squared distances
267# @param window Window parameter for the kernel
268#
269.computeSimils <- function(distances2, window)
270{
271 sd_dist = sd(distances2)
272 if (sd_dist < .25 * sqrt(.Machine$double.eps))
273 {
274# warning("All computed distances are very close: stdev too small")
275 sd_dist = 1 #mostly for tests... FIXME:
276 }
277 exp(-distances2/(sd_dist*window^2))
278}
279
280.computeDistsEndo <- function(data, today, tdays, predict_from)
281{
282 lastSerie = c( data$getSerie(today-1),
283 data$getSerie(today)[if (predict_from>=2) 1:(predict_from-1) else c()] )
284 sapply(tdays, function(i) {
285 delta = lastSerie - c(data$getSerie(i-1),
286 data$getSerie(i)[if (predict_from>=2) 1:(predict_from-1) else c()])
287 sqrt(mean(delta^2))
288 })
289}
290
291.computeDistsExo <- function(data, today, tdays)
292{
293 M = matrix( ncol=1+length(tdays), nrow=1+length(data$getExo(1)) )
294 M[,1] = c( data$getLevelHat(today), as.double(data$getExoHat(today)) )
295 for (i in seq_along(tdays))
296 M[,i+1] = c( data$getLevel(tdays[i]), as.double(data$getExo(tdays[i])) )
297
298 sigma = cov(t(M)) #NOTE: robust covariance is way too slow
299 # TODO: 10 == magic number; more robust way == det, or always ginv()
300 sigma_inv =
301 if (length(tdays) > 10)
302 solve(sigma)
303 else
304 MASS::ginv(sigma)
305
306 # Distances from last observed day to days in the past
307 sapply(seq_along(tdays), function(i) {
308 delta = M[,1] - M[,i+1]
309 delta %*% sigma_inv %*% delta
310 })
311}