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(...)$local, TRUE) #same level + season?
  26             simtype = ifelse(hasArg("simtype"), list(...)$simtype, "none") #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 N "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             # TODO: 7 == magic number
  58             if (simtype != "endo")
  59             {
  60                 best_window_exo = optimize(
  61                     errorOnLastNdays, c(0,7), simtype="exo")$minimum
  62             }
  63             if (simtype != "exo")
  64             {
  65                 best_window_endo = optimize(
  66                     errorOnLastNdays, c(0,7), simtype="endo")$minimum
  67             }
  68
  69             if (simtype == "endo")
  70             {
  71                 return (private$.predictShapeAux(data, fdays, today, horizon, local,
  72                     best_window_endo, "endo", TRUE))
  73             }
  74             if (simtype == "exo")
  75             {
  76                 return (private$.predictShapeAux(data, fdays, today, horizon, local,
  77                     best_window_exo, "exo", TRUE))
  78             }
  79             if (simtype == "mix")
  80             {
  81                 return(private$.predictShapeAux(data, fdays, today, horizon, local,
  82                     c(best_window_endo,best_window_exo), "mix", TRUE))
  83             }
  84         }
  85     ),
  86     private = list(
  87         # Precondition: "today" is full (no NAs)
  88         .predictShapeAux = function(data, fdays, today, horizon, local, window, simtype,
  89             final_call)
  90         {
  91             fdays_cut = fdays[ fdays < today ]
  92             if (length(fdays_cut) <= 1)
  93                 return (NA)
  94
  95             if (local)
  96             {
  97                 # Neighbors: days in "same season"; TODO: 60 == magic number...
  98                 fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
  99                     days_in=fdays_cut)
 100                 if (length(fdays) <= 1)
 101                     return (NA)
 102                 levelToday = data$getLevel(today)
 103                 distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
 104                 #TODO: 2, 10, 3, 12 magic numbers here...
 105                 dist_thresh = 2
 106                 min_neighbs = min(10,length(fdays))
 107                 repeat
 108                 {
 109                     same_pollution = (distances <= dist_thresh)
 110                     nb_neighbs = sum(same_pollution)
 111                     if (nb_neighbs >= min_neighbs) #will eventually happen
 112                         break
 113                     dist_thresh = dist_thresh + 3
 114                 }
 115                 fdays = fdays[same_pollution]
 116                 max_neighbs = 12
 117                 if (nb_neighbs > max_neighbs)
 118                 {
 119                     # Keep only max_neighbs closest neighbors
 120                     fdays = fdays[
 121                         sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
 122                 }
 123                 if (length(fdays) == 1) #the other extreme...
 124                 {
 125                     if (final_call)
 126                     {
 127                         private$.params$weights <- 1
 128                         private$.params$indices <- fdays
 129                         private$.params$window <- 1
 130                     }
 131                     return ( data$getSerie(fdays[1])[1:horizon] ) #what else?!
 132                 }
 133             }
 134             else
 135                 fdays = fdays_cut #no conditioning
 136
 137             if (simtype == "endo" || simtype == "mix")
 138             {
 139                 # Compute endogen similarities using given window
 140                 window_endo = ifelse(simtype=="mix", window[1], window)
 141
 142                 # Distances from last observed day to days in the past
 143                 serieToday = data$getSerie(today)
 144                 distances2 = sapply(fdays, function(i) {
 145                     delta = serieToday - data$getSerie(i)
 146                     mean(delta^2)
 147                 })
 148
 149                 sd_dist = sd(distances2)
 150                 if (sd_dist < .25 * sqrt(.Machine$double.eps))
 151                 {
 152 #                   warning("All computed distances are very close: stdev too small")
 153                     sd_dist = 1 #mostly for tests... FIXME:
 154                 }
 155                 simils_endo = exp(-distances2/(sd_dist*window_endo^2))
 156             }
 157
 158             if (simtype == "exo" || simtype == "mix")
 159             {
 160                 # Compute exogen similarities using given window
 161                 window_exo = ifelse(simtype=="mix", window[2], window)
 162
 163                 M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
 164                 M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
 165                 for (i in seq_along(fdays))
 166                     M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
 167
 168                 sigma = cov(M) #NOTE: robust covariance is way too slow
 169                 # TODO: 10 == magic number; more robust way == det, or always ginv()
 170                 sigma_inv =
 171                     if (length(fdays) > 10)
 172                         solve(sigma)
 173                     else
 174                         MASS::ginv(sigma)
 175
 176                 # Distances from last observed day to days in the past
 177                 distances2 = sapply(seq_along(fdays), function(i) {
 178                     delta = M[1,] - M[i+1,]
 179                     delta %*% sigma_inv %*% delta
 180                 })
 181
 182                 sd_dist = sd(distances2)
 183                 if (sd_dist < .25 * sqrt(.Machine$double.eps))
 184                 {
 185 #                   warning("All computed distances are very close: stdev too small")
 186                     sd_dist = 1 #mostly for tests... FIXME:
 187                 }
 188                 simils_exo = exp(-distances2/(sd_dist*window_exo^2))
 189             }
 190
 191             similarities =
 192                 if (simtype == "exo")
 193                     simils_exo
 194                 else if (simtype == "endo")
 195                     simils_endo
 196                 else if (simtype == "mix")
 197                     simils_endo * simils_exo
 198                 else #none
 199                     rep(1, length(fdays))
 200             similarities = similarities / sum(similarities)
 201
 202             prediction = rep(0, horizon)
 203             for (i in seq_along(fdays))
 204                 prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
 205
 206             if (final_call)
 207             {
 208                 private$.params$weights <- similarities
 209                 private$.params$indices <- fdays
 210                 private$.params$window <-
 211                     if (simtype=="endo")
 212                         window_endo
 213                     else if (simtype=="exo")
 214                         window_exo
 215                     else #mix
 216                         c(window_endo,window_exo)
 217             }
 218
 219             return (prediction)
 220         }
 221     )
 222 )