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             simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
  26             kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
  27             if (hasArg(h_window))
  28             {
  29                 return ( private$.predictShapeAux(data,
  30                     fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
  31             }
  32
  33             # Indices of similar days for cross-validation; TODO: 45 = magic number
  34             sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
  35
  36             # Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
  37             errorOnLastNdays = function(h, kernel, simtype)
  38             {
  39                 error = 0
  40                 nb_jours = 0
  41                 for (i in intersect(fdays,sdays))
  42                 {
  43                     # mix_strategy is never used here (simtype != "mix"), therefore left blank
  44                     prediction = private$.predictShapeAux(data,
  45                         fdays, i, horizon, h, kernel, simtype, FALSE)
  46                     if (!is.na(prediction[1]))
  47                     {
  48                         nb_jours = nb_jours + 1
  49                         error = error +
  50                             mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2)
  51                     }
  52                 }
  53                 return (error / nb_jours)
  54             }
  55
  56             if (simtype != "endo")
  57             {
  58                 h_best_exo = optimize(
  59                     errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
  60             }
  61             if (simtype != "exo")
  62             {
  63                 h_best_endo = optimize(
  64                     errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
  65             }
  66
  67             if (simtype == "endo")
  68             {
  69                 return (private$.predictShapeAux(data,
  70                     fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
  71             }
  72             if (simtype == "exo")
  73             {
  74                 return (private$.predictShapeAux(data,
  75                     fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
  76             }
  77             if (simtype == "mix")
  78             {
  79                 h_best_mix = c(h_best_endo,h_best_exo)
  80                 return(private$.predictShapeAux(data,
  81                     fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
  82             }
  83         }
  84     ),
  85     private = list(
  86         # Precondition: "today" is full (no NAs)
  87         .predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
  88         {
  89             fdays = fdays[ fdays < today ]
  90             # TODO: 3 = magic number
  91             if (length(fdays) < 3)
  92                 return (NA)
  93
  94             if (simtype != "exo")
  95             {
  96                 h_endo = ifelse(simtype=="mix", h[1], h)
  97
  98                 # Distances from last observed day to days in the past
  99                 distances2 = rep(NA, length(fdays))
 100                 for (i in seq_along(fdays))
 101                 {
 102                     delta = data$getCenteredSerie(today) - data$getCenteredSerie(fdays[i])
 103                     # Require at least half of non-NA common values to compute the distance
 104                     if ( !any( is.na(delta) ) )
 105                         distances2[i] = mean(delta^2)
 106                 }
 107
 108                 sd_dist = sd(distances2)
 109                 if (sd_dist < .Machine$double.eps)
 110                 {
 111 #                   warning("All computed distances are very close: stdev too small")
 112                     sd_dist = 1 #mostly for tests... FIXME:
 113                 }
 114                 simils_endo =
 115                     if (kernel=="Gauss")
 116                         exp(-distances2/(sd_dist*h_endo^2))
 117                     else
 118                     {
 119                         # Epanechnikov
 120                         u = 1 - distances2/(sd_dist*h_endo^2)
 121                         u[abs(u)>1] = 0.
 122                         u
 123                     }
 124             }
 125
 126             if (simtype != "endo")
 127             {
 128                 h_exo = ifelse(simtype=="mix", h[2], h)
 129
 130                 M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
 131                 M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
 132                 for (i in seq_along(fdays))
 133                     M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
 134
 135                 sigma = cov(M) #NOTE: robust covariance is way too slow
 136                 sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
 137
 138                 # Distances from last observed day to days in the past
 139                 distances2 = rep(NA, nrow(M)-1)
 140                 for (i in 2:nrow(M))
 141                 {
 142                     delta = M[1,] - M[i,]
 143                     distances2[i-1] = delta %*% sigma_inv %*% delta
 144                 }
 145
 146                 sd_dist = sd(distances2)
 147                 if (sd_dist < .Machine$double.eps)
 148                 {
 149 #                   warning("All computed distances are very close: stdev too small")
 150                     sd_dist = 1 #mostly for tests... FIXME:
 151                 }
 152                 simils_exo =
 153                     if (kernel=="Gauss")
 154                         exp(-distances2/(sd_dist*h_exo^2))
 155                     else
 156                     {
 157                         # Epanechnikov
 158                         u = 1 - distances2/(sd_dist*h_exo^2)
 159                         u[abs(u)>1] = 0.
 160                         u
 161                     }
 162             }
 163
 164             similarities =
 165                 if (simtype == "exo")
 166                     simils_exo
 167                 else if (simtype == "endo")
 168                     simils_endo
 169                 else #mix
 170                     simils_endo * simils_exo
 171
 172             prediction = rep(0, horizon)
 173             for (i in seq_along(fdays))
 174                 prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
 175             prediction = prediction / sum(similarities, na.rm=TRUE)
 176
 177             if (final_call)
 178             {
 179                 private$.params$weights <- similarities
 180                 private$.params$indices <- fdays
 181                 private$.params$window <-
 182                     if (simtype=="endo")
 183                         h_endo
 184                     else if (simtype=="exo")
 185                         h_exo
 186                     else #mix
 187                         c(h_endo,h_exo)
 188             }
 189
 190             return (prediction)
 191         }
 192     )
 193 )