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 NeighborsForecaster = R6::R6Class("NeighborsForecaster",
   8     inherit = Forecaster,
   9
  10     public = list(
  11         predictShape = function(data, today, memory, horizon, ...)
  12         {
  13             # (re)initialize computed parameters
  14             private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
  15
  16             # Determine indices of no-NAs days followed by no-NAs tomorrows
  17             fdays = getNoNA2(data, max(today-memory,1), today-1)
  18
  19             # Get optional args
  20             simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
  21             kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
  22             if (hasArg(h_window))
  23             {
  24                 return ( private$.predictShapeAux(data,
  25                     fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
  26             }
  27
  28             # Indices of similar days for cross-validation; TODO: 45 = magic number
  29             sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
  30
  31             # Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
  32             errorOnLastNdays = function(h, kernel, simtype)
  33             {
  34                 error = 0
  35                 nb_jours = 0
  36                 for (i in intersect(fdays,sdays))
  37                 {
  38                     # mix_strategy is never used here (simtype != "mix"), therefore left blank
  39                     prediction = private$.predictShapeAux(data,
  40                         fdays, i, horizon, h, kernel, simtype, FALSE)
  41                     if (!is.na(prediction[1]))
  42                     {
  43                         nb_jours = nb_jours + 1
  44                         error = error +
  45                             mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2)
  46                     }
  47                 }
  48                 return (error / nb_jours)
  49             }
  50
  51             if (simtype != "endo")
  52             {
  53                 h_best_exo = optimize(
  54                     errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
  55             }
  56             if (simtype != "exo")
  57             {
  58                 h_best_endo = optimize(
  59                     errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
  60             }
  61
  62             if (simtype == "endo")
  63             {
  64                 return (private$.predictShapeAux(data,
  65                     fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
  66             }
  67             if (simtype == "exo")
  68             {
  69                 return (private$.predictShapeAux(data,
  70                     fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
  71             }
  72             if (simtype == "mix")
  73             {
  74                 h_best_mix = c(h_best_endo,h_best_exo)
  75                 return(private$.predictShapeAux(data,
  76                     fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
  77             }
  78         }
  79     ),
  80     private = list(
  81         # Precondition: "today" is full (no NAs)
  82         .predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
  83         {
  84             fdays = fdays[ fdays < today ]
  85             # TODO: 3 = magic number
  86             if (length(fdays) < 3)
  87                 return (NA)
  88
  89             if (simtype != "exo")
  90             {
  91                 h_endo = ifelse(simtype=="mix", h[1], h)
  92
  93                 # Distances from last observed day to days in the past
  94                 distances2 = rep(NA, length(fdays))
  95                 for (i in seq_along(fdays))
  96                 {
  97                     delta = data$getCenteredSerie(today) - data$getCenteredSerie(fdays[i])
  98                     # Require at least half of non-NA common values to compute the distance
  99                     if (sum(is.na(delta)) <= 0) #length(delta)/2)
 100                         distances2[i] = mean(delta^2) #, na.rm=TRUE)
 101                 }
 102
 103                 sd_dist = sd(distances2)
 104                 if (sd_dist < .Machine$double.eps)
 105                     sd_dist = 1 #mostly for tests... FIXME:
 106                 simils_endo =
 107                     if (kernel=="Gauss")
 108                         exp(-distances2/(sd_dist*h_endo^2))
 109                     else { #Epanechnikov
 110                         u = 1 - distances2/(sd_dist*h_endo^2)
 111                         u[abs(u)>1] = 0.
 112                         u
 113                     }
 114             }
 115
 116             if (simtype != "endo")
 117             {
 118                 h_exo = ifelse(simtype=="mix", h[2], h)
 119
 120                 M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
 121                 M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
 122                 for (i in seq_along(fdays))
 123                     M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
 124
 125                 sigma = cov(M) #NOTE: robust covariance is way too slow
 126                 sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
 127
 128                 # Distances from last observed day to days in the past
 129                 distances2 = rep(NA, nrow(M)-1)
 130                 for (i in 2:nrow(M))
 131                 {
 132                     delta = M[1,] - M[i,]
 133                     distances2[i-1] = delta %*% sigma_inv %*% delta
 134                 }
 135
 136                 sd_dist = sd(distances2)
 137                 simils_exo =
 138                     if (kernel=="Gauss")
 139                         exp(-distances2/(sd_dist*h_exo^2))
 140                     else { #Epanechnikov
 141                         u = 1 - distances2/(sd_dist*h_exo^2)
 142                         u[abs(u)>1] = 0.
 143                         u
 144                     }
 145             }
 146
 147             similarities =
 148                 if (simtype == "exo")
 149                     simils_exo
 150                 else if (simtype == "endo")
 151                     simils_endo
 152                 else #mix
 153                     simils_endo * simils_exo
 154
 155             prediction = rep(0, horizon)
 156             for (i in seq_along(fdays))
 157                 prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
 158             prediction = prediction / sum(similarities, na.rm=TRUE)
 159
 160             if (final_call)
 161             {
 162                 private$.params$weights <- similarities
 163                 private$.params$indices <- fdays
 164                 private$.params$window <-
 165                     if (simtype=="endo") {
 166                         h_endo
 167                     } else if (simtype=="exo") {
 168                         h_exo
 169                     } else { #mix
 170                         c(h_endo,h_exo)
 171                     }
 172             }
 173
 174             return (prediction)
 175         }
 176     )
 177 )