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