update documention, fix package to compete with 'method Bruno'

[talweg.git] / pkg / R / F_Neighbors.R

diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index 02536eb..9d1e3fb 100644 (file)
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -1,27 +1,23 @@
 #' Neighbors Forecaster
 #'
-#' Predict next serie as a weighted combination of "futures of the past" days,
-#' where days in the past are chosen and weighted according to some similarity measures.
+#' Predict next serie as a weighted combination of curves observed on "similar" days in
+#' the past (and future if 'opera'=FALSE); the nature of the similarity is controlled by
+#' the options 'simtype' and 'local' (see below).
 #'
-#' The main method is \code{predictShape()}, taking arguments data, today, memory,
-#' predict_from, horizon respectively for the dataset (object output of
-#' \code{getData()}), the current index, the data depth (in days), the first predicted
-#' hour and the last predicted hour.
-#' In addition, optional arguments can be passed:
+#' Optional arguments:
 #' \itemize{
-#'   \item local : TRUE (default) to constrain neighbors to be "same days within same
-#'     season"
-#'   \item simtype : 'endo' for a similarity based on the series only,<cr>
+#'   \item local: TRUE (default) to constrain neighbors to be "same days in same season"
+#'   \item simtype: 'endo' for a similarity based on the series only,<cr>
 #'             'exo' for a similarity based on exogenous variables only,<cr>
 #'             'mix' for the product of 'endo' and 'exo',<cr>
 #'             'none' (default) to apply a simple average: no computed weights
-#'   \item window : A window for similarities computations; override cross-validation
+#'   \item window: A window for similarities computations; override cross-validation
 #'     window estimation.
 #' }
 #' The method is summarized as follows:
 #' \enumerate{
-#'   \item Determine N (=20) recent days without missing values, and followed by a
-#'     tomorrow also without missing values.
+#'   \item Determine N (=20) recent days without missing values, and preceded by a
+#'     curve also without missing values.
 #'   \item Optimize the window parameters (if relevant) on the N chosen days.
 #'   \item Considering the optimized window, compute the neighbors (with locality
 #'     constraint or not), compute their similarities -- using a gaussian kernel if
@@ -61,8 +57,8 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
                        if (!opera)
                                tdays = setdiff(tdays, today) #always exclude current day
 
-                       # Shortcut if window is known
-                       if (hasArg("window"))
+                       # Shortcut if window is known or local==TRUE && simtype==none
+                       if (hasArg("window") || (local && simtype=="none"))
                        {
                                return ( private$.predictShapeAux(data, tdays, today, predict_from, horizon,
                                        local, list(...)$window, simtype, opera, TRUE) )
@@ -129,8 +125,8 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 
                        if (local)
                        {
-                               # TODO: 60 == magic number
-                               tdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
+                               # limit=Inf to not censor any day (TODO: finite limit? 60?)
+                               tdays = getSimilarDaysIndices(today, data, limit=Inf, same_season=TRUE,
                                        days_in=tdays_cut, operational=opera)
 #                              if (length(tdays) <= 1)
 #                                      return (NA)
@@ -146,6 +142,13 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
                                        }
                                        return ( data$getSerie(tdays[1])[predict_from:horizon] )
                                }
+                               max_neighbs = 10 #TODO: 12 = arbitrary number
+                               if (length(tdays) > max_neighbs)
+                               {
+                                       distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
+                                       ordering <- order(distances2)
+                                       tdays <- tdays[ ordering[1:max_neighbs] ]
+                               }
                        }
                        else
                                tdays = tdays_cut #no conditioning
@@ -156,19 +159,9 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
                                window_endo = ifelse(simtype=="mix", window[1], window)
 
                                # Distances from last observed day to selected days in the past
+                               # TODO: redundant computation if local==TRUE
                                distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
 
-                               if (local)
-                               {
-                                       max_neighbs = 12 #TODO: 12 = arbitrary number
-                                       if (length(distances2) > max_neighbs)
-                                       {
-                                               ordering <- order(distances2)
-                                               tdays <- tdays[ ordering[1:max_neighbs] ]
-                                               distances2 <- distances2[ ordering[1:max_neighbs] ]
-                                       }
-                               }
-
                                simils_endo <- .computeSimils(distances2, window_endo)
                        }
 
@@ -284,7 +277,8 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
        sapply(tdays, function(i) {
                delta = lastSerie - c(data$getSerie(i-1),
                        data$getSerie(i)[if (predict_from>=2) 1:(predict_from-1) else c()])
-               sqrt(mean(delta^2))
+#              sqrt(mean(delta^2))
+               sqrt(sum(delta^2))
        })
 }