X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors.R;h=ffb068f9f248eec2e02aad151ed5b7dc2d460213;hb=3ddf1c12af0c167fe7d3bb59e63258550270cfc5;hp=c55291aa996838a2a02535725f72c4fb8709b922;hpb=aa059de77cbcd28a3a66c7ff29ebe0346882867b;p=talweg.git

diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index c55291a..ffb068f 100644
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -1,9 +1,36 @@
-#' @include Forecaster.R
-#'
 #' Neighbors Forecaster
 #'
-#' Predict tomorrow as a weighted combination of "futures of the past" days.
-#' Inherits \code{\link{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.
+#'
+#' The main method is \code{predictShape()}, taking arguments data, today, memory,
+#' horizon respectively for the dataset (object output of \code{getData()}), the current
+#' index, the data depth (in days) and the number of time steps to forecast.
+#' In addition, optional arguments can be passed:
+#' \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>
+#'             'exo' for a similaruty 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
+#'     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 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
+#'     simtype != "none" -- and average accordingly the "tomorrows of neigbors" to
+#'     obtain the final prediction.
+#' }
+#'
+#' @docType class
+#' @format R6 class, inherits Forecaster
+#' @aliases F_Neighbors
 #'
 NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 	inherit = Forecaster,
@@ -19,11 +46,11 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				return (NA)
 
 			# Determine indices of no-NAs days followed by no-NAs tomorrows
-			fdays = getNoNA2(data, max(today-memory,1), today-1)
+			fdays = .getNoNA2(data, max(today-memory,1), today-1)
 
 			# Get optional args
-			local = ifelse(hasArg("local"), list(...)$local, FALSE) #same level + season?
-			simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
+			local = ifelse(hasArg("local"), list(...)$local, TRUE) #same level + season?
+			simtype = ifelse(hasArg("simtype"), list(...)$simtype, "none") #or "endo", or "exo"
 			if (hasArg("window"))
 			{
 				return ( private$.predictShapeAux(data,
@@ -34,7 +61,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 			cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
 				days_in=fdays)
 
-			# Optimize h : h |--> sum of prediction errors on last 45 "similar" days
+			# Optimize h : h |--> sum of prediction errors on last N "similar" days
 			errorOnLastNdays = function(window, simtype)
 			{
 				error = 0
@@ -54,32 +81,30 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				return (error / nb_jours)
 			}
 
-			if (simtype != "endo")
-			{
-				best_window_exo = optimize(
-					errorOnLastNdays, c(0,7), simtype="exo")$minimum
-			}
-			if (simtype != "exo")
+			# TODO: 7 == magic number
+			if (simtype=="endo" || simtype=="mix")
 			{
 				best_window_endo = optimize(
 					errorOnLastNdays, c(0,7), simtype="endo")$minimum
 			}
-
-			if (simtype == "endo")
-			{
-				return (private$.predictShapeAux(data, fdays, today, horizon, local,
-					best_window_endo, "endo", TRUE))
-			}
-			if (simtype == "exo")
-			{
-				return (private$.predictShapeAux(data, fdays, today, horizon, local,
-					best_window_exo, "exo", TRUE))
-			}
-			if (simtype == "mix")
+			if (simtype=="exo" || simtype=="mix")
 			{
-				return(private$.predictShapeAux(data, fdays, today, horizon, local,
-					c(best_window_endo,best_window_exo), "mix", TRUE))
+				best_window_exo = optimize(
+					errorOnLastNdays, c(0,7), simtype="exo")$minimum
 			}
+
+			best_window =
+				if (simtype == "endo")
+					best_window_endo
+				else if (simtype == "exo")
+					best_window_exo
+				else if (simtype == "mix")
+					c(best_window_endo,best_window_exo)
+				else #none: value doesn't matter
+					1
+
+			return(private$.predictShapeAux(data, fdays, today, horizon, local,
+				best_window, simtype, TRUE))
 		}
 	),
 	private = list(
@@ -93,33 +118,14 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 
 			if (local)
 			{
-				# Neighbors: days in "same season"; TODO: 60 == magic number...
+				# TODO: 60 == magic number
 				fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
 					days_in=fdays_cut)
 				if (length(fdays) <= 1)
 					return (NA)
-				levelToday = data$getLevel(today)
-				distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
-				#TODO: 2, 3, 5, 10 magic numbers here...
-				dist_thresh = 2
-				min_neighbs = min(3,length(fdays))
-				repeat
-				{
-					same_pollution = (distances <= dist_thresh)
-					nb_neighbs = sum(same_pollution)
-					if (nb_neighbs >= min_neighbs) #will eventually happen
-						break
-					dist_thresh = dist_thresh + 3
-				}
-				fdays = fdays[same_pollution]
-				max_neighbs = 10
-				if (nb_neighbs > max_neighbs)
-				{
-					# Keep only max_neighbs closest neighbors
-					fdays = fdays[
-						sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
-				}
-				if (length(fdays) == 1) #the other extreme...
+				# TODO: 10, 12 == magic numbers
+				fdays = .getConstrainedNeighbs(today,data,fdays,min_neighbs=10,max_neighbs=12)
+				if (length(fdays) == 1)
 				{
 					if (final_call)
 					{
@@ -127,13 +133,13 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 						private$.params$indices <- fdays
 						private$.params$window <- 1
 					}
-					return ( data$getSerie(fdays[1])[1:horizon] ) #what else?!
+					return ( data$getSerie(fdays[1])[1:horizon] )
 				}
 			}
 			else
 				fdays = fdays_cut #no conditioning
 
-			if (simtype != "exo")
+			if (simtype == "endo" || simtype == "mix")
 			{
 				# Compute endogen similarities using given window
 				window_endo = ifelse(simtype=="mix", window[1], window)
@@ -145,19 +151,13 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					mean(delta^2)
 				})
 
-				sd_dist = sd(distances2)
-				if (sd_dist < .25 * sqrt(.Machine$double.eps))
-				{
-#					warning("All computed distances are very close: stdev too small")
-					sd_dist = 1 #mostly for tests... FIXME:
-				}
-				simils_endo = exp(-distances2/(sd_dist*window_endo^2))
+				simils_endo <- .computeSimils(distances2, window_endo)
 			}
 
-			if (simtype != "endo")
+			if (simtype == "exo" || simtype == "mix")
 			{
 				# Compute exogen similarities using given window
-				h_exo = ifelse(simtype=="mix", window[2], window)
+				window_exo = ifelse(simtype=="mix", window[2], window)
 
 				M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
 				M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
@@ -178,13 +178,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					delta %*% sigma_inv %*% delta
 				})
 
-				sd_dist = sd(distances2)
-				if (sd_dist < .25 * sqrt(.Machine$double.eps))
-				{
-#					warning("All computed distances are very close: stdev too small")
-					sd_dist = 1 #mostly for tests... FIXME:
-				}
-				simils_exo = exp(-distances2/(sd_dist*window_exo^2))
+				simils_exo <- .computeSimils(distances2, window_exo)
 			}
 
 			similarities =
@@ -192,8 +186,10 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					simils_exo
 				else if (simtype == "endo")
 					simils_endo
-				else #mix
+				else if (simtype == "mix")
 					simils_endo * simils_exo
+				else #none
+					rep(1, length(fdays))
 			similarities = similarities / sum(similarities)
 
 			prediction = rep(0, horizon)
@@ -209,11 +205,82 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 						window_endo
 					else if (simtype=="exo")
 						window_exo
-					else #mix
+					else if (simtype=="mix")
 						c(window_endo,window_exo)
+					else #none
+						1
 			}
 
 			return (prediction)
 		}
 	)
 )
+
+#' getNoNA2
+#'
+#' Get indices in data of no-NA series followed by no-NA, within [first,last] range.
+#'
+#' @inheritParams dateIndexToInteger
+#' @param first First index (included)
+#' @param last Last index (included)
+#'
+.getNoNA2 = function(data, first, last)
+{
+	(first:last)[ sapply(first:last, function(i)
+		!any( is.na(data$getCenteredSerie(i)) | is.na(data$getCenteredSerie(i+1)) )
+	) ]
+}
+
+#' getConstrainedNeighbs
+#'
+#' Get indices of neighbors of similar pollution level (among same season + day type).
+#'
+#' @param today Index of current day
+#' @param data Object of class Data
+#' @param fdays Current set of "first days" (no-NA pairs)
+#' @param min_neighbs Minimum number of points in a neighborhood
+#' @param max_neighbs Maximum number of points in a neighborhood
+#'
+.getConstrainedNeighbs = function(today, data, fdays, min_neighbs=10, max_neighbs=12)
+{
+	levelToday = data$getLevel(today)
+	distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
+	#TODO: 2, +3 : magic numbers
+	dist_thresh = 2
+	min_neighbs = min(min_neighbs,length(fdays))
+	repeat
+	{
+		same_pollution = (distances <= dist_thresh)
+		nb_neighbs = sum(same_pollution)
+		if (nb_neighbs >= min_neighbs) #will eventually happen
+			break
+		dist_thresh = dist_thresh + 3
+	}
+	fdays = fdays[same_pollution]
+	max_neighbs = 12
+	if (nb_neighbs > max_neighbs)
+	{
+		# Keep only max_neighbs closest neighbors
+		fdays = fdays[
+			sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
+	}
+	fdsays
+}
+
+#' compute similarities
+#'
+#' Apply the gaussian kernel on computed squared distances.
+#'
+#' @param distances2 Squared distances
+#' @param window Window parameter for the kernel
+#'
+.computeSimils <- function(distances2, window)
+{
+	sd_dist = sd(distances2)
+	if (sd_dist < .25 * sqrt(.Machine$double.eps))
+	{
+#		warning("All computed distances are very close: stdev too small")
+		sd_dist = 1 #mostly for tests... FIXME:
+	}
+	exp(-distances2/(sd_dist*window^2))
+}