X-Git-Url: https://git.auder.net/?p=talweg.git;a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors.R;fp=pkg%2FR%2FF_Neighbors.R;h=8eb1ddc240be802f50b52afeb63ac95a373676d1;hp=143744247d5facd3a2c2cdd1a2aa27c3ea7f7e3c;hb=af718fd5a9a330b13b331e78824a47407a3479ae;hpb=c8a81efd2e8302cde424165539f49e4bb7466fc3

diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index 1437442..8eb1ddc 100644
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -1,26 +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,
-#' 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:
+#' 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>
-#'             'exo' for a similaruty based on exogenous variables 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
@@ -38,30 +35,38 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 	inherit = Forecaster,
 
 	public = list(
-		predictShape = function(data, today, memory, horizon, ...)
+		predictShape = function(data, today, memory, predict_from, horizon, ...)
 		{
 			# (re)initialize computed parameters
 			private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
 
 			# Do not forecast on days with NAs (TODO: softer condition...)
-			if (any(is.na(data$getCenteredSerie(today))))
+			if (any(is.na(data$getSerie(today-1))) ||
+				(predict_from>=2 && any(is.na(data$getSerie(today)[1:(predict_from-1)]))))
+			{
 				return (NA)
-
-			# Determine indices of no-NAs days followed by no-NAs tomorrows
-			fdays = .getNoNA2(data, max(today-memory,1), today-1)
+			}
 
 			# Get optional args
 			local = ifelse(hasArg("local"), list(...)$local, TRUE) #same level + season?
 			simtype = ifelse(hasArg("simtype"), list(...)$simtype, "none") #or "endo", or "exo"
+			opera = ifelse(hasArg("opera"), list(...)$opera, FALSE) #operational mode?
+
+			# Determine indices of no-NAs days preceded by no-NAs yerstedays
+			tdays = .getNoNA2(data, max(today-memory,2), ifelse(opera,today-1,data$getSize()))
+			if (!opera)
+				tdays = setdiff(tdays, today) #always exclude current day
+
+			# Shortcut if window is known #TODO: cross-validation for number of days, on similar (yerste)days
 			if (hasArg("window"))
 			{
-				return ( private$.predictShapeAux(data,
-					fdays, today, horizon, local, list(...)$window, simtype, TRUE) )
+				return ( private$.predictShapeAux(data, tdays, today, predict_from, horizon,
+					local, list(...)$window, simtype, opera, TRUE) )
 			}
 
 			# Indices of similar days for cross-validation; TODO: 20 = magic number
 			cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
-				days_in=fdays)
+				days_in=tdays, operational=opera)
 
 			# Optimize h : h |--> sum of prediction errors on last N "similar" days
 			errorOnLastNdays = function(window, simtype)
@@ -71,13 +76,13 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				for (i in seq_along(cv_days))
 				{
 					# mix_strategy is never used here (simtype != "mix"), therefore left blank
-					prediction = private$.predictShapeAux(data, fdays, cv_days[i], horizon, local,
-						window, simtype, FALSE)
+					prediction = private$.predictShapeAux(data, tdays, cv_days[i], predict_from,
+						horizon, local, window, simtype, opera, FALSE)
 					if (!is.na(prediction[1]))
 					{
 						nb_jours = nb_jours + 1
 						error = error +
-							mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
+							mean((data$getSerie(cv_days[i])[predict_from:horizon] - prediction)^2)
 					}
 				}
 				return (error / nb_jours)
@@ -105,53 +110,55 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				else #none: value doesn't matter
 					1
 
-			return(private$.predictShapeAux(data, fdays, today, horizon, local,
-				best_window, simtype, TRUE))
+			return( private$.predictShapeAux(data, tdays, today, predict_from, horizon, local,
+				best_window, simtype, opera, TRUE) )
 		}
 	),
 	private = list(
-		# Precondition: "today" is full (no NAs)
-		.predictShapeAux = function(data, fdays, today, horizon, local, window, simtype,
-			final_call)
+		# Precondition: "yersteday until predict_from-1" is full (no NAs)
+		.predictShapeAux = function(data, tdays, today, predict_from, horizon, local, window,
+			simtype, opera, final_call)
 		{
-			fdays_cut = fdays[ fdays < today ]
-			if (length(fdays_cut) <= 1)
+			tdays_cut = tdays[ tdays != today ]
+			if (length(tdays_cut) == 0)
 				return (NA)
 
 			if (local)
 			{
-				# TODO: 60 == magic number
-				fdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
-					days_in=fdays_cut)
-				if (length(fdays) <= 1)
-					return (NA)
-				# TODO: 10, 12 == magic numbers
-				fdays = .getConstrainedNeighbs(today,data,fdays,min_neighbs=10,max_neighbs=12)
-				if (length(fdays) == 1)
+				# 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)
+				# TODO: 10 == magic number
+				tdays = .getConstrainedNeighbs(today, data, tdays, min_neighbs=10)
+				if (length(tdays) == 1)
 				{
 					if (final_call)
 					{
 						private$.params$weights <- 1
-						private$.params$indices <- fdays
+						private$.params$indices <- tdays
 						private$.params$window <- 1
 					}
-					return ( data$getSerie(fdays[1])[1:horizon] )
+					return ( data$getSerie(tdays[1])[predict_from:horizon] )
+				}
+				max_neighbs = 12 #TODO: 10 or 12 or... ?
+				if (length(tdays) > max_neighbs)
+				{
+					distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
+					ordering <- order(distances2)
+					tdays <- tdays[ ordering[1:max_neighbs] ]
 				}
 			}
 			else
-				fdays = fdays_cut #no conditioning
+				tdays = tdays_cut #no conditioning
 
 			if (simtype == "endo" || simtype == "mix")
 			{
 				# Compute endogen similarities using given window
 				window_endo = ifelse(simtype=="mix", window[1], window)
 
-				# Distances from last observed day to days in the past
-				serieToday = data$getSerie(today)
-				distances2 = sapply(fdays, function(i) {
-					delta = serieToday - data$getSerie(i)
-					mean(delta^2)
-				})
+				# Distances from last observed day to selected days in the past
+				# TODO: redundant computation if local==TRUE
+				distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
 
 				simils_endo <- .computeSimils(distances2, window_endo)
 			}
@@ -161,24 +168,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				# Compute exogen similarities using given 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$getExo(today)) )
-				for (i in seq_along(fdays))
-					M[i+1,] = c( data$getLevel(fdays[i]), as.double(data$getExo(fdays[i])) )
-
-				sigma = cov(M) #NOTE: robust covariance is way too slow
-				# TODO: 10 == magic number; more robust way == det, or always ginv()
-				sigma_inv =
-					if (length(fdays) > 10)
-						solve(sigma)
-					else
-						MASS::ginv(sigma)
-
-				# Distances from last observed day to days in the past
-				distances2 = sapply(seq_along(fdays), function(i) {
-					delta = M[1,] - M[i+1,]
-					delta %*% sigma_inv %*% delta
-				})
+				distances2 <- .computeDistsExo(data, today, tdays)
 
 				simils_exo <- .computeSimils(distances2, window_exo)
 			}
@@ -191,17 +181,20 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				else if (simtype == "mix")
 					simils_endo * simils_exo
 				else #none
-					rep(1, length(fdays))
+					rep(1, length(tdays))
 			similarities = similarities / sum(similarities)
 
-			prediction = rep(0, horizon)
-			for (i in seq_along(fdays))
-				prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
+			prediction = rep(0, horizon-predict_from+1)
+			for (i in seq_along(tdays))
+			{
+				prediction = prediction +
+					similarities[i] * data$getSerie(tdays[i])[predict_from:horizon]
+			}
 
 			if (final_call)
 			{
 				private$.params$weights <- similarities
-				private$.params$indices <- fdays
+				private$.params$indices <- tdays
 				private$.params$window <-
 					if (simtype=="endo")
 						window_endo
@@ -224,34 +217,26 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 #
 # @param today Index of current day
 # @param data Object of class Data
-# @param fdays Current set of "first days" (no-NA pairs)
+# @param tdays Current set of "second 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)
+.getConstrainedNeighbs = function(today, data, tdays, min_neighbs=10)
 {
-	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))
+	levelToday = data$getLevelHat(today)
+	distances = sapply( tdays, function(i) abs(data$getLevel(i) - levelToday) )
+	#TODO: 1, +1, +3 : magic numbers
+	dist_thresh = 1
+	min_neighbs = min(min_neighbs,length(tdays))
 	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
+		dist_thresh = dist_thresh + ifelse(dist_thresh>1,3,1)
 	}
-	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] ]
-	}
-	fdays
+	tdays[same_pollution]
 }
 
 # compute similarities
@@ -271,3 +256,36 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 	}
 	exp(-distances2/(sd_dist*window^2))
 }
+
+.computeDistsEndo <- function(data, today, tdays, predict_from)
+{
+	lastSerie = c( data$getSerie(today-1),
+		data$getSerie(today)[if (predict_from>=2) 1:(predict_from-1) else c()] )
+	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))
+	})
+}
+
+.computeDistsExo <- function(data, today, tdays)
+{
+	M = matrix( ncol=1+length(tdays), nrow=1+length(data$getExo(1)) )
+	M[,1] = c( data$getLevelHat(today), as.double(data$getExoHat(today)) )
+	for (i in seq_along(tdays))
+		M[,i+1] = c( data$getLevel(tdays[i]), as.double(data$getExo(tdays[i])) )
+
+	sigma = cov(t(M)) #NOTE: robust covariance is way too slow
+	# TODO: 10 == magic number; more robust way == det, or always ginv()
+	sigma_inv =
+		if (length(tdays) > 10)
+			solve(sigma)
+		else
+			MASS::ginv(sigma)
+
+	# Distances from last observed day to days in the past
+	sapply(seq_along(tdays), function(i) {
+		delta = M[,1] - M[,i+1]
+		delta %*% sigma_inv %*% delta
+	})
+}