X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors.R;h=f140b0bb5559d1f51852e55d7ea7d98aa02c1be6;hb=cf3bb00128ac8cb930996455faf7c99a3fc102fb;hp=c8a33554f92fef75dc327fb526faea9027b4b535;hpb=6774e53de7b8bdac191d6203a380ad46c3b4d9ba;p=talweg.git

diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index c8a3355..f140b0b 100644
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -1,164 +1,192 @@
-#' @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,
+#' 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:
+#' \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 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
+#'     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.
+#' }
+#'
+#' @usage # NeighborsForecaster$new(pjump)
+#'
+#' @docType class
+#' @format R6 class, inherits Forecaster
+#' @aliases F_Neighbors
 #'
 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)
+			# Determine indices of no-NAs days preceded by no-NAs yerstedays
+			tdays = .getNoNA2(data, max(today-memory,2), today-1)
 
 			# Get optional args
-			simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
-			kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
-			if (hasArg(h_window))
+			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$.predictShapeAux(data,
-					fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
+					tdays, today, predict_from, horizon, local, list(...)$window, simtype, 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)
+			cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
+				days_in=tdays)
 
-			# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
-			errorOnLastNdays = function(h, kernel, simtype)
+			# Optimize h : h |--> sum of prediction errors on last N "similar" days
+			errorOnLastNdays = function(window, simtype)
 			{
 				error = 0
 				nb_jours = 0
 				for (i in seq_along(cv_days))
 				{
 					# mix_strategy is never used here (simtype != "mix"), therefore left blank
-					prediction = private$.predictShapeAux(data,
-						fdays, cv_days[i], horizon, h, kernel, simtype, FALSE)
+					prediction = private$.predictShapeAux(data, tdays, cv_days[i], predict_from,
+						horizon, local, window, simtype, FALSE)
 					if (!is.na(prediction[1]))
 					{
 						nb_jours = nb_jours + 1
 						error = error +
-							mean((data$getCenteredSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
+							mean((data$getSerie(cv_days[i])[predict_from:horizon] - prediction)^2)
 					}
 				}
 				return (error / nb_jours)
 			}
 
-			if (simtype != "endo")
+			# TODO: 7 == magic number
+			if (simtype=="endo" || simtype=="mix")
 			{
-				h_best_exo = optimize(
-					errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
+				best_window_endo = optimize(
+					errorOnLastNdays, c(0,7), simtype="endo")$minimum
 			}
-			if (simtype != "exo")
+			if (simtype=="exo" || simtype=="mix")
 			{
-				h_best_endo = optimize(
-					errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
+				best_window_exo = optimize(
+					errorOnLastNdays, c(0,7), simtype="exo")$minimum
 			}
 
-			if (simtype == "endo")
-			{
-				return (private$.predictShapeAux(data,
-					fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
-			}
-			if (simtype == "exo")
-			{
-				return (private$.predictShapeAux(data,
-					fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
-			}
-			if (simtype == "mix")
-			{
-				h_best_mix = c(h_best_endo,h_best_exo)
-				return(private$.predictShapeAux(data,
-					fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
-			}
+			best_window =
+				if (simtype == "endo")
+					best_window_endo
+				else if (simtype == "exo")
+					best_window_exo
+				else if (simtype == "mix")
+					c(best_window_endo,best_window_exo)
+				else #none: value doesn't matter
+					1
+
+			return( private$.predictShapeAux(data, tdays, today, predict_from, horizon, local,
+				best_window, simtype, TRUE) )
 		}
 	),
 	private = list(
 		# Precondition: "today" is full (no NAs)
-		.predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
+		.predictShapeAux = function(data, tdays, today, predict_from, horizon, local, window,
+			simtype, final_call)
 		{
-			fdays = fdays[ fdays < today ]
-			# TODO: 3 = magic number
-			if (length(fdays) < 3)
+			tdays_cut = tdays[ tdays <= today-1 ]
+			if (length(tdays_cut) <= 1)
 				return (NA)
 
-			if (simtype != "exo")
+			if (local)
+			{
+				# TODO: 60 == magic number
+				tdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
+					days_in=tdays_cut)
+				if (length(tdays) <= 1)
+					return (NA)
+				# TODO: 10, 12 == magic numbers
+				tdays = .getConstrainedNeighbs(today,data,tdays,min_neighbs=10,max_neighbs=12)
+				if (length(tdays) == 1)
+				{
+					if (final_call)
+					{
+						private$.params$weights <- 1
+						private$.params$indices <- tdays
+						private$.params$window <- 1
+					}
+					return ( data$getSerie(tdays[1])[predict_from:horizon] )
+				}
+			}
+			else
+				tdays = tdays_cut #no conditioning
+
+			if (simtype == "endo" || simtype == "mix")
 			{
-				h_endo = ifelse(simtype=="mix", h[1], h)
+				# 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)
+				lastSerie = c( data$getSerie(today-1),
+					data$getSerie(today)[if (predict_from>=2) 1:(predict_from-1) else c()] )
+				distances2 = 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))
 				})
 
-				sd_dist = sd(distances2)
-				if (sd_dist < .Machine$double.eps)
-				{
-#					warning("All computed distances are very close: stdev too small")
-					sd_dist = 1 #mostly for tests... FIXME:
-				}
-				simils_endo =
-					if (kernel=="Gauss")
-						exp(-distances2/(sd_dist*h_endo^2))
-					else
-					{
-						# Epanechnikov
-						u = 1 - distances2/(sd_dist*h_endo^2)
-						u[abs(u)>1] = 0.
-						u
-					}
+				simils_endo <- .computeSimils(distances2, window_endo)
 			}
 
-			if (simtype != "endo")
+			if (simtype == "exo" || simtype == "mix")
 			{
-				h_exo = ifelse(simtype=="mix", h[2], h)
+				# 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$getExo(fdays[i])) )
+				M = matrix( ncol=1+length(tdays), nrow=1+length(data$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(M) #NOTE: robust covariance is way too slow
+				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(fdays) > 10)
+					if (length(tdays) > 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,]
+				distances2 = sapply(seq_along(tdays), function(i) {
+					delta = M[,1] - M[,i+1]
 					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 =
-					if (kernel=="Gauss")
-						exp(-distances2/(sd_dist*h_exo^2))
-					else
-					{
-						# Epanechnikov
-						u = 1 - distances2/(sd_dist*h_exo^2)
-						u[abs(u)>1] = 0.
-						u
-					}
+				simils_exo <- .computeSimils(distances2, window_exo)
 			}
 
 			similarities =
@@ -166,28 +194,91 @@ 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(tdays))
+			similarities = similarities / sum(similarities)
 
-			prediction = rep(0, horizon)
-			for (i in seq_along(fdays))
-				prediction = prediction + similarities[i] * data$getCenteredSerie(fdays[i]+1)[1:horizon]
-			prediction = prediction / sum(similarities, na.rm=TRUE)
+			prediction = rep(0, horizon-predict_from+1)
+			for (i in seq_along(tdays))
+			{
+				prediction = prediction +
+					similarities[i] * data$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")
-						h_endo
+						window_endo
 					else if (simtype=="exo")
-						h_exo
-					else #mix
-						c(h_endo,h_exo)
+						window_exo
+					else if (simtype=="mix")
+						c(window_endo,window_exo)
+					else #none
+						1
 			}
 
 			return (prediction)
 		}
 	)
 )
+
+# 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 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, tdays, min_neighbs=10, max_neighbs=12)
+{
+	levelToday = data$getLevelHat(today)
+	levelYersteday = data$getLevel(today-1)
+	distances = sapply(tdays, function(i) {
+		sqrt((data$getLevel(i-1)-levelYersteday)^2 + (data$getLevel(i)-levelToday)^2)
+	})
+	#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 + ifelse(dist_thresh>1,3,1)
+	}
+	tdays = tdays[same_pollution]
+	max_neighbs = 12
+	if (nb_neighbs > max_neighbs)
+	{
+		# Keep only max_neighbs closest neighbors
+		tdays = tdays[ order(distances[same_pollution])[1:max_neighbs] ]
+	}
+	tdays
+}
+
+# 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))
+}