X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors.R;h=02536ebf164c9634c6bb7a6f23eeb3cf27fbbea9;hb=638f27f4296727aff62b56643beb9f42aa5b57ef;hp=ffb6d371df57a910451f0a79ffeed340886132ff;hpb=99f83c9af27492f6fb9b10f51fb8704ed588f5c1;p=talweg.git

diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index ffb6d37..02536eb 100644
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -1,259 +1,311 @@
-#' @include Forecaster.R
+#' Neighbors Forecaster
 #'
-#' @title 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.
 #'
-#' @description Predict tomorrow as a weighted combination of "futures of the past" days.
-#'   Inherits \code{\link{Forecaster}}
-NeighborsForecaster = setRefClass(
-	Class = "NeighborsForecaster",
-	contains = "Forecaster",
+#' 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,
 
-	methods = list(
-		initialize = function(...)
-		{
-			callSuper(...)
-		},
-		predictShape = function(today, memory, horizon, ...)
+	public = list(
+		predictShape = function(data, today, memory, predict_from, horizon, ...)
 		{
 			# (re)initialize computed parameters
-			params <<- list("weights"=NA, "indices"=NA, "window"=NA)
+			private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
 
-			first_day = max(today - memory, 1)
-			# The first day is generally not complete:
-			if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(2)))
-				first_day = 2
-
-			# Predict only on (almost) non-NAs days
-			nas_in_serie = is.na(data$getSerie(today))
-			if (any(nas_in_serie))
+			# Do not forecast on days with NAs (TODO: softer condition...)
+			if (any(is.na(data$getSerie(today-1))) ||
+				(predict_from>=2 && any(is.na(data$getSerie(today)[1:(predict_from-1)]))))
 			{
-				#TODO: better define "repairing" conditions (and method)
-				if (sum(nas_in_serie) >= length(nas_in_serie) / 2)
-					return (NA)
-				for (i in seq_along(nas_in_serie))
-				{
-					if (nas_in_serie[i])
-					{
-						#look left
-						left = i-1
-						while (left>=1 && nas_in_serie[left])
-							left = left-1
-						#look right
-						right = i+1
-						while (right<=length(nas_in_serie) && nas_in_serie[right])
-							right = right+1
-						#HACK: modify by-reference Data object...
-						data$data[[today]]$serie[i] <<-
-							if (left==0) data$data[[today]]$serie[right]
-							else if (right==0) data$data[[today]]$serie[left]
-							else (data$data[[today]]$serie[left] + data$data[[today]]$serie[right]) / 2.
-					}
-				}
+				return (NA)
 			}
 
-			# Determine indices of no-NAs days followed by no-NAs tomorrows
-			fdays_indices = c()
-			for (i in first_day:(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
+			if (hasArg("window"))
 			{
-				if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
-					fdays_indices = c(fdays_indices, i)
+				return ( private$.predictShapeAux(data, tdays, today, predict_from, horizon,
+					local, list(...)$window, simtype, opera, TRUE) )
 			}
 
-			#GET OPTIONAL PARAMS
-			# Similarity computed with exogenous variables ? endogenous ? both ? ("exo","endo","mix")
-			simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix")
-			simthresh = ifelse(hasArg("simthresh"), list(...)$simthresh, 0.)
-			kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
-			mix_strategy = ifelse(hasArg("mix_strategy"), list(...)$mix_strategy, "mult") #or "neighb"
-			same_season = ifelse(hasArg("same_season"), list(...)$same_season, FALSE)
-			if (hasArg(h_window))
-				return (.predictShapeAux(fdays_indices, today, horizon, list(...)$h_window, kernel,
-					simtype, simthresh, mix_strategy, TRUE))
-			#END GET
-
-			# Indices for cross-validation; TODO: 45 = magic number
-			indices = getSimilarDaysIndices(today, limit=45, same_season=same_season)
-			if (tail(indices,1) == 1)
-				indices = head(indices,-1)
+			# Indices of similar days for cross-validation; TODO: 20 = magic number
+			cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
+				days_in=tdays, operational=opera)
 
-			# 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 indices)
+				for (i in seq_along(cv_days))
 				{
-					# NOTE: predict only on non-NAs days followed by non-NAs (TODO:)
-					if (!any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))))
+					# mix_strategy is never used here (simtype != "mix"), therefore left blank
+					prediction = private$.predictShapeAux(data, tdays, cv_days[i], predict_from,
+						horizon, local, window, simtype, opera, FALSE)
+					if (!is.na(prediction[1]))
 					{
 						nb_jours = nb_jours + 1
-						# mix_strategy is never used here (simtype != "mix"), therefore left blank
-						prediction = .predictShapeAux(fdays_indices, i, horizon, h, kernel, simtype,
-							simthresh, "", FALSE)
-						if (!is.na(prediction[1]))
-							error = error + mean((data$getCenteredSerie(i+1)[1:horizon] - prediction)^2)
+						error = error +
+							mean((data$getSerie(cv_days[i])[predict_from:horizon] - prediction)^2)
 					}
 				}
 				return (error / nb_jours)
 			}
 
-			h_best_exo = 1.
-			if (simtype != "endo" && !(simtype=="mix" && mix_strategy=="neighb"))
+			# TODO: 7 == magic number
+			if (simtype=="endo" || simtype=="mix")
 			{
-				h_best_exo = optimize(errorOnLastNdays, interval=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, interval=c(0,10), kernel=kernel,
-					simtype="endo")$minimum
+				best_window_exo = optimize(
+					errorOnLastNdays, c(0,7), simtype="exo")$minimum
 			}
 
-			if (simtype == "endo")
-			{
-				return (.predictShapeAux(fdays_indices, today, horizon, h_best_endo, kernel, "endo",
-					simthresh, "", TRUE))
-			}
-			if (simtype == "exo")
-			{
-				return (.predictShapeAux(fdays_indices, today, horizon, h_best_exo, kernel, "exo",
-					simthresh, "", TRUE))
-			}
-			if (simtype == "mix")
-			{
-				return (.predictShapeAux(fdays_indices, today, horizon, c(h_best_endo,h_best_exo),
-					kernel, "mix", simthresh, mix_strategy, TRUE))
-			}
-		},
-		# Precondition: "today" is full (no NAs)
-		.predictShapeAux = function(fdays_indices, today, horizon, h, kernel, simtype, simthresh,
-			mix_strategy, final_call)
-		{
-			dat = data$data #HACK: faster this way...
+			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
 
-			fdays_indices = fdays_indices[fdays_indices < today]
-			# TODO: 3 = magic number
-			if (length(fdays_indices) < 3)
+			return( private$.predictShapeAux(data, tdays, today, predict_from, horizon, local,
+				best_window, simtype, opera, TRUE) )
+		}
+	),
+	private = list(
+		# Precondition: "yersteday until predict_from-1" is full (no NAs)
+		.predictShapeAux = function(data, tdays, today, predict_from, horizon, local, window,
+			simtype, opera, final_call)
+		{
+			tdays_cut = tdays[ tdays != today ]
+			if (length(tdays_cut) == 0)
 				return (NA)
 
-			if (simtype != "exo")
+			if (local)
 			{
-				h_endo = ifelse(simtype=="mix", h[1], h)
-
-				# Distances from last observed day to days in the past
-				distances2 = rep(NA, length(fdays_indices))
-				for (i in seq_along(fdays_indices))
+				# TODO: 60 == magic number
+				tdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
+					days_in=tdays_cut, operational=opera)
+#				if (length(tdays) <= 1)
+#					return (NA)
+				# TODO: 10 == magic number
+				tdays = .getConstrainedNeighbs(today, data, tdays, min_neighbs=10)
+				if (length(tdays) == 1)
 				{
-					delta = dat[[today]]$serie - dat[[ fdays_indices[i] ]]$serie
-					# Require at least half of non-NA common values to compute the distance
-					if (sum(is.na(delta)) <= 0) #length(delta)/2)
-						distances2[i] = mean(delta^2) #, na.rm=TRUE)
-				}
-
-				sd_dist = sd(distances2)
-				if (sd_dist < .Machine$double.eps)
-					sd_dist = 1 #mostly for tests... FIXME:
-				simils_endo =
-					if (kernel=="Gauss")
-						exp(-distances2/(sd_dist*h_endo^2))
-					else { #Epanechnikov
-						u = 1 - distances2/(sd_dist*h_endo^2)
-						u[abs(u)>1] = 0.
-						u
+					if (final_call)
+					{
+						private$.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")
+			if (simtype == "endo" || simtype == "mix")
 			{
-				h_exo = ifelse(simtype=="mix", h[2], h)
-
-				M = matrix( nrow=1+length(fdays_indices), ncol=1+length(dat[[today]]$exo) )
-				M[1,] = c( dat[[today]]$level, as.double(dat[[today]]$exo) )
-				for (i in seq_along(fdays_indices))
-				{
-					M[i+1,] = c( dat[[ fdays_indices[i] ]]$level,
-						as.double(dat[[ fdays_indices[i] ]]$exo) )
-				}
+				# Compute endogen similarities using given window
+				window_endo = ifelse(simtype=="mix", window[1], window)
 
-				sigma = cov(M) #NOTE: robust covariance is way too slow
-				sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
+				# Distances from last observed day to selected days in the past
+				distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
 
-				# Distances from last observed day to days in the past
-				distances2 = rep(NA, nrow(M)-1)
-				for (i in 2:nrow(M))
+				if (local)
 				{
-					delta = M[1,] - M[i,]
-					distances2[i-1] = delta %*% sigma_inv %*% delta
+					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] ]
+					}
 				}
 
-				sd_dist = sd(distances2)
-				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_endo <- .computeSimils(distances2, window_endo)
 			}
 
-			if (simtype=="mix")
+			if (simtype == "exo" || simtype == "mix")
 			{
-				if (mix_strategy == "neighb")
-				{
-					#Only (60) most similar days according to exogen variables are kept into consideration
-					#TODO: 60 = magic number
-					keep_indices = sort(simils_exo, index.return=TRUE)$ix[1:(min(60,length(simils_exo)))]
-					simils_endo[-keep_indices] = 0.
-				}
-				else #mix_strategy == "mult"
-					simils_endo = simils_endo * simils_exo
+				# Compute exogen similarities using given window
+				window_exo = ifelse(simtype=="mix", window[2], window)
+
+				distances2 <- .computeDistsExo(data, today, tdays)
+
+				simils_exo <- .computeSimils(distances2, window_exo)
 			}
 
 			similarities =
-				if (simtype != "exo") {
-					simils_endo
-				} else {
+				if (simtype == "exo")
 					simils_exo
-				}
+				else if (simtype == "endo")
+					simils_endo
+				else if (simtype == "mix")
+					simils_endo * simils_exo
+				else #none
+					rep(1, length(tdays))
+			similarities = similarities / sum(similarities)
 
-			if (simthresh > 0.)
+			prediction = rep(0, horizon-predict_from+1)
+			for (i in seq_along(tdays))
 			{
-				max_sim = max(similarities)
-				# Set to 0 all similarities s where s / max_sim < simthresh, but keep at least 60
-				ordering = sort(similarities / max_sim, index.return=TRUE)
-				if (ordering[60] < simthresh)
-				{
-					similarities[ ordering$ix[ - (1:60) ] ] = 0.
-				} else
-				{
-					limit = 61
-					while (limit < length(similarities) && ordering[limit] >= simthresh)
-						limit = limit + 1
-					similarities[ ordering$ix[ - 1:limit] ] = 0.
-				}
+				prediction = prediction +
+					similarities[i] * data$getSerie(tdays[i])[predict_from:horizon]
 			}
 
-			prediction = rep(0, horizon)
-			for (i in seq_along(fdays_indices))
-				prediction = prediction + similarities[i] * dat[[ fdays_indices[i]+1 ]]$serie[1:horizon]
-			prediction = prediction / sum(similarities, na.rm=TRUE)
-
 			if (final_call)
 			{
-				params$weights <<- similarities
-				params$indices <<- fdays_indices
-				params$window <<-
-					if (simtype=="endo") {
-						h_endo
-					} else if (simtype=="exo") {
-						h_exo
-					} else {
-						c(h_endo,h_exo)
-					}
+				private$.params$weights <- similarities
+				private$.params$indices <- tdays
+				private$.params$window <-
+					if (simtype=="endo")
+						window_endo
+					else if (simtype=="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)
+{
+	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)
+		abs(data$getLevel(i)-levelToday)
+	})
+	#TODO: 1, +1, +3 : magic numbers
+	dist_thresh = 1
+	min_neighbs = min(min_neighbs,length(tdays))
+	repeat
+	{
+		same_pollution = (distances <= dist_thresh)
+		nb_neighbs = sum(same_pollution)
+		if (nb_neighbs >= min_neighbs) #will eventually happen
+			break
+		dist_thresh = dist_thresh + ifelse(dist_thresh>1,3,1)
+	}
+	tdays = tdays[same_pollution]
+#	max_neighbs = 12
+#	if (nb_neighbs > max_neighbs)
+#	{
+#		# Keep only max_neighbs closest neighbors
+#		tdays = tdays[ order(distances[same_pollution])[1:max_neighbs] ]
+#	}
+	tdays
+}
+
+# compute similarities
+#
+# Apply the gaussian kernel on computed squared distances.
+#
+# @param distances2 Squared distances
+# @param window Window parameter for the kernel
+#
+.computeSimils <- function(distances2, window)
+{
+	sd_dist = sd(distances2)
+	if (sd_dist < .25 * sqrt(.Machine$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))
+}
+
+.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
+	})
+}