X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors2.R;h=60916b4d77c3f7b365c34ed6fb44cd6d3b219fd2;hb=ea5c7e56ca05a51ce4f0535ffa08cda4c14bff4a;hp=83ef453093ed5b4430c1ef1cbbf5ace2ebc95902;hpb=a866acb3c0ae138b22df9dae9ec576b866794417;p=talweg.git

diff --git a/pkg/R/F_Neighbors2.R b/pkg/R/F_Neighbors2.R
index 83ef453..60916b4 100644
--- a/pkg/R/F_Neighbors2.R
+++ b/pkg/R/F_Neighbors2.R
@@ -9,15 +9,6 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 	inherit = Forecaster,
 
 	public = list(
-#		predictSerie = function(data, today, memory, horizon, ...)
-#		{
-#			# Parameters (potentially) computed during shape prediction stage
-#			predicted_shape = self$predictShape(data, today, memory, horizon, ...)
-##			predicted_delta = private$.pjump(data,today,memory,horizon,private$.params,...)
-#			# Predicted shape is aligned it on the end of current day + jump
-##			predicted_shape+tail(data$getSerie(today),1)-predicted_shape[1]+predicted_delta
-#			predicted_shape
-#		},
 		predictShape = function(data, today, memory, horizon, ...)
 		{
 			# (re)initialize computed parameters
@@ -39,12 +30,8 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 					fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
 			}
 
-			# Indices of similar days for cross-validation; TODO: 45 = magic number
-			sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
-
-			cv_days = intersect(fdays,sdays)
-			# Limit to 20 most recent matching days (TODO: 20 == magic number)
-			cv_days = sort(cv_days,decreasing=TRUE)[1:min(20,length(cv_days))]
+			# Indices of similar days for cross-validation; TODO: 20 = magic number
+			cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE, days_in=fdays)
 
 			# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
 			errorOnLastNdays = function(h, kernel, simtype)
@@ -60,7 +47,7 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 					{
 						nb_jours = nb_jours + 1
 						error = error +
-							mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
+							mean((data$getCenteredSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
 					}
 				}
 				return (error / nb_jours)
@@ -69,12 +56,12 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 			if (simtype != "endo")
 			{
 				h_best_exo = optimize(
-					errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
+					errorOnLastNdays, c(0,7), kernel=kernel, simtype="exo")$minimum
 			}
 			if (simtype != "exo")
 			{
 				h_best_endo = optimize(
-					errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
+					errorOnLastNdays, c(0,7), kernel=kernel, simtype="endo")$minimum
 			}
 
 			if (simtype == "endo")
@@ -99,35 +86,44 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 		# Precondition: "today" is full (no NAs)
 		.predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
 		{
-			fdays = fdays[ fdays < today ]
+			fdays_cut = fdays[ fdays < today ]
 			# TODO: 3 = magic number
-			if (length(fdays) < 1)
+			if (length(fdays_cut) < 3)
 				return (NA)
 
-			# Neighbors: days in "same season"
-			sdays = getSimilarDaysIndices(today, limit=45, same_season=TRUE, data)
-			indices = intersect(fdays,sdays)
+			# Neighbors: days in "same season"; 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$getLevel(today)
-			distances = sapply(indices, function(i) abs(data$getLevel(i)-levelToday))
-			same_pollution = (distances <= 2)
-			if (sum(same_pollution) < 1) #TODO: 3 == magic number
+			distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
+			#TODO: 2, 3, 5, 10 magic numbers here...
+			dist_thresh = 2
+			min_neighbs = min(3,length(fdays))
+			repeat
 			{
-				same_pollution = (distances <= 5)
-				if (sum(same_pollution) < 1)
-					return (NA)
+				same_pollution = (distances <= dist_thresh)
+				nb_neighbs = sum(same_pollution)
+				if (nb_neighbs >= min_neighbs) #will eventually happen
+					break
+				dist_thresh = dist_thresh + 3
 			}
-			indices = indices[same_pollution]
-
-			#TODO: we shouldn't need that block
-			if (length(indices) == 1)
+			fdays = fdays[same_pollution]
+			max_neighbs = 10
+			if (nb_neighbs > max_neighbs)
+			{
+				# Keep only max_neighbs closest neighbors
+				fdays = fdays[ sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
+			}
+			if (length(fdays) == 1) #the other extreme...
 			{
 				if (final_call)
 				{
 					private$.params$weights <- 1
-					private$.params$indices <- indices
+					private$.params$indices <- fdays
 					private$.params$window <- 1
 				}
-				return ( data$getSerie(indices[1])[1:horizon] ) #what else?!
+				return ( data$getSerie(fdays[1])[1:horizon] ) #what else?!
 			}
 
 			if (simtype != "exo")
@@ -136,7 +132,7 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 
 				# Distances from last observed day to days in the past
 				serieToday = data$getSerie(today)
-				distances2 = sapply(indices, function(i) {
+				distances2 = sapply(fdays, function(i) {
 					delta = serieToday - data$getSerie(i)
 					mean(delta^2)
 				})
@@ -163,17 +159,21 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 			{
 				h_exo = ifelse(simtype=="mix", h[2], h)
 
-				M = matrix( nrow=1+length(indices), ncol=1+length(data$getExo(today)) )
+				M = matrix( nrow=1+length(fdays), ncol=1+length(data$getExo(today)) )
 				M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
-				for (i in seq_along(indices))
-					M[i+1,] = c( data$getLevel(indices[i]), as.double(data$getExo(indices[i])) )
+				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
-#				sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
-				sigma_inv = MASS::ginv(sigma)
+				# 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(indices), function(i) {
+				distances2 = sapply(seq_along(fdays), function(i) {
 					delta = M[1,] - M[i+1,]
 					delta %*% sigma_inv %*% delta
 				})
@@ -203,16 +203,16 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 					simils_endo
 				else #mix
 					simils_endo * simils_exo
+			similarities = similarities / sum(similarities)
 
 			prediction = rep(0, horizon)
-			for (i in seq_along(indices))
-				prediction = prediction + similarities[i] * data$getSerie(indices[i]+1)[1:horizon]
-			prediction = prediction / sum(similarities, na.rm=TRUE)
+			for (i in seq_along(fdays))
+				prediction = prediction + similarities[i] * data$getCenteredSerie(fdays[i]+1)[1:horizon]
 
 			if (final_call)
 			{
 				private$.params$weights <- similarities
-				private$.params$indices <- indices
+				private$.params$indices <- fdays
 				private$.params$window <-
 					if (simtype=="endo")
 						h_endo