X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors2.R;h=ee40f61192dd744451e9e447ee1b5d8b62f404d1;hb=9003747badc4416d68cab45ff17de3ecea327942;hp=69e69dcca8e1c8a6938b97d410013401f922ae63;hpb=6774e53de7b8bdac191d6203a380ad46c3b4d9ba;p=talweg.git

diff --git a/pkg/R/F_Neighbors2.R b/pkg/R/F_Neighbors2.R
index 69e69dc..ee40f61 100644
--- a/pkg/R/F_Neighbors2.R
+++ b/pkg/R/F_Neighbors2.R
@@ -46,8 +46,7 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 					if (!is.na(prediction[1]))
 					{
 						nb_jours = nb_jours + 1
-						error = error +
-							mean((data$getCenteredSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
+						error = error + mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
 					}
 				}
 				return (error / nb_jours)
@@ -56,12 +55,12 @@ 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")
@@ -97,16 +96,25 @@ Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
 				return (NA)
 			levelToday = data$getLevel(today)
 			distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
-			dist_thresh = 1
+			#TODO: 2, 3, 5, 10 magic numbers here...
+			dist_thresh = 2
+			min_neighbs = min(3,length(fdays))
 			repeat
 			{
 				same_pollution = (distances <= dist_thresh)
-				if (sum(same_pollution) >= 2) #will eventually happen
+				nb_neighbs = sum(same_pollution)
+				if (nb_neighbs >= min_neighbs) #will eventually happen
 					break
-				dist_thresh = dist_thresh + 1
+				dist_thresh = dist_thresh + 3
 			}
 			fdays = fdays[same_pollution]
-			if (length(fdays) == 1)
+			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)
 				{
@@ -194,14 +202,15 @@ 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(fdays))
-				prediction = prediction + similarities[i] * data$getCenteredSerie(fdays[i]+1)[1:horizon]
-			prediction = prediction / sum(similarities, na.rm=TRUE)
+				prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
 
 			if (final_call)
 			{
+				prediction = prediction - mean(prediction) #predict centered serie (artificial...)
 				private$.params$weights <- similarities
 				private$.params$indices <- fdays
 				private$.params$window <-