X-Git-Url: https://git.auder.net/?p=talweg.git;a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors2.R;h=60916b4d77c3f7b365c34ed6fb44cd6d3b219fd2;hp=69e69dcca8e1c8a6938b97d410013401f922ae63;hb=ea5c7e56ca05a51ce4f0535ffa08cda4c14bff4a;hpb=bb3e3cec32bc1bf05986a2bff438f4d29f2d9630

diff --git a/pkg/R/F_Neighbors2.R b/pkg/R/F_Neighbors2.R
index 69e69dc..60916b4 100644
--- a/pkg/R/F_Neighbors2.R
+++ b/pkg/R/F_Neighbors2.R
@@ -56,12 +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")
@@ -97,16 +97,25 @@ 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)
 				{
@@ -194,11 +203,11 @@ 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)
 
 			if (final_call)
 			{