X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FF_Neighbors.R;h=27cd23a7c31a5ad5691434568afee26c96499410;hb=ea5c7e56ca05a51ce4f0535ffa08cda4c14bff4a;hp=5b2c8990a850d2dff0d75c23d67815e7393ccd07;hpb=5e838b3e17465c376ca075b766cf2543c82e9864;p=talweg.git

diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index 5b2c899..27cd23a 100644
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -30,12 +30,8 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					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)
@@ -60,12 +56,12 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 			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")
@@ -134,7 +130,12 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					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?
+				# 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(fdays), function(i) {
@@ -143,7 +144,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				})
 
 				sd_dist = sd(distances2)
-				if (sd_dist < .Machine$double.eps)
+				if (sd_dist < .25 * sqrt(.Machine$double.eps))
 				{
 #					warning("All computed distances are very close: stdev too small")
 					sd_dist = 1 #mostly for tests... FIXME:
@@ -167,11 +168,11 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					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)
 			{