From 638f27f4296727aff62b56643beb9f42aa5b57ef Mon Sep 17 00:00:00 2001
From: Benjamin Auder <benjamin.auder@somewhere>
Date: Wed, 26 Apr 2017 16:55:41 +0200
Subject: [PATCH] adapt Bruno method into package, add 'operational' mode

---
 pkg/R/F_Average.R                          |  18 +++
 pkg/R/F_Neighbors.R                        | 131 +++++++++++++--------
 pkg/R/computeForecast.R                    |   2 +
 pkg/R/utils.R                              |  30 +++--
 pkg/tests/testthat/test-Forecaster.R       |   4 +-
 pkg/tests/testthat/test-computeFilaments.R |  42 +++----
 6 files changed, 143 insertions(+), 84 deletions(-)

diff --git a/pkg/R/F_Average.R b/pkg/R/F_Average.R
index 6cd2d6e..bee1974 100644
--- a/pkg/R/F_Average.R
+++ b/pkg/R/F_Average.R
@@ -23,6 +23,7 @@ AverageForecaster = R6::R6Class("AverageForecaster",
 			first_day = max(1, today-memory)
 			index <- today
 			nb_no_na_series = 0
+			opera = ifelse(hasArg("opera"), list(...)$opera, FALSE)
 			repeat
 			{
 				index = index - 7
@@ -35,6 +36,23 @@ AverageForecaster = R6::R6Class("AverageForecaster",
 					nb_no_na_series = nb_no_na_series + 1
 				}
 			}
+			if (!opera)
+			{
+				# The same, in the future
+				index <- today
+				repeat
+				{
+					index = index + 7
+					if (index > data$getSize())
+						break
+					serie_on_horizon = data$getCenteredSerie(index)[predict_from:horizon]
+					if (!any(is.na(serie_on_horizon)))
+					{
+						avg = avg + serie_on_horizon
+						nb_no_na_series = nb_no_na_series + 1
+					}
+				}
+			}
 			avg / nb_no_na_series
 		}
 	)
diff --git a/pkg/R/F_Neighbors.R b/pkg/R/F_Neighbors.R
index f140b0b..02536eb 100644
--- a/pkg/R/F_Neighbors.R
+++ b/pkg/R/F_Neighbors.R
@@ -51,21 +51,26 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				return (NA)
 			}
 
-			# Determine indices of no-NAs days preceded by no-NAs yerstedays
-			tdays = .getNoNA2(data, max(today-memory,2), 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"))
 			{
-				return ( private$.predictShapeAux(data,
-					tdays, today, predict_from, horizon, local, list(...)$window, simtype, TRUE) )
+				return ( private$.predictShapeAux(data, tdays, today, predict_from, horizon,
+					local, list(...)$window, simtype, opera, TRUE) )
 			}
 
 			# Indices of similar days for cross-validation; TODO: 20 = magic number
 			cv_days = getSimilarDaysIndices(today, data, limit=20, same_season=FALSE,
-				days_in=tdays)
+				days_in=tdays, operational=opera)
 
 			# Optimize h : h |--> sum of prediction errors on last N "similar" days
 			errorOnLastNdays = function(window, simtype)
@@ -76,7 +81,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				{
 					# 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, FALSE)
+						horizon, local, window, simtype, opera, FALSE)
 					if (!is.na(prediction[1]))
 					{
 						nb_jours = nb_jours + 1
@@ -110,27 +115,27 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 					1
 
 			return( private$.predictShapeAux(data, tdays, today, predict_from, horizon, local,
-				best_window, simtype, TRUE) )
+				best_window, simtype, opera, TRUE) )
 		}
 	),
 	private = list(
-		# Precondition: "today" is full (no NAs)
+		# Precondition: "yersteday until predict_from-1" is full (no NAs)
 		.predictShapeAux = function(data, tdays, today, predict_from, horizon, local, window,
-			simtype, final_call)
+			simtype, opera, final_call)
 		{
-			tdays_cut = tdays[ tdays <= today-1 ]
-			if (length(tdays_cut) <= 1)
+			tdays_cut = tdays[ tdays != today ]
+			if (length(tdays_cut) == 0)
 				return (NA)
 
 			if (local)
 			{
 				# TODO: 60 == magic number
 				tdays = getSimilarDaysIndices(today, data, limit=60, same_season=TRUE,
-					days_in=tdays_cut)
-				if (length(tdays) <= 1)
-					return (NA)
-				# TODO: 10, 12 == magic numbers
-				tdays = .getConstrainedNeighbs(today,data,tdays,min_neighbs=10,max_neighbs=12)
+					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)
 				{
 					if (final_call)
@@ -150,14 +155,19 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				# Compute endogen similarities using given window
 				window_endo = ifelse(simtype=="mix", window[1], window)
 
-				# Distances from last observed day to days in the past
-				lastSerie = c( data$getSerie(today-1),
-					data$getSerie(today)[if (predict_from>=2) 1:(predict_from-1) else c()] )
-				distances2 = 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))
-				})
+				# Distances from last observed day to selected days in the past
+				distances2 <- .computeDistsEndo(data, today, tdays, predict_from)
+
+				if (local)
+				{
+					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] ]
+					}
+				}
 
 				simils_endo <- .computeSimils(distances2, window_endo)
 			}
@@ -167,24 +177,7 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 				# Compute exogen similarities using given window
 				window_exo = ifelse(simtype=="mix", window[2], window)
 
-				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
-				distances2 = sapply(seq_along(tdays), function(i) {
-					delta = M[,1] - M[,i+1]
-					delta %*% sigma_inv %*% delta
-				})
+				distances2 <- .computeDistsExo(data, today, tdays)
 
 				simils_exo <- .computeSimils(distances2, window_exo)
 			}
@@ -237,12 +230,13 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 # @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, max_neighbs=12)
+.getConstrainedNeighbs = function(today, data, tdays, min_neighbs=10)
 {
 	levelToday = data$getLevelHat(today)
-	levelYersteday = data$getLevel(today-1)
+#	levelYersteday = data$getLevel(today-1)
 	distances = sapply(tdays, function(i) {
-		sqrt((data$getLevel(i-1)-levelYersteday)^2 + (data$getLevel(i)-levelToday)^2)
+#		sqrt((data$getLevel(i-1)-levelYersteday)^2 + (data$getLevel(i)-levelToday)^2)
+		abs(data$getLevel(i)-levelToday)
 	})
 	#TODO: 1, +1, +3 : magic numbers
 	dist_thresh = 1
@@ -256,12 +250,12 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 		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] ]
-	}
+#	max_neighbs = 12
+#	if (nb_neighbs > max_neighbs)
+#	{
+#		# Keep only max_neighbs closest neighbors
+#		tdays = tdays[ order(distances[same_pollution])[1:max_neighbs] ]
+#	}
 	tdays
 }
 
@@ -282,3 +276,36 @@ NeighborsForecaster = R6::R6Class("NeighborsForecaster",
 	}
 	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$getExo(tdays[i])) )
+
+	sigma = cov(t(M)) #NOTE: robust covariance is way too slow
+	# TODO: 10 == magic number; more robust way == det, or always ginv()
+	sigma_inv =
+		if (length(tdays) > 10)
+			solve(sigma)
+		else
+			MASS::ginv(sigma)
+
+	# Distances from last observed day to days in the past
+	sapply(seq_along(tdays), function(i) {
+		delta = M[,1] - M[,i+1]
+		delta %*% sigma_inv %*% delta
+	})
+}
diff --git a/pkg/R/computeForecast.R b/pkg/R/computeForecast.R
index ca8badd..ef46dd3 100644
--- a/pkg/R/computeForecast.R
+++ b/pkg/R/computeForecast.R
@@ -56,6 +56,8 @@ computeForecast = function(data, indices, forecaster, pjump, predict_from,
 	predict_from = as.integer(predict_from)[1]
 	if (! predict_from %in% 1:length(data$getSerie(1)))
 		stop("predict_from in [1,24] (hours)")
+	if (hasArg("opera") && !list(...)$opera && memory < Inf)
+		memory <- Inf #finite memory in training mode makes no sense
 	horizon = as.integer(horizon)[1]
 	if (horizon<=predict_from || horizon>length(data$getSerie(1)))
 		stop("Horizon in [predict_from+1,24] (hours)")
diff --git a/pkg/R/utils.R b/pkg/R/utils.R
index a4efd61..bb76996 100644
--- a/pkg/R/utils.R
+++ b/pkg/R/utils.R
@@ -63,7 +63,8 @@ integerIndexToDate = function(index, data)
 #' @param days_in Optional set to intersect with results (NULL to discard)
 #'
 #' @export
-getSimilarDaysIndices = function(index, data, limit, same_season, days_in=NULL)
+getSimilarDaysIndices = function(index, data, limit, same_season,
+	days_in=NULL, operational=TRUE)
 {
 	index = dateIndexToInteger(index, data)
 
@@ -73,15 +74,30 @@ getSimilarDaysIndices = function(index, data, limit, same_season, days_in=NULL)
 	day_ref = dt_ref$wday #1=monday, ..., 6=saturday, 0=sunday
 	month_ref = as.POSIXlt(data$getTime(index)[1])$mon+1 #month in 1...12
 	i = index - 1
-	while (i >= 1 && length(days) < limit)
+	if (!operational)
+		j = index + 1
+	while (length(days) < min( limit, ifelse(is.null(days_in),Inf,length(days_in)) ))
 	{
-		dt = as.POSIXlt(data$getTime(i)[1])
-		if ((is.null(days_in) || i %in% days_in) && .isSameDay(dt$wday, day_ref))
+		if (i >= 1)
 		{
-			if (!same_season || .isSameSeason(dt$mon+1, month_ref))
-				days = c(days, i)
+			dt = as.POSIXlt(data$getTime(i)[1])
+			if ((is.null(days_in) || i %in% days_in) && .isSameDay(dt$wday, day_ref))
+			{
+				if (!same_season || .isSameSeason(dt$mon+1, month_ref))
+					days = c(days, i)
+			}
+			i = i - 1
+		}
+		if (!operational && j <= data$getSize())
+		{
+			dt = as.POSIXlt(data$getTime(j)[1])
+			if ((is.null(days_in) || j %in% days_in) && .isSameDay(dt$wday, day_ref))
+			{
+				if (!same_season || .isSameSeason(dt$mon+1, month_ref))
+					days = c(days, j)
+			}
+			j = j + 1
 		}
-		i = i - 1
 	}
 	return ( days )
 }
diff --git a/pkg/tests/testthat/test-Forecaster.R b/pkg/tests/testthat/test-Forecaster.R
index 78e387a..3f5cf9c 100644
--- a/pkg/tests/testthat/test-Forecaster.R
+++ b/pkg/tests/testthat/test-Forecaster.R
@@ -97,12 +97,12 @@ test_that("Neighbors method behave as expected",
 {
 	#Situation A: +Zero; correct if jump, wrong otherwise
 	pred00 = computeForecast(data_p, indices, "Neighbors", "Zero", 1, Inf, 24,
-		simtype="mix", local=FALSE)
+		simtype="mix", local=FALSE, window=c(1,1))
 	for (i in 1:7)
 		expect_equal(pred00$getForecast(i), rep(pred_order[i],24))
 
 	pred13 = computeForecast(data_p, indices, "Persistence", "Zero", 14, Inf, 24,
-		simtype="mix", local=FALSE)
+		simtype="mix", local=FALSE, window=c(1,1))
 	for (i in 1:7)
 		expect_equal(pred13$getForecast(i), rep(i,24) )
 
diff --git a/pkg/tests/testthat/test-computeFilaments.R b/pkg/tests/testthat/test-computeFilaments.R
index 6169a77..0c58c69 100644
--- a/pkg/tests/testthat/test-computeFilaments.R
+++ b/pkg/tests/testthat/test-computeFilaments.R
@@ -4,55 +4,51 @@ test_that("output is as expected on simulated series",
 {
 	data = getDataTest(150)
 
-
-
-
-#TODO: debug
-
-
-
-	# index 144-1 == 143 : serie type 2
-	pred = computeForecast(data, 143, "Neighbors", "Zero", predict_from=8,
-		horizon=length(data$getSerie(1)), simtype="endo", local=FALSE, h_window=1)
+	# index 144 : serie type 3, yersteday type 2
+	pred = computeForecast(data, 144, "Neighbors", "Zero", predict_from=1,
+		horizon=length(data$getSerie(1)), simtype="endo", local=FALSE, window=1, opera=TRUE)
 	f = computeFilaments(data, pred, 1, 8, limit=60, plot=FALSE)
 
-	# Expected output: 50-3-10 series of type 2, then 23 series of type 3 (closest next)
+	# Expected output: 50-3-10 series of type 2+1 = 3,
+	# then 23 series of type 3+1 %% 3 = 1 (3 = closest next)
 	expect_identical(length(f$neighb_indices), as.integer(60))
 	expect_identical(length(f$colors), as.integer(60))
-	expect_equal(f$index, 143)
-	expect_true(all(I(f$neighb_indices) >= 2))
+	expect_equal(f$index, 144)
+	expect_true(all(I(f$neighb_indices) != 2))
 	for (i in 1:37)
 	{
-		expect_equal(I(f$neighb_indices[i]), 2)
+		expect_equal(I(f$neighb_indices[i]), 3)
 		expect_match(f$colors[i], f$colors[1])
 	}
 	for (i in 38:60)
 	{
-		expect_equal(I(f$neighb_indices[i]), 3)
+		expect_equal(I(f$neighb_indices[i]), 1)
 		expect_match(f$colors[i], f$colors[38])
 	}
 	expect_match(f$colors[1], "#1*")
 	expect_match(f$colors[38], "#E*")
 
-	# index 143-1 == 142 : serie type 1
-	pred = computeForecast(data, 143, "Neighbors", "Zero", predict_from=8,
-		horizon=length(data$getSerie(1)), simtype="endo", local=FALSE, h_window=1)
+	# index 143 : serie type 2
+	pred = computeForecast(data, 143, "Neighbors", "Zero", predict_from=1,
+		horizon=length(data$getSerie(1)), simtype="endo", local=FALSE, window=1, opera=TRUE)
 	f = computeFilaments(data, pred, 1, 8, limit=50, plot=FALSE)
 
-	# Expected output: 50-10-3 series of type 1, then 13 series of type 3 (closest next)
-	# NOTE: -10 because only past days with no-NAs tomorrow => exclude type 1 in [60,90[
+	# Expected output: 50-10-3 series of type 1+1=2,
+	# then 13 series of type 3+1 %% 3 = 1 (closest next)
+	# NOTE: -10 because only past tomorrows with no-NAs yerstedays
+	#        => exclude type 2 in [60,90[
 	expect_identical(length(f$neighb_indices), as.integer(50))
 	expect_identical(length(f$colors), as.integer(50))
 	expect_equal(f$index, 143)
-	expect_true(all(I(f$neighb_indices) != 2))
+	expect_true(all(I(f$neighb_indices) <= 2))
 	for (i in 1:37)
 	{
-		expect_equal(I(f$neighb_indices[i]), 1)
+		expect_equal(I(f$neighb_indices[i]), 2)
 		expect_match(f$colors[i], f$colors[1])
 	}
 	for (i in 38:50)
 	{
-		expect_equal(I(f$neighb_indices[i]), 3)
+		expect_equal(I(f$neighb_indices[i]), 1)
 		expect_match(f$colors[i], f$colors[38])
 	}
 	expect_match(f$colors[1], "#1*")
-- 
2.44.0