fix methods, update report generation

[talweg.git] / pkg / R / F_Neighbors2.R

#' @include Forecaster.R
#'
#' Neighbors2 Forecaster
#'
#' Predict tomorrow as a weighted combination of "futures of the past" days.
#' Inherits \code{\link{Forecaster}}
#'
Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
	inherit = Forecaster,

	public = list(
		predictSerie = function(data, today, memory, horizon, ...)
		{
			# This method predict shape + level at the same time, all in next call
			self$predictShape(data, today, memory, horizon, ...)
		},
		predictShape = function(data, today, memory, horizon, ...)
		{
			# (re)initialize computed parameters
			private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)

			# Do not forecast on days with NAs (TODO: softer condition...)
			if (any(is.na(data$getCenteredSerie(today))))
				return (NA)

			# Determine indices of no-NAs days followed by no-NAs tomorrows
			fdays = getNoNA2(data, max(today-memory,1), today-1)

			# Get optional args
			simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
			kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
			if (hasArg(h_window))
			{
				return ( private$.predictShapeAux(data,
					fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
			}

			# Indices of similar days for cross-validation; TODO: 45 = magic number
			sdays = getSimilarDaysIndices(today, data, 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))]

			# Function to optimize h : h |--> sum of prediction errors on last 45 "similar" days
			errorOnLastNdays = function(h, kernel, simtype)
			{
				error = 0
				nb_jours = 0
				for (i in seq_along(cv_days))
				{
					# mix_strategy is never used here (simtype != "mix"), therefore left blank
					prediction = private$.predictShapeAux(data,
						fdays, cv_days[i], horizon, h, kernel, simtype, FALSE)
					if (!is.na(prediction[1]))
					{
						nb_jours = nb_jours + 1
						error = error +
							mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
					}
				}
				return (error / nb_jours)
			}

			if (simtype != "endo")
			{
				h_best_exo = optimize(
					errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
			}
			if (simtype != "exo")
			{
				h_best_endo = optimize(
					errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
			}

			if (simtype == "endo")
			{
				return (private$.predictShapeAux(data,
					fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
			}
			if (simtype == "exo")
			{
				return (private$.predictShapeAux(data,
					fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
			}
			if (simtype == "mix")
			{
				h_best_mix = c(h_best_endo,h_best_exo)
				return(private$.predictShapeAux(data,
					fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
			}
		}
	),
	private = list(
		# Precondition: "today" is full (no NAs)
		.predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
		{
			fdays = fdays[ fdays < today ]
			# TODO: 3 = magic number
			if (length(fdays) < 3)
				return (NA)

			# Neighbors: days in "same season"
			sdays = getSimilarDaysIndices(today, data, limit=45, same_season=TRUE)
			indices = intersect(fdays,sdays)
			if (length(indices) <= 1)
				return (NA)
			levelToday = data$getLevel(today)
			distances = sapply(indices, function(i) abs(data$getLevel(i)-levelToday))
			# 2 and 5 below == magic numbers (determined by Bruno & Michel)
			same_pollution = (distances <= 2)
			if (sum(same_pollution) == 0)
			{
				same_pollution = (distances <= 5)
				if (sum(same_pollution) == 0)
					return (NA)
			}
			indices = indices[same_pollution]
			if (length(indices) == 1)
			{
				if (final_call)
				{
					private$.params$weights <- 1
					private$.params$indices <- indices
					private$.params$window <- 1
				}
				return ( data$getSerie(indices[1])[1:horizon] ) #what else?!
			}

			if (simtype != "exo")
			{
				h_endo = ifelse(simtype=="mix", h[1], h)

				# Distances from last observed day to days in the past
				serieToday = data$getSerie(today)
				distances2 = sapply(indices, function(i) {
					delta = serieToday - data$getSerie(i)
					mean(delta^2)
				})

				sd_dist = sd(distances2)
				if (sd_dist < .Machine$double.eps)
				{
#					warning("All computed distances are very close: stdev too small")
					sd_dist = 1 #mostly for tests... FIXME:
				}
				simils_endo =
					if (kernel=="Gauss")
						exp(-distances2/(sd_dist*h_endo^2))
					else
					{
						# Epanechnikov
						u = 1 - distances2/(sd_dist*h_endo^2)
						u[abs(u)>1] = 0.
						u
					}
			}

			if (simtype != "endo")
			{
				h_exo = ifelse(simtype=="mix", h[2], h)

				M = matrix( nrow=1+length(indices), 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])) )

				sigma = cov(M) #NOTE: robust covariance is way too slow
				# TODO: 10 == magic number; more robust way == det, or always ginv()
				sigma_inv =
					if (length(indices) > 10)
						solve(sigma)
					else
						MASS::ginv(sigma)

				# Distances from last observed day to days in the past
				distances2 = sapply(seq_along(indices), function(i) {
					delta = M[1,] - M[i+1,]
					delta %*% sigma_inv %*% delta
				})

				sd_dist = sd(distances2)
				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:
				}
				simils_exo =
					if (kernel=="Gauss")
						exp(-distances2/(sd_dist*h_exo^2))
					else
					{
						# Epanechnikov
						u = 1 - distances2/(sd_dist*h_exo^2)
						u[abs(u)>1] = 0.
						u
					}
			}

			similarities =
				if (simtype == "exo")
					simils_exo
				else if (simtype == "endo")
					simils_endo
				else #mix
					simils_endo * simils_exo

			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)

			if (final_call)
			{
				private$.params$weights <- similarities
				private$.params$indices <- indices
				private$.params$window <-
					if (simtype=="endo")
						h_endo
					else if (simtype=="exo")
						h_exo
					else #mix
						c(h_endo,h_exo)
			}

			return (prediction)
		}
	)
)