Simplify plots: version OK with R6 classes

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

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

	public = list(
		predictShape = function(data, today, memory, horizon, ...)
		{
			# (re)initialize computed parameters
			private$.params <- list("weights"=NA, "indices"=NA, "window"=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, limit=45, same_season=FALSE)

			# 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 intersect(fdays,sdays))
				{
					# mix_strategy is never used here (simtype != "mix"), therefore left blank
					prediction = private$.predictShapeAux(data,
						fdays, i, horizon, h, kernel, simtype, FALSE)
					if (!is.na(prediction[1]))
					{
						nb_jours = nb_jours + 1
						error = error +
							mean((data$getCenteredSerie(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)

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

				# Distances from last observed day to days in the past
				distances2 = rep(NA, length(fdays))
				for (i in seq_along(fdays))
				{
					delta = data$getCenteredSerie(today) - data$getCenteredSerie(fdays[i])
					# Require at least half of non-NA common values to compute the distance
					if (sum(is.na(delta)) <= 0) #length(delta)/2)
						distances2[i] = mean(delta^2) #, na.rm=TRUE)
				}

				sd_dist = sd(distances2)
				if (sd_dist < .Machine$double.eps)
					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(fdays), ncol=1+length(data$getExo(today)) )
				M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
				for (i in seq_along(fdays))
					M[i+1,] = c( data$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?

				# Distances from last observed day to days in the past
				distances2 = rep(NA, nrow(M)-1)
				for (i in 2:nrow(M))
				{
					delta = M[1,] - M[i,]
					distances2[i-1] = delta %*% sigma_inv %*% delta
				}

				sd_dist = sd(distances2)
				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(fdays))
				prediction = prediction + similarities[i] * data$getSerie(fdays[i]+1)[1:horizon]
			prediction = prediction / sum(similarities, na.rm=TRUE)

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

			return (prediction)
		}
	)
)