[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, ...)
#		{
#			# Parameters (potentially) computed during shape prediction stage
#			predicted_shape = self$predictShape(data, today, memory, horizon, ...)
##			predicted_delta = private$.pjump(data,today,memory,horizon,private$.params,...)
#			# Predicted shape is aligned it on the end of current day + jump
##			predicted_shape+tail(data$getSerie(today),1)-predicted_shape[1]+predicted_delta
#			predicted_shape
#		},
		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, 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) < 1)
				return (NA)

			# Neighbors: days in "same season"
			sdays = getSimilarDaysIndices(today, limit=45, same_season=TRUE, data)
			indices = intersect(fdays,sdays)
			levelToday = data$getLevel(today)
			distances = sapply(indices, function(i) abs(data$getLevel(i)-levelToday))
			same_pollution = (distances <= 2)
			if (sum(same_pollution) < 1) #TODO: 3 == magic number
			{
				same_pollution = (distances <= 5)
				if (sum(same_pollution) < 1)
					return (NA)
			}
			indices = indices[same_pollution]

			#TODO: we shouldn't need that block
			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
#				sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
				sigma_inv = 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)
		}
	)
)
Commit	Line	Data
5c49f6ce BA	1	#' @include Forecaster.R
	2	#'
	3	#' Neighbors2 Forecaster
	4	#'
	5	#' Predict tomorrow as a weighted combination of "futures of the past" days.
	6	#' Inherits \code{\link{Forecaster}}
	7	#'
	8	Neighbors2Forecaster = R6::R6Class("Neighbors2Forecaster",
	9	inherit = Forecaster,
	10
	11	public = list(
a866acb3 BA	12	# predictSerie = function(data, today, memory, horizon, ...)
	13	# {
	14	# # Parameters (potentially) computed during shape prediction stage
	15	# predicted_shape = self$predictShape(data, today, memory, horizon, ...)
	16	## predicted_delta = private$.pjump(data,today,memory,horizon,private$.params,...)
	17	# # Predicted shape is aligned it on the end of current day + jump
	18	## predicted_shape+tail(data$getSerie(today),1)-predicted_shape[1]+predicted_delta
	19	# predicted_shape
	20	# },
5c49f6ce BA	21	predictShape = function(data, today, memory, horizon, ...)
	22	{
	23	# (re)initialize computed parameters
	24	private$.params <- list("weights"=NA, "indices"=NA, "window"=NA)
	25
	26	# Do not forecast on days with NAs (TODO: softer condition...)
	27	if (any(is.na(data$getCenteredSerie(today))))
	28	return (NA)
	29
	30	# Determine indices of no-NAs days followed by no-NAs tomorrows
9db234c5	31	fdays = getNoNA2(data, max(today-memory,1), today-1)
5c49f6ce BA	32
5c49f6ce BA	33	# Get optional args
5e838b3e	34	simtype = ifelse(hasArg("simtype"), list(...)$simtype, "mix") #or "endo", or "exo"
5c49f6ce BA	35	kernel = ifelse(hasArg("kernel"), list(...)$kernel, "Gauss") #or "Epan"
	36	if (hasArg(h_window))
	37	{
	38	return ( private$.predictShapeAux(data,
5e838b3e	39	fdays, today, horizon, list(...)$h_window, kernel, simtype, TRUE) )
5c49f6ce BA	40	}
5c49f6ce BA	41
9db234c5 BA	42	# Indices of similar days for cross-validation; TODO: 45 = magic number
	43	sdays = getSimilarDaysIndices(today, limit=45, same_season=FALSE)
	44
5e838b3e BA	45	cv_days = intersect(fdays,sdays)
	46	# Limit to 20 most recent matching days (TODO: 20 == magic number)
	47	cv_days = sort(cv_days,decreasing=TRUE)[1:min(20,length(cv_days))]
	48
5c49f6ce	49	# Function to optimize h : h \|--> sum of prediction errors on last 45 "similar" days
5e838b3e	50	errorOnLastNdays = function(h, kernel, simtype)
5c49f6ce BA	51	{
	52	error = 0
	53	nb_jours = 0
5e838b3e	54	for (i in seq_along(cv_days))
5c49f6ce BA	55	{
5c49f6ce BA	56	# mix_strategy is never used here (simtype != "mix"), therefore left blank
5e838b3e BA	57	prediction = private$.predictShapeAux(data,
5e838b3e BA	58	fdays, cv_days[i], horizon, h, kernel, simtype, FALSE)
5c49f6ce BA	59	if (!is.na(prediction[1]))
	60	{
	61	nb_jours = nb_jours + 1
	62	error = error +
5e838b3e	63	mean((data$getSerie(cv_days[i]+1)[1:horizon] - prediction)^2)
5c49f6ce BA	64	}
	65	}
	66	return (error / nb_jours)
	67	}
	68
5e838b3e BA	69	if (simtype != "endo")
	70	{
	71	h_best_exo = optimize(
	72	errorOnLastNdays, c(0,10), kernel=kernel, simtype="exo")$minimum
	73	}
	74	if (simtype != "exo")
	75	{
	76	h_best_endo = optimize(
	77	errorOnLastNdays, c(0,10), kernel=kernel, simtype="endo")$minimum
	78	}
	79
	80	if (simtype == "endo")
	81	{
	82	return (private$.predictShapeAux(data,
	83	fdays, today, horizon, h_best_endo, kernel, "endo", TRUE))
	84	}
	85	if (simtype == "exo")
	86	{
	87	return (private$.predictShapeAux(data,
	88	fdays, today, horizon, h_best_exo, kernel, "exo", TRUE))
	89	}
	90	if (simtype == "mix")
	91	{
	92	h_best_mix = c(h_best_endo,h_best_exo)
	93	return(private$.predictShapeAux(data,
	94	fdays, today, horizon, h_best_mix, kernel, "mix", TRUE))
	95	}
5c49f6ce BA	96	}
	97	),
	98	private = list(
	99	# Precondition: "today" is full (no NAs)
5e838b3e	100	.predictShapeAux = function(data, fdays, today, horizon, h, kernel, simtype, final_call)
5c49f6ce BA	101	{
	102	fdays = fdays[ fdays < today ]
	103	# TODO: 3 = magic number
a866acb3	104	if (length(fdays) < 1)
5c49f6ce BA	105	return (NA)
5c49f6ce BA	106
9db234c5 BA	107	# Neighbors: days in "same season"
	108	sdays = getSimilarDaysIndices(today, limit=45, same_season=TRUE, data)
	109	indices = intersect(fdays,sdays)
	110	levelToday = data$getLevel(today)
5e838b3e	111	distances = sapply(indices, function(i) abs(data$getLevel(i)-levelToday))
9db234c5	112	same_pollution = (distances <= 2)
a866acb3	113	if (sum(same_pollution) < 1) #TODO: 3 == magic number
5c49f6ce	114	{
9db234c5	115	same_pollution = (distances <= 5)
a866acb3	116	if (sum(same_pollution) < 1)
9db234c5	117	return (NA)
5c49f6ce	118	}
9db234c5 BA	119	indices = indices[same_pollution]
9db234c5 BA	120
a866acb3 BA	121	#TODO: we shouldn't need that block
	122	if (length(indices) == 1)
	123	{
	124	if (final_call)
	125	{
	126	private$.params$weights <- 1
	127	private$.params$indices <- indices
	128	private$.params$window <- 1
	129	}
	130	return ( data$getSerie(indices[1])[1:horizon] ) #what else?!
	131	}
	132
5e838b3e BA	133	if (simtype != "exo")
	134	{
	135	h_endo = ifelse(simtype=="mix", h[1], h)
9db234c5	136
5e838b3e BA	137	# Distances from last observed day to days in the past
	138	serieToday = data$getSerie(today)
	139	distances2 = sapply(indices, function(i) {
	140	delta = serieToday - data$getSerie(i)
	141	mean(delta^2)
	142	})
5c49f6ce	143
5e838b3e BA	144	sd_dist = sd(distances2)
	145	if (sd_dist < .Machine$double.eps)
	146	{
5c49f6ce	147	# warning("All computed distances are very close: stdev too small")
5e838b3e BA	148	sd_dist = 1 #mostly for tests... FIXME:
	149	}
	150	simils_endo =
	151	if (kernel=="Gauss")
	152	exp(-distances2/(sd_dist*h_endo^2))
	153	else
	154	{
	155	# Epanechnikov
	156	u = 1 - distances2/(sd_dist*h_endo^2)
	157	u[abs(u)>1] = 0.
	158	u
	159	}
5c49f6ce	160	}
5e838b3e BA	161
	162	if (simtype != "endo")
	163	{
	164	h_exo = ifelse(simtype=="mix", h[2], h)
	165
	166	M = matrix( nrow=1+length(indices), ncol=1+length(data$getExo(today)) )
	167	M[1,] = c( data$getLevel(today), as.double(data$getExo(today)) )
	168	for (i in seq_along(indices))
	169	M[i+1,] = c( data$getLevel(indices[i]), as.double(data$getExo(indices[i])) )
	170
	171	sigma = cov(M) #NOTE: robust covariance is way too slow
	172	# sigma_inv = solve(sigma) #TODO: use pseudo-inverse if needed?
	173	sigma_inv = MASS::ginv(sigma)
a866acb3	174
5e838b3e BA	175	# Distances from last observed day to days in the past
	176	distances2 = sapply(seq_along(indices), function(i) {
	177	delta = M[1,] - M[i+1,]
	178	delta %% sigma_inv %% delta
	179	})
	180
	181	sd_dist = sd(distances2)
	182	if (sd_dist < .25 * sqrt(.Machine$double.eps))
5c49f6ce	183	{
5e838b3e BA	184	# warning("All computed distances are very close: stdev too small")
5e838b3e BA	185	sd_dist = 1 #mostly for tests... FIXME:
5c49f6ce	186	}
5e838b3e BA	187	simils_exo =
	188	if (kernel=="Gauss")
	189	exp(-distances2/(sd_dist*h_exo^2))
	190	else
	191	{
	192	# Epanechnikov
	193	u = 1 - distances2/(sd_dist*h_exo^2)
	194	u[abs(u)>1] = 0.
	195	u
	196	}
	197	}
5c49f6ce	198
5e838b3e BA	199	similarities =
	200	if (simtype == "exo")
	201	simils_exo
	202	else if (simtype == "endo")
	203	simils_endo
	204	else #mix
	205	simils_endo * simils_exo
5c49f6ce BA	206
5c49f6ce BA	207	prediction = rep(0, horizon)
9db234c5 BA	208	for (i in seq_along(indices))
9db234c5 BA	209	prediction = prediction + similarities[i] * data$getSerie(indices[i]+1)[1:horizon]
5c49f6ce BA	210	prediction = prediction / sum(similarities, na.rm=TRUE)
	211
	212	if (final_call)
	213	{
	214	private$.params$weights <- similarities
a866acb3	215	private$.params$indices <- indices
5e838b3e BA	216	private$.params$window <-
	217	if (simtype=="endo")
	218	h_endo
	219	else if (simtype=="exo")
	220	h_exo
	221	else #mix
	222	c(h_endo,h_exo)
5c49f6ce BA	223	}
	224
	225	return (prediction)
	226	}
	227	)
	228	)