X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FcomputeForecast.R;h=e1b29b6b9c9a800e946031f663589937963e1cdf;hb=8ab6420267542d34b7428f978aa76ba939b9754b;hp=3537e8a8c2ba090b46989a3aafc88605f2840682;hpb=5e838b3e17465c376ca075b766cf2543c82e9864;p=talweg.git

diff --git a/pkg/R/computeForecast.R b/pkg/R/computeForecast.R
index 3537e8a..e1b29b6 100644
--- a/pkg/R/computeForecast.R
+++ b/pkg/R/computeForecast.R
@@ -1,82 +1,117 @@
 #' Compute forecast
 #'
-#' Predict time-series curves for the selected days indices (lines in data).
+#' Predict time-series curves ("today" from predict_from to horizon) at the selected days
+#' indices ("today" from 1am to predict_from-1). This function just runs a loop over all
+#' requested indices, and stores the individual forecasts into a Forecast object.
 #'
-#' @param data Dataset, object of type \code{Data} output of \code{getData}
-#' @param indices Days indices where to forecast (the day after)
-#' @param forecaster Name of the main forcaster
-#' \itemize{
-#'   \item Persistence : use values of last (similar, next) day
-#'   \item Neighbors : use values from the k closest neighbors' tomorrows
-#'   \item Average : global average of all the (similar) "tomorrow of past"
-#'   \item Zero : just output 0 (benchmarking purpose)
-#' }
-#' @param pjump How to predict the jump at the interface between two days ?
-#' \itemize{
-#'   \item Persistence : use last (similar) day values
-#'   \item Neighbors: re-use the weights optimized in corresponding forecaster
-#'   \item Zero: just output 0 (no adjustment)
-#' }
-#' @param memory Data depth (in days) to be used for prediction
-#' @param horizon Number of time steps to predict
-#' @param ... Additional parameters for the forecasting models
+#' @param data Object of class Data, output of \code{getData()}.
+#' @param indices Indices where to forecast (the day after); integers relative to the
+#'   beginning of data, or (convertible to) Date objects.
+#' @param forecaster Name of the main forecaster; more details: ?F_<forecastername>
+#'   \itemize{
+#'     \item Persistence : use last (similar) day
+#'     \item Neighbors : weighted similar days
+#'     \item Average : average curve of all same day-in-week
+#'     \item Zero : just output 0 (benchmarking purpose)
+#'   }
+#' @param pjump Function to predict the jump at the interface between two days;
+#'   more details: ?J_<functionname>
+#'   \itemize{
+#'     \item Persistence : use last (similar) day
+#'     \item Neighbors: re-use the weights from F_Neighbors
+#'     \item Zero: just output 0 (no adjustment)
+#'   }
+#'   If pjump=NULL, then no adjustment is performed (output of \code{predictShape()} is
+#'   used directly).
+#' @param predict_from First time step to predict.
+#' @param memory Data depth (in days) to be used for prediction.
+#' @param horizon Last time step to predict.
+#' @param ncores Number of cores for parallel execution (1 to disable).
+#' @param verbose TRUE to print basic traces (runs beginnings)
+#' @param ... Additional parameters for the forecasting models.
 #'
 #' @return An object of class Forecast
 #'
 #' @examples
-#' ts_data = system.file("extdata","pm10_mesures_H_loc.csv",package="talweg")
-#' exo_data = system.file("extdata","meteo_extra_noNAs.csv",package="talweg")
-#' data = getData(ts_data, exo_data, input_tz = "Europe/Paris",
-#'   working_tz="Europe/Paris", predict_at=7)
-#' pred = computeForecast(data, 2200:2230, "Persistence", "Persistence", 500, 12)
-#' \dontrun{#Sketch for real-time mode:
-#' data = new("Data", ...)
-#' forecaster = new(..., data=data)
+#' ts_data <- system.file("extdata","pm10_mesures_H_loc.csv",package="talweg")
+#' exo_data <- system.file("extdata","meteo_extra_noNAs.csv",package="talweg")
+#' data <- getData(ts_data, exo_data, limit=200)
+#' pred <- computeForecast(data, 100:130, "Persistence", "Zero",
+#'   predict_from=8, memory=50, horizon=12, ncores=1)
+#' \dontrun{
+#' #Sketch for real-time mode:
+#' data <- Data$new()
+#' forecaster <- MyForecaster$new(myJumpPredictFunc)
 #' repeat {
-#'   data$append(some_new_data)
-#'   pred = forecaster$predict(data$getSize(), ...)
+#'   # As soon as daily predictions are available:
+#'   data$append(
+#'     level_hat=predicted_level,
+#'     exo_hat=predicted_exogenous)
+#'   # When a day ends:
+#'   data$append(
+#'     level=observed_level,
+#'     exo=observed_exogenous)
+#'   # And, at every hour:
+#'   data$append(
+#'     time=current_hour,
+#'     value=current_PM10)
+#'   # Finally, a bit before predict_from hour:
+#'   pred <- forecaster$predictSerie(data, data$getSize(), ...)
 #'   #do_something_with_pred
-#' }}
+#' } }
 #' @export
-computeForecast = function(data, indices, forecaster, pjump,
-	memory=Inf, horizon=data$getStdHorizon(), ...)
+computeForecast = function(data, indices, forecaster, pjump, predict_from,
+	memory=Inf, horizon=length(data$getSerie(1)), ncores=3, verbose=FALSE, ...)
 {
 	# (basic) Arguments sanity checks
+	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<=0 || horizon>length(data$getCenteredSerie(2)))
-		stop("Horizon too short or too long")
+	if (horizon<=predict_from || horizon>length(data$getSerie(1)))
+		stop("Horizon in [predict_from+1,24] (hours)")
 	integer_indices = sapply(indices, function(i) dateIndexToInteger(i,data))
 	if (any(integer_indices<=0 | integer_indices>data$getSize()))
 		stop("Indices out of range")
-	if (!is.character(forecaster) || !is.character(pjump))
-		stop("forecaster (name) and pjump (function) should be of class character")
+	if (!is.character(forecaster))
+		stop("forecaster (name): character")
+	if (!is.null(pjump) && !is.character(pjump))
+		stop("pjump (function): character or NULL")
 
 	pred = Forecast$new( sapply(indices, function(i) integerIndexToDate(i,data)) )
-	forecaster_class_name = getFromNamespace(paste(forecaster,"Forecaster",sep=""), "talweg")
-	forecaster = forecaster_class_name$new( #.pjump =
-		getFromNamespace(paste("get",pjump,"JumpPredict",sep=""), "talweg"))
+	forecaster_class_name = getFromNamespace(
+		paste(forecaster,"Forecaster",sep=""), "talweg")
 
-#oo = forecaster$predictSerie(data, integer_indices[1], memory, horizon, ...)
-#browser()
+	if (!is.null(pjump))
+		pjump <- getFromNamespace(paste("get",pjump,"JumpPredict",sep=""), "talweg")
+	forecaster = forecaster_class_name$new(pjump)
 
-	library(parallel)
-	ppp <- parallel::mclapply(seq_along(integer_indices), function(i) {
+	computeOneForecast <- function(i)
+	{
+		if (verbose)
+			print(paste("Index",i))
 		list(
-			"forecast" = forecaster$predictSerie(data, integer_indices[i], memory, horizon, ...),
-			"params"= forecaster$getParameters(),
-			"index" = integer_indices[i] )
-		}, mc.cores=3)
+			"forecast" = forecaster$predictSerie(data,i,memory,predict_from,horizon,...),
+			"params" = forecaster$getParameters(),
+			"index" = i )
+	}
 
-#browser()
-
-for (i in seq_along(integer_indices))
-{
-	pred$append(
-			new_serie = ppp[[i]]$forecast,
-			new_params = ppp[[i]]$params,
-			new_index_in_data = ppp[[i]]$index
-	)
-}
+	p <-
+		if (ncores > 1 && requireNamespace("parallel",quietly=TRUE))
+			parallel::mclapply(integer_indices, computeOneForecast, mc.cores=ncores)
+		else
+			lapply(integer_indices, computeOneForecast)
 
+	# TODO: find a way to fill pred in //...
+	for (i in seq_along(integer_indices))
+	{
+		pred$append(
+			forecast = p[[i]]$forecast,
+			params = p[[i]]$params,
+			index_in_data = p[[i]]$index
+		)
+	}
 	pred
 }