X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FcomputeForecast.R;h=a4a539aaf83a8e48411a5a81a268898bd36e351e;hb=3ddf1c12af0c167fe7d3bb59e63258550270cfc5;hp=8cf8861a39b33909aed575c2d587f6c12a05feaa;hpb=98e958cab563866f8e00886b54336018a2e8bc97;p=talweg.git

diff --git a/pkg/R/computeForecast.R b/pkg/R/computeForecast.R
index 8cf8861..a4a539a 100644
--- a/pkg/R/computeForecast.R
+++ b/pkg/R/computeForecast.R
@@ -1,49 +1,60 @@
 #' Compute forecast
 #'
-#' Predict time-series curves for the selected days indices (lines in data).
+#' Predict time-series curves ("tomorrows") at the selected days indices ("todays").
+#' This function just runs a loop over all requested indices, and stores the individual
+#' forecasts into a list which is then turned 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
+#' @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 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 Persistence : use last (similar, next) day
+#'   \item Neighbors : weighted tomorrows of similar days
+#'   \item Average : average tomorrow of all same day-in-week
 #'   \item Zero : just output 0 (benchmarking purpose)
 #' }
-#' @param pjump How to predict the jump at the interface between two days ?
+#' @param pjump Function to predict the jump at the interface between two days;
+#'   more details: ?J_<functionname>
 #' \itemize{
-#'   \item Persistence : use last (similar) day values
-#'   \item Neighbors: re-use the weights optimized in corresponding forecaster
+#'   \item Persistence : use last (similar, next) day
+#'   \item Neighbors: re-use the weights from F_Neighbors
 #'   \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 memory Data depth (in days) to be used for prediction.
+#' @param horizon Number of time steps to predict.
+#' @param ncores Number of cores for parallel execution (1 to disable).
+#' @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)
+#' 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="GMT", working_tz="GMT",
+#'   predict_at=7, limit=200)
+#' pred <- computeForecast(data, 100:130, "Persistence", "Zero",
+#'   memory=50, horizon=12, ncores=1)
 #' \dontrun{#Sketch for real-time mode:
-#' data = new("Data", ...)
-#' forecaster = new(..., data=data)
+#' data <- Data$new()
+#' forecaster <- MyForecaster$new(myJumpPredictFunc)
 #' repeat {
-#'   data$append(some_new_data)
-#'   pred = forecaster$predict(data$getSize(), ...)
+#'   # In the morning 7am+ or afternoon 1pm+:
+#'   data$append(
+#'     times_from_H+1_yersteday_to_Hnow,
+#'     PM10_values_of_last_24h,
+#'     exogenous_measures_of_last_24h,
+#'     exogenous_predictions_for_next_24h)
+#'   pred <- forecaster$predictSerie(data, data$getSize(), ...)
 #'   #do_something_with_pred
 #' }}
 #' @export
 computeForecast = function(data, indices, forecaster, pjump,
-	memory=Inf, horizon=data$getStdHorizon(), ...)
+	memory=Inf, horizon=data$getStdHorizon(), ncores=3, ...)
 {
 	# (basic) Arguments sanity checks
 	horizon = as.integer(horizon)[1]
-	if (horizon<=0 || horizon>length(data$getCenteredSerie(2)))
+	if (horizon<=0 || horizon>length(data$getCenteredSerie(1)))
 		stop("Horizon too short or too long")
 	integer_indices = sapply(indices, function(i) dateIndexToInteger(i,data))
 	if (any(integer_indices<=0 | integer_indices>data$getSize()))
@@ -52,15 +63,39 @@ computeForecast = function(data, indices, forecaster, pjump,
 		stop("forecaster (name) and pjump (function) should be of class character")
 
 	pred = Forecast$new( sapply(indices, function(i) integerIndexToDate(i,data)) )
-	forecaster_class_name = getFromNamespace(paste(forecaster,"Forecaster",sep=""), "talweg")
+	forecaster_class_name = getFromNamespace(
+		paste(forecaster,"Forecaster",sep=""), "talweg")
 	forecaster = forecaster_class_name$new( #.pjump =
 		getFromNamespace(paste("get",pjump,"JumpPredict",sep=""), "talweg"))
-	for (today in integer_indices)
+
+	if (ncores > 1 && requireNamespace("parallel",quietly=TRUE))
+	{
+		p <- parallel::mclapply(seq_along(integer_indices), function(i) {
+			list(
+				"forecast" = forecaster$predictSerie(
+					data, integer_indices[i], memory, horizon, ...),
+				"params"= forecaster$getParameters(),
+				"index" = integer_indices[i] )
+			}, mc.cores=ncores)
+	}
+	else
+	{
+		p <- lapply(seq_along(integer_indices), function(i) {
+			list(
+				"forecast" = forecaster$predictSerie(
+					data, integer_indices[i], memory, horizon, ...),
+				"params"= forecaster$getParameters(),
+				"index" = integer_indices[i] )
+			})
+	}
+
+	# TODO: find a way to fill pred in //...
+	for (i in seq_along(integer_indices))
 	{
 		pred$append(
-			new_serie = forecaster$predictSerie(data, today, memory, horizon, ...),
-			new_params = forecaster$getParameters(),
-			new_index_in_data = today
+			forecast = p[[i]]$forecast,
+			params = p[[i]]$params,
+			index_in_data = p[[i]]$index
 		)
 	}
 	pred