X-Git-Url: https://git.auder.net/?p=talweg.git;a=blobdiff_plain;f=pkg%2FR%2FgetData.R;h=df94895af633b137f29c6fc1462a6724d178f97e;hp=da4b4594bd30f2b761e55c37917be346cb0cb2a9;hb=25b75559e2d9bf84e2de35b851d93fefdae36e17;hpb=66877df35f2fc9561728537c713c963230b0de45

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index da4b459..df94895 100644
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -2,8 +2,7 @@
 #'
 #' @description Take in input data frames and/or files containing raw data, and timezones, and
 #'   output a Data object, roughly corresponding to a list where each cell contains all value
-#'   for one day (see \code{?Data}). Current limitation: series (in working_tz) must start at
-#'   right after midnight (to keep in sync with exogenous vars)
+#'   for one day (see \code{?Data}).
 #'
 #' @param ts_data Time-series, as a data frame (DB style: 2 columns, first is date/time,
 #'   second is value) or a CSV file
@@ -16,12 +15,19 @@
 #' @param predict_at When does the prediction take place ? Integer, in hours. Default: 0
 #' @param limit Number of days to extract (default: Inf, for "all")
 #'
-#' @return An object of class Data
+#' @return A list where data[[i]] contains
+#'   \itemize{
+#'     \item time: vector of times
+#'     \item centered_serie: centered serie
+#'     \item level: corresponding level
+#'     \item exo: exogenous variables
+#'     \item exo_hat: predicted exogenous variables
+#'   }
 #'
 #' @examples
 #' ts_data = read.csv(system.file("extdata","pm10_mesures_H_loc.csv",package="talweg"))
 #' exo_data = read.csv(system.file("extdata","meteo_extra_noNAs.csv",package="talweg"))
-#' getData(ts_data, exo_data, input_tz="Europe/Paris", working_tz="Europe/Paris", limit=150)
+#' data = getData(ts_data, exo_data, limit=120)
 #' @export
 getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%M",
 	working_tz="GMT", predict_at=0, limit=Inf)
@@ -62,7 +68,7 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 	line = 1 #index in PM10 file (24 lines for 1 cell)
 	nb_lines = nrow(ts_df)
 	nb_exos = ( ncol(exo_df) - 1 ) / 2
-	data = Data$new()
+	data = list()
 	i = 1 #index of a cell in data
 	while (line <= nb_lines)
 	{
@@ -83,18 +89,22 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 		exo_hat = as.data.frame( exo_df[i,(1+nb_exos+1):(1+2*nb_exos)] )
 		level = mean(serie, na.rm=TRUE)
 		centered_serie = serie - level
-		data$append(time, centered_serie, level, exo, exo_hat)
+		data[[i]] = list("time"=time, "centered_serie"=centered_serie, "level"=level,
+			"exo"=exo, "exo_hat"=exo_hat)
 		if (i >= limit)
 			break
 		i = i + 1
 	}
-	if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(1)))
-		data$removeFirst()
-	if (length(data$getCenteredSerie( data$getSize() )) <
-		length(data$getCenteredSerie( data$getSize()-1 )))
+	start = 1
+	end = length(data)
+	if (length(data[[1]]$centered_serie) < length(data[[2]]$centered_serie))
+		start = 2
+	if (length(data[[length(data)]]$centered_serie) <
+		length(data[[length(data)-1]]$centered_serie))
 	{
-		data$removeLast()
+		end = end-1
 	}
-
+	if (start>1 || end<length(data))
+		data = data[start:end]
 	data
 }