X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FgetData.R;h=d0e69d73daaf374c2e655d9b82df7de5090aaa56;hb=0730374e2981d7b950dced9f667713865b44b390;hp=b095d01ea3a4c7002b79cdfecd4caf98757846c7;hpb=2057c793ad9929ed5bef8663ea28b896c84df0fc;p=talweg.git

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index b095d01..d0e69d7 100644
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -1,19 +1,17 @@
-#' @title Acquire data in a clean format
+#' getData
 #'
-#' @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}).
+#' Acquire data as a Data object; see ?Data.
+#'
+#' Since series are given in columns (database format), this function builds series one
+#' by one and incrementally grows a Data object which is finally returned.
 #'
 #' @param ts_data Time-series, as a data frame (DB style: 2 columns, first is date/time,
-#'   second is value) or a CSV file
-#' @param exo_data Exogenous variables, as a data frame or a CSV file; first comlumn is
+#'   second is value) or a CSV file.
+#' @param exo_data Exogenous variables, as a data frame or a CSV file; first column is
 #'   dates, next block are measurements for the day, and final block are exogenous
-#'   forecasts
-#' @param input_tz Timezone in the input files ("GMT" or e.g. "Europe/Paris")
+#'   forecasts (for the same day).
 #' @param date_format How date/time are stored (e.g. year/month/day hour:minutes;
-#'   see \code{strptime})
-#' @param working_tz Timezone to work with ("GMT" or e.g. "Europe/Paris")
-#' @param predict_at When does the prediction take place ? Integer, in hours. Default: 0
+#'   see ?strptime)
 #' @param limit Number of days to extract (default: Inf, for "all")
 #'
 #' @return An object of class Data
@@ -23,14 +21,9 @@
 #' exo_data = read.csv(system.file("extdata","meteo_extra_noNAs.csv",package="talweg"))
 #' 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)
+getData = function(ts_data, exo_data, date_format="%d/%m/%Y %H:%M", limit=Inf)
 {
 	# Sanity checks (not full, but sufficient at this stage)
-	if (!is.character(input_tz) || !is.character(working_tz))
-		stop("Bad timezone (see ?timezone)")
-	input_tz = input_tz[1]
-	working_tz = working_tz[1]
 	if ( (!is.data.frame(ts_data) && !is.character(ts_data)) ||
 			(!is.data.frame(exo_data) && !is.character(exo_data)) )
 		stop("Bad time-series / exogenous input (data frame or CSV file)")
@@ -38,22 +31,20 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 		ts_data = ts_data[1]
 	if (is.character(exo_data))
 		exo_data = exo_data[1]
-	predict_at = as.integer(predict_at)[1]
-	if (predict_at<0 || predict_at>23)
-		stop("Bad predict_at (0-23)")
 	if (!is.character(date_format))
 		stop("Bad date_format (character)")
 	date_format = date_format[1]
+	if (!is.numeric(limit) || limit < 0)
+		stop("limit: positive integer")
 
 	ts_df =
 		if (is.character(ts_data))
 			read.csv(ts_data)
 		else
 			ts_data
-	# Convert to the desired timezone (usually "GMT" or "Europe/Paris")
-	formatted_dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz=input_tz)
-	ts_df[,1] = format(
-		as.POSIXct(formatted_dates_POSIXlt, tz=input_tz), tz=working_tz, usetz=TRUE)
+	# Convert to GMT (pretend it's GMT; no impact)
+	dates_POSIXlt = strptime(as.character(ts_df[,1]), date_format, tz="GMT")
+	ts_df[,1] = format(as.POSIXct(dates_POSIXlt, tz="GMT"), tz="GMT", usetz=TRUE)
 
 	exo_df =
 		if (is.character(exo_data))
@@ -71,34 +62,28 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 	{
 		time = c()
 		serie = c()
+		level_hat = c()
 		repeat
 		{
 			{
 				time = c(time, ts_df[line,1])
 				serie = c(serie, ts_df[line,2])
+				level_hat = c(level_hat, #in case of data file is incomplete...
+					ifelse(ncol(ts_df) > 2, ts_df[line,3], mean(serie,na.rm=TRUE)))
 				line = line + 1
 			};
 			if (line >= nb_lines + 1
-				|| as.POSIXlt(ts_df[line-1,1],tz=working_tz)$hour == predict_at)
+				|| as.POSIXlt(ts_df[line-1,1],tz="GMT")$hour == 0)
 			{
 				break
 			}
 		}
 
-		hat_exo = as.data.frame( exo_df[i,(1+nb_exos+1):(1+2*nb_exos)] )
-		exo = as.data.frame( exo_df[i,2:(1+nb_exos)] )
-		data$appendHat(time, hat_exo)
-		data$append(serie, exo) #in realtime, this call comes hours later
+		data$append(time=time, value=serie, level_hat=level_hat,
+			exo=exo_df[i,2:(1+nb_exos)], exo_hat=exo_df[i,(1+nb_exos+1):(1+2*nb_exos)])
 		if (i >= limit)
 			break
 		i = i + 1
 	}
-	if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(2)))
-		data$removeFirst()
-	if (length(data$getCenteredSerie(data$getSize()))
-		< length(data$getCenteredSerie(data$getSize()-1)))
-	{
-		data$removeLast()
-	}
 	data
 }