X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FgetData.R;h=4e2e3fd1a75d2c4506206278d02497c7d4eced29;hb=c1be989885d1e402569d55a34aef01b57d6aea1c;hp=a4e1e17b2e1808568dc5b0dd88cbaf5f86abbb26;hpb=a66a84b56467194852f2faee15f4725759b24158;p=talweg.git

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index a4e1e17..4e2e3fd 100644
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -1,13 +1,14 @@
 #' @title Acquire data in a clean format
 #'
-#' @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}).
+#' @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}).
 #'
 #' @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 dates,
-#'   next block are measurements for the day, and final block are exogenous forecasts
+#' @param exo_data Exogenous variables, as a data frame or a CSV file; first comlumn 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")
 #' @param date_format How date/time are stored (e.g. year/month/day hour:minutes;
 #'   see \code{strptime})
@@ -49,14 +50,17 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 			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)
+
 	exo_df =
 		if (is.character(exo_data))
 			read.csv(exo_data)
 		else
 			exo_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=working_tz, usetz=TRUE)
+	# Times in exogenous variables file are ignored: no conversions required
 
 	line = 1 #index in PM10 file (24 lines for 1 cell)
 	nb_lines = nrow(ts_df)
@@ -74,15 +78,16 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 				serie = c(serie, ts_df[line,2])
 				line = line + 1
 			};
-			if (line >= nb_lines + 1 || as.POSIXlt(ts_df[line-1,1])$hour == predict_at)
+			if (line >= nb_lines + 1
+				|| as.POSIXlt(ts_df[line-1,1],tz=working_tz)$hour == predict_at)
+			{
 				break
+			}
 		}
 
 		exo = as.data.frame( exo_df[i,2:(1+nb_exos)] )
 		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$append(time, centered_serie, level, exo, exo_hat)
+		data$append(time, serie, exo, exo_hat)
 		if (i >= limit)
 			break
 		i = i + 1