X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FgetData.R;h=d0e69d73daaf374c2e655d9b82df7de5090aaa56;hb=0730374e2981d7b950dced9f667713865b44b390;hp=5139a4da18dfda81105ce0e2b57e2ff1839a8090;hpb=469529710f56c790ae932b45d13fed2e34bcabf2;p=talweg.git

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index 5139a4d..d0e69d7 100644
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -1,96 +1,89 @@
-#' @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}). Current limitation: series (in working_tz) must start at
-#'   right after midnight (to keep in sync with exogenous vars)
+#' 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 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")
+#'   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 (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
 #'
+#' @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"))
+#' 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)
+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))
-		stop("Bad time-series input (data frame or CSV file)")
+	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)")
 	if (is.character(ts_data))
 		ts_data = ts_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(exo_data))
+		exo_data = exo_data[1]
 	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)) {
+		if (is.character(ts_data))
 			read.csv(ts_data)
-		} else {
+		else
 			ts_data
-		}
+	# 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)) {
+		if (is.character(exo_data))
 			read.csv(exo_data)
-		} else {
+		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)
 	nb_exos = ( ncol(exo_df) - 1 ) / 2
-	data = list() #new("Data")
+	data = Data$new()
 	i = 1 #index of a cell in data
 	while (line <= nb_lines)
 	{
 		time = c()
 		serie = c()
+		level_hat = c()
 		repeat
 		{
 			{
 				time = c(time, ts_df[line,1])
 				serie = c(serie, ts_df[line,2])
+				level_hat = c(level_hat, #in case of data file is incomplete...
+					ifelse(ncol(ts_df) > 2, ts_df[line,3], mean(serie,na.rm=TRUE)))
 				line = line + 1
 			};
-			if (line >= nb_lines + 1 || as.POSIXlt(ts_df[line-1,1])$hour == predict_at)
+			if (line >= nb_lines + 1
+				|| as.POSIXlt(ts_df[line-1,1],tz="GMT")$hour == 0)
+			{
 				break
+			}
 		}
 
-		# NOTE: if predict_at does not cut days at midnight,
-		# for the exogenous to be synchronized they need to be shifted
-		if (predict_at > 0)
-		{
-			exo_hat = as.data.frame(exo_df[max(1,i-1),(1+nb_exos+1):(1+2*nb_exos)])
-			exo_Dm1 = if (i>=3) as.data.frame(exo_df[i-1,2:(1+nb_exos)]) else NA
-		} else
-		{
-			exo_hat = as.data.frame(exo_df[i,(1+nb_exos+1):(1+2*nb_exos)])
-			exo_Dm1 = if (i>=2) as.data.frame(exo_df[i-1,2:(1+nb_exos)]) else NA
-		}
+		data$append(time=time, value=serie, level_hat=level_hat,
+			exo=exo_df[i,2:(1+nb_exos)], exo_hat=exo_df[i,(1+nb_exos+1):(1+2*nb_exos)])
+		if (i >= limit)
+			break
 		i = i + 1
-		#center data
-		level = mean(serie, na.rm=TRUE)
-		centered_serie = serie - level
-#		data$append(time, centered_serie, level, exo_hat, exo_Jm1) #TODO: slow: why ?
-		data[[length(data)+1]] = list("time"=time, "serie"=centered_serie, "level"=level,
-			"exo_hat"=exo_hat, "exo_Dm1"=exo_Dm1)
 	}
-	new("Data",data=data)
+	data
 }