X-Git-Url: https://git.auder.net/?a=blobdiff_plain;f=pkg%2FR%2FgetData.R;h=a6401f9e5cf98b8974e47324f3e8659accdd7cb1;hb=102bcfda4afbb5cfee885cbee0f55545624168fd;hp=8d1a6faa9c29bcae9cb27fc9fbc20158a240abb6;hpb=44a9990b6d608ffcd2e99d5193fa8b9e6cbdb436;p=talweg.git

diff --git a/pkg/R/getData.R b/pkg/R/getData.R
index 8d1a6fa..a6401f9 100644
--- a/pkg/R/getData.R
+++ b/pkg/R/getData.R
@@ -1,26 +1,28 @@
-#' @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
+#'   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 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})
+#'   see ?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
+#' @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
 #'
 #' @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)
@@ -49,19 +51,22 @@ 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)
 	nb_exos = ( ncol(exo_df) - 1 ) / 2
-	data = list() #new("Data")
+	data = Data$new()
 	i = 1 #index of a cell in data
 	while (line <= nb_lines)
 	{
@@ -74,22 +79,30 @@ getData = function(ts_data, exo_data, input_tz="GMT", date_format="%d/%m/%Y %H:%
 				serie = c(serie, ts_df[line,2])
 				line = line + 1
 			};
-			if (line >= nb_lines + 1 || as.POSIXlt(ts_df[line-1,1])$hour == predict_at)
+			if (line >= nb_lines + 1
+				|| as.POSIXlt(ts_df[line-1,1],tz=working_tz)$hour == predict_at)
+			{
 				break
+			}
 		}
 
-		# NOTE: if predict_at does not cut days at midnight, exogenous vars need to be shifted
-		exo_hat = as.data.frame( exo_df[
-			ifelse(predict_at>0,max(1,i-1),i) , (1+nb_exos+1):(1+2*nb_exos) ] )
-		exo = as.data.frame( exo_df[ ifelse(predict_at>0,max(1,i-1),i) , 2:(1+nb_exos) ] )
-		level = mean(serie, na.rm=TRUE)
-		centered_serie = serie - level
-		#data$append(time, centered_serie, level, exo_hat, exo_Jm1) #too slow; TODO: use R6 class
-		data[[length(data)+1]] = list("time"=time, "serie"=centered_serie, "level"=level,
-			"exo_hat"=exo_hat, "exo"=exo)
+		exo = as.data.frame( exo_df[i,2:(1+nb_exos)] )
+		exo_hat =
+			if (i < nrow(exo_df))
+				as.data.frame( exo_df[i+1,(1+nb_exos+1):(1+2*nb_exos)] )
+			else
+				NA #exogenous prediction for next day are useless on last day
+		data$append(time, serie, exo, exo_hat)
 		if (i >= limit)
 			break
 		i = i + 1
 	}
-	new("Data",data=data)
+	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
 }