X-Git-Url: https://git.auder.net/?p=talweg.git;a=blobdiff_plain;f=pkg%2FR%2Futils.R;h=5ba72f05684ae4b61f9785f161461e3659bd2901;hp=0918a3257d892bc9853602aa055a923e3285e1f0;hb=3ddf1c12af0c167fe7d3bb59e63258550270cfc5;hpb=25b75559e2d9bf84e2de35b851d93fefdae36e17

diff --git a/pkg/R/utils.R b/pkg/R/utils.R
index 0918a32..5ba72f0 100644
--- a/pkg/R/utils.R
+++ b/pkg/R/utils.R
@@ -1,21 +1,23 @@
 #' dateIndexToInteger
 #'
-#' Transform a (potential) date index into an integer (relative to data)
+#' Transform a (potential) date index into an integer (relative to data beginning).
 #'
 #' @param index Date (or integer) index
-#' @param data Object of class \code{Data}
+#' @param data Object of class Data, output of \code{getData()}
 #'
 #' @export
 dateIndexToInteger = function(index, data)
 {
-	index = index[1]
+	# Works on integers too: trust input
 	if (is.numeric(index))
 		index = as.integer(index)
 	if (is.integer(index))
 		return (index)
+
 	if (inherits(index, "Date") || is.character(index))
 	{
-		tryCatch(indexAsDate <- as.Date(index), error=function(e) stop("Unrecognized index format"))
+		tryCatch(indexAsDate <- as.Date(index),
+			error=function(e) stop("Unrecognized index format"))
 		#TODO: tz arg to difftime ?
 		integerIndex <- round( as.numeric(
 			difftime(indexAsDate, as.Date(data$getTime(1)[1])) ) ) + 1
@@ -28,76 +30,90 @@ dateIndexToInteger = function(index, data)
 
 #' integerIndexToDate
 #'
-#' Transform an integer index to date index (relative to data)
+#' Transform an integer index (relative to data beginning) into a date index.
 #'
-#' @param index Date (or integer) index
-#' @param data Object of class \code{Data}
+#' @inheritParams dateIndexToInteger
 #'
 #' @export
 integerIndexToDate = function(index, data)
 {
+	# Works on dates too: trust input
+	if (is.character(index))
+		index = as.Date(index)
+	if (is(index,"Date"))
+		return (index)
+
 	index = index[1]
 	if (is.numeric(index))
 		index = as.integer(index)
 	if (!is.integer(index))
-		stop("'index' should be an integer")
+		stop("'index' should be a date or integer")
 	as.Date( data$getTime(index)[1] )
 }
 
 #' getSimilarDaysIndices
 #'
-#' Find similar days indices in the past
+#' Find similar days indices in the past; at least same type of day in the week:
+#' monday=tuesday=wednesday=thursday != friday != saturday != sunday.
 #'
 #' @param index Day index (numeric or date)
+#' @param data Reference dataset, object output of \code{getData}
 #' @param limit Maximum number of indices to return
-#' @param same_seaon Should the indices correspond to day in same season?
+#' @param same_season Should the indices correspond to day in same season?
+#' @param days_in Optional set to intersect with results (NULL to discard)
 #'
 #' @export
-getSimilarDaysIndices = function(index, limit, same_season)
+getSimilarDaysIndices = function(index, data, limit, same_season, days_in=NULL)
 {
-	index = dateIndexToInteger(index)
+	index = dateIndexToInteger(index, data)
 
-	#TODO: mardi similaire à lundi mercredi jeudi aussi ...etc
-	if (!same_season)
-	{
-		#take all similar days in recent past
-		nb_days = min( (index-1) %/% 7, limit)
-		return ( rep(index,nb_days) - 7*seq_len(nb_days) )
-	}
-
-	#Look for similar days in similar season (+/- 30 days)
+	# Look for similar days (optionally in same season)
+	i = index - 1
 	days = c()
-	i = index
+	dt_ref = as.POSIXlt(data$getTime(index)[1]) #first date-time of current day
+	day_ref = dt_ref$wday #1=monday, ..., 6=saturday, 0=sunday
+	month_ref = as.POSIXlt(data$getTime(index)[1])$mon+1 #month in 1...12
 	while (i >= 1 && length(days) < limit)
 	{
-		if (i < index)
-		{
-			days = c(days, i)
-			#look in the "future of the past"
-			for (j in 1:4)
-				days = c(days, i+7*j)
-		}
-		#...and in the "past of the past"
-		for (j in 1:4)
+		dt = as.POSIXlt(data$getTime(i)[1])
+		if ((is.null(days_in) || i %in% days_in) && .isSameDay(dt$wday, day_ref))
 		{
-			if (i - 7*j >= 1)
-				days = c(days, i-7*j)
+			if (!same_season || .isSameSeason(dt$mon+1, month_ref))
+				days = c(days, i)
 		}
-		# TODO: exact computation instead of -364
-		# 364 = closest multiple of 7 to 365 - drift along the years... but not so many years so OK
-		i = i - 364
+		i = i - 1
 	}
+	return ( days )
+}
 
-	return ( days[1:min(limit,length(days))] )
+# isSameSeason
+#
+# Check if two months fall in the same "season" (defined by estimated pollution rate).
+#
+# @param month Month index to test
+# @param month_ref Month to compare to
+#
+.isSameSeason = function(month, month_ref)
+{
+	if (month_ref %in% c(11,12,1,2)) #~= mid-polluted
+		return (month %in% c(11,12,1,2))
+	if (month_ref %in% c(3,4,9,10)) #~= high-polluted
+		return (month %in% c(3,4,9,10))
+	return (month %in% c(5,6,7,8)) #~= non polluted
 }
 
-#' getSerie
-#'
-#' Return a time-serie from its centered version + level
-#'
-#' @param data A list as returned by \code{getData}
-#' @param index The index to return
-#'
-#' @export
-getSerie = function(data, index)
-	data[[index]]$centered_serie + data[[index]]$level
+# isSameDay
+#
+# Monday=Tuesday=Wednesday=Thursday ; Friday, Saturday, Sunday: specials.
+#
+# @param day Day index to test
+# @param day_ref Day index to compare to
+#
+.isSameDay = function(day, day_ref)
+{
+	if (day_ref == 0)
+		return (day==0)
+	if (day_ref <= 4)
+		return (day <= 4)
+	return (day == day_ref)
+}