+
+#' getNoNA2
+#'
+#' Get indices in data of no-NA series followed by no-NA, within [first,last] range.
+#'
+#' @inheritParams dateIndexToInteger
+#' @param first First index (included)
+#' @param last Last index (included)
+#'
+.getNoNA2 = function(data, first, last)
+{
+ (first:last)[ sapply(first:last, function(i)
+ !any( is.na(data$getCenteredSerie(i)) | is.na(data$getCenteredSerie(i+1)) )
+ ) ]
+}
+
+#' getConstrainedNeighbs
+#'
+#' Get indices of neighbors of similar pollution level (among same season + day type).
+#'
+#' @param today Index of current day
+#' @param data Object of class Data
+#' @param fdays Current set of "first days" (no-NA pairs)
+#' @param min_neighbs Minimum number of points in a neighborhood
+#' @param max_neighbs Maximum number of points in a neighborhood
+#'
+.getConstrainedNeighbs = function(today, data, fdays, min_neighbs=10, max_neighbs=12)
+{
+ levelToday = data$getLevel(today)
+ distances = sapply(fdays, function(i) abs(data$getLevel(i)-levelToday))
+ #TODO: 2, +3 : magic numbers
+ dist_thresh = 2
+ min_neighbs = min(min_neighbs,length(fdays))
+ repeat
+ {
+ same_pollution = (distances <= dist_thresh)
+ nb_neighbs = sum(same_pollution)
+ if (nb_neighbs >= min_neighbs) #will eventually happen
+ break
+ dist_thresh = dist_thresh + 3
+ }
+ fdays = fdays[same_pollution]
+ max_neighbs = 12
+ if (nb_neighbs > max_neighbs)
+ {
+ # Keep only max_neighbs closest neighbors
+ fdays = fdays[
+ sort(distances[same_pollution],index.return=TRUE)$ix[1:max_neighbs] ]
+ }
+ fdsays
+}
+
+#' compute similarities
+#'
+#' Apply the gaussian kernel on computed squared distances.
+#'
+#' @param distances2 Squared distances
+#' @param window Window parameter for the kernel
+#'
+.computeSimils <- function(distances2, window)
+{
+ sd_dist = sd(distances2)
+ if (sd_dist < .25 * sqrt(.Machine$double.eps))
+ {
+# warning("All computed distances are very close: stdev too small")
+ sd_dist = 1 #mostly for tests... FIXME:
+ }
+ exp(-distances2/(sd_dist*window^2))
+}
projects / talweg.git / commitdiff