fix plotting; TODO: tests, reports

[talweg.git] / pkg / R / plot.R

diff --git a/pkg/R/plot.R b/pkg/R/plot.R
index f4fc3bf..e414798 100644 (file)
--- a/pkg/R/plot.R
+++ b/pkg/R/plot.R
@@ -61,48 +61,48 @@ computeFilaments <- function(data, index, limit=60, plot=TRUE)
        if (any(is.na(ref_serie)))
                stop("computeFilaments requires a serie without NAs")
        L = length(ref_serie)
-       first_day = ifelse(length(data$getCenteredSerie(1)<L), 2, 1)
-       distances = sapply(first_day:(index-1), function(i) {
-               sqrt( sum( (ref_serie - data$getCenteredSerie(i))^2 ) / L )
-       })
-       # HACK to suppress NA effect while keeping indexation
-       
-
-
-
-
-##TOCONTINUE
-
-
 
+       # Determine indices of no-NAs days followed by no-NAs tomorrows
+       first_day = ifelse(length(data$getCenteredSerie(1))<L, 2, 1)
+       fdays_indices = c()
+       for (i in first_day:(index-1))
+       {
+               if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
+                       fdays_indices = c(fdays_indices, i)
+       }
 
-       distances[is.na(distances)] = max(distances,na.rm=TRUE) + 1
+       distances = sapply(fdays_indices, function(i) {
+               sqrt( sum( (ref_serie - data$getCenteredSerie(i))^2 ) / L )
+       })
        indices = sort(distances, index.return=TRUE)$ix[1:min(limit,length(distances))]
        yrange = quantile( range( ref_serie, sapply( indices, function(i) {
-               ii = i - 1 + first_day
+               ii = fdays_indices[i]
                serie = c(data$getCenteredSerie(ii), data$getCenteredSerie(ii+1))
                if (!all(is.na(serie)))
                        return (range(serie, na.rm=TRUE))
                c()
        }) ), probs=c(0.05,0.95) )
        grays = gray.colors(20, 0.1, 0.9) #TODO: 20 == magic number
-       color_values = floor( 20.5 * distances[indices] / (1+max(distances[indices])) )
-       plot_order = sort(color_values, index.return=TRUE)$ix
+       min_dist = min(distances[indices])
+       max_dist = max(distances[indices])
+       color_values = floor( 19.5 * (distances[indices]-min_dist) / (max_dist-min_dist) ) + 1
+       plot_order = sort(color_values, index.return=TRUE, decreasing=TRUE)$ix
        colors = c(grays[ color_values[plot_order] ], "#FF0000")
        if (plot)
        {
                par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
-               for ( i in c(plot_order,length(indices)+1) )
+               for ( i in seq_len(length(indices)+1) )
                {
-                       ind = ifelse(i<=length(indices), indices[i] - first_day + 1, index)
-                       plot(c(data$getCenteredSerie(ind),data$getCenteredSerie(ind+1)),
+                       ii = ifelse(i<=length(indices), fdays_indices[ indices[plot_order[i]] ], index)
+                       plot(c(data$getCenteredSerie(ii),data$getCenteredSerie(ii+1)),
                                ylim=yrange, type="l", col=colors[i],
                                xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10 centré",""))
                        if (i <= length(indices))
                                par(new=TRUE)
                }
+               abline(v=24, lty=2, col=colors()[56])
        }
-       list("indices"=c(indices[plot_order]-first_day+1,index), "colors"=colors)
+       list("indices"=c(fdays_indices[ indices[plot_order] ],index), "colors"=colors)
 }
 
 #' @title Plot similarities
@@ -233,3 +233,50 @@ plotFilamentsBox = function(data, indices, ...)
        plot(data$getSerie(tail(indices,1)), type="l", lwd=2, lty=2,
                ylim=c(usr[3] + yr, usr[4] - yr), xlab="", ylab="")
 }
+
+#' @title Plot relative conditional variability / absolute variability
+#'
+#' @description Draw the relative conditional variability / absolute variability based on on
+#'   filaments obtained by \code{computeFilaments}
+#'
+#' @param data Object return by \code{getData}
+#' @param indices Indices as output by \code{computeFilaments}
+#'
+#' @export
+plotRelativeVariability = function(data, indices, ...)
+{
+       #plot left / right separated by vertical line brown dotted
+       #median of 3 runs for random length(indices) series
+       ref_series = t( sapply(indices, function(i) {
+               c( data$getSerie(i), data$getSerie(i+1) )
+       }) )
+       ref_var = apply(ref_series, 2, sd)
+
+       # Determine indices of no-NAs days followed by no-NAs tomorrows
+       first_day = ifelse(length(data$getCenteredSerie(1))<length(ref_series[1,]), 2, 1)
+       fdays_indices = c()
+       for (i in first_day:(tail(indices,1)-1))
+       {
+               if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
+                       fdays_indices = c(fdays_indices, i)
+       }
+
+       # TODO: 3 == magic number
+       random_var = matrix(nrow=3, ncol=48)
+       for (mc in seq_len(nrow(random_var)))
+       {
+               random_indices = sample(fdays_indices, length(indices))
+               random_series = t( sapply(random_indices, function(i) {
+                       c( data$getSerie(i), data$getSerie(i+1) )
+               }) )
+               random_var[mc,] = apply(random_series, 2, sd)
+       }
+       random_var = apply(random_var, 2, median)
+
+       yrange = range(ref_var, random_var)
+       par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
+       plot(ref_var, type="l", col=1, lwd=3, ylim=yrange, xlab="Temps (heures)", ylab="Écart-type")
+       par(new=TRUE)
+       plot(random_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
+       abline(v=24, lty=2, col=colors()[56])
+}