pkg/R/plot.R

   1 #' Plot curves
   2 #'
   3 #' Plot a range of curves in data
   4 #'
   5 #' @param data Object of class Data
   6 #' @param indices Range of indices (integers or dates)
   7 #'
   8 #' @export
   9 plotCurves <- function(data, indices=seq_len(data$getSize()))
  10 {
  11     series = data$getSeries(indices)
  12     yrange = quantile(series, probs=c(0.025,0.975), na.rm=TRUE)
  13     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
  14     for (i in seq_along(indices))
  15     {
  16         plot(series[,i], type="l", ylim=yrange,
  17             xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10",""))
  18         if (i < length(indices))
  19             par(new=TRUE)
  20     }
  21 }
  22
  23 #' Plot error
  24 #'
  25 #' Draw error graphs, potentially from several runs of \code{computeForecast}
  26 #'
  27 #' @param err Error as returned by \code{computeError}
  28 #' @param cols Colors for each error (default: 1,2,3,...)
  29 #'
  30 #' @seealso \code{\link{plotCurves}}, \code{\link{plotPredReal}},
  31 #'   \code{\link{plotSimils}}, \code{\link{plotFbox}},
  32 #'   \code{\link{computeFilaments}, }\code{\link{plotFilamentsBox}}, \code{\link{plotRelVar}}
  33 #'
  34 #' @export
  35 plotError <- function(err, cols=seq_along(err))
  36 {
  37     if (!is.null(err$abs))
  38         err = list(err)
  39     par(mfrow=c(2,2), mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
  40     L = length(err)
  41     yrange = range( sapply(1:L, function(i) ( err[[i]]$abs$day ) ), na.rm=TRUE )
  42     for (i in seq_len(L))
  43     {
  44         plot(err[[i]]$abs$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
  45             ylab=ifelse(i==1,"Moyenne |y - y_hat|",""), ylim=yrange, col=cols[i])
  46         if (i < L)
  47             par(new=TRUE)
  48     }
  49     yrange = range( sapply(1:L, function(i) ( err[[i]]$abs$indices ) ), na.rm=TRUE )
  50     for (i in seq_len(L))
  51     {
  52         plot(err[[i]]$abs$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
  53             ylab=ifelse(i==1,"Moyenne |y - y_hat|",""), ylim=yrange, col=cols[i])
  54         if (i < L)
  55             par(new=TRUE)
  56     }
  57     yrange = range( sapply(1:L, function(i) ( err[[i]]$MAPE$day ) ), na.rm=TRUE )
  58     for (i in seq_len(L))
  59     {
  60         plot(err[[i]]$MAPE$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
  61             ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
  62         if (i < L)
  63             par(new=TRUE)
  64     }
  65     yrange = range( sapply(1:L, function(i) ( err[[i]]$MAPE$indices ) ), na.rm=TRUE )
  66     for (i in seq_len(L))
  67     {
  68         plot(err[[i]]$MAPE$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
  69             ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
  70         if (i < L)
  71             par(new=TRUE)
  72     }
  73 }
  74
  75 #' Plot measured / predicted
  76 #'
  77 #' Plot measured curve (in black) and predicted curve (in blue)
  78 #'
  79 #' @param data Object return by \code{getData}
  80 #' @param pred Object as returned by \code{computeForecast}
  81 #' @param index Index in forecasts (integer or date)
  82 #'
  83 #' @export
  84 plotPredReal <- function(data, pred, index)
  85 {
  86     horizon = length(pred$getSerie(1))
  87     measure = data$getSerie( pred$getIndexInData(index)+1 )[1:horizon]
  88     prediction = pred$getSerie(index)
  89     yrange = range(measure, prediction)
  90     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=3)
  91     plot(measure, type="l", ylim=yrange, xlab="Temps (en heures)", ylab="PM10")
  92     par(new=TRUE)
  93     plot(prediction, type="l", col="#0000FF", ylim=yrange, xlab="", ylab="")
  94 }
  95
  96 #' Plot similarities
  97 #'
  98 #' Plot histogram of similarities (weights)
  99 #'
 100 #' @param pred Object as returned by \code{computeForecast}
 101 #' @param index Index in forecasts (integer or date)
 102 #'
 103 #' @export
 104 plotSimils <- function(pred, index)
 105 {
 106     weights = pred$getParams(index)$weights
 107     if (is.null(weights))
 108         stop("plotSimils only works on 'Neighbors' forecasts")
 109     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 110     hist(pred$getParams(index)$weights, nclass=20, xlab="Poids", ylab="Effectif")
 111 }
 112
 113 #' Functional boxplot
 114 #'
 115 #' Draw the functional boxplot on the left, and bivariate plot on the right
 116 #'
 117 #' @param data Object return by \code{getData}
 118 #' @param indices integer or date indices to process
 119 #' @param plot_bivariate Should the bivariate plot appear?
 120 #'
 121 #' @export
 122 plotFbox <- function(data, indices=seq_len(data$getSize()))
 123 {
 124     if (!requireNamespace("rainbow", quietly=TRUE))
 125         stop("Functional boxplot requires the rainbow package")
 126
 127     series_matrix = data$getSeries(indices)
 128     # Remove series with NAs
 129     no_NAs_indices = sapply( 1:ncol(series_matrix),
 130         function(i) all(!is.na(series_matrix[,i])) )
 131     series_matrix = series_matrix[,no_NAs_indices]
 132
 133     series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
 134     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 135     rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Temps (heures)", ylab="PM10",
 136         plotlegend=FALSE, lwd=2)
 137     rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
 138 }
 139
 140 #' Compute filaments
 141 #'
 142 #' Get similar days in the past, as black as distances are small
 143 #'
 144 #' @param data Object as returned by \code{getData}
 145 #' @param index Index in data (integer or date)
 146 #' @param limit Number of neighbors to consider
 147 #' @param plot Should the result be plotted?
 148 #'
 149 #' @return A list with
 150 #' \itemize{
 151 #'   \item index : index of the current serie ('today')
 152 #'   \item neighb_indices : indices of its neighbors
 153 #'   \item colors : colors of neighbors curves (shades of gray)
 154 #' }
 155 #'
 156 #' @export
 157 computeFilaments <- function(data, index, limit=60, plot=TRUE)
 158 {
 159     ref_serie = data$getCenteredSerie(index)
 160     if (any(is.na(ref_serie)))
 161         stop("computeFilaments requires a serie without NAs")
 162
 163     # Determine indices of no-NAs days followed by no-NAs tomorrows
 164     fdays = getNoNA2(data, 1, dateIndexToInteger(index,data)-1)
 165     # Series + tomorrows in columns, ref_serie first
 166     centered_series = data$getCenteredSeries(fdays)
 167
 168     # Obtain neighbors (closest for euclidian norm)
 169     L = length(ref_serie)
 170     distances = sqrt( colSums( (centered_series - ref_serie)^2 / L ) )
 171     sorted_distances = sort(distances, index.return=TRUE)
 172
 173     # Compute colors for each neighbor (from darkest to lightest)
 174     nn = min(limit, length(distances))
 175     min_dist = min(sorted_distances$x[1:nn])
 176     max_dist = max(sorted_distances$x[1:nn])
 177     color_values = floor( 19.5 * (sorted_distances$x[1:nn]-min_dist) / (max_dist-min_dist) ) + 1
 178     colors = gray.colors(20,0.1,0.9)[color_values] #TODO: 20 == magic number
 179
 180     if (plot)
 181     {
 182         # Complete series with (past and present) tomorrows
 183         ref_serie = c(ref_serie,data$getCenteredSerie(index+1))
 184         centered_series = rbind( centered_series, data$getCenteredSeries(fdays+1) )
 185         yrange = quantile(cbind(ref_serie,centered_series), probs=c(0.025,0.975), na.rm=TRUE)
 186         par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
 187         for (i in nn:1)
 188         {
 189             plot(centered_series[,sorted_distances$ix[i]], ylim=yrange, type="l", col=colors[i],
 190                 xlab=ifelse(i==nn,"Temps (en heures)",""), ylab=ifelse(i==nn,"PM10 centré",""))
 191             par(new=TRUE)
 192         }
 193         # Also plot ref curve, in red
 194         plot(ref_serie, ylim=yrange, type="l", col="#FF0000", xlab="", ylab="")
 195         abline(v=24, lty=2, col=colors()[56], lwd=1)
 196     }
 197
 198     list("index"=index,"neighb_indices"=fdays[sorted_distances$ix[1:nn]],"colors"=colors)
 199 }
 200
 201 #' Functional boxplot on filaments
 202 #'
 203 #' Draw the functional boxplot on filaments obtained by \code{computeFilaments}
 204 #'
 205 #' @param data Object return by \code{getData}
 206 #' @param fil Output of \code{computeFilaments}
 207 #'
 208 #' @export
 209 plotFilamentsBox = function(data, fil, ...)
 210 {
 211     if (!requireNamespace("rainbow", quietly=TRUE))
 212         stop("Functional boxplot requires the rainbow package")
 213
 214     series_matrix = rbind(
 215         data$getSeries(fil$neighb_indices), data$getSeries(fil$neighb_indices+1) )
 216     series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
 217     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 218     rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Temps (heures)", ylab="PM10",
 219         plotlegend=FALSE, lwd=2)
 220
 221     # "Magic" found at http://stackoverflow.com/questions/13842560/get-xlim-from-a-plot-in-r
 222     usr <- par("usr")
 223     yr <- (usr[4] - usr[3]) / 27
 224     par(new=TRUE)
 225     plot(c(data$getSerie(fil$index),data$getSerie(fil$index+1)), type="l", lwd=2, lty=2,
 226         ylim=c(usr[3] + yr, usr[4] - yr), xlab="", ylab="")
 227     abline(v=24, lty=2, col=colors()[56])
 228 }
 229
 230 #' Plot relative conditional variability / absolute variability
 231 #'
 232 #' Draw the relative conditional variability / absolute variability based on filaments
 233 #' obtained by \code{computeFilaments}
 234 #'
 235 #' @param data Object return by \code{getData}
 236 #' @param fil Output of \code{computeFilaments}
 237 #'
 238 #' @export
 239 plotRelVar = function(data, fil, ...)
 240 {
 241     ref_var = c( apply(data$getSeries(fil$neighb_indices),1,sd),
 242         apply(data$getSeries(fil$neighb_indices+1),1,sd) )
 243     fdays = getNoNA2(data, 1, fil$index-1)
 244     global_var = c( apply(data$getSeries(fdays),1,sd), apply(data$getSeries(fdays+1),1,sd) )
 245
 246     yrange = range(ref_var, global_var)
 247     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 248     plot(ref_var, type="l", col=1, lwd=3, ylim=yrange,
 249         xlab="Temps (heures)", ylab="Écart-type")
 250     par(new=TRUE)
 251     plot(global_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
 252     abline(v=24, lty=2, col=colors()[56])
 253 }