pkg/R/plot.R

   1 #' @title plot curves
   2 #'
   3 #' @description 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$getSize()))
  10 {
  11     yrange = quantile( sapply( indices, function(i) {
  12         serie = c(data$getCenteredSerie(i))
  13         if (!all(is.na(serie)))
  14             range(serie, na.rm=TRUE)
  15         c()
  16     }), probs=c(0.05,0.95) )
  17     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
  18     for (i in seq_along(indices))
  19     {
  20         plot(data$getSerie(indices[i]), type="l", ylim=yrange,
  21             xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10",""))
  22         if (i < length(indices))
  23             par(new=TRUE)
  24     }
  25 }
  26
  27 #' @title plot measured / predicted
  28 #'
  29 #' @description Plot measured curve (in black) and predicted curve (in red)
  30 #'
  31 #' @param data Object return by \code{getData}
  32 #' @param pred Object as returned by \code{computeForecast}
  33 #' @param index Index in forecasts
  34 #'
  35 #' @export
  36 plotPredReal <- function(data, pred, index)
  37 {
  38     horizon = length(pred$getSerie(1))
  39     measure = data$getSerie(pred$getIndexInData(index)+1)[1:horizon]
  40     yrange = range( pred$getSerie(index), measure )
  41     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=3)
  42     plot(measure, type="l", ylim=yrange, xlab="Temps (en heures)", ylab="PM10")
  43     par(new=TRUE)
  44     plot(pred$getSerie(index), type="l", col="#0000FF", ylim=yrange, xlab="", ylab="")
  45 }
  46
  47 #' @title Compute filaments
  48 #'
  49 #' @description Get similar days in the past + "past tomorrow", as black as distances are small
  50 #'
  51 #' @param data Object as returned by \code{getData}
  52 #' @param index Index in data
  53 #' @param limit Number of neighbors to consider
  54 #' @param plot Should the result be plotted?
  55 #'
  56 #' @export
  57 computeFilaments <- function(data, index, limit=60, plot=TRUE)
  58 {
  59     index = dateIndexToInteger(index, data)
  60     ref_serie = data$getCenteredSerie(index)
  61     if (any(is.na(ref_serie)))
  62         stop("computeFilaments requires a serie without NAs")
  63     L = length(ref_serie)
  64
  65     # Determine indices of no-NAs days followed by no-NAs tomorrows
  66     fdays = c()
  67     for (i in 1:(index-1))
  68     {
  69         if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
  70             fdays = c(fdays, i)
  71     }
  72
  73     distances = sapply(fdays, function(i) {
  74         sqrt( sum( (ref_serie - data$getCenteredSerie(i))^2 ) / L )
  75     })
  76     indices = sort(distances, index.return=TRUE)$ix[1:min(limit,length(distances))]
  77     yrange = quantile( c(ref_serie, sapply( indices, function(i) {
  78         serie = c(data$getCenteredSerie(fdays[i]), data$getCenteredSerie(fdays[i]+1))
  79         if (!all(is.na(serie)))
  80             return (range(serie, na.rm=TRUE))
  81         c()
  82     }) ), probs=c(0.05,0.95) )
  83     grays = gray.colors(20, 0.1, 0.9) #TODO: 20 == magic number
  84     min_dist = min(distances[indices])
  85     max_dist = max(distances[indices])
  86     color_values = floor( 19.5 * (distances[indices]-min_dist) / (max_dist-min_dist) ) + 1
  87     plot_order = sort(color_values, index.return=TRUE, decreasing=TRUE)$ix
  88     colors = c(grays[ color_values[plot_order] ], "#FF0000")
  89     if (plot)
  90     {
  91         par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
  92         for ( i in seq_len(length(indices)+1) )
  93         {
  94             ii = ifelse(i<=length(indices), fdays[ indices[plot_order[i]] ], index)
  95             plot(c(data$getCenteredSerie(ii),data$getCenteredSerie(ii+1)),
  96                 ylim=yrange, type="l", col=colors[i],
  97                 xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10 centré",""))
  98             if (i <= length(indices))
  99                 par(new=TRUE)
 100         }
 101         abline(v=24, lty=2, col=colors()[56])
 102     }
 103     list("indices"=c(fdays[ indices[plot_order] ],index), "colors"=colors)
 104 }
 105
 106 #' @title Plot similarities
 107 #'
 108 #' @description Plot histogram of similarities (weights)
 109 #'
 110 #' @param pred Object as returned by \code{computeForecast}
 111 #' @param index Index in forecasts (not in data)
 112 #'
 113 #' @export
 114 plotSimils <- function(pred, index)
 115 {
 116     weights = pred$getParams(index)$weights
 117     if (is.null(weights))
 118         stop("plotSimils only works on 'Neighbors' forecasts")
 119     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 120     hist(pred$getParams(index)$weights, nclass=20, xlab="Poids", ylab="Effectif")
 121 }
 122
 123 #' @title Plot error
 124 #'
 125 #' @description Draw error graphs, potentially from several runs of \code{computeForecast}
 126 #'
 127 #' @param err Error as returned by \code{computeError}
 128 #' @param cols Colors for each error (default: 1,2,3,...)
 129 #'
 130 #' @seealso \code{\link{plotPredReal}}, \code{\link{plotFilaments}}, \code{\link{plotSimils}}
 131 #'   \code{\link{plotFbox}}
 132 #'
 133 #' @export
 134 plotError <- function(err, cols=seq_along(err))
 135 {
 136     if (!is.null(err$abs))
 137         err = list(err)
 138     par(mfrow=c(2,2), mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
 139     L = length(err)
 140     yrange = range( sapply(1:L, function(index) ( err[[index]]$abs$day ) ), na.rm=TRUE )
 141     for (i in seq_len(L))
 142     {
 143         plot(err[[i]]$abs$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
 144             ylab=ifelse(i==1,"Moyenne |y - y_hat|",""), ylim=yrange, col=cols[i])
 145         if (i < L)
 146             par(new=TRUE)
 147     }
 148     yrange = range( sapply(1:L, function(index) ( err[[index]]$abs$indices ) ), na.rm=TRUE )
 149     for (i in seq_len(L))
 150     {
 151         plot(err[[i]]$abs$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
 152             ylab=ifelse(i==1,"Moyenne |y - y_hat|",""), ylim=yrange, col=cols[i])
 153         if (i < L)
 154             par(new=TRUE)
 155     }
 156     yrange = range( sapply(1:L, function(index) ( err[[index]]$MAPE$day ) ), na.rm=TRUE )
 157     for (i in seq_len(L))
 158     {
 159         plot(err[[i]]$MAPE$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
 160             ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
 161         if (i < L)
 162             par(new=TRUE)
 163     }
 164     yrange = range( sapply(1:L, function(index) ( err[[index]]$MAPE$indices ) ), na.rm=TRUE )
 165     for (i in seq_len(L))
 166     {
 167         plot(err[[i]]$MAPE$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
 168             ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
 169         if (i < L)
 170             par(new=TRUE)
 171     }
 172 }
 173
 174 #' @title Functional boxplot
 175 #'
 176 #' @description Draw the functional boxplot on the left, and bivariate plot on the right
 177 #'
 178 #' @param data Object return by \code{getData}
 179 #' @param fiter Optional filter: return TRUE on indices to process
 180 #' @param plot_bivariate Should the bivariate plot appear?
 181 #'
 182 #' @export
 183 plotFbox <- function(data, filter=function(index) TRUE, plot_bivariate=TRUE)
 184 {
 185     if (!requireNamespace("rainbow", quietly=TRUE))
 186         stop("Functional boxplot requires the rainbow package")
 187
 188     L = length(data$getCenteredSerie(2))
 189     series_matrix = sapply(1:data$getSize(), function(index) {
 190         if (filter(index))
 191             as.matrix(data$getSerie(index))
 192         else
 193             rep(NA,L)
 194     })
 195     # TODO: merge with previous step: only one pass should be required
 196     no_NAs_indices = sapply( 1:ncol(series_matrix), function(i) all(!is.na(series_matrix[,i])) )
 197     series_matrix = series_matrix[,no_NAs_indices]
 198
 199     series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
 200     if (plot_bivariate)
 201         par(mfrow=c(1,2))
 202     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 203     rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Temps (heures)", ylab="PM10",
 204         plotlegend=FALSE, lwd=2)
 205     if (plot_bivariate)
 206         rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
 207 }
 208
 209 #' @title Functional boxplot on filaments
 210 #'
 211 #' @description Draw the functional boxplot on filaments obtained by \code{computeFilaments}
 212 #'
 213 #' @param data Object return by \code{getData}
 214 #' @param indices Indices as output by \code{computeFilaments}
 215 #'
 216 #' @export
 217 plotFilamentsBox = function(data, indices, ...)
 218 {
 219     past_neighbs_indices = head(indices,-1)
 220     plotFbox(data, function(i) i %in% past_neighbs_indices, plot_bivariate=FALSE)
 221     par(new=TRUE)
 222     # "Magic" found at http://stackoverflow.com/questions/13842560/get-xlim-from-a-plot-in-r
 223     usr <- par("usr")
 224     yr <- (usr[4] - usr[3]) / 27
 225     plot(data$getSerie(tail(indices,1)), type="l", lwd=2, lty=2,
 226         ylim=c(usr[3] + yr, usr[4] - yr), xlab="", ylab="")
 227 }
 228
 229 #' @title Plot relative conditional variability / absolute variability
 230 #'
 231 #' @description Draw the relative conditional variability / absolute variability based on on
 232 #'   filaments obtained by \code{computeFilaments}
 233 #'
 234 #' @param data Object return by \code{getData}
 235 #' @param indices Indices as output by \code{computeFilaments}
 236 #'
 237 #' @export
 238 plotRelativeVariability = function(data, indices, ...)
 239 {
 240     #plot left / right separated by vertical line brown dotted
 241     #median of 3 runs for random length(indices) series
 242     ref_series = t( sapply(indices, function(i) {
 243         c( data$getSerie(i), data$getSerie(i+1) )
 244     }) )
 245     ref_var = apply(ref_series, 2, sd)
 246
 247     # Determine indices of no-NAs days followed by no-NAs tomorrows
 248     fdays = c()
 249     for (i in 1:(tail(indices,1)-1))
 250     {
 251         if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
 252             fdays = c(fdays, i)
 253     }
 254
 255     # TODO: 3 == magic number
 256     random_var = matrix(nrow=3, ncol=48)
 257     for (mc in seq_len(nrow(random_var)))
 258     {
 259         random_indices = sample(fdays, length(indices))
 260         random_series = t( sapply(random_indices, function(i) {
 261             c( data$getSerie(i), data$getSerie(i+1) )
 262         }) )
 263         random_var[mc,] = apply(random_series, 2, sd)
 264     }
 265     random_var = apply(random_var, 2, median)
 266
 267     yrange = range(ref_var, random_var)
 268     par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
 269     plot(ref_var, type="l", col=1, lwd=3, ylim=yrange, xlab="Temps (heures)", ylab="Écart-type")
 270     par(new=TRUE)
 271     plot(random_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
 272     abline(v=24, lty=2, col=colors()[56])
 273 }