-#' plot curves
+#' Plot curves
#'
#' Plot a range of curves in data
#'
#' @export
plotCurves <- function(data, indices=seq_len(data$getSize()))
{
- yrange = quantile( sapply( indices, function(i) {
- serie = c(data$getCenteredSerie(i))
- if (!all(is.na(serie)))
- range(serie, na.rm=TRUE)
- c()
- }), probs=c(0.05,0.95) )
+ series = data$getSeries(indices)
+ yrange = quantile(series, probs=c(0.025,0.975), na.rm=TRUE)
par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
for (i in seq_along(indices))
{
- plot(data$getSerie(indices[i]), type="l", ylim=yrange,
- xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10",""))
+ plot(series[,i], type="l", ylim=yrange,
+ xlab=ifelse(i==1,"Time (hours)",""), ylab=ifelse(i==1,"PM10",""))
if (i < length(indices))
par(new=TRUE)
}
}
-#' plot measured / predicted
-#'
-#' Plot measured curve (in black) and predicted curve (in red)
-#'
-#' @param data Object return by \code{getData}
-#' @param pred Object as returned by \code{computeForecast}
-#' @param index Index in forecasts
-#'
-#' @export
-plotPredReal <- function(data, pred, index)
-{
- horizon = length(pred$getSerie(1))
- measure = data$getSerie(pred$getIndexInData(index)+1)[1:horizon]
- yrange = range( pred$getSerie(index), measure )
- par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=3)
- plot(measure, type="l", ylim=yrange, xlab="Temps (en heures)", ylab="PM10")
- par(new=TRUE)
- plot(pred$getSerie(index), type="l", col="#0000FF", ylim=yrange, xlab="", ylab="")
-}
-
-#' Compute filaments
-#'
-#' Get similar days in the past + "past tomorrow", as black as distances are small
-#'
-#' @param data Object as returned by \code{getData}
-#' @param index Index in data
-#' @param limit Number of neighbors to consider
-#' @param plot Should the result be plotted?
-#'
-#' @export
-computeFilaments <- function(data, index, limit=60, plot=TRUE)
-{
- index = dateIndexToInteger(index, data)
- ref_serie = data$getCenteredSerie(index)
- if (any(is.na(ref_serie)))
- stop("computeFilaments requires a serie without NAs")
- L = length(ref_serie)
-
- # Determine indices of no-NAs days followed by no-NAs tomorrows
- fdays = c()
- for (i in 1:(index-1))
- {
- if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
- fdays = c(fdays, i)
- }
-
- distances = sapply(fdays, 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( c(ref_serie, sapply( indices, function(i) {
- serie = c(data$getCenteredSerie(fdays[i]), data$getCenteredSerie(fdays[i]+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
- 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)$ix
- colors = c(grays[ color_values[plot_order] ], "#FF0000")
- if (plot)
- {
- par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
- for ( i in seq_len(length(indices)+1) )
- {
- ii = ifelse(i<=length(indices), fdays[ indices[plot_order[i]] ], index)
- plot(c(data$getCenteredSerie(ii),data$getCenteredSerie(ii+1)),
- ylim=yrange, type="l", col=colors[i],
- xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10 centré",""))
- if (i <= length(indices))
- par(new=TRUE)
- }
- abline(v=24, lty=2, col=colors()[56])
- }
- list("indices"=c(fdays[ indices[plot_order] ],index), "colors"=colors)
-}
-
-#' Plot similarities
-#'
-#' Plot histogram of similarities (weights)
-#'
-#' @param pred Object as returned by \code{computeForecast}
-#' @param index Index in forecasts (not in data)
-#'
-#' @export
-plotSimils <- function(pred, index)
-{
- weights = pred$getParams(index)$weights
- if (is.null(weights))
- stop("plotSimils only works on 'Neighbors' forecasts")
- par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
- hist(pred$getParams(index)$weights, nclass=20, xlab="Poids", ylab="Effectif")
-}
-
#' Plot error
#'
#' Draw error graphs, potentially from several runs of \code{computeForecast}
#' @param err Error as returned by \code{computeError}
#' @param cols Colors for each error (default: 1,2,3,...)
#'
-#' @seealso \code{\link{plotPredReal}},\code{\link{plotFilaments}}
-#' \code{\link{plotSimils}},\code{\link{plotFbox}},\code{\link{plotRelativeVariability}}
+#' @seealso \code{\link{plotCurves}}, \code{\link{plotPredReal}},
+#' \code{\link{plotSimils}}, \code{\link{plotFbox}},
+#' \code{\link{computeFilaments}, }\code{\link{plotFilamentsBox}}, \code{\link{plotRelVar}}
#'
#' @export
plotError <- function(err, cols=seq_along(err))
err = list(err)
par(mfrow=c(2,2), mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
L = length(err)
- yrange = range( sapply(1:L, function(index) ( err[[index]]$abs$day ) ), na.rm=TRUE )
+ yrange = range( sapply(1:L, function(i) ( err[[i]]$abs$day ) ), na.rm=TRUE )
for (i in seq_len(L))
{
- plot(err[[i]]$abs$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
- ylab=ifelse(i==1,"Moyenne |y - y_hat|",""), ylim=yrange, col=cols[i])
+ plot(err[[i]]$abs$day, type="l", xlab=ifelse(i==1,"Time (hours)",""),
+ ylab=ifelse(i==1,"Mean |y - y_hat|",""), ylim=yrange, col=cols[i])
if (i < L)
par(new=TRUE)
}
- yrange = range( sapply(1:L, function(index) ( err[[index]]$abs$indices ) ), na.rm=TRUE )
+ yrange = range( sapply(1:L, function(i) ( err[[i]]$abs$indices ) ), na.rm=TRUE )
for (i in seq_len(L))
{
- plot(err[[i]]$abs$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
- ylab=ifelse(i==1,"Moyenne |y - y_hat|",""), ylim=yrange, col=cols[i])
+ plot(err[[i]]$abs$indices, type="l", xlab=ifelse(i==1,"Time (days)",""),
+ ylab=ifelse(i==1,"Mean |y - y_hat|",""), ylim=yrange, col=cols[i])
if (i < L)
par(new=TRUE)
}
- yrange = range( sapply(1:L, function(index) ( err[[index]]$MAPE$day ) ), na.rm=TRUE )
+ yrange = range( sapply(1:L, function(i) ( err[[i]]$MAPE$day ) ), na.rm=TRUE )
for (i in seq_len(L))
{
- plot(err[[i]]$MAPE$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
- ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
+ plot(err[[i]]$MAPE$day, type="l", xlab=ifelse(i==1,"Time (hours)",""),
+ ylab=ifelse(i==1,"Mean MAPE",""), ylim=yrange, col=cols[i])
if (i < L)
par(new=TRUE)
}
- yrange = range( sapply(1:L, function(index) ( err[[index]]$MAPE$indices ) ), na.rm=TRUE )
+ yrange = range( sapply(1:L, function(i) ( err[[i]]$MAPE$indices ) ), na.rm=TRUE )
for (i in seq_len(L))
{
- plot(err[[i]]$MAPE$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
- ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
+ plot(err[[i]]$MAPE$indices, type="l", xlab=ifelse(i==1,"Time (days)",""),
+ ylab=ifelse(i==1,"Mean MAPE",""), ylim=yrange, col=cols[i])
if (i < L)
par(new=TRUE)
}
}
+#' Plot measured / predicted
+#'
+#' Plot measured curve (in black) and predicted curve (in blue)
+#'
+#' @param data Object return by \code{getData}
+#' @param pred Object as returned by \code{computeForecast}
+#' @param index Index in forecasts (integer or date)
+#'
+#' @export
+plotPredReal <- function(data, pred, index)
+{
+ horizon = length(pred$getSerie(1))
+ measure = data$getSerie( pred$getIndexInData(index)+1 )[1:horizon]
+ prediction = pred$getSerie(index)
+ yrange = range(measure, prediction)
+ par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=3)
+ plot(measure, type="l", ylim=yrange, xlab="Time (hours)", ylab="PM10")
+ par(new=TRUE)
+ plot(prediction, type="l", col="#0000FF", ylim=yrange, xlab="", ylab="")
+}
+
+#' Plot similarities
+#'
+#' Plot histogram of similarities (weights)
+#'
+#' @param pred Object as returned by \code{computeForecast}
+#' @param index Index in forecasts (integer or date)
+#'
+#' @export
+plotSimils <- function(pred, index)
+{
+ weights = pred$getParams(index)$weights
+ if (is.null(weights))
+ stop("plotSimils only works on 'Neighbors' forecasts")
+ par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
+ hist(pred$getParams(index)$weights, nclass=20, main="", xlab="Weight", ylab="Count")
+}
+
#' Functional boxplot
#'
#' Draw the functional boxplot on the left, and bivariate plot on the right
#'
#' @param data Object return by \code{getData}
-#' @param fiter Optional filter: return TRUE on indices to process
-#' @param plot_bivariate Should the bivariate plot appear?
+#' @param indices integer or date indices to process
#'
#' @export
-plotFbox <- function(data, filter=function(index) TRUE, plot_bivariate=TRUE)
+plotFbox <- function(data, indices=seq_len(data$getSize()))
{
if (!requireNamespace("rainbow", quietly=TRUE))
stop("Functional boxplot requires the rainbow package")
- L = length(data$getCenteredSerie(2))
- series_matrix = sapply(1:data$getSize(), function(index) {
- if (filter(index))
- as.matrix(data$getSerie(index))
- else
- rep(NA,L)
- })
- # TODO: merge with previous step: only one pass should be required
+ series_matrix = data$getSeries(indices)
+ # Remove series with NAs
no_NAs_indices = sapply( 1:ncol(series_matrix),
function(i) all(!is.na(series_matrix[,i])) )
series_matrix = series_matrix[,no_NAs_indices]
series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
- if (plot_bivariate)
- par(mfrow=c(1,2))
par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
- rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Temps (heures)", ylab="PM10",
+ rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Time (hours)", ylab="PM10",
plotlegend=FALSE, lwd=2)
- if (plot_bivariate)
- rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
+ rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
+}
+
+#' Compute filaments
+#'
+#' Get similar days in the past, as black as distances are small
+#'
+#' @param data Object as returned by \code{getData}
+#' @param pred Object of class Forecast
+#' @param index Index in forecast (integer or date)
+#' @param limit Number of neighbors to consider
+#' @param plot Should the result be plotted?
+#'
+#' @return A list with
+#' \itemize{
+#' \item index : index of the current serie ('today')
+#' \item neighb_indices : indices of its neighbors
+#' \item colors : colors of neighbors curves (shades of gray)
+#' }
+#'
+#' @export
+computeFilaments <- function(data, pred, index, limit=60, plot=TRUE)
+{
+ ref_serie = data$getCenteredSerie( pred$getIndexInData(index) )
+ if (any(is.na(ref_serie)))
+ stop("computeFilaments requires a serie without NAs")
+
+ # Compute colors for each neighbor (from darkest to lightest)
+ sorted_dists = sort(-log(pred$getParams(index)$weights), index.return=TRUE)
+ nn = min(limit, length(sorted_dists$x))
+ min_dist = min(sorted_dists$x[1:nn])
+ max_dist = max(sorted_dists$x[1:nn])
+ color_values = floor(19.5*(sorted_dists$x[1:nn]-min_dist)/(max_dist-min_dist)) + 1
+ colors = gray.colors(20,0.1,0.9)[color_values] #TODO: 20 == magic number
+
+ if (plot)
+ {
+ # Complete series with (past and present) tomorrows
+ ref_serie = c(ref_serie, data$getCenteredSerie( pred$getIndexInData(index)+1 ))
+ centered_series = rbind(
+ data$getCenteredSeries( pred$getParams(index)$indices ),
+ data$getCenteredSeries( pred$getParams(index)$indices+1 ) )
+ yrange = range( ref_serie, quantile(centered_series, probs=c(0.025,0.975), na.rm=TRUE) )
+ par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
+ for (i in nn:1)
+ {
+ plot(centered_series[,sorted_dists$ix[i]], ylim=yrange, type="l", col=colors[i],
+ xlab=ifelse(i==1,"Time (hours)",""), ylab=ifelse(i==1,"Centered PM10",""))
+ par(new=TRUE)
+ }
+ # Also plot ref curve, in red
+ plot(ref_serie, ylim=yrange, type="l", col="#FF0000", xlab="", ylab="")
+ abline(v=24, lty=2, col=colors()[56], lwd=1)
+ }
+
+ list(
+ "index"=pred$getIndexInData(index),
+ "neighb_indices"=pred$getParams(index)$indices[sorted_dists$ix[1:nn]],
+ "colors"=colors)
}
#' Functional boxplot on filaments
#' Draw the functional boxplot on filaments obtained by \code{computeFilaments}
#'
#' @param data Object return by \code{getData}
-#' @param indices Indices as output by \code{computeFilaments}
+#' @param fil Output of \code{computeFilaments}
#'
#' @export
-plotFilamentsBox = function(data, indices, ...)
+plotFilamentsBox = function(data, fil)
{
- past_neighbs_indices = head(indices,-1)
- plotFbox(data, function(i) i %in% past_neighbs_indices, plot_bivariate=FALSE)
- par(new=TRUE)
+ if (!requireNamespace("rainbow", quietly=TRUE))
+ stop("Functional boxplot requires the rainbow package")
+
+ series_matrix = rbind(
+ data$getSeries(fil$neighb_indices), data$getSeries(fil$neighb_indices+1) )
+ series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
+ par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
+ rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Time (hours)", ylab="PM10",
+ plotlegend=FALSE, lwd=2)
+
# "Magic" found at http://stackoverflow.com/questions/13842560/get-xlim-from-a-plot-in-r
usr <- par("usr")
yr <- (usr[4] - usr[3]) / 27
- plot(data$getSerie(tail(indices,1)), type="l", lwd=2, lty=2,
+ par(new=TRUE)
+ plot(c(data$getSerie(fil$index),data$getSerie(fil$index+1)), type="l", lwd=2, lty=2,
ylim=c(usr[3] + yr, usr[4] - yr), xlab="", ylab="")
+ abline(v=24, lty=2, col=colors()[56])
}
#' Plot relative conditional variability / absolute variability
#' obtained by \code{computeFilaments}
#'
#' @param data Object return by \code{getData}
-#' @param indices Indices as output by \code{computeFilaments}
+#' @param fil Output of \code{computeFilaments}
#'
#' @export
-plotRelativeVariability = function(data, indices, ...)
+plotRelVar = function(data, fil)
{
- 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
- fdays = c()
- for (i in 1:(tail(indices,1)-1))
- {
- if ( !any(is.na(data$getSerie(i)) | is.na(data$getSerie(i+1))) )
- fdays = c(fdays, i)
- }
- global_var = c( apply(data$getSerie(fdays),2,sd), apply(data$getSerie(fdays+1),2,sd) )
+ ref_var = c( apply(data$getSeries(fil$neighb_indices),1,sd),
+ apply(data$getSeries(fil$neighb_indices+1),1,sd) )
+ fdays = getNoNA2(data, 1, fil$index-1)
+ global_var = c( apply(data$getSeries(fdays),1,sd), apply(data$getSeries(fdays+1),1,sd) )
yrange = range(ref_var, global_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")
+ xlab="Time (hours)", ylab="Standard deviation")
par(new=TRUE)
- plot(random_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
+ plot(global_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
abline(v=24, lty=2, col=colors()[56])
}
projects / talweg.git / blobdiff