-#' @title plot curves
+#' Plot curves
#'
-#' @description Plot a range of curves in data
+#' Plot a range of curves in data.
#'
-#' @param data Object of class Data
+#' @inheritParams computeError
#' @param indices Range of indices (integers or dates)
#'
#' @export
plotCurves <- function(data, indices=seq_len(data$getSize()))
{
- yrange = quantile( range( sapply( indices, function(i) {
- serie = c(data$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",""))
- if (i < length(indices))
- par(new=TRUE)
- }
+ matplot(series, type="l", ylim=yrange, xlab="Time (hours)", ylab="PM10")
}
-#' @title plot measured / predicted
+#' Plot error
#'
-#' @description Plot measured curve (in black) and predicted curve (in red)
+#' Draw error graphs, potentially from several runs of \code{computeForecast()}.
#'
-#' @param data Object return by \code{getData}
-#' @param pred Object as returned by \code{getForecast}
-#' @param index Index in forecasts
+#' @param err Error as returned by \code{computeError()}
+#' @param cols Colors for each error (default: 1,2,3,...)
+<<<<<<< HEAD
+=======
+#' @param agg Aggregation level ("day", "week" or "month")
+>>>>>>> 3a38473a435221cc15b6215b0d6677cd370dc2d6
+#'
+#' @seealso \code{\link{plotCurves}}, \code{\link{plotPredReal}},
+#' \code{\link{plotSimils}}, \code{\link{plotFbox}}, \code{\link{computeFilaments}},
+#' \code{\link{plotFilamentsBox}}, \code{\link{plotRelVar}}
#'
#' @export
-plotPredReal <- function(data, pred, index)
+plotError <- function(err, cols=seq_along(err), agg="day")
{
- 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$getSerie(index), type="l", col="#0000FF", ylim=yrange, xlab="", ylab="")
+ if (!is.null(err$abs))
+ err = list(err)
+ par(mfrow=c(2,2), mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
+ L = length(err)
+
+ yrange = range( sapply(1:L, function(i) err[[i]]$abs$day), na.rm=TRUE )
+ matplot(sapply( seq_len(L), function(i) err[[i]]$abs$day ), type="l",
+ xlab="Time (hours)", ylab="Mean |y - y_hat|", ylim=yrange, col=cols, lwd=2, lty=1)
+
+ agg_curves <- sapply( seq_len(L), function(i) {
+ curve <- err[[i]]$abs$indices
+ delta <- if (agg=="day") 1 else if (agg=="week") 7 else if (agg=="month") 30
+ vapply( seq(1,length(curve),delta), function(i) {
+ mean(curve[i:(i+delta-1)], na.rm=TRUE)
+ }, vector("double",1), USE.NAMES=FALSE )
+ })
+ yrange = range(agg_curves, na.rm=TRUE)
+ matplot(agg_curves, type="l", xlab=paste("Time (",agg,"s)", sep=""),
+ ylab="Mean |y - y_hat|", ylim=yrange, col=cols, lwd=2, lty=1)
+
+ yrange = range( sapply(1:L, function(i) err[[i]]$MAPE$day), na.rm=TRUE )
+ matplot(sapply( seq_len(L), function(i) err[[i]]$MAPE$day ), type="l",
+ xlab="Time (hours)", ylab="Mean MAPE", ylim=yrange, col=cols, lwd=2, lty=1)
+
+ agg_curves <- sapply( seq_len(L), function(i) {
+ curve <- err[[i]]$MAPE$indices
+ delta <- if (agg=="day") 1 else if (agg=="week") 7 else if (agg=="month") 30
+ vapply( seq(1,length(curve),delta), function(i) {
+ mean(curve[i:(i+delta-1)], na.rm=TRUE)
+ }, vector("double",1), USE.NAMES=FALSE )
+ })
+ yrange = range(agg_curves, na.rm=TRUE)
+ matplot(agg_curves, type="l", xlab=paste("Time (",agg,"s)", sep=""),
+ ylab="Mean MAPE", ylim=yrange, col=cols, lwd=2, lty=1)
}
-#' @title Compute filaments
+#' Plot measured / predicted
#'
-#' @description Get similar days in the past + "past tomorrow", as black as distances are small
+#' Plot measured curve (in black) and predicted curve (in blue).
#'
-#' @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?
+#' @inheritParams computeError
+#' @param index Index in forecasts (integer or date)
#'
#' @export
-computeFilaments <- function(data, index, limit=60, plot=TRUE)
+plotPredReal <- function(data, pred, index)
{
- index = dateIndexToInteger(index, data)
- ref_serie = data$getCenteredSerie(index)
- if (any(is.na(ref_serie)))
- stop("computeFilaments requires a serie without NAs")
- L = length(ref_serie)
+ prediction = pred$getForecast(index)
+ measure = data$getSerie( pred$getIndexInData(index) )[1:length(pred$getForecast(1))]
- # Determine indices of no-NAs days followed by no-NAs tomorrows
- first_day = ifelse(length(data$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)
- }
+ # Remove the common part, where prediction == measure
+ dot_mark <- ifelse(prediction[1]==measure[1],
+ which.max(seq_along(prediction)[prediction==measure]), 0)
+ prediction = prediction[(dot_mark+1):length(prediction)]
+ measure = measure[(dot_mark+1):length(measure)]
- 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 = 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
- 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)$ix
- colors = c(grays[ color_values[plot_order] ], "#FF0000")
- if (plot)
- {
- par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
- for ( i in seq_len(length(indices)+1) )
- {
- ii = ifelse(i<=length(indices), fdays_indices[ indices[plot_order[i]] ], index)
- plot(c(data$getCenteredSerie(ii),data$getCenteredSerie(ii+1)),
- ylim=yrange, type="l", col=colors[i],
- xlab=ifelse(i==1,"Temps (en heures)",""), ylab=ifelse(i==1,"PM10 centré",""))
- if (i <= length(indices))
- par(new=TRUE)
- }
- abline(v=24, lty=2, col=colors()[56])
- }
- list("indices"=c(fdays_indices[ indices[plot_order] ],index), "colors"=colors)
+ yrange = range(measure, prediction)
+ par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=3)
+ plot(measure, type="l", ylim=yrange, xlab="Time (hours)", ylab="PM10")
+ par(new=TRUE)
+ plot(prediction, type="l", col="#0000FF", ylim=yrange, xlab="", ylab="")
}
-#' @title Plot similarities
+#' Plot similarities
#'
-#' @description Plot histogram of similarities (weights)
+#' Plot histogram of similarities (weights), for 'Neighbors' method.
#'
-#' @param pred Object as returned by \code{getForecast}
-#' @param index Index in forecasts (not in data)
+#' @inheritParams computeError
+#' @param index Index in forecasts (integer or date)
#'
#' @export
plotSimils <- function(pred, index)
weights = pred$getParams(index)$weights
if (is.null(weights))
stop("plotSimils only works on 'Neighbors' forecasts")
+ par(mfrow=c(1,2), mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
+ small_weights = weights[ weights < 1/length(weights) ]
+ large_weights = weights[ weights >= 1/length(weights) ]
+ hist(small_weights, nclass=25, main="", xlab="Weight < 1/N", ylab="Count")
+ hist(large_weights, nclass=25, main="", xlab="Weight >= 1/N", ylab="Count")
+}
+
+#' Functional boxplot
+#'
+#' Draw the functional boxplot on the left, and bivariate plot on the right.
+#'
+#' @inheritParams computeError
+#' @inheritParams plotCurves
+#'
+#' @export
+plotFbox <- function(data, indices=seq_len(data$getSize()))
+{
+ if (!requireNamespace("rainbow", quietly=TRUE))
+ stop("Functional boxplot requires the rainbow package")
+
+ series_matrix = data$getSeries(indices)
+ # Remove series with NAs
+ no_NAs_indices = sapply( 1:ncol(series_matrix),
+ function(i) all(!is.na(series_matrix[,i])) )
+ series_matrix = series_matrix[,no_NAs_indices]
+
+ series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
- hist(pred$getParams(index)$weights, nclass=20, xlab="Poids", ylab="Effectif")
+ rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Time (hours)", ylab="PM10",
+ plotlegend=FALSE, lwd=2)
+ rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
}
-#' @title Plot error
+#' Compute filaments
#'
-#' @description Draw error graphs, potentially from several runs of \code{getForecast}
+#' Obtain similar days in the past, and (optionally) plot them -- as black as distances
+#' are small.
#'
-#' @param err Error as returned by \code{getError}
-#' @param cols Colors for each error (default: 1,2,3,...)
+#' @inheritParams computeError
+#' @param index Index in forecast (integer or date)
+#' @param limit Number of neighbors to consider
+#' @param plot Should the result be plotted?
#'
-#' @seealso \code{\link{plotPredReal}}, \code{\link{plotFilaments}}, \code{\link{plotSimils}}
-#' \code{\link{plotFbox}}
+#' @return A list with
+#' \itemize{
+#' \item index : index of the current serie ('today')
+#' \item neighb_indices : indices of its neighbors
+#' \item colors : colors of neighbors curves (shades of gray)
+#' }
#'
#' @export
-plotError <- function(err, cols=seq_along(err))
+computeFilaments <- function(data, pred, index, limit=60, plot=TRUE)
{
- if (!is.null(err$abs))
- 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 )
- 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])
- if (i < L)
- par(new=TRUE)
- }
- yrange = range( sapply(1:L, function(index) ( err[[index]]$abs$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])
- if (i < L)
- par(new=TRUE)
- }
- yrange = range( sapply(1:L, function(index) ( err[[index]]$MAPE$day ) ), na.rm=TRUE )
- for (i in seq_len(L))
+ weights <- pred$getParams(index)$weights
+ if (is.null(weights) || is.na(pred$getParams(index)$weights[1]))
+ stop("computeFilaments requires a serie without NAs")
+
+ nn <- min(limit, length(weights))
+ sorted_dists = sort(-log(weights), index.return=TRUE)
+ # Compute colors for each neighbor (from darkest to lightest), if weights differ
+ if ( any( weights != weights[1] ) )
{
- plot(err[[i]]$MAPE$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
- ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
- if (i < L)
- par(new=TRUE)
+ min_dist = min(sorted_dists$x[1:nn])
+ max_dist = max(sorted_dists$x[1:nn])
+ color_values = floor(19.5*(sorted_dists$x[1:nn]-min_dist)/(max_dist-min_dist)) + 1
+ colors = gray.colors(20,0.1,0.9)[color_values] #TODO: 20 == magic number
}
- yrange = range( sapply(1:L, function(index) ( err[[index]]$MAPE$indices ) ), na.rm=TRUE )
- for (i in seq_len(L))
+ else
+ colors <- rep(colors()[17], length(weights))
+
+ if (plot)
{
- plot(err[[i]]$MAPE$indices, type="l", xlab=ifelse(i==1,"Temps (jours)",""),
- ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
- if (i < L)
+ # Complete series with (past and present) tomorrows
+ ref_serie = c( data$getCenteredSerie( pred$getIndexInData(index)-1 ),
+ data$getCenteredSerie( pred$getIndexInData(index) ) )
+ centered_series = rbind(
+ data$getCenteredSeries( pred$getParams(index)$indices-1 ),
+ data$getCenteredSeries( pred$getParams(index)$indices ) )
+ yrange = range( ref_serie,
+ quantile(centered_series, probs=c(0.025,0.975), na.rm=TRUE) )
+ par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=2)
+ for (i in nn:1)
+ {
+ plot(centered_series[,sorted_dists$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="")
+ dot_mark <- 0.5 + which.max( pred$getForecast(1) ==
+ data$getSerie( pred$getIndexInData(1) )[1:length(pred$getForecast(1))] )
+ abline(v=24+dot_mark, 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)
}
-#' @title Functional boxplot
+#' Functional boxplot on filaments
#'
-#' @description Draw the functional boxplot on the left, and bivariate plot on the right
+#' Draw the functional boxplot on filaments obtained by \code{computeFilaments()}.
#'
-#' @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?
+#' @inheritParams computeError
+#' @param fil Output of \code{computeFilaments}
+#' @param predict_from First predicted time step
#'
#' @export
-plotFbox <- function(data, filter=function(index) TRUE, plot_bivariate=TRUE)
+plotFilamentsBox = function(data, fil, predict_from)
{
if (!requireNamespace("rainbow", quietly=TRUE))
stop("Functional boxplot requires the rainbow package")
- start_index = 1
- end_index = data$getSize()
- if (length(data$getCenteredSerie(1)) < length(data$getCenteredSerie(2)))
- {
- # Shifted start (7am, or 1pm, or...)
- start_index = 2
- end_index = data$getSize() - 1
- }
-
- series_matrix = sapply(start_index:end_index, function(index) {
- as.matrix(data$getSerie(index))
- })
- # Remove NAs. + filter TODO: merge with previous step: only one pass required...
- nas_indices = seq_len(ncol(series_matrix))[ sapply( 1:ncol(series_matrix),
- function(index) ( !filter(index) || any(is.na(series_matrix[,index])) ) ) ]
- series_matrix = series_matrix[,-nas_indices]
-
+ series_matrix = rbind(
+ data$getSeries(fil$neighb_indices-1), data$getSeries(fil$neighb_indices) )
series_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
- if (plot_bivariate)
- par(mfrow=c(1,2))
+
par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5)
- rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Temps (heures)", ylab="PM10",
+ rainbow::fboxplot(series_fds, "functional", "hdr", xlab="Time (hours)", ylab="PM10",
plotlegend=FALSE, lwd=2)
- if (plot_bivariate)
- rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
-}
-#' @title Functional boxplot on filaments
-#'
-#' @description Draw the functional boxplot on filaments obtained by \code{computeFilaments}
-#'
-#' @param data Object return by \code{getData}
-#' @param indices Indices as output by \code{computeFilaments}
-#'
-#' @export
-plotFilamentsBox = function(data, indices, ...)
-{
- past_neighbs_indices = head(indices,-1)
- plotFbox(data, function(i) i %in% past_neighbs_indices, plot_bivariate=FALSE)
- par(new=TRUE)
- # "Magic" found at http://stackoverflow.com/questions/13842560/get-xlim-from-a-plot-in-r
+ # "Magic": http://stackoverflow.com/questions/13842560/get-xlim-from-a-plot-in-r
usr <- par("usr")
yr <- (usr[4] - usr[3]) / 27
- plot(data$getSerie(tail(indices,1)), type="l", lwd=2, lty=2,
+ par(new=TRUE)
+ plot(c(data$getSerie(fil$index-1),data$getSerie(fil$index)), type="l", lwd=2, lty=2,
ylim=c(usr[3] + yr, usr[4] - yr), xlab="", ylab="")
+ abline(v=24+predict_from-0.5, lty=2, col=colors()[56])
}
-#' @title Plot relative conditional variability / absolute variability
+#' Plot relative conditional variability / absolute variability
#'
-#' @description Draw the relative conditional variability / absolute variability based on on
-#' filaments obtained by \code{computeFilaments}
+#' Draw the relative conditional variability / absolute variability based on filaments
+#' obtained by \code{computeFilaments()}.
#'
-#' @param data Object return by \code{getData}
-#' @param indices Indices as output by \code{computeFilaments}
+#' @inheritParams computeError
+#' @inheritParams plotFilamentsBox
#'
#' @export
-plotRelativeVariability = function(data, indices, ...)
+plotRelVar = function(data, fil, predict_from)
{
- #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$getSerie(i+1) )
- }) )
- random_var[mc,] = apply(random_series, 2, sd)
- }
- random_var = apply(random_var, 2, median)
+ ref_var = c( apply(data$getSeries(fil$neighb_indices-1),1,sd),
+ apply(data$getSeries(fil$neighb_indices),1,sd) )
+ tdays = .getNoNA2(data, 2, fil$index)
+ global_var = c(
+ apply(data$getSeries(tdays-1),1,sd),
+ apply(data$getSeries(tdays),1,sd) )
- yrange = range(ref_var, random_var)
+ 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")
+ plot(ref_var, type="l", col=1, lwd=3, ylim=yrange,
+ xlab="Time (hours)", ylab="Standard deviation")
par(new=TRUE)
- plot(random_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
- abline(v=24, lty=2, col=colors()[56])
+ plot(global_var, type="l", col=2, lwd=3, ylim=yrange, xlab="", ylab="")
+ abline(v=24+predict_from-0.5, lty=2, col=colors()[56])
}