jupyter batch; lower font size on plots

[talweg.git] / R / plot.R

#' @title plot measured / predicted
#'
#' @description Plot measured curve (in black) and predicted curve (in red)
#'
#' @param data Object return by \code{getData}
#' @param pred Object as returned by \code{getForecast}
#' @param index Index in forecasts
#'
#' @export
plotPredReal <- function(data, pred, index)
{
	horizon = length(pred$getSerie(1))
	par(mar=c(4.7,5,1,1), cex.axis=1.5, cex.lab=1.5, lwd=3)
	measure = data$getSerie(pred$getIndexInData(index)+1)[1:horizon]
	yrange = range( pred$getSerie(index), measure )
	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="")
}

#' @title Plot filaments
#'
#' @description Plot 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
#'
#' @export
plotFilaments <- function(data, index, limit=60)
{
	index = dateIndexToInteger(index, data)
	ref_serie = data$getCenteredSerie(index)
	if (any(is.na(ref_serie)))
		stop("plotFilaments requires a serie without NAs")
	L = length(ref_serie)
	first_day = ifelse(length(data$getCenteredSerie(1)<L), 2, 1)
	distances = sapply(first_day:(index-1), function(i) {
		sqrt( sum( (ref_serie - data$getCenteredSerie(i))^2 ) / L )
	})
	# HACK to suppress NA effect while keeping indexation
	distances[is.na(distances)] = max(distances,na.rm=TRUE) + 1
	indices = sort(distances, index.return=TRUE)$ix[1:min(limit,index-first_day)]
	yrange = range( ref_serie, sapply( indices, function(i) {
		index = i - first_day + 1
		serie = c(data$getCenteredSerie(index), data$getCenteredSerie(index+1))
		if (!all(is.na(serie)))
			return ( range(serie, na.rm=TRUE) )
		return (0)
	}) )
	grays = gray.colors(20, 0.1, 0.9) #TODO: 20 == magic number
	colors = c(
		grays[ floor( 20.5 * distances[indices] / (1+max(distances[indices])) ) ], "#FF0000")
	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))
	{
		ind = ifelse(i<=length(indices), indices[i] - first_day + 1, index)
		plot(c(data$getCenteredSerie(ind),data$getCenteredSerie(ind+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)
	}
}

#' @title Plot similarities
#'
#' @description Plot histogram of similarities (weights)
#'
#' @param pred Object as returned by \code{getForecast}
#' @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")
}

#' @title Plot error
#'
#' @description Draw error graphs, potentially from several runs of \code{getForecast}
#'
#' @param err Error as returned by \code{getError}
#' @param cols Colors for each error (default: 1,2,3,...)
#'
#' @seealso \code{\link{plotPredReal}}, \code{\link{plotFilaments}}, \code{\link{plotSimils}}
#'   \code{\link{plotFbox}}
#'
#' @export
plotError <- function(err, cols=seq_along(err))
{
	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$day ) ), na.rm=TRUE )
	for (i in seq_len(L))
	{
		plot(err[[i]]$MAPE$day, type="l", xlab=ifelse(i==1,"Temps (heures)",""),
			ylab=ifelse(i==1,"MAPE moyen",""), ylim=yrange, col=cols[i])
		if (i < L)
			par(new=TRUE)
	}
	yrange = range( sapply(1:L, function(index) ( err[[index]]$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])
		if (i < L)
			par(new=TRUE)
	}
}

#' @title Functional boxplot
#'
#' @description 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
#'
#' @export
plotFbox <- function(data, filter=function(index) TRUE)
{
	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_fds = rainbow::fds(seq_len(nrow(series_matrix)), series_matrix)
	par(mfrow=c(1,2), 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",
		plotlegend=FALSE, lwd=2)
	rainbow::fboxplot(series_fds, "bivariate", "hdr", plotlegend=FALSE)
}