X-Git-Url: https://git.auder.net/?p=talweg.git;a=blobdiff_plain;f=pkg%2FR%2Fplot.R;h=0f895bd16483795302623b53ea983f3ab9c2cd92;hp=2b7411763b21dfe0877cc16268c63131265fd7ee;hb=HEAD;hpb=2201696688c637888b0bf9dcabf45908520fa488

diff --git a/pkg/R/plot.R b/pkg/R/plot.R
index 2b74117..0f895bd 100644
--- a/pkg/R/plot.R
+++ b/pkg/R/plot.R
@@ -11,13 +11,7 @@ plotCurves <- function(data, indices=seq_len(data$getSize()))
 	series = data$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(series[,i], type="l", ylim=yrange,
-			xlab=ifelse(i==1,"Time (hours)",""), ylab=ifelse(i==1,"PM10",""))
-		if (i < length(indices))
-			par(new=TRUE)
-	}
+	matplot(series, type="l", ylim=yrange, xlab="Time (hours)", ylab="PM10")
 }
 
 #' Plot error
@@ -26,50 +20,49 @@ plotCurves <- function(data, indices=seq_len(data$getSize()))
 #'
 #' @param err Error as returned by \code{computeError()}
 #' @param cols Colors for each error (default: 1,2,3,...)
+#' @param agg Aggregation level ("day", "week" or "month")
 #'
 #' @seealso \code{\link{plotCurves}}, \code{\link{plotPredReal}},
 #'   \code{\link{plotSimils}}, \code{\link{plotFbox}}, \code{\link{computeFilaments}},
 #'   \code{\link{plotFilamentsBox}}, \code{\link{plotRelVar}}
 #'
 #' @export
-plotError <- function(err, cols=seq_along(err))
+plotError <- function(err, cols=seq_along(err), agg="day")
 {
 	if (!is.null(err$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)
+	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 )
-	for (i in seq_len(L))
-	{
-		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(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,"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(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,"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(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,"Time (days)",""),
-			ylab=ifelse(i==1,"Mean MAPE",""), ylim=yrange, col=cols[i])
-		if (i < L)
-			par(new=TRUE)
-	}
+
+	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)
 }
 
 #' Plot measured / predicted
@@ -83,7 +76,14 @@ plotError <- function(err, cols=seq_along(err))
 plotPredReal <- function(data, pred, index)
 {
 	prediction = pred$getForecast(index)
-	measure = data$getSerie( pred$getIndexInData(index) )[1:length(prediction)]
+	measure = data$getSerie( pred$getIndexInData(index) )[1:length(pred$getForecast(1))]
+
+	# 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)]
+
 	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")
@@ -104,8 +104,11 @@ 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")
+	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
@@ -143,7 +146,6 @@ plotFbox <- function(data, indices=seq_len(data$getSize()))
 #' @param index Index in forecast (integer or date)
 #' @param limit Number of neighbors to consider
 #' @param plot Should the result be plotted?
-#' @param predict_from First prediction instant
 #'
 #' @return A list with
 #' \itemize{
@@ -153,18 +155,24 @@ plotFbox <- function(data, indices=seq_len(data$getSize()))
 #' }
 #'
 #' @export
-computeFilaments <- function(data, pred, index, predict_from, limit=60, plot=TRUE)
+computeFilaments <- function(data, pred, index, limit=60, plot=TRUE)
 {
-	if (is.null(pred$getParams(index)$weights) || is.na(pred$getParams(index)$weights[1]))
+	weights <- pred$getParams(index)$weights
+	if (is.null(weights) || is.na(pred$getParams(index)$weights[1]))
 		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
+	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] ) )
+	{
+		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
+	}
+	else
+		colors <- rep(colors()[17], length(weights))
 
 	if (plot)
 	{
@@ -172,8 +180,8 @@ computeFilaments <- function(data, pred, index, predict_from, limit=60, plot=TRU
 		ref_serie = c( data$getCenteredSerie( pred$getIndexInData(index)-1 ),
 			data$getCenteredSerie( pred$getIndexInData(index) ) )
 		centered_series = rbind(
-			data$getCenteredSeries( pred$getParams(index)$indices ),
-			data$getCenteredSeries( pred$getParams(index)$indices+1 ) )
+			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)
@@ -185,7 +193,9 @@ computeFilaments <- function(data, pred, index, predict_from, limit=60, plot=TRU
 		}
 		# Also plot ref curve, in red
 		plot(ref_serie, ylim=yrange, type="l", col="#FF0000", xlab="", ylab="")
-		abline(v=24+predict_from-0.5, lty=2, col=colors()[56], lwd=1)
+		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(
@@ -200,6 +210,7 @@ computeFilaments <- function(data, pred, index, predict_from, limit=60, plot=TRU
 #'
 #' @inheritParams computeError
 #' @param fil Output of \code{computeFilaments}
+#' @param predict_from First predicted time step
 #'
 #' @export
 plotFilamentsBox = function(data, fil, predict_from)
@@ -219,7 +230,7 @@ plotFilamentsBox = function(data, fil, predict_from)
 	usr <- par("usr")
 	yr <- (usr[4] - usr[3]) / 27
 	par(new=TRUE)
-	plot(c(data$getSerie(fil$index),data$getSerie(fil$index+1)), type="l", lwd=2, lty=2,
+	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])
 }