In wiesenfa/challengeR: Analyzing assessment data of biomedical image analysis competitions and visualization of results
options(width=80)
#out.format <- knitr::opts_knit$get("out.format")
out.format <- knitr::opts_knit$get("rmarkdown.pandoc.to")
img_template <- switch( out.format,
docx = list("img-params"=list(dpi=150,
fig.width=6,
fig.height=6,
out.width="504px",
out.height="504px")),
{
# default
list("img-params"=list( fig.width=7,
fig.height = 3,
dpi=300))
} )
knitr::opts_template$set( img_template )
knitr::opts_chunk$set(echo = F) # ,#fig.width=7,fig.height = 3,dpi=300,
if (out.format != "docx") knitr::opts_chunk$set(fig.align = "center")
if (!is.null(params$fig.format)) knitr::opts_chunk$set(dev = params$fig.format) # can be vector, e.g. fig.format=c('jpeg','png', 'pdf')
if (!is.null(params$dpi)) knitr::opts_chunk$set(dpi = params$dpi)
theme_set(theme_light())
isMultiTask = params$isMultiTask
bootstrappingEnabled = params$bootstrappingEnabled
object = params$object
if (isMultiTask) {
if (is.numeric(params$consensus) & !is.null(names(params$consensus)) ){
ordering_consensus <- names(params$consensus)[order(params$consensus)]
} else if (is.character(ordering)){
ordering_consensus=names(params$consensus)
} else stop("Argument ordering has to be a named vector of ranks or a vector of algorithm names in the ranking order.")
} else
{
ordering_consensus=names(sort(t(object$matlist[[1]][,"rank",drop=F])["rank",]))
}
color.fun=params$colors
challenge_multiple=object$data
ranking.fun=object$FUN
cols_numbered=cols=color.fun(length(ordering_consensus))
names(cols)=ordering_consensus
names(cols_numbered)= paste(1:length(cols),names(cols))
if (bootstrappingEnabled) {
boot_object = params$object
challenge_multiple=boot_object$data
ranking.fun=boot_object$FUN
object=challenge_multiple%>%ranking.fun
object$FUN.list = boot_object$FUN.list
object$fulldata=boot_object$fulldata # only not NULL if subset of algorithms used
}
n.tasks <- length(object$matlist)
n.algorithms <- nrow((object$matlist[[1]]))
This document presents a systematic report on the benchmark study "r params$name". Input data comprises raw metric values for all algorithms and cases. Generated plots are:
Details can be found in Wiesenfarth et al. (2021).
if (isMultiTask) {
cat("# Rankings\n")
} else {
cat("# Ranking")
}
Algorithms within a task are ranked according to the following ranking scheme:
a=( lapply(object$FUN.list[1:2],function(x) {
if (class(x)== "standardGeneric") return(paste0("aggregate using function ",
x@generic
))
else if (!is.character(x)) return(paste0("aggregate using function ",
paste(gsub("UseMethod","",
deparse(functionBody(x))),
collapse=" ")
))
else if (x=="rank") return(x)
else return(paste0("aggregate using function ",x))
}))
cat(" *",paste0(a,collapse=" then "),"*",sep="")
if (is.character(object$FUN.list[[1]]) && object$FUN.list[[1]]=="significance") cat("\n\n Column 'prop_significance' is equal to the number of pairwise significant test results for a given algorithm divided by the number of algorithms.")
if (isMultiTask) {
cat("Ranking for each task:\n")
for (t in 1:n.tasks){
cat("\n",names(object$matlist)[t],": ")
n.cases=nrow(challenge_multiple[[t]])/length(unique(challenge_multiple[[t]][[attr(challenge_multiple,"algorithm")]]))
numberOfAlgorithms <- length(unique(challenge_multiple[[t]][[attr(challenge_multiple, "algorithm")]]))
cat("\nThe analysis is based on",
numberOfAlgorithms,
"algorithms and",
n.cases,
"cases.",
attr(object$data,"n.missing")[[t]], "missing cases have been found in the data set. ")
if (nrow(attr(object$data,"missingData")[[t]])>0) {
if(attr(object$data,"n.missing")[[t]]==0 ) cat("However, ")
else if(attr(object$data,"n.missing")[[t]]>0 ) cat("Additionally, ")
cat("performance of not all algorithms has been observed for all cases in task '",
names(object$matlist)[t],
"'. Therefore, missings have been inserted in the following cases:")
print(knitr::kable(as.data.frame(attr(object$data,"missingData")[[t]])))
}
if (nrow(attr(object$data,"missingData")[[t]])>0 | attr(object$data,"n.missing")[[t]]>0) {
if (is.numeric(attr(object$data,"na.treat"))) cat("All missings have been replaced by values of", attr(object$data,"na.treat"),".\n")
else if (is.character(attr(object$data,"na.treat")) && attr(object$data,"na.treat")=="na.rm") cat("All missings have been removed.")
else if (is.function(attr(object$data,"na.treat"))) {
cat("Missings have been replaced using function ")
print(attr(object$data,"na.treat"))
}
else if (is.character(object$FUN.list[[1]]) && object$FUN.list[[1]]=="rank") cat("Missings lead to the algorithm ranked last for the missing case.")
}
x=object$matlist[[t]]
print(knitr::kable(x[order(x$rank),]))
}
} else {
n.cases=nrow(challenge_multiple[[1]])/length(unique(challenge_multiple[[1]][[attr(challenge_multiple,"algorithm")]]))
# Is subset of algorithms used?
if (!is.null(object$fulldata[[1]])) {
cat("The top ",
length(unique(challenge_multiple[[1]][[attr(challenge_multiple, "algorithm")]])),
" out of ",
length(unique(object$fulldata[[1]][[attr(challenge_multiple, "algorithm")]])),
" algorithms are considered.\n")
cat("\nThe analysis is based on",
n.cases,
"cases. ")
} else {
cat("\nThe analysis is based on",
length(unique(challenge_multiple[[1]][[attr(challenge_multiple, "algorithm")]])),
"algorithms and",
n.cases,
"cases. ")
}
cat(attr(object$data,"n.missing")[[1]], "missing cases have been found in the data set. ")
if (nrow(attr(object$data,"missingData")[[1]])>0) {
if(attr(object$data,"n.missing")[[1]]==0 ) cat("However, ")
else if(attr(object$data,"n.missing")[[1]]>0 ) cat("Additionally, ")
cat("performance of not all algorithms has been observed for all cases. Therefore, missings have been inserted in the following cases:")
print(knitr::kable(as.data.frame(attr(object$data,"missingData")[[1]])))
}
if (nrow(attr(object$data,"missingData")[[1]])>0 | attr(object$data,"n.missing")[[1]]>0) {
if (is.numeric(attr(object$data,"na.treat"))) cat("All missings have been replaced by values of", attr(object$data,"na.treat"),".\n")
else if (is.character(attr(object$data,"na.treat")) && attr(object$data,"na.treat")=="na.rm") cat("All missings have been removed.")
else if (is.function(attr(object$data,"na.treat"))) {
cat("Missings have been replaced using function ")
print(attr(object$data,"na.treat"))
}
else if (is.character(object$FUN.list[[1]]) && object$FUN.list[[1]]=="rank") cat("Missings lead to the algorithm ranked last for the missing case.")
}
cat("\n\nRanking:")
x=object$matlist[[1]]
print(knitr::kable(x[order(x$rank),]))
}
\bigskip
\newpage
Visualization of raw assessment data
if (isMultiTask) {
cat("The algorithms are ordered according to the computed ranks for each task.")
}
Dot- and boxplot
Dot- and boxplots for visualizing raw assessment data separately for each algorithm. Boxplots representing descriptive statistics over all cases (median, quartiles and outliers) are combined with horizontally jittered dots representing individual cases.
\bigskip
boxplot(object, size=.8) %++% scale_color_manual(values=cols)
\newpage
Podium plot
Podium plots (see also Eugster et al., 2008) for visualizing raw assessment data. Upper part (spaghetti plot): Participating algorithms are color-coded, and each colored dot in the plot represents a metric value achieved with the respective algorithm. The actual metric value is encoded by the y-axis. Each podium (here: $p$=r length(ordering_consensus)) represents one possible rank, ordered from best (1) to last (here: r length(ordering_consensus)). The assignment of metric values (i.e. colored dots) to one of the podiums is based on the rank that the respective algorithm achieved on the corresponding case. Note that the plot part above each podium place is further subdivided into $p$ "columns", where each column represents one participating algorithm (here: $p=$ r length(ordering_consensus)). Dots corresponding to identical cases are connected by a line, leading to the shown spaghetti structure. Lower part: Bar charts represent the relative frequency for each algorithm to achieve the rank encoded by the podium place.
cex.legend = 1.2
plot.new()
# bottom legend
# get number of columns
legend.width=1e5 #arbitrarily large
ncol.legend <- n.algorithms + 1
while(legend.width>12){
ncol.legend <- ncol.legend-1
algs=ordering_consensus
l=legend("bottom",
paste0(1:length(algs),": ",algs),
xpd=NA,
lwd = 1, col = cols,
bg = NA,
ncol=ncol.legend,
bty="n",
cex=cex.legend, seg.len=1.1,
title="Rank: Alg.",
title.adj = 0,
plot=F)
legend.width=grconvertX(l$rect$w,"user","inches")
}
w=0
h<-hh<- grconvertY(l$rect$h, to='ndc') - grconvertY(0, to='ndc')
nrow.legend=length(unique(l$text$y))
legend.height = nrow.legend* max( cex.legend * par()$cin[2],max(strheight(ordering_consensus, units = "inches", cex = cex.legend)))
addy= 6+ legend.height
#c(bottom, left, top, right
op <- par(no.readonly = TRUE)
hh<- grconvertY(legend.height, from="inches",to='ndc')
par(pin=c(par()$pin[1],6),
omd=c(0, 1, hh, 1),
mar=c(par('mar')[1:3], 0)+c(-.5,0.5,-.5,0),
cex.axis=1.5,
cex.lab=1.5,
cex.main=1.7)
par(omi=c(legend.height+grconvertY(3, from="lines",to='inches'),0,0,0))
l1=par('usr')[1]
l2=par('usr')[3] - (par()$mai[1]/par()$pin[2])
set.seed(38)
podium(object,
col=cols,
lines.show = T, lines.alpha = .4,
dots.cex=.9,
ylab="Metric value",
layout.heights=c(1,.35),
legendfn = function(algs, cols) {
legend(l1,l2,
paste0(1:length(algs),": ",algs),
xpd=NA,
lwd = 1, col = cols,
bg = NA,
ncol=ncol.legend,
bty="n",
cex=cex.legend, seg.len=1.1,
title="Rank: Alg.",
title.adj = 0
)
}
)
par(op)
\newpage
Ranking heatmap
Ranking heatmaps for visualizing raw assessment data. Each cell $\left( i, A_j \right)$ shows the absolute frequency of cases in which algorithm $A_j$ achieved rank $i$.
\bigskip
rankingHeatmap(object)
\newpage
Visualization of ranking stability
Significance maps for visualizing ranking stability based on statistical significance
Significance maps depict incidence matrices of
pairwise significant test results for the one-sided Wilcoxon signed rank test at a 5\% significance level with adjustment for multiple testing according to Holm. Yellow shading indicates that metric values from the algorithm on the x-axis were significantly superior to those from the algorithm on the y-axis, blue color indicates no significant difference.
\bigskip
significanceMap(object,alpha=0.05,p.adjust.method="holm")
\newpage
Ranking robustness to ranking methods
Line plots for visualizing ranking robustness across different ranking methods. Each algorithm is represented by one colored line. For each ranking method encoded on the x-axis, the height of the line represents the corresponding rank. Horizontal lines indicate identical ranks for all methods.
\bigskip
if (n.tasks<=6 &n.algorithms<=10 ){
methodsplot(challenge_multiple,
ordering = ordering_consensus,
na.treat=object$call[[1]][[1]]$na.treat) +
scale_color_manual(values=cols)
} else {
for (subt in names(challenge_multiple)){
dd=as.challenge(challenge_multiple[[subt]],
value=attr(challenge_multiple,"value"),
algorithm=attr(challenge_multiple,"algorithm") ,
case=attr(challenge_multiple,"case"),
annotator = attr(challenge_multiple,"annotator"),
by=attr(challenge_multiple,"by"),
smallBetter = attr(challenge_multiple,"smallBetter"),
na.treat=object$call[[1]][[1]]$na.treat
)
print(methodsplot(dd,
ordering = ordering_consensus) +
ggtitle(subt) +
scale_color_manual(values=cols) +
theme(legend.position = ifelse(n.algorithms>20,
yes = "bottom",
no = "right"))
)
}
}
\newpage
References
Wiesenfarth, M., Reinke, A., Landman, B.A., Eisenmann, M., Aguilera Saiz, L., Cardoso, M.J., Maier-Hein, L. and Kopp-Schneider, A. Methods and open-source toolkit for analyzing and visualizing challenge results. Sci Rep 11, 2369 (2021). https://doi.org/10.1038/s41598-021-82017-6
M. J. A. Eugster, T. Hothorn, and F. Leisch, “Exploratory
and inferential analysis of benchmark experiments,”
Institut fuer Statistik, Ludwig-Maximilians-Universitaet Muenchen, Germany, Technical Report 30,
2008. [Online]. Available: http://epub.ub.uni-muenchen.de/4134/.
wiesenfa/challengeR documentation built on Aug. 25, 2023, 6:43 a.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
options(width=80) #out.format <- knitr::opts_knit$get("out.format") out.format <- knitr::opts_knit$get("rmarkdown.pandoc.to") img_template <- switch( out.format, docx = list("img-params"=list(dpi=150, fig.width=6, fig.height=6, out.width="504px", out.height="504px")), { # default list("img-params"=list( fig.width=7, fig.height = 3, dpi=300)) } ) knitr::opts_template$set( img_template ) knitr::opts_chunk$set(echo = F) # ,#fig.width=7,fig.height = 3,dpi=300, if (out.format != "docx") knitr::opts_chunk$set(fig.align = "center") if (!is.null(params$fig.format)) knitr::opts_chunk$set(dev = params$fig.format) # can be vector, e.g. fig.format=c('jpeg','png', 'pdf') if (!is.null(params$dpi)) knitr::opts_chunk$set(dpi = params$dpi) theme_set(theme_light()) isMultiTask = params$isMultiTask bootstrappingEnabled = params$bootstrappingEnabled
object = params$object if (isMultiTask) { if (is.numeric(params$consensus) & !is.null(names(params$consensus)) ){ ordering_consensus <- names(params$consensus)[order(params$consensus)] } else if (is.character(ordering)){ ordering_consensus=names(params$consensus) } else stop("Argument ordering has to be a named vector of ranks or a vector of algorithm names in the ranking order.") } else { ordering_consensus=names(sort(t(object$matlist[[1]][,"rank",drop=F])["rank",])) } color.fun=params$colors
challenge_multiple=object$data ranking.fun=object$FUN cols_numbered=cols=color.fun(length(ordering_consensus)) names(cols)=ordering_consensus names(cols_numbered)= paste(1:length(cols),names(cols)) if (bootstrappingEnabled) { boot_object = params$object challenge_multiple=boot_object$data ranking.fun=boot_object$FUN object=challenge_multiple%>%ranking.fun object$FUN.list = boot_object$FUN.list object$fulldata=boot_object$fulldata # only not NULL if subset of algorithms used } n.tasks <- length(object$matlist) n.algorithms <- nrow((object$matlist[[1]]))
This document presents a systematic report on the benchmark study "r params$name". Input data comprises raw metric values for all algorithms and cases. Generated plots are:
Details can be found in Wiesenfarth et al. (2021).
if (isMultiTask) { cat("# Rankings\n") } else { cat("# Ranking") }
Algorithms within a task are ranked according to the following ranking scheme:
a=( lapply(object$FUN.list[1:2],function(x) { if (class(x)== "standardGeneric") return(paste0("aggregate using function ", x@generic )) else if (!is.character(x)) return(paste0("aggregate using function ", paste(gsub("UseMethod","", deparse(functionBody(x))), collapse=" ") )) else if (x=="rank") return(x) else return(paste0("aggregate using function ",x)) })) cat(" *",paste0(a,collapse=" then "),"*",sep="") if (is.character(object$FUN.list[[1]]) && object$FUN.list[[1]]=="significance") cat("\n\n Column 'prop_significance' is equal to the number of pairwise significant test results for a given algorithm divided by the number of algorithms.")
if (isMultiTask) { cat("Ranking for each task:\n") for (t in 1:n.tasks){ cat("\n",names(object$matlist)[t],": ") n.cases=nrow(challenge_multiple[[t]])/length(unique(challenge_multiple[[t]][[attr(challenge_multiple,"algorithm")]])) numberOfAlgorithms <- length(unique(challenge_multiple[[t]][[attr(challenge_multiple, "algorithm")]])) cat("\nThe analysis is based on", numberOfAlgorithms, "algorithms and", n.cases, "cases.", attr(object$data,"n.missing")[[t]], "missing cases have been found in the data set. ") if (nrow(attr(object$data,"missingData")[[t]])>0) { if(attr(object$data,"n.missing")[[t]]==0 ) cat("However, ") else if(attr(object$data,"n.missing")[[t]]>0 ) cat("Additionally, ") cat("performance of not all algorithms has been observed for all cases in task '", names(object$matlist)[t], "'. Therefore, missings have been inserted in the following cases:") print(knitr::kable(as.data.frame(attr(object$data,"missingData")[[t]]))) } if (nrow(attr(object$data,"missingData")[[t]])>0 | attr(object$data,"n.missing")[[t]]>0) { if (is.numeric(attr(object$data,"na.treat"))) cat("All missings have been replaced by values of", attr(object$data,"na.treat"),".\n") else if (is.character(attr(object$data,"na.treat")) && attr(object$data,"na.treat")=="na.rm") cat("All missings have been removed.") else if (is.function(attr(object$data,"na.treat"))) { cat("Missings have been replaced using function ") print(attr(object$data,"na.treat")) } else if (is.character(object$FUN.list[[1]]) && object$FUN.list[[1]]=="rank") cat("Missings lead to the algorithm ranked last for the missing case.") } x=object$matlist[[t]] print(knitr::kable(x[order(x$rank),])) } } else { n.cases=nrow(challenge_multiple[[1]])/length(unique(challenge_multiple[[1]][[attr(challenge_multiple,"algorithm")]])) # Is subset of algorithms used? if (!is.null(object$fulldata[[1]])) { cat("The top ", length(unique(challenge_multiple[[1]][[attr(challenge_multiple, "algorithm")]])), " out of ", length(unique(object$fulldata[[1]][[attr(challenge_multiple, "algorithm")]])), " algorithms are considered.\n") cat("\nThe analysis is based on", n.cases, "cases. ") } else { cat("\nThe analysis is based on", length(unique(challenge_multiple[[1]][[attr(challenge_multiple, "algorithm")]])), "algorithms and", n.cases, "cases. ") } cat(attr(object$data,"n.missing")[[1]], "missing cases have been found in the data set. ") if (nrow(attr(object$data,"missingData")[[1]])>0) { if(attr(object$data,"n.missing")[[1]]==0 ) cat("However, ") else if(attr(object$data,"n.missing")[[1]]>0 ) cat("Additionally, ") cat("performance of not all algorithms has been observed for all cases. Therefore, missings have been inserted in the following cases:") print(knitr::kable(as.data.frame(attr(object$data,"missingData")[[1]]))) } if (nrow(attr(object$data,"missingData")[[1]])>0 | attr(object$data,"n.missing")[[1]]>0) { if (is.numeric(attr(object$data,"na.treat"))) cat("All missings have been replaced by values of", attr(object$data,"na.treat"),".\n") else if (is.character(attr(object$data,"na.treat")) && attr(object$data,"na.treat")=="na.rm") cat("All missings have been removed.") else if (is.function(attr(object$data,"na.treat"))) { cat("Missings have been replaced using function ") print(attr(object$data,"na.treat")) } else if (is.character(object$FUN.list[[1]]) && object$FUN.list[[1]]=="rank") cat("Missings lead to the algorithm ranked last for the missing case.") } cat("\n\nRanking:") x=object$matlist[[1]] print(knitr::kable(x[order(x$rank),])) }
\bigskip
\newpage
Visualization of raw assessment data
if (isMultiTask) { cat("The algorithms are ordered according to the computed ranks for each task.") }
Dot- and boxplot
Dot- and boxplots for visualizing raw assessment data separately for each algorithm. Boxplots representing descriptive statistics over all cases (median, quartiles and outliers) are combined with horizontally jittered dots representing individual cases.
\bigskip
boxplot(object, size=.8) %++% scale_color_manual(values=cols)
\newpage
Podium plot
Podium plots (see also Eugster et al., 2008) for visualizing raw assessment data. Upper part (spaghetti plot): Participating algorithms are color-coded, and each colored dot in the plot represents a metric value achieved with the respective algorithm. The actual metric value is encoded by the y-axis. Each podium (here: $p$=r length(ordering_consensus)) represents one possible rank, ordered from best (1) to last (here: r length(ordering_consensus)). The assignment of metric values (i.e. colored dots) to one of the podiums is based on the rank that the respective algorithm achieved on the corresponding case. Note that the plot part above each podium place is further subdivided into $p$ "columns", where each column represents one participating algorithm (here: $p=$ r length(ordering_consensus)). Dots corresponding to identical cases are connected by a line, leading to the shown spaghetti structure. Lower part: Bar charts represent the relative frequency for each algorithm to achieve the rank encoded by the podium place.
cex.legend = 1.2 plot.new() # bottom legend # get number of columns legend.width=1e5 #arbitrarily large ncol.legend <- n.algorithms + 1 while(legend.width>12){ ncol.legend <- ncol.legend-1 algs=ordering_consensus l=legend("bottom", paste0(1:length(algs),": ",algs), xpd=NA, lwd = 1, col = cols, bg = NA, ncol=ncol.legend, bty="n", cex=cex.legend, seg.len=1.1, title="Rank: Alg.", title.adj = 0, plot=F) legend.width=grconvertX(l$rect$w,"user","inches") } w=0 h<-hh<- grconvertY(l$rect$h, to='ndc') - grconvertY(0, to='ndc') nrow.legend=length(unique(l$text$y)) legend.height = nrow.legend* max( cex.legend * par()$cin[2],max(strheight(ordering_consensus, units = "inches", cex = cex.legend))) addy= 6+ legend.height
#c(bottom, left, top, right op <- par(no.readonly = TRUE) hh<- grconvertY(legend.height, from="inches",to='ndc') par(pin=c(par()$pin[1],6), omd=c(0, 1, hh, 1), mar=c(par('mar')[1:3], 0)+c(-.5,0.5,-.5,0), cex.axis=1.5, cex.lab=1.5, cex.main=1.7) par(omi=c(legend.height+grconvertY(3, from="lines",to='inches'),0,0,0)) l1=par('usr')[1] l2=par('usr')[3] - (par()$mai[1]/par()$pin[2]) set.seed(38) podium(object, col=cols, lines.show = T, lines.alpha = .4, dots.cex=.9, ylab="Metric value", layout.heights=c(1,.35), legendfn = function(algs, cols) { legend(l1,l2, paste0(1:length(algs),": ",algs), xpd=NA, lwd = 1, col = cols, bg = NA, ncol=ncol.legend, bty="n", cex=cex.legend, seg.len=1.1, title="Rank: Alg.", title.adj = 0 ) } ) par(op)
\newpage
Ranking heatmap
Ranking heatmaps for visualizing raw assessment data. Each cell $\left( i, A_j \right)$ shows the absolute frequency of cases in which algorithm $A_j$ achieved rank $i$.
\bigskip
rankingHeatmap(object)
\newpage
Visualization of ranking stability
Significance maps for visualizing ranking stability based on statistical significance
Significance maps depict incidence matrices of pairwise significant test results for the one-sided Wilcoxon signed rank test at a 5\% significance level with adjustment for multiple testing according to Holm. Yellow shading indicates that metric values from the algorithm on the x-axis were significantly superior to those from the algorithm on the y-axis, blue color indicates no significant difference.
\bigskip
significanceMap(object,alpha=0.05,p.adjust.method="holm")
\newpage
Ranking robustness to ranking methods
Line plots for visualizing ranking robustness across different ranking methods. Each algorithm is represented by one colored line. For each ranking method encoded on the x-axis, the height of the line represents the corresponding rank. Horizontal lines indicate identical ranks for all methods.
\bigskip
if (n.tasks<=6 &n.algorithms<=10 ){ methodsplot(challenge_multiple, ordering = ordering_consensus, na.treat=object$call[[1]][[1]]$na.treat) + scale_color_manual(values=cols) } else { for (subt in names(challenge_multiple)){ dd=as.challenge(challenge_multiple[[subt]], value=attr(challenge_multiple,"value"), algorithm=attr(challenge_multiple,"algorithm") , case=attr(challenge_multiple,"case"), annotator = attr(challenge_multiple,"annotator"), by=attr(challenge_multiple,"by"), smallBetter = attr(challenge_multiple,"smallBetter"), na.treat=object$call[[1]][[1]]$na.treat ) print(methodsplot(dd, ordering = ordering_consensus) + ggtitle(subt) + scale_color_manual(values=cols) + theme(legend.position = ifelse(n.algorithms>20, yes = "bottom", no = "right")) ) } }
\newpage
References
Wiesenfarth, M., Reinke, A., Landman, B.A., Eisenmann, M., Aguilera Saiz, L., Cardoso, M.J., Maier-Hein, L. and Kopp-Schneider, A. Methods and open-source toolkit for analyzing and visualizing challenge results. Sci Rep 11, 2369 (2021). https://doi.org/10.1038/s41598-021-82017-6
M. J. A. Eugster, T. Hothorn, and F. Leisch, “Exploratory and inferential analysis of benchmark experiments,” Institut fuer Statistik, Ludwig-Maximilians-Universitaet Muenchen, Germany, Technical Report 30, 2008. [Online]. Available: http://epub.ub.uni-muenchen.de/4134/.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.