diff --git a/inst/appdir/consensusRanking.Rmd b/inst/appdir/consensusRanking.Rmd index ce183f7..c530b49 100644 --- a/inst/appdir/consensusRanking.Rmd +++ b/inst/appdir/consensusRanking.Rmd @@ -1,6 +1,6 @@ -Consensus ranking according to chosen method `r attr(params$consensus,"method")`: +Consensus ranking across tasks according to chosen method "`r attr(params$consensus,"method")`": ```{r} knitr::kable(data.frame(value=round(params$consensus,3), rank=rank(params$consensus, ties.method="min"))) ``` diff --git a/inst/appdir/reportMultiple.Rmd b/inst/appdir/reportMultiple.Rmd index c89d7f1..b36ca3d 100644 --- a/inst/appdir/reportMultiple.Rmd +++ b/inst/appdir/reportMultiple.Rmd @@ -1,393 +1,393 @@ --- params: object: NA colors: NA name: NULL consensus: NA isMultiTask: NA bootstrappingEnabled: NA fig.format: NULL title: "Benchmarking report for `r params$name` " author: "created by challengeR v`r packageVersion('challengeR')`" date: "`r Sys.setlocale('LC_TIME', 'English'); format(Sys.time(), '%d %B, %Y')`" editor_options: chunk_output_type: console --- ```{r setup, include=FALSE} options(width=80) #out.format <- knitr::opts_knit$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$fig.format) # can be vector, e.g. fig.format=c('jpeg','png', 'pdf') theme_set(theme_light()) isMultiTask = params$isMultiTask bootstrappingEnabled = params$bootstrappingEnabled ``` ```{r } object = params$object if (isMultiTask) { ordering_consensus=names(params$consensus) } else { ordering_consensus=names(sort(t(object$matlist[[1]][,"rank",drop=F])["rank",])) } color.fun=params$colors ``` ```{r } challenge_multiple=object$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 cols_numbered=cols=color.fun(length(ordering_consensus)) names(cols)=ordering_consensus names(cols_numbered)= paste(1:length(cols),names(cols)) } ``` This document presents a systematic report on the benchmark study "`r params$name`". Input data comprises raw metric values for all algorithms and cases. Generated plots are: ```{r, child=if (!isMultiTask && !bootstrappingEnabled) system.file("appdir", "overviewSingleTaskNoBootstrapping.Rmd", package="challengeR")} ``` ```{r, child=if (!isMultiTask && bootstrappingEnabled) system.file("appdir", "overviewSingleTaskBootstrapping.Rmd", package="challengeR")} ``` ```{r, child=if (isMultiTask && !bootstrappingEnabled) system.file("appdir", "overviewMultiTaskNoBootstrapping.Rmd", package="challengeR")} ``` ```{r, child=if (isMultiTask && bootstrappingEnabled) system.file("appdir", "overviewMultiTaskBootstrapping.Rmd", package="challengeR")} ``` Details can be found in Wiesenfarth et al. (2019). ```{r,results='asis'} if (isMultiTask) { cat("# Rankings\n") } else { cat("# Ranking") } ``` -Ranking of algorithms within tasks according to the following chosen ranking scheme: + +Algorithms within a task are ranked according to the following ranking scheme: ```{r,results='asis'} a=( lapply(object$FUN.list[1:2],function(x) { 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.sign' is equal to the number of pairwise significant test results for a given algorithm divided by the number of algorithms.") ``` ```{r,results='asis'} if (isMultiTask) { cat("Ranking for each task:\n") for (t in 1:length(object$matlist)){ cat("\n",names(object$matlist)[t],": ") n.cases=nrow(challenge_multiple[[t]])/length(unique(challenge_multiple[[t]][[attr(challenge_multiple,"algorithm")]])) numberOfAlgorithms <- length(levels(challenge_multiple[[t]][[attr(challenge_multiple, "algorithm")]])) cat("\nThe analysis is based on", numberOfAlgorithms, "algorithms and", n.cases, "cases.", attr(object$data,"n.missing")[[t]], "observations had been missing. ") if (nrow(attr(object$data,"missingData")[[t]])>0) { cat("Performance of not all algorithms is 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 { algorithmAttribute <- attr(challenge_multiple, "algorithm") totalNumberOfAlgorithms <- length(levels(attr(object$data, "missingData")[[1]][[algorithmAttribute]])) cat("The top ", length(levels(challenge_multiple[[1]][[attr(challenge_multiple, "algorithm")]])), " out of ", totalNumberOfAlgorithms, " algorithms are considered.\n") n.cases=nrow(challenge_multiple[[1]])/length(unique(challenge_multiple[[1]][[attr(challenge_multiple,"algorithm")]])) cat("\nThe analysis is based on", n.cases, "cases.", attr(object$data,"n.missing")[[1]], "observations had been missing. ") if (nrow(attr(object$data,"missingData")[[1]])>0) { cat("Performance of not all algorithms has been observed for all cases. Therefore, missings have been inserted in the following cases:") print(knitr::kable(as.data.frame(attr(object$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 list:") + cat("\n\nRanking:") x=object$matlist[[1]] print(knitr::kable(x[order(x$rank),])) } ``` \bigskip ```{r, child=if (isMultiTask) system.file("appdir", "consensusRanking.Rmd", package="challengeR")} ``` # Visualization of raw assessment data ```{r,results='asis'} if (isMultiTask) { - cat("Algorithms are ordered according to chosen ranking scheme for each task.") + 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 ```{r boxplots} boxplot(object, size=.8) ``` ## 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. ```{r, include=FALSE, fig.keep="none",dev=NULL} plot.new() algs=ordering_consensus l=legend("topright", paste0(1:length(algs),": ",algs), lwd = 1, cex=1.4,seg.len=1.1, title="Rank: Alg.", plot=F) w <- grconvertX(l$rect$w, to='ndc') - grconvertX(0, to='ndc') h<- grconvertY(l$rect$h, to='ndc') - grconvertY(0, to='ndc') addy=max(grconvertY(l$rect$h,"user","inches"),6) ``` ```{r podium,eval=T,fig.width=12, fig.height=addy} #c(bottom, left, top, right op<-par(pin=c(par()$pin[1],6), omd=c(0, 1-w, 0, 1), mar=c(par('mar')[1:3], 0)+c(-.5,0.5,-.5,0), cex.axis=1.5, cex.lab=1.5, cex.main=1.7) oh=grconvertY(l$rect$h,"user","lines")-grconvertY(6,"inches","lines") if (oh>0) par(oma=c(oh,0,0,0)) 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(par('usr')[2], par('usr')[4], xpd=NA, paste0(1:length(algs),": ",algs), lwd = 1, col = cols, bg = NA, cex=1.4, seg.len=1.1, title="Rank: Alg.") } ) par(op) ``` ## 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 ```{r rankingHeatmap,fig.width=9, fig.height=9,out.width='70%'} rankingHeatmap(object) ``` # Visualization of ranking stability ```{r, child=if (bootstrappingEnabled) system.file("appdir", "visualizationBlobPlots.Rmd", package="challengeR")} ``` ```{r, child=if (bootstrappingEnabled) system.file("appdir", "visualizationViolinPlots.Rmd", package="challengeR")} ``` ## *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 of 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 ```{r significancemap,fig.width=6, fig.height=6,out.width='200%'} significanceMap(object,alpha=0.05,p.adjust.method="holm") ``` ## Ranking robustness to ranking methods *Line plots* for visualizing rankings 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 ```{r lineplot,fig.width=8, fig.height=6,out.width='95%'} if (length(object$matlist)<=6 &nrow((object$matlist[[1]]))<=10 ){ methodsplot(challenge_multiple, ordering = ordering_consensus, na.treat=object$call[[1]][[1]]$na.treat) + scale_color_manual(values=cols) }else { x=challenge_multiple for (subt in names(challenge_multiple)){ dd=as.challenge(x[[subt]], value=attr(x,"value"), algorithm=attr(x,"algorithm") , case=attr(x,"case"), annotator = attr(x,"annotator"), by=attr(x,"by"), smallBetter = !attr(x,"largeBetter"), na.treat=object$call[[1]][[1]]$na.treat ) print(methodsplot(dd, ordering = ordering_consensus) + scale_color_manual(values=cols) ) } } ``` ```{r, child=if (isMultiTask) system.file("appdir", "visualizationAcrossTasks.Rmd", package="challengeR")} ``` # References Wiesenfarth, M., Reinke, A., Landman, B.A., Cardoso, M.J., Maier-Hein, L. and Kopp-Schneider, A. (2019). Methods and open-source toolkit for analyzing and visualizing challenge results. *arXiv preprint arXiv:1910.05121* 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/. +2008. [Online]. Available: http://epub.ub.uni-muenchen.de/4134/. diff --git a/inst/appdir/visualizationAcrossTasks.Rmd b/inst/appdir/visualizationAcrossTasks.Rmd index d42cf0a..c5dba90 100644 --- a/inst/appdir/visualizationAcrossTasks.Rmd +++ b/inst/appdir/visualizationAcrossTasks.Rmd @@ -1,131 +1,124 @@ # Visualization of cross-task insights -Algorithms are ordered according to consensus ranking. - - - +The algorithms are ordered according to consensus ranking. ## Characterization of algorithms ### Ranking stability: Variability of achieved rankings across tasks Algorithms are color-coded, and the area of each blob at position $\left( A_i, \text{rank } j \right)$ is proportional to the relative frequency $A_i$ achieved rank $j$ across multiple tasks. The median rank for each algorithm is indicated by a black cross. This way, the distribution of ranks across tasks can be intuitively visualized. \bigskip ```{r blobplot_raw,fig.width=9, fig.height=9} #stability.ranked.list stability(object,ordering=ordering_consensus,max_size=9,size=8,shape=4)+ scale_color_manual(values=cols) ``` - - - ```{r, child=if (isMultiTask && bootstrappingEnabled) system.file("appdir", "characterizationOfAlgorithmsBootstrapping.Rmd", package="challengeR")} ``` - ## Characterization of tasks ```{r, child=if (isMultiTask && bootstrappingEnabled) system.file("appdir", "characterizationOfTasksBootstrapping.Rmd", package="challengeR")} ``` ### Cluster Analysis Dendrogram from hierarchical cluster analysis} and \textit{network-type graphs} for assessing the similarity of tasks based on challenge rankings. A dendrogram is a visualization approach based on hierarchical clustering. It depicts clusters according to a chosen distance measure (here: Spearman's footrule) as well as a chosen agglomeration method (here: complete and average agglomeration). \bigskip ```{r dendrogram_complete, fig.width=6, fig.height=5,out.width='60%'} if (length(object$matlist)>2) { dendrogram(object, dist = "symdiff", method="complete") } else cat("\nCluster analysis only sensible if there are >2 tasks.\n\n") ``` \bigskip ```{r dendrogram_average, fig.width=6, fig.height=5,out.width='60%'} if (length(object$matlist)>2) dendrogram(object, dist = "symdiff", method="average") ``` In network-type graphs (see Eugster et al, 2008), every task is represented by a node and nodes are connected by edges whose length is determined by a chosen distance measure. Here, distances between nodes are chosen to increase exponentially in Spearman's footrule distance with growth rate 0.05 to accentuate large distances. Hence, tasks that are similar with respect to their algorithm ranking appear closer together than those that are dissimilar. Nodes representing tasks with a unique winner are colored-coded by the winning algorithm. In case there are more than one first-ranked algorithms in a task, the corresponding node remains uncolored. \bigskip ```{r ,eval=T,fig.width=12, fig.height=6,include=FALSE, fig.keep="none"} if (length(object$matlist)>2) { netw=network(object, method = "symdiff", edge.col=grDevices::grey.colors, edge.lwd=1, rate=1.05, cols=cols ) plot.new() leg=legend("topright", names(netw$leg.col), lwd = 1, col = netw$leg.col, bg =NA,plot=F,cex=.8) w <- grconvertX(leg$rect$w, to='inches') addy=6+w } else addy=1 ``` ```{r network, fig.width=addy, fig.height=6,out.width='100%',dev=NULL} if (length(object$matlist)>2) { plot(netw, layoutType = "neato", fixedsize=TRUE, # fontsize, # width, # height, shape="ellipse", cex=.8 ) } ``` \ No newline at end of file