## ----setup,include=FALSE------------------------------------------------------ knitr::opts_chunk$set(collapse=TRUE,comment='#>',message=FALSE,warning=FALSE, out.width='100%',fig.align='center') # Prefer this checkout's snapshot when rendering the maintained source. bundle <- '../inst/extdata/fermat-density-curvature/benchmark.rds' if(!file.exists(bundle)) bundle <- system.file('extdata','fermat-density-curvature', 'benchmark.rds',package='dgraphs',mustWork=TRUE) b <- readRDS(bundle); m <- b$metrics; s <- b$summary; power_data <- b$power_tuning surface_names <- c(paraboloid_a1='Paraboloid, $a=1$',paraboloid_a2='Paraboloid, $a=2$', paraboloid_a4='Paraboloid, $a=4$',saddle_a1='Saddle, $a=1$',saddle_a2='Saddle, $a=2$', saddle_a4='Saddle, $a=4$',swiss_roll='Swiss roll') helper <- '../inst/doc-tools/compact-figures.R' if(!file.exists(helper)) helper <- system.file('doc-tools','compact-figures.R',package='dgraphs',mustWork=TRUE) source(helper,local=TRUE) figure <- function(name) knitr::include_graphics(dgraphs_document_figure( paste0('figures/fermat-density-curvature/',name,'.png')), rel_path=FALSE) ## ----small-sample,eval=FALSE-------------------------------------------------- # library(dgraphs) # A <- diag(c(2,-2)) # geometry <- synthetic.quadform(2L,3L,forms=list(A)) # sampling <- synthetic.sampling.quadform.lab('disk',extent=1,mode='area') # sample <- sample.synthetic.geometry(geometry,sampling,n=300L,seed=62117L) # X <- sample$predictors # endpoints <- 1:12 # D150 <- fermat.distances(points=X[1:150,],p=1.25,backend='implicit', # sources=endpoints,targets=endpoints,rooted=FALSE) # D300 <- fermat.distances(points=X,p=1.25,backend='implicit', # sources=endpoints,targets=endpoints,rooted=FALSE) # stopifnot(all(D300 <= D150 + 1e-10)) ## ----small-graph,eval=FALSE--------------------------------------------------- # graph <- create.sknn.graph(X,k=10,neighbor.method='exact', # connect.components=FALSE) # edges <- graph.edges(graph) # ig <- igraph::graph_from_data_frame(edges[,1:2],directed=FALSE, # vertices=data.frame(name=seq_len(nrow(X)))) # Dknn <- igraph::distances(ig,v=endpoints,to=endpoints,weights=edges$length) # igraph::components(ig)$no ## ----surfaces,echo=FALSE,fig.alt='Paraboloid and saddle patches at three coefficients, with a common vertical range within each family.'---- figure('surfaces') ## ----interactive-surfaces,echo=FALSE------------------------------------------ have.ivue <- !identical(Sys.getenv('DGRAPHS_STATIC_VIGNETTES','true'),'true') && requireNamespace('ivue',quietly=TRUE) && requireNamespace('rgl',quietly=TRUE) && requireNamespace('htmlwidgets',quietly=TRUE) && requireNamespace('htmltools',quietly=TRUE) && all(c('plot3D.plain','layer3D.callback','layer3D.axes','camera.zup') %in% getNamespaceExports('ivue')) && 'limits' %in% names(formals(ivue::plot3D.plain)) if(have.ivue) { options(rgl.useNULL=TRUE) helper <- '../inst/doc-tools/fermat-surface-views.R' if(!file.exists(helper)) helper <- system.file('doc-tools','fermat-surface-views.R',package='dgraphs',mustWork=TRUE) source(helper,local=TRUE) surface_views <- readRDS(file.path(dirname(bundle),'surface-views.rds')) fermat_surface_gallery(surface_views) } else { cat('The installed guide uses the static surface views in Figure 1. Interactive views are available when rebuilding with DGRAPHS_STATIC_VIGNETTES=false and the optional visualization packages.') } ## ----coverage,echo=FALSE------------------------------------------------------ q <- subset(m,family=='euclidean_knn') coverage <- do.call(rbind,lapply(split(q,q$policy),function(x) data.frame(Rule=x$policy[1],Minimum.coverage=100*min(x$test_pairs/x$requested_test), Disconnected=sum(x$components>1)))) knitr::kable(coverage,row.names=FALSE,digits=1, col.names=c('$k$ rule','Minimum evaluation coverage (%)','Disconnected conditions')) ## ----paraboloid,echo=FALSE,fig.alt='Fermat distance errors across sample sizes on three paraboloids; intermediate powers outperform ambient chords.'---- figure('paraboloid_fermat') ## ----saddle,echo=FALSE,fig.alt='Fermat distance errors on three saddles, showing the benefit of a larger intermediate power on the strongest saddle.'---- figure('saddle_fermat') ## ----roll,echo=FALSE,fig.alt='Swiss-roll errors across sample sizes: larger Fermat powers suppress shortcuts more effectively than powers close to one.'---- figure('swiss_roll_fermat') ## ----winners,echo=FALSE------------------------------------------------------- z <- subset(s,n==2400 & family=='complete' & p>1) w <- do.call(rbind,lapply(split(z,z$id),function(x)x[which.min(x$mean),])) knitr::kable(data.frame(Surface=unname(surface_names[w$id]),Power=w$p, Fermat=100*w$mean,Ambient=100*w$ambient,Wins=w$wins),row.names=FALSE,digits=2, col.names=c('Surface','Best tested $p$','Fermat error (%)','Ambient error (%)','Wins out of 5')) ## ----ratios,echo=FALSE,fig.alt='Geodesic-to-chord ratios on seven surfaces, with a logarithmic ratio axis and a long Swiss-roll tail.'---- figure('chord_distortion') ## ----knn,echo=FALSE,fig.alt='Euclidean symmetric kNN errors on paraboloids, saddles and the Swiss roll, with ambient baselines and conditional intervals.'---- figure(c('paraboloid_knn','saddle_knn','swiss_roll_knn')) ## ----clairaut,echo=FALSE,fig.alt='Paraboloid errors using Clairaut references, showing reduced apparent error on the strongest patch.'---- figure('paraboloid_clairaut') ## ----paired,echo=FALSE,fig.alt='Paired Fermat-minus-ambient errors at 2,400 observations, showing replicate differences and conditional intervals.'---- figure('paired_difference') ## ----power-full,echo=FALSE,fig.alt='Full cross-validation curves for all six quadforms, including ambient power one and the selected interior minima.'---- figure('power_tuning_full') ## ----power-near,echo=FALSE,fig.alt='Enlarged neighborhoods of each tuning minimum, displaying relative excess error and a one-percent threshold.'---- figure('power_tuning_near') ## ----power-choices,echo=FALSE------------------------------------------------- x<-subset(power_data$selection,reference=='best_of_six') z<-subset(power_data$transfer_summary,reference=='best_of_six' & method=='selected_best_of_six') at_n<-function(n)z$mean[match(paste(x$id,n),paste(z$id,z$n))] knitr::kable(data.frame(Surface=surface_names[x$id],`Selected $p$`=sprintf('%.3f',x$p), `Within 1% of minimum`=sprintf('%.3f–%.3f',x$near_min,x$near_max), `Test error, $n=300$ (%)`=round(100*at_n(300),2), `Test error, $n=2400$ (%)`=round(100*at_n(2400),2),check.names=FALSE),row.names=FALSE) ## ----power-transfer,echo=FALSE,fig.alt='Frozen selected-power error across five sample sizes, with ambient, fixed powers, and ordinary Euclidean neighborhood-graph comparisons.'---- figure('power_transfer') ## ----power-difference,echo=FALSE,fig.alt='Paired selected-power minus fixed power 1.25 errors, showing a reversal on the intermediate saddle as sample size increases.'---- figure('power_transfer_difference') ## ----power-clairaut-tuning,echo=FALSE,fig.alt='Paraboloid cross-validation curves against best-of-six and Clairaut references, with separate selected powers.'---- figure('power_clairaut_tuning') ## ----power-clairaut-table,echo=FALSE------------------------------------------ x<-subset(power_data$selection,reference=='clairaut') a<-subset(power_data$selection,reference=='best_of_six') z<-subset(power_data$transfer_summary,reference=='clairaut' & n==2400) value<-function(method) {q<-z[z$method==method,];round(100*q$mean[match(x$id,q$id)],2)} knitr::kable(data.frame(Surface=surface_names[x$id], `Best-of-six $p$`=sprintf('%.3f',a$p[match(x$id,a$id)]), `Clairaut $p$`=sprintf('%.3f',x$p), `Best-of-six choice error (%)`=value('selected_best_of_six'), `Clairaut choice error (%)`=value('selected_clairaut'),check.names=FALSE),row.names=FALSE) ## ----power-clairaut-transfer,echo=FALSE,fig.alt='Sample-size transfer curves scored against Clairaut, comparing powers selected with each reference and the unchanged baselines.'---- figure('power_clairaut_transfer') ## ----read-snapshot,eval=FALSE------------------------------------------------- # path <- system.file('extdata','fermat-density-curvature','benchmark.rds', # package='dgraphs',mustWork=TRUE) # benchmark <- readRDS(path) # nrow(benchmark$metrics) # 2,100 condition-level records # nrow(benchmark$references) # 10,500 main reference pairs # benchmark$power_tuning$selection # nrow(benchmark$power_tuning$transfer_metrics) # 1,275 follow-up records # benchmark$provenance ## ----copy-workflow,eval=FALSE------------------------------------------------- # src <- system.file('examples','fermat-density-curvature',package='dgraphs', # mustWork=TRUE) # work <- file.path(tempdir(),'fermat-recovery-reproduction') # dir.create(work,showWarnings=FALSE) # file.copy(list.files(src,full.names=TRUE),work,overwrite=FALSE)