Skip to content

docs: v3.1.0 documentation sweep (HELD — do not merge until v3.0.0 accepted)#109

Draft
ehrlinger wants to merge 16 commits into
mainfrom
docs/v3.1.0-doc-sweep
Draft

docs: v3.1.0 documentation sweep (HELD — do not merge until v3.0.0 accepted)#109
ehrlinger wants to merge 16 commits into
mainfrom
docs/v3.1.0-doc-sweep

Conversation

@ehrlinger
Copy link
Copy Markdown
Owner

HELD DRAFT — do NOT merge until CRAN accepts v3.0.0. Version stays 3.0.0 on this branch; the cut to 3.1.0 (DESCRIPTION + NEWS) happens at the post-acceptance RC. Per dev/plans/2026-05-29-v3.1.0-doc-sweep-design.md + ...-plan.md.

What this is

A documentation deepening pass against the upstream canonical sources (varprotools.org, randomForestSRC.org), in John's voice, building on the v3.0.0 PR #92 voice audit. No user-facing behaviour change.

Changes

  • Roxygen — deep content: the varPro family (gg_varpro/beta/ivarpro/udependent/isopro/partial_varpro) and rfsrc importance/partial/survival (gg_vimp, gg_partial(_rfsrc), gg_rfsrc, gg_survival, gg_brier). The headline clarification: gg_vimp (permutation / Breiman-Cutler VIMP) vs gg_varpro (varPro release-rule, no-synthetic-features importance), explicit and cross-@seealso'd in both.
  • Roxygen — drift check: remaining topics; fixed a stale gg_roc @return (documented a yvar column the function never returns).
  • Vignettes (all 4): content deepened with the upstream framing; varprotools.org / randomForestSRC.org links + Lee:2021 reference added; em-dashes trimmed to voice standard.
  • R/ code comments: 2 surgical fixes (misleading trapezoid comment in calc_roc; stale varPro-one-hot comment in gg_partial).
  • NEWS: v3.1.0 (development) heading opened (version line unchanged).

Verification

  • R CMD check --as-cran with manual: 0 errors / 0 warnings / 0 notes.
  • All 4 vignettes render clean; tests pass; devtools::document() clean.
  • Built subagent-driven with two-stage review (voice/anti-slop, then accuracy-vs-code) per unit.

On v3.0.0 acceptance

Cut version → 3.1.0, finalize NEWS + cran-comments.md, full release gate, merge to main, submit, then forward-merge maindev.

🤖 Generated with Claude Code

ehrlinger and others added 15 commits June 1, 2026 08:51
…rpro)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Remove stale yvar @return item from gg_roc — the function returns
sens/spec/pct (from calc_roc), not a yvar column per observation.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Deepens all prose sections of varpro.qmd with release-rules/guided-splitting
framing; adds Lee:2021 bib key (AOS 49:4) cited in PBC section; adds
varProtools URL in Further Reading.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Fix a misleading AUC trapezoidal-rule comment in calc_roc.R (the old
text introduced Δ(FPR) but the code uses Δspec; reworded to state the
equivalence plainly). Remove a stale varPro-specific note from the
categorical branch of gg_partial.R (plot.variable output has no
connection to varPro one-hot encoding).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
@codecov
Copy link
Copy Markdown

codecov Bot commented Jun 1, 2026

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 87.04%. Comparing base (026f9e7) to head (bae77e1).

Additional details and impacted files

Impacted file tree graph

@@           Coverage Diff           @@
##             main     #109   +/-   ##
=======================================
  Coverage   87.04%   87.04%           
=======================================
  Files          44       44           
  Lines        3936     3938    +2     
=======================================
+ Hits         3426     3428    +2     
  Misses        510      510           
Files with missing lines Coverage Δ
R/calc_roc.R 83.33% <ø> (ø)
R/gg_beta_varpro.R 92.45% <ø> (ø)
R/gg_brier.R 89.33% <ø> (ø)
R/gg_ivarpro.R 76.22% <ø> (ø)
R/gg_partial.R 100.00% <ø> (ø)
R/gg_partial_rfsrc.R 89.68% <ø> (ø)
R/gg_partial_varpro.R 95.23% <ø> (ø)
R/gg_rfsrc.R 76.25% <ø> (ø)
R/gg_roc.R 87.71% <ø> (ø)
R/gg_survival.R 90.00% <ø> (ø)
... and 7 more
🚀 New features to boost your workflow:
  • ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Copy link
Copy Markdown

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Documentation-focused sweep to deepen and tighten ggRandomForests’ v3.x docs (roxygen, vignettes, and a couple of code comments), clarifying the conceptual split between gg_vimp() (permutation/Breiman–Cutler VIMP) and the varPro “release-rule” family, while keeping the branch held at version 3.0.0 pending CRAN acceptance.

Changes:

  • Deepened vignette prose (varPro + regression + survival + intro) and added cross-engine framing/links/references (incl. Lee et al. 2021 BibTeX entry).
  • Expanded roxygen documentation across rfsrc/varPro-related functions and plot methods; regenerated corresponding man/*.Rd.
  • Opened a v3.1.0 (development) section in NEWS.md (without bumping the package version line).

Reviewed changes

Copilot reviewed 32 out of 42 changed files in this pull request and generated 3 comments.

Show a summary per file
File Description
vignettes/varpro.qmd Expanded varPro vignette narrative and methodological framing.
vignettes/ggRandomForests.qmd Intro vignette updated to mention varPro as a parallel engine and contrast importance methods.
vignettes/ggRandomForests.bib Added Lee et al. (2021) reference entry.
vignettes/ggRandomForests-survival.qmd Deepened survival vignette explanations (survival/CHF/mortality, VIMP, Brier/CRPS).
vignettes/ggRandomForests-regression.qmd Added explicit gg_vimp() vs gg_varpro() contrast in regression vignette.
R/plot.gg_vimp.R Roxygen expanded to explain permutation VIMP plotting and positive coloring.
R/plot.gg_survival.R Roxygen expanded to explain plot behavior, CI overlays, and y-axis types.
R/plot.gg_rfsrc.R Roxygen expanded to explain OOB ensemble predictions and family-specific geometries.
R/plot.gg_partial.R Roxygen expanded for partial dependence plotting (incl. model overlay behavior).
R/plot.gg_ivarpro.R Roxygen clarified SHAP-like visual resemblance vs release-rule contributions.
R/plot.gg_brier.R Roxygen expanded to explain Brier/CRPS interpretation and envelope ribbon.
R/gg_vimp.R Added @details contrasting permutation VIMP vs varPro release rules; updated @seealso.
R/gg_survival.R Expanded @details describing KM baseline purpose and rfsrc/default dispatch behavior.
R/gg_roc.R Corrected @return column documentation (now documents pct).
R/gg_rfsrc.R Expanded roxygen describing OOB ensemble predictions and family-specific returned structure.
R/gg_partial.R Expanded roxygen; removed stale inline comment about varPro factor handling.
R/gg_partial_varpro.R Added @seealso cross-links to gg_varpro and gg_vimp.
R/gg_partial_rfsrc.R Expanded roxygen describing marginalization, survival partial.type, and partial.time.
R/gg_ivarpro.R Expanded “What this is doing” section; added cross-link to gg_vimp.
R/gg_brier.R Expanded description/details explaining Brier/CRPS + IPCW and returned objects.
R/gg_beta_varpro.R Expanded “What this is doing” section; added cross-link to gg_vimp.
R/calc_roc.R Clarified AUC trapezoid-rule comment wording (no functional change).
NEWS.md Opened v3.1.0 (development) heading while keeping version line at 3.0.0.
man/plot.gg_vimp.Rd Regenerated Rd reflecting plot.gg_vimp roxygen updates.
man/plot.gg_survival.Rd Regenerated Rd reflecting plot.gg_survival roxygen updates.
man/plot.gg_rfsrc.Rd Regenerated Rd reflecting plot.gg_rfsrc roxygen updates.
man/plot.gg_partial.Rd Regenerated Rd reflecting plot.gg_partial roxygen updates.
man/plot.gg_partial_rfsrc.Rd Regenerated Rd reflecting plot.gg_partial_rfsrc roxygen updates.
man/plot.gg_ivarpro.Rd Regenerated Rd reflecting plot.gg_ivarpro roxygen updates.
man/plot.gg_brier.Rd Regenerated Rd reflecting plot.gg_brier roxygen updates.
man/gg_vimp.Rd Regenerated Rd reflecting gg_vimp roxygen updates and @seealso links.
man/gg_survival.Rd Regenerated Rd reflecting gg_survival roxygen updates.
man/gg_roc.rfsrc.Rd Regenerated Rd reflecting gg_roc return-column doc fix (pct).
man/gg_rfsrc.rfsrc.Rd Regenerated Rd reflecting gg_rfsrc roxygen updates.
man/gg_partial.Rd Regenerated Rd reflecting gg_partial roxygen updates.
man/gg_partial_varpro.Rd Regenerated Rd reflecting gg_partial_varpro @seealso updates.
man/gg_partial_rfsrc.Rd Regenerated Rd reflecting gg_partial_rfsrc roxygen updates.
man/gg_ivarpro.Rd Regenerated Rd reflecting gg_ivarpro roxygen updates and @seealso links.
man/gg_brier.Rd Regenerated Rd reflecting gg_brier roxygen updates.
man/gg_beta_varpro.Rd Regenerated Rd reflecting gg_beta_varpro roxygen updates and @seealso links.
dev/plans/2026-05-29-v3.1.0-doc-sweep-plan.md Added implementation plan document for the held doc sweep.
dev/plans/2026-05-29-v3.1.0-doc-sweep-design.md Added design/spec document for the held doc sweep.
Files not reviewed (10)
  • man/gg_beta_varpro.Rd: Language not supported
  • man/gg_brier.Rd: Language not supported
  • man/gg_ivarpro.Rd: Language not supported
  • man/gg_partial.Rd: Language not supported
  • man/gg_partial_rfsrc.Rd: Language not supported
  • man/gg_partial_varpro.Rd: Language not supported
  • man/gg_rfsrc.rfsrc.Rd: Language not supported
  • man/gg_roc.rfsrc.Rd: Language not supported
  • man/gg_survival.Rd: Language not supported
  • man/gg_vimp.Rd: Language not supported

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread vignettes/ggRandomForests-survival.qmd Outdated
Comment thread vignettes/ggRandomForests-survival.qmd Outdated
Comment thread R/gg_vimp.R
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants