V1.2

.Rbuildignore

@@ -10,4 +10,5 @@
 ^\.vscode$
 ^Dockerfile$
 ^_pkgdown\.yml$
-^docs$
+^docs$
+^vignettes/.*_cache$

.github/workflows/R-CMD-check.yaml

@@ -18,9 +18,9 @@ jobs:
       fail-fast: false
       matrix:
         config:
-          - {os: macos-latest,   r: '4.4'}
-          - {os: windows-latest, r: '4.4'}
-          - {os: ubuntu-latest,   r: '4.4'}
+          - {os: macos-latest,   r: '4.5'}
+          - {os: windows-latest, r: '4.5'}
+          - {os: ubuntu-latest,   r: '4.5'}
 
     env:
       GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/pkgdown.yaml

@@ -0,0 +1,76 @@
+on:
+  pull_request:
+    branches: [main, master]
+
+name: vignette-check
+
+permissions: read-all
+
+jobs:
+  vignette-check:
+    runs-on: ubuntu-latest
+    permissions:
+      pull-requests: write
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check vignette freshness
+        id: check
+        run: |
+          # Check if any source files changed that could affect the vignette
+          CHANGED=$(git diff --name-only origin/${{ github.base_ref }}...HEAD -- 'R/' 'man/' 'DESCRIPTION' 'NAMESPACE' 'vignettes/*.Rmd' '_pkgdown.yml')
+          if [ -z "$CHANGED" ]; then
+            echo "source_changed=false" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+          echo "source_changed=true" >> "$GITHUB_OUTPUT"
+
+          # Check the rendered vignette for its compile date
+          VIGNETTE="docs/articles/quick_start_guide.html"
+          if [ ! -f "$VIGNETTE" ]; then
+            echo "status=missing" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          # Extract the "Compiled: YYYY-MM-DD" date from the rendered HTML
+          COMPILE_DATE=$(grep -oP 'Compiled: \K[0-9]{4}-[0-9]{2}-[0-9]{2}' "$VIGNETTE" || true)
+          if [ -z "$COMPILE_DATE" ]; then
+            echo "status=no_date" >> "$GITHUB_OUTPUT"
+            exit 0
+          fi
+
+          # Find the most recent commit date for source files on this branch
+          LAST_SOURCE_CHANGE=$(git log -1 --format=%cs origin/${{ github.base_ref }}...HEAD -- 'R/' 'man/' 'DESCRIPTION' 'NAMESPACE' 'vignettes/*.Rmd')
+          echo "compile_date=$COMPILE_DATE" >> "$GITHUB_OUTPUT"
+          echo "last_source_change=$LAST_SOURCE_CHANGE" >> "$GITHUB_OUTPUT"
+
+          if [[ "$COMPILE_DATE" < "$LAST_SOURCE_CHANGE" ]]; then
+            echo "status=stale" >> "$GITHUB_OUTPUT"
+          else
+            echo "status=fresh" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Post vignette status comment
+        if: steps.check.outputs.source_changed == 'true' && steps.check.outputs.status != 'fresh'
+        uses: marocchino/sticky-pull-request-comment@v3
+        with:
+          header: vignette-check
+          message: |
+            ${{ steps.check.outputs.status == 'stale' && format('⚠️ **Vignette and site are out of date.** Compiled on {0} but source files were changed on {1}.', steps.check.outputs.compile_date, steps.check.outputs.last_source_change) || steps.check.outputs.status == 'missing' && '⚠️ **Rendered vignette not found.** No `docs/articles/quick_start_guide.html` in this branch.' || '⚠️ **Could not determine vignette compile date.** Please verify it has been re-rendered.' }}
+
+            Please rebuild the site locally before merging:
+
+            ```r
+            pkgdown::build_site()
+            ```
+
+            The vignette requires the tutorial dataset and ~32GB RAM, so it cannot be built in CI.
+
+      - name: Clear stale comment if vignette is fresh
+        if: steps.check.outputs.status == 'fresh'
+        uses: marocchino/sticky-pull-request-comment@v3
+        with:
+          header: vignette-check
+          delete: true

.gitignore

@@ -8,4 +8,6 @@ inst/doc
 /Meta/
 .vscode/
 CLAUDE.md
-.claude
+.claude
+local_only
+vignettes/quick_start_guide_cache/

CODE_OF_CONDUCT.md

@@ -0,0 +1,133 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socioeconomic status,
+nationality, personal appearance, race, caste, color, religion, or sexual
+identity and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+- Focusing on what is best not just for us as individuals, but for the overall
+  community
+
+Examples of unacceptable behavior include:
+
+- The use of sexualized language or imagery, and sexual attention or advances of
+  any kind
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email address,
+  without their explicit permission
+- Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official email address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+[natalie.gill@gladstone.ucsf.edu](mailto:natalie.gill@gladstone.ucsf.edu).
+
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series of
+actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or permanent
+ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior, harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within the
+community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.1, available at
+[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1].
+
+Community Impact Guidelines were inspired by
+[Mozilla's code of conduct enforcement ladder][mozilla coc].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][faq]. Translations are available at
+[https://www.contributor-covenant.org/translations][translations].
+
+[faq]: https://www.contributor-covenant.org/faq
+[homepage]: https://www.contributor-covenant.org
+[mozilla coc]: https://github.com/mozilla/diversity
+[translations]: https://www.contributor-covenant.org/translations
+[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html

CONTRIBUTING.md

@@ -0,0 +1,77 @@
+# Contributing to clustOpt
+
+## Before You Start
+
+- **Open an issue first.** Before writing code, open an issue describing the bug or feature so we can discuss the approach. This avoids wasted effort on changes that may not fit the project direction.
+- **Keep PRs focused.** One bug fix or feature per PR. Smaller PRs are easier to review and merge.
+- **Run `devtools::check()` before submitting.** CI can be slow with the R dependency install -- catching issues locally saves time for everyone.
+- **Questions?** Open a [GitHub issue](https://github.com/gladstone-institutes/clustOpt/issues) if you get stuck or need guidance.
+
+## Development Workflow
+
+1. [Fork the repository and create a feature branch](https://docs.github.com/en/get-started/exploring-projects-on-github/contributing-to-a-project) from `main`.
+2. Make code changes in `R/`, `man/`, etc.
+3. `devtools::document()` to regenerate roxygen docs.
+4. `devtools::test()` to run tests.
+5. When ready to merge, rebuild the site (includes the vignette):
+   ```r
+   pkgdown::build_site()
+   ```
+6. Commit everything including `docs/`.
+7. Open a pull request against `main`. CI will run R-CMD-check and verify the vignette compile date is current.
+
+## Development Setup
+
+```r
+# Install dependencies
+devtools::install_deps(dependencies = TRUE)
+
+# Load package for interactive development
+devtools::load_all()
+
+# Run tests
+devtools::test()
+
+# Check package
+devtools::check()
+```
+
+## Code Style
+
+This package follows the [tidyverse style guide](https://style.tidyverse.org/). The [`styler`](https://styler.r-lib.org/) package can help format code automatically:
+
+```r
+# Style a single file
+styler::style_file("R/clust_opt.R")
+
+# Style the whole package
+styler::style_pkg()
+```
+
+Use `roxygen2` for documentation and run `devtools::document()` to regenerate man pages.
+
+Verbosity levels for user-facing functions: 0 = silent, 1 = milestones, 2 = detailed, 3 = includes Seurat output. Use `cli` for all user-facing messages.
+
+## Versioning
+
+This package uses [semantic versioning](https://semver.org/) (`MAJOR.MINOR.PATCH`). Most PRs should **not** bump the version -- version bumps are coordinated by maintainers at release time.
+
+- **PATCH** (e.g., 1.2 -> 1.2.1): Bug fixes, documentation updates, internal refactors with no user-facing changes.
+- **MINOR** (e.g., 1.2 -> 1.3): New features, new exported functions, or changes to default behavior.
+- **MAJOR** (e.g., 1.3 -> 2.0): Breaking changes to the API (renamed/removed functions, changed return types).
+
+When a version bump is needed, update `Version` and `Date` in `DESCRIPTION` and add a section to `NEWS.md`.
+
+## Rebuilding the Vignette and Site
+
+The vignette requires the tutorial dataset and ~32GB RAM, so it cannot be built in CI. Before merging any PR that changes package source or documentation, rebuild the site locally:
+
+```r
+pkgdown::build_site()
+```
+
+This rebuilds the full site including reference docs and the vignette.
+
+Commit the updated `docs/` directory with your PR.
+
+The CI will warn on PRs if the vignette's compile date is older than the most recent source change. The check uses day granularity, so rebuild after all source changes are finalized -- any source commits made after the vignette was last rendered will trigger the warning.

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: clustOpt
-Version: 1.0
-Date: 2024-07-22
+Version: 1.2
+Date: 2025-02-20
 Title: Optimizing Clustering Resolution for Multi-subject Single Cell Studies
 Description: Optimal clustering resolution parameters determined through Random Forests, a silhouette score-based assessment of clustering validity, and subject-wise cross-validation.
 Author: Natalie Gill [aut, cre], Reuben Thomas [aut], Min-Gyoung Shin [aut], Ayushi Agrawal [aut]
@@ -11,8 +11,9 @@ Authors@R: c(person("Natalie", "Gill", role = c("aut", "cre"), email = "natalie.
 	person("Erwin", "Perez", role = c("aut"), email = "perezerw@usc.edu"),
 	person("Reuben", "Thomas", role = c("aut"), email = "reuben.thomas@gladstone.ucsf.edu"))
 Depends:
-    R (>= 4.4)
+    R (>= 4.5.0)
 Imports:
+    cli,
     progressr,
     future.apply,
     ranger,
@@ -22,24 +23,26 @@ Imports:
     dplyr (>= 1.1.3),
     ggplot2 (>= 3.3.5),
     purrr (>= 0.3.4),
-    tibble (>= 3.2.1),
+    tidyr,
+    Matrix,
     methods,
     stats,
     rlang
 License: MIT + file LICENSE
 URL: https://gladstone-institutes.github.io/clustOpt, https://github.com/gladstone-institutes/clustOpt
 BugReports: https://github.com/gladstone-institutes/clustOpt/issues
-RoxygenNote: 7.3.2
+RoxygenNote: 7.3.3
 Encoding: UTF-8
-Collate: 
-    'pca_split.R'
-    'utils.R'
-    'clustOpt.R'
-    'plot.R'
-Suggests: 
+Collate:
+    'metrics.R'
+    'data_preparation.R'
+    'sketching.R'
+    'validation.R'
+    'clust_opt.R'
+    'visualization.R'
+Suggests:
     knitr,
     rmarkdown,
-    tidyr,
     testthat (>= 3.0.0),
     BPCells,
     glmGamPoi