Skip to content

docs: add hospital readmissions tutorial - #725

Open
zywind wants to merge 6 commits into
mainfrom
yunfeng/healthcare-readmissions-tutorial
Open

docs: add hospital readmissions tutorial#725
zywind wants to merge 6 commits into
mainfrom
yunfeng/healthcare-readmissions-tutorial

Conversation

@zywind

@zywind zywind commented Aug 19, 2026

Copy link
Copy Markdown
Contributor

Summary

  • Add a healthcare-focused Safe Synthesizer tutorial using the simulated hospital readmissions dataset, manual sensitive-column configuration, healthcare utility plots, and an XGBoost TSTR comparison.
  • Add the fourth tutorial to the documentation and Brev navigation; the final notebook has no saved outputs, and generated artifact directories remain excluded.
  • Closes SDGR-21 (Linear issue).
  • Closes SDGR-19 (Linear issue).

Test plan

  • Parsed 9,997 CSV rows and validated notebook JSON and Python cell syntax.
  • mise run format-check
  • mise run docs:build

Summary by CodeRabbit

New Features

  • Added a Healthcare Hospital Readmissions tutorial covering synthetic data generation, privacy configuration, healthcare analyses, and predictive modeling.
  • Added the tutorial to the Tutorials navigation and welcome guide.
  • Included evaluation metrics and visualizations for generated healthcare data.

Documentation

  • Updated environment and home-directory documentation to reflect four preinstalled tutorial notebooks and their datasets.

Signed-off-by: Yunfeng Zhang <yunzhang@nvidia.com>
@zywind
zywind requested review from a team as code owners August 19, 2026 19:35
@coderabbitai

coderabbitai Bot commented Aug 19, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

Note

Reviews paused

It looks like this branch is under active development. To avoid overwhelming you with review comments due to an influx of new commits, CodeRabbit has automatically paused this review. You can configure this behavior by changing the reviews.auto_review.auto_pause_after_reviewed_commits setting.

Use the following commands to manage reviews:

  • @coderabbitai resume to resume automatic reviews.
  • @coderabbitai review to trigger a single review.

Use the checkboxes below for quick actions:

  • ▶️ Resume reviews
  • 🔍 Trigger review

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 600d6f45-45b3-4979-b012-54ad1e0b996f

📥 Commits

Reviewing files that changed from the base of the PR and between 685ef80 and b570d35.

📒 Files selected for processing (1)
  • docs/tutorials/healthcare-hospital-readmissions.ipynb
🚧 Files skipped from review as they are similar to previous changes (1)
  • docs/tutorials/healthcare-hospital-readmissions.ipynb

Included review availability: Your plan provides up to 12 included reviews per hour; 10 remain after this review.

📜 Recent review details
⏰ Context from checks skipped due to timeout. (6)
  • GitHub Check: Format
  • GitHub Check: Detect changes
  • GitHub Check: Typecheck
  • GitHub Check: Greptile Review
  • GitHub Check: Analyze (Python)
  • GitHub Check: Analyze (python)

Walkthrough

The pull request adds a Healthcare Hospital Readmissions tutorial notebook. It configures privacy-aware synthesis, evaluates synthetic data quality and integrity, compares predictive utility, and updates tutorial navigation and onboarding documentation.

Changes

Healthcare readmissions tutorial

Layer / File(s) Summary
Tutorial catalog and onboarding documentation
docs/tutorials/index.md, mkdocs.yml, script/brev/README.md, script/brev/welcome.md
The documentation now lists four tutorial notebooks, adds the Healthcare Hospital Readmissions tutorial to navigation, and includes it in the welcome guide.
Notebook setup and privacy policy
docs/tutorials/healthcare-hospital-readmissions.ipynb
The notebook defines its environment, loads simulated admissions data, and configures deterministic replacement for healthcare PII.
Synthesis generation and reporting
docs/tutorials/healthcare-hospital-readmissions.ipynb
The notebook trains Safe Synthesizer, generates synthetic records, validates the output, and displays evaluation reports.
Utility and predictive evaluation
docs/tutorials/healthcare-hospital-readmissions.ipynb
The notebook compares original and synthetic cohorts through healthcare analyses, integrity checks, and TRTR/TSTR XGBoost metrics.
Synthetic dataset scanning exclusion
.github/workflows/config/.secrets.baseline
The secrets baseline excludes the generated hospital readmissions CSV path from secret scanning.

Estimated code review effort: 4 (Complex) | ~45 minutes

Merge Risk: ⚪ Minimal · up to b570d

This PR adds a documentation tutorial and navigation updates without any actionable merge-blocking risk remaining after normal checks and review.

Suggested reviewers: alexahaushalter

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly and concisely describes the main change: adding the hospital readmissions tutorial.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch yunfeng/healthcare-readmissions-tutorial

Comment @coderabbitai help to get the list of available commands.

@coderabbitai coderabbitai Bot added the feature New feature or request label Aug 19, 2026
Signed-off-by: Yunfeng Zhang <yunzhang@nvidia.com>
@greptile-apps

greptile-apps Bot commented Aug 19, 2026

Copy link
Copy Markdown
Contributor

Greptile Summary

The PR adds a hospital-readmissions tutorial using simulated healthcare data and integrates it into the documentation and Brev navigation.

  • Adds the tutorial notebook and its simulated admissions dataset.
  • Demonstrates manual sensitive-column replacement, utility analysis, and TSTR modeling.
  • Updates tutorial indexes, navigation, Brev guidance, and the secrets baseline.

Confidence Score: 5/5

The PR appears safe to merge because no blocking failure remains.

No blocking failure remains.

Important Files Changed

Filename Overview
docs/tutorials/healthcare-hospital-readmissions.ipynb Adds the end-to-end healthcare synthesis, evaluation, and predictive-modeling tutorial.
docs/tutorials/datasets/hospital_readmissions_synthetic_2026_08_18.csv Adds the simulated hospital-admissions dataset consumed by the tutorial.
mkdocs.yml Registers the healthcare tutorial in the documentation navigation.
script/brev/welcome.md Adds the new tutorial to the Brev welcome page.
.github/workflows/config/.secrets.baseline Excludes the simulated healthcare dataset from secret scanning.

Reviews (6): Last reviewed commit: "docs: quiet tutorial dependency installa..." | Re-trigger Greptile

@coderabbitai coderabbitai Bot added docs Documentation-only change and removed feature New feature or request labels Aug 19, 2026
@zywind
zywind requested a review from alexahaushalter August 19, 2026 19:41
Signed-off-by: Yunfeng Zhang <yunzhang@nvidia.com>
@coderabbitai coderabbitai Bot removed the docs Documentation-only change label Aug 19, 2026
@zywind
zywind enabled auto-merge August 19, 2026 19:58
@codecov

codecov Bot commented Aug 19, 2026

Copy link
Copy Markdown

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

zywind added 2 commits August 20, 2026 13:45
Signed-off-by: Yunfeng Zhang <yunzhang@nvidia.com>
Signed-off-by: Yunfeng Zhang <yunzhang@nvidia.com>
## Summary
- Add `--quiet` to uv and pip install commands in all tutorial
notebooks.
- Suppress routine setup output while preserving warnings and failures.
- Stacked on #725; merge after #725.

## Test plan
- [x] Validate notebook JSON and install-cell Bash syntax.
- [x] Run the uv install commands for the core package, datasets,
kagglehub, and xgboost.
- [x] Verify the child diff contains only `--quiet` changes.

Signed-off-by: Yunfeng Zhang <yunzhang@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant