Fix R/clean.R for surveys in which only age range is reported for participants

[LloydChapman]

Suggested fix for #249. This restores including part_age_est_min and part_age_est_max in x$participantsin clean.contact_survey() in clean.R. The code in #249 for the CoMix survey with only participant age ranges reported will then work as the default value of estimated.participant.age ("mean") ensures that the mean of part_age_est_min and part_age_est_max is taken for part_age in survey$participants in contact_matrix.

Summary by CodeRabbit

• New Features

  • Added estimated participant age-range fields: estimated minimum and estimated maximum alongside the existing exact age to improve reporting, display, and filtering.

• Tests

  • Added a unit test verifying age-range strings are parsed into the new estimated min/max fields.

• Chores

  • Updated package metadata to add a new contributor.

_{✏️ Tip: You can customize this high-level summary in your review settings.}

[coderabbitai]

📝 Walkthrough

Walkthrough

Adds two participant age estimate columns to the cleaning pipeline and a unit test; updates AUTHORS metadata. The new columns <participant.age.column>_est_min and <participant.age.column>_est_max are set from ..low and ..high before creating the _exact age column.

Changes

Cohort / File(s)	Summary
Age estimation column addition R/clean.R	In clean.contact_survey, create <participant.age.column>_est_min (from ..low) and <participant.age.column>_est_max (from ..high) on x$participants; inserted after numeric/NA handling and before <participant.age.column>_exact creation.
Tests tests/testthat/test-clean.R	Adds a unit test asserting that an age range string like "20-30" yields est_min = 20 and est_max = 30 for a participant after clean().
Metadata DESCRIPTION	Adds author Lloyd Chapman (ctb, email l.chapman4@lancaster.ac.uk) and adjusts Pietro Coletti's author entry punctuation.

Sequence Diagram(s)

(omitted — changes are limited to adding columns and a test; no new multi-component control flow introduced)

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related issues

• clean() not working for surveys that only report participant age range #249 — Restores/introduces participant age _est_min and _est_max columns in clean.contact_survey, matching this change.

Possibly related PRs

• Streamline participant and contact age handling #248 — Adds/handles the same participant age estimate fields and related helpers (add_age/impute_ages), overlapping with these edits.

Poem

🐰
I hopped through rows with careful zest,
Split ranges, set min and max to rest,
Columns tucked in tidy line,
Numbers snug and fields align,
A tiny hop — the table's blessed 🥕

Pre-merge checks

✅ Passed checks (3 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title clearly and specifically describes the main change: handling surveys where only participant age ranges (not exact ages) are reported, and the fix to R/clean.R to support this scenario.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

---

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between fb9a952 and c8817ae.

📒 Files selected for processing (1)

• tests/testthat/test-clean.R

🚧 Files skipped from review as they are similar to previous changes (1)

• tests/testthat/test-clean.R

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between a0b456c and 74b9d7b.

📒 Files selected for processing (1)

• R/clean.R (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

R/**/*.{R,r}

📄 CodeRabbit inference engine (CLAUDE.md)

Run devtools::document() to regenerate documentation from roxygen comments before committing

Files:

• R/clean.R

**/*.{R,r}

📄 CodeRabbit inference engine (CLAUDE.md)

Run lintr::lint_package() to check for style issues and fix any in files you modified before committing

Files:

• R/clean.R

🧠 Learnings (3)

📓 Common learnings

Learnt from: sbfnk
Repo: epiforecasts/socialmixr PR: 248
File: R/contact-matrix-utils.R:206-216
Timestamp: 2025-12-12T19:08:42.596Z
Learning: In the socialmixr package, the add_age() helper function in R/contact-matrix-utils.R intentionally overwrites the age column (e.g., part_age, cnt_age) with values from the exact age column (e.g., part_age_exact, cnt_age_exact) when the exact column exists. This overwriting behavior is by design.

Learnt from: njtierney
Repo: epiforecasts/socialmixr PR: 196
File: R/contact-matrix-utils.R:7-13
Timestamp: 2025-09-02T05:04:15.939Z
Learning: In the socialmixr package, functions like est_part_age_mean create new columns (part_age) by imputing from other existing columns (part_age_exact, part_age_est_min, part_age_est_max). The condition checks the source columns, not the target column being created.

📚 Learning: 2025-09-02T05:04:15.939Z

Learnt from: njtierney
Repo: epiforecasts/socialmixr PR: 196
File: R/contact-matrix-utils.R:7-13
Timestamp: 2025-09-02T05:04:15.939Z
Learning: In the socialmixr package, functions like est_part_age_mean create new columns (part_age) by imputing from other existing columns (part_age_exact, part_age_est_min, part_age_est_max). The condition checks the source columns, not the target column being created.

Applied to files:

• R/clean.R

📚 Learning: 2025-12-12T19:08:42.596Z

Learnt from: sbfnk
Repo: epiforecasts/socialmixr PR: 248
File: R/contact-matrix-utils.R:206-216
Timestamp: 2025-12-12T19:08:42.596Z
Learning: In the socialmixr package, the add_age() helper function in R/contact-matrix-utils.R intentionally overwrites the age column (e.g., part_age, cnt_age) with values from the exact age column (e.g., part_age_exact, cnt_age_exact) when the exact column exists. This overwriting behavior is by design.

Applied to files:

• R/clean.R

🪛 GitHub Actions: format-suggest.yaml

R/clean.R

[error] 136-139: Reviewdog detected issues with severity >= error in diff context (lines 136-139).

[sbfnk]

Thanks @LloydChapman for catching this and suggesting a fix! A few things:

1. We get a lintr error about single vs. double quotes - could you fix this?
2. Can you add yourself as a contributor (role = "ctb") to the DESCRIPTION file?
3. Can we add a regression test? Here's a suggestion but happy for you to do something different.

(e.g. in a new file tests/testthat/test-clean.R)

  test_that("clean() creates est_min/est_max for age ranges", {
    survey <- polymod
    # Replace exact ages with ranges
    survey$participants$part_age <- "20-30"
    survey$participants$part_age_exact <- NULL

    cleaned <- clean(survey)

    expect_true("part_age_est_min" %in% names(cleaned$participants))
    expect_true("part_age_est_max" %in% names(cleaned$participants))
    expect_equal(cleaned$participants$part_age_est_min[1], 20)
    expect_equal(cleaned$participants$part_age_est_max[1], 30)
  })

[LloydChapman]

Thanks @sbfnk. Sure thing. I've made those changes.

[coderabbitai]

Actionable comments posted: 0

🧹 Nitpick comments (1)

tests/testthat/test-clean.R (1)

1-13: Regression test successfully implements the requested validation.

The test correctly verifies that clean() creates part_age_est_min and part_age_est_max columns from age range strings, which addresses the regression test requirement from the PR review.

One minor suggestion: Consider using expect_equal() instead of expect_identical() on lines 11-12. The reviewer's example code used expect_equal(), which is more idiomatic for numeric comparisons in testthat and avoids potential type-mismatch issues between integer and numeric values.

Optional: Use expect_equal for numeric comparisons

-  expect_identical(cleaned$participants$part_age_est_min[1], 20)
-  expect_identical(cleaned$participants$part_age_est_max[1], 30)
+  expect_equal(cleaned$participants$part_age_est_min[1], 20)
+  expect_equal(cleaned$participants$part_age_est_max[1], 30)

Optional: Additional test cases for broader coverage

If desired, you could extend coverage with:

• Different age range formats (e.g., "0-5", "65-100")
• Multiple participants with different ranges
• Edge cases (NA values, invalid ranges)

However, this basic regression test is sufficient for the immediate fix.

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 78579ad and fb9a952.

📒 Files selected for processing (1)

• tests/testthat/test-clean.R (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

tests/**/*.{R,r}

📄 CodeRabbit inference engine (CLAUDE.md)

tests/**/*.{R,r}: Run devtools::test() to ensure all tests pass before committing
Add tests for bug fixes (regression tests) or new features where appropriate

Files:

• tests/testthat/test-clean.R

**/*.{R,r}

📄 CodeRabbit inference engine (CLAUDE.md)

Run lintr::lint_package() to check for style issues and fix any in files you modified before committing

Files:

• tests/testthat/test-clean.R

🧠 Learnings (3)

📓 Common learnings

Learnt from: sbfnk
Repo: epiforecasts/socialmixr PR: 248
File: R/contact-matrix-utils.R:206-216
Timestamp: 2025-12-12T19:08:46.874Z
Learning: In the socialmixr package, the add_age() helper function in R/contact-matrix-utils.R intentionally overwrites the age column (e.g., part_age, cnt_age) with values from the exact age column (e.g., part_age_exact, cnt_age_exact) when the exact column exists. This overwriting behavior is by design.

Learnt from: njtierney
Repo: epiforecasts/socialmixr PR: 196
File: R/contact-matrix-utils.R:7-13
Timestamp: 2025-09-02T05:04:15.939Z
Learning: In the socialmixr package, functions like est_part_age_mean create new columns (part_age) by imputing from other existing columns (part_age_exact, part_age_est_min, part_age_est_max). The condition checks the source columns, not the target column being created.

📚 Learning: 2025-12-12T19:13:48.046Z

Learnt from: CR
Repo: epiforecasts/socialmixr PR: 0
File: CLAUDE.md:0-0
Timestamp: 2025-12-12T19:13:48.046Z
Learning: Applies to tests/**/*.{R,r} : Add tests for bug fixes (regression tests) or new features where appropriate

Applied to files:

• tests/testthat/test-clean.R

📚 Learning: 2025-09-02T05:04:15.939Z

Learnt from: njtierney
Repo: epiforecasts/socialmixr PR: 196
File: R/contact-matrix-utils.R:7-13
Timestamp: 2025-09-02T05:04:15.939Z
Learning: In the socialmixr package, functions like est_part_age_mean create new columns (part_age) by imputing from other existing columns (part_age_exact, part_age_est_min, part_age_est_max). The condition checks the source columns, not the target column being created.

Applied to files:

• tests/testthat/test-clean.R