chore: drop dplyr from DESCRIPTION, regenerate NAMESPACE/man, final R CMD check verification

CHANGELOG.md

@@ -18,6 +18,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Converted all 6 `dplyr::group_by()`/`dplyr::summarise()` grouped-aggregation call sites in `zi_aggregate.R` and the paired `group_by()`+`slice()`+`ungroup()` combo in `zi_prep_hud.R` to a new internal `group_summarise_base()` helper (`R/zi_utils.R`), as part of Epic L's dplyr removal; the helper matches `dplyr::group_by()`+`summarise()`'s output contract exactly (row/column ordering, `.groups` semantics, NA-as-a-real-level grouping, and NA-vs-NaN distinction in numeric grouping columns), verified via a 4-round adversarial code-review pass and 6 new regression tests; behavior is unchanged, no `rlang` introduced (#132)
 - Converted all 7 `dplyr::left_join()` call sites in `zi_aggregate.R`, `zi_crosswalk.R`, `zi_label.R`, and `zi_prep_hud.R` to a new internal `left_join_base()` helper (`R/zi_utils.R`) wrapping Base R `merge()`, as part of Epic L's dplyr removal; the helper restores `merge()`'s row and column ordering to match `dplyr::left_join()`'s contract exactly (`x`'s original row order, `x` columns followed by new `y` columns) and disambiguates colliding non-key column names with `.x`/`.y` suffixes the same way `dplyr::left_join()` does, verified against NA-key matching, one-to-many duplicate-key expansion, and column-name collisions; behavior is unchanged, no `rlang` introduced (#131)
 - Converted all `dplyr::filter()`, `select()`, `mutate()`, and `arrange()` call sites in `zi_aggregate.R`, `zi_crosswalk.R`, `zi_get_demographics.R`, `zi_get_geometry.R`, `zi_list_zctas.R`, `zi_load_crosswalk.R`, `zi_load_labels.R`, and `zi_prep_hud.R` to Base R equivalents, as part of Epic L's dplyr removal; behavior is unchanged, no `rlang` introduced (#130)
+- Converted `dplyr::filter()`, `mutate()`, `arrange()`, and `bind_rows()` call sites in `data-raw/build_uds_crosswalk.R` and 18 `dplyr::filter()`/`select()` call sites in `tests/testthat/test_zi_aggregate.R` (discovered as an unstated test dependency during `R CMD check`) to Base R equivalents, and removed `dplyr (>= 1.0.0)` from `DESCRIPTION` Imports, completing Epic L's dplyr removal; `devtools::check()` now runs with 0 errors and 0 warnings (#134)
 - Registered `[Epic K] Vendored Workflow Toolkit Adoption & Governance` (#123) on `docs/ROADMAP.md` under `Next`, with a preferred-but-not-blocking dependency edge to `[Epic J]` (#111) and a note that #120 gates #118 and #119 (#123)
 - Added a `brew link --overwrite udunits gdal proj` step after the macOS `sf` dependency install in `R-CMD-check.yaml`, so a cache miss no longer silently leaves the runner-image-preinstalled formulae unlinked with a `##[warning] ... not linked` annotation (#122)
 - Retired `[Epic I] CI & Development Infrastructure Health` (#110) from `docs/ROADMAP.md` to `Recently Shipped`; all five sub-issues (#102, #113, #114, #115, #122) shipped, resolving the caching-layer defects, checks-not-firing gap, Node.js 20 deprecation warnings, and macOS Homebrew warnings

DESCRIPTION

@@ -29,7 +29,6 @@ Language: en-US
 Config/testthat/edition: 3
 Imports:
     cli (>= 3.0.0),
-    dplyr (>= 1.0.0),
     httr2 (>= 1.0.0),
     jsonlite (>= 1.7.0),
     sf (>= 1.0-0),

R/zi_prep_hud.R

@@ -90,6 +90,10 @@ zi_prep_hud <- function(.data, by, return_max = TRUE){
   # identify max
   out <- out[order(out$zip5, out$state, out$geoid), ]
 
+  # NOTE: comments below intentionally reference dplyr by name to document
+  # the exact behavior each Base R construct reproduces (Epic L, #129).
+  # These are explanatory references, not functional dplyr usage, and are
+  # out of scope for "dplyr reference removal" (see #141).
   # ave() groups by combining vectors via split(); unlike dplyr::group_by(),
   # split() drops NA keys into per-row singleton groups instead of grouping
   # them together. Coercing to factors with exclude = NULL preserves NA as a

R/zi_utils.R

@@ -1,3 +1,8 @@
+# NOTE: the comments in this file intentionally reference dplyr by name to
+# document the exact behavior each Base R helper reproduces (Epic L, #129).
+# These are explanatory references, not functional dplyr usage, and are
+# out of scope for "dplyr reference removal" (see #141).
+
 # Internal left join helper (replaces dplyr::left_join())
 # Wraps base merge() to reproduce dplyr::left_join()'s row-order and
 # column-order contract: all rows of x are kept in their original order,

data-raw/build_uds_crosswalk.R

@@ -17,7 +17,6 @@
 #   Retrieved: run Sys.time() below to record date of build
 
 # Dependencies ---------------------------------------------------------------
-library(dplyr)
 library(readr)
 library(stringr)
 library(tibble)
@@ -58,7 +57,7 @@ normalize_uds_year <- function(year) {
 
   # remove rows with no ZCTA (must happen before zero-padding so "N/A" is caught)
   if ("zcta" %in% names(df)) {
-    df <- dplyr::filter(df, !(zcta %in% c("N/A", NA, "No ZCTA", "")))
+    df <- df[!(df$zcta %in% c("N/A", NA, "No ZCTA", "")), , drop = FALSE]
   }
 
   # zero-pad ZIP and ZCTA to 5 digits
@@ -67,25 +66,52 @@ normalize_uds_year <- function(year) {
 
   # remove military ZIPs
   if ("zip_type" %in% names(df)) {
-    df <- dplyr::filter(df, !grepl("^M", zip_type))
+    df <- df[!grepl("^M", df$zip_type), , drop = FALSE]
   }
 
   # title-case post office names
   if ("po_name" %in% names(df)) {
-    df <- dplyr::mutate(df, po_name = stringr::str_to_title(po_name))
+    df$po_name <- stringr::str_to_title(df$po_name)
   }
 
   # sort and add year tag
-  df <- dplyr::arrange(df, zip)
+  df <- df[order(df$zip), , drop = FALSE]
   df$year <- as.integer(year)
 
   cat(" OK (", nrow(df), "rows )\n", sep = "")
   tibble::as_tibble(df)
 }
 
 # Build combined dataset -----------------------------------------------------
+# NOTE: comments below intentionally reference dplyr by name to document
+# the exact behavior this Base R helper reproduces (Epic L, #129). These
+# are explanatory references, not functional dplyr usage, and are out of
+# scope for "dplyr reference removal" (see #141).
+# bind_rows_base(): row-binds two data frames by column name (matching
+# dplyr::bind_rows()'s contract), since not every year's schema includes
+# every standard column (see standard_cols intersection above). Missing
+# columns are filled with NA for the frame that lacks them.
+bind_rows_base <- function(x, y) {
+  x_cols <- names(x)
+  y_only_cols <- setdiff(names(y), x_cols)
+  all_cols <- c(x_cols, y_only_cols)
+
+  for (col in y_only_cols) {
+    x[[col]] <- NA
+  }
+  for (col in x_cols) {
+    if (!(col %in% names(y))) {
+      y[[col]] <- NA
+    }
+  }
+
+  out <- rbind(x[, all_cols, drop = FALSE], y[, all_cols, drop = FALSE])
+  rownames(out) <- NULL
+  out
+}
+
 all_years <- lapply(UDS_YEARS, normalize_uds_year)
-crosswalk  <- dplyr::bind_rows(all_years)
+crosswalk  <- Reduce(bind_rows_base, all_years)
 
 cat("\nCombined rows:", nrow(crosswalk), "\n")
 cat("Years present:", paste(sort(unique(crosswalk$year)), collapse = ", "), "\n")

tests/testthat/test_zi_aggregate.R

@@ -106,39 +106,39 @@ dec_weights <- tibble::tibble(
 )
 
 test_that("zi_census_extensive sums values by ZCTA3 and variable", {
-  input <- dplyr::filter(dec_fixture, variable == "P001001")
+  input <- dec_fixture[dec_fixture$variable == "P001001", ]
   result <- zi_census_extensive(input)
 
   expect_s3_class(result, "tbl_df")
   expect_true(all(c("ZCTA3", "variable", "value") %in% names(result)))
 
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
-  r631 <- dplyr::filter(result, ZCTA3 == "631")
+  r630 <- result[result$ZCTA3 == "630", ]
+  r631 <- result[result$ZCTA3 == "631", ]
 
   expect_equal(r630$value, 600)
   expect_equal(r631$value, 750)
 })
 
 test_that("zi_census_intensive computes weighted mean correctly", {
-  input <- dplyr::filter(dec_fixture, variable == "P013001")
+  input <- dec_fixture[dec_fixture$variable == "P013001", ]
   result <- zi_census_intensive(input, weights = dec_weights, method = "mean")
 
   expect_s3_class(result, "tbl_df")
   expect_true(all(c("ZCTA3", "variable", "value") %in% names(result)))
 
   # expected weighted mean for 630: (35.2*100 + 38.1*200 + 42.0*300) / 600
   expected_630 <- stats::weighted.mean(c(35.2, 38.1, 42.0), c(100 / 600, 200 / 600, 300 / 600))
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
+  r630 <- result[result$ZCTA3 == "630", ]
   expect_equal(r630$value, expected_630, tolerance = 1e-6)
 
   # expected weighted mean for 631: (29.5*150 + 33.7*250 + 40.1*350) / 750
   expected_631 <- stats::weighted.mean(c(29.5, 33.7, 40.1), c(150 / 750, 250 / 750, 350 / 750))
-  r631 <- dplyr::filter(result, ZCTA3 == "631")
+  r631 <- result[result$ZCTA3 == "631", ]
   expect_equal(r631$value, expected_631, tolerance = 1e-6)
 })
 
 test_that("zi_census_intensive computes weighted median correctly", {
-  input <- dplyr::filter(dec_fixture, variable == "P013001")
+  input <- dec_fixture[dec_fixture$variable == "P013001", ]
   result <- zi_census_intensive(input, weights = dec_weights, method = "median")
 
   expect_s3_class(result, "tbl_df")
@@ -148,7 +148,7 @@ test_that("zi_census_intensive computes weighted median correctly", {
   # sorted x = c(35.2, 38.1, 42.0), cumsum(w)/sum(w) = c(1/6, 1/2, 1)
   # first index where cumsum >= 0.5 is index 2 → value 38.1
   expected_630 <- 38.1
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
+  r630 <- result[result$ZCTA3 == "630", ]
   expect_equal(r630$value, expected_630, tolerance = 1e-6)
 })
 
@@ -181,24 +181,24 @@ acs_weights <- tibble::tibble(
 )
 
 test_that("zi_acs_extensive sums estimates and propagates MOE correctly", {
-  input <- dplyr::filter(acs_fixture, variable == "B01003_001")
+  input <- acs_fixture[acs_fixture$variable == "B01003_001", ]
   result <- zi_acs_extensive(input)
 
   expect_s3_class(result, "tbl_df")
   expect_true(all(c("ZCTA3", "variable", "estimate", "moe") %in% names(result)))
 
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
+  r630 <- result[result$ZCTA3 == "630", ]
   expect_equal(r630$estimate, 6000)
   # MOE = sqrt(100^2 + 150^2 + 200^2)
   expect_equal(r630$moe, sqrt(100^2 + 150^2 + 200^2), tolerance = 1e-6)
 
-  r631 <- dplyr::filter(result, ZCTA3 == "631")
+  r631 <- result[result$ZCTA3 == "631", ]
   expect_equal(r631$estimate, 7500)
   expect_equal(r631$moe, sqrt(120^2 + 180^2 + 220^2), tolerance = 1e-6)
 })
 
 test_that("zi_acs_intensive computes weighted mean for estimate and moe", {
-  input <- dplyr::filter(acs_fixture, variable == "B19013_001")
+  input <- acs_fixture[acs_fixture$variable == "B19013_001", ]
   result <- zi_acs_intensive(input, weights = acs_weights, method = "mean")
 
   expect_s3_class(result, "tbl_df")
@@ -209,13 +209,13 @@ test_that("zi_acs_intensive computes weighted mean for estimate and moe", {
   expected_est_630 <- stats::weighted.mean(c(55000, 62000, 48000), w630)
   expected_moe_630 <- stats::weighted.mean(c(5000, 6000, 4500), w630)
 
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
+  r630 <- result[result$ZCTA3 == "630", ]
   expect_equal(r630$estimate, expected_est_630, tolerance = 1e-6)
   expect_equal(r630$moe, expected_moe_630, tolerance = 1e-6)
 })
 
 test_that("zi_acs_intensive computes weighted median for estimate and moe", {
-  input <- dplyr::filter(acs_fixture, variable == "B19013_001")
+  input <- acs_fixture[acs_fixture$variable == "B19013_001", ]
   result <- zi_acs_intensive(input, weights = acs_weights, method = "median")
 
   expect_s3_class(result, "tbl_df")
@@ -228,7 +228,7 @@ test_that("zi_acs_intensive computes weighted median for estimate and moe", {
   expected_est_630 <- 48000
   expected_moe_630 <- 4500
 
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
+  r630 <- result[result$ZCTA3 == "630", ]
   expect_equal(r630$estimate, expected_est_630, tolerance = 1e-6)
   expect_equal(r630$moe, expected_moe_630, tolerance = 1e-6)
 })
@@ -250,10 +250,10 @@ test_that("zi_aggregate works with decennial extensive data", {
   expect_true(all(c("ZCTA3", "variable", "value") %in% names(result)))
   expect_equal(nrow(result), 2)
 
-  r630 <- dplyr::filter(result, ZCTA3 == "630")
+  r630 <- result[result$ZCTA3 == "630", ]
   expect_equal(r630$value, 600)
 
-  r631 <- dplyr::filter(result, ZCTA3 == "631")
+  r631 <- result[result$ZCTA3 == "631", ]
   expect_equal(r631$value, 750)
 })
 
@@ -354,7 +354,7 @@ test_that("zi_aggregate works with live Census data", {
     variables = c(medincome = "B19013_001"),
     state = "VT",
     year = 2020
-  ) |> dplyr::select(-NAME)
+  ) |> (\(d) d[, setdiff(names(d), "NAME"), drop = FALSE])()
 
   expect_error(
     zi_aggregate(year = 2020, survey = correct_survey,

tests/testthat/test_zi_utils.R

@@ -1,4 +1,8 @@
 # fixture data (no API calls) ------------------------------------------------
+# NOTE: several test titles/comments below intentionally reference dplyr by
+# name to document the exact behavior each Base R helper reproduces (Epic
+# L, #129). These are explanatory references, not functional dplyr usage,
+# and are out of scope for "dplyr reference removal" (see #141).
 
 x_simple <- data.frame(
   id = c(1, 2, NA, 3),