feat: cog_find_peers + cog_peer_compare

cog_find_peers selects peers from canonical_fips_xwalk by same-type,
same-state, and population-range (ratio or absolute) criteria,
ordered by |log(pop_ratio)| ascending.

cog_peer_compare accepts the find_peers result (or a plain character
vector of govids), pulls spending for target + peers via cog_spending,
and appends summary rows (summary_p25/p50/p75) so the whole result
can be faceted by `role` in a single ggplot call. Summary rows honor
per_capita + adjust_to_year by picking the right value column.
target_rank reports the target's rank among target+peers at max(years).

Provenance is rewritten with verb = cog_peer_compare and peer_count.

Also: globalVariables('.data') in zzz.R to silence R CMD check on
tidy-eval pronouns.

Tests: 21 new / 120 total pass. devtools::check() 0E/0W/2N.

NAMESPACE

@@ -1,6 +1,8 @@
 # Generated by roxygen2: do not edit by hand
 
 export(cog_explain)
+export(cog_find_peers)
 export(cog_geographic_rollup)
+export(cog_peer_compare)
 export(cog_revenue)
 export(cog_spending)

R/peers.R

@@ -0,0 +1,195 @@
+# R/peers.R
+
+#' Find peer governments by similarity criteria
+#'
+#' Selects peer governments from `canonical_fips_xwalk` by combinations of
+#' government type, state, and population range. Peers are ordered by
+#' `|log(pop_ratio)|` ascending (closest to the target's population first).
+#'
+#' @param target_govid Character scalar — `canonical_govid` of the target.
+#' @param same_type If `TRUE` (default) restrict peers to the target's
+#'   `govs_type`.
+#' @param same_state If `TRUE` restrict peers to the target's `fips_state`.
+#'   Default `FALSE`.
+#' @param pop_range Length-2 numeric vector giving lower/upper bounds.
+#' @param is_ratio If `TRUE` (default) `pop_range` is multiplied by the
+#'   target's `population_acs` to produce absolute bounds. If `FALSE`,
+#'   `pop_range` is interpreted as absolute population counts.
+#' @param pop_year Reserved for future use (selecting ACS vintage). Currently
+#'   the corpus has a single snapshot so this argument has no effect.
+#' @param max_peers Integer cap on the number of peers returned.
+#' @return Tibble with columns `canonical_govid`, `gov_name`, `fips_state`,
+#'   `population_acs`, `pop_ratio`, `rank`.
+#' @export
+cog_find_peers <- function(target_govid,
+                           same_type = TRUE,
+                           same_state = FALSE,
+                           pop_range = c(0.7, 1.3),
+                           is_ratio = TRUE,
+                           pop_year = NULL,
+                           max_peers = 10L) {
+  if (!is.character(target_govid) || length(target_govid) != 1L) {
+    cli::cli_abort("`target_govid` must be a length-1 character string.")
+  }
+  if (!is.numeric(pop_range) || length(pop_range) != 2L ||
+      pop_range[1] >= pop_range[2]) {
+    cli::cli_abort("`pop_range` must be a length-2 numeric with lo < hi.")
+  }
+
+  con <- .ensure_session()
+
+  target_sql <- sprintf(
+    "SELECT canonical_govid, gov_name, govs_type, fips_state, population_acs
+     FROM canonical_fips_xwalk
+     WHERE canonical_govid = %s",
+    .sql_lit_chr(target_govid)
+  )
+  target <- DBI::dbGetQuery(con, target_sql)
+  if (nrow(target) == 0L) {
+    cli::cli_abort(c(
+      "govid {target_govid} not found in corpus.",
+      i = "v0.1 covers types 0-3 only (state/county/city/township); see vignette('coverage-scope')."
+    ))
+  }
+  if (is.na(target$population_acs) || target$population_acs <= 0) {
+    cli::cli_abort("Target {target_govid} has missing or non-positive population; cannot build pop_ratio band.")
+  }
+
+  if (isTRUE(is_ratio)) {
+    lo <- target$population_acs * pop_range[1]
+    hi <- target$population_acs * pop_range[2]
+  } else {
+    lo <- pop_range[1]; hi <- pop_range[2]
+  }
+
+  preds <- c(
+    sprintf("canonical_govid != %s", .sql_lit_chr(target_govid)),
+    sprintf("population_acs BETWEEN %.6f AND %.6f", lo, hi)
+  )
+  if (isTRUE(same_type))  preds <- c(preds, sprintf("govs_type = %d", target$govs_type))
+  if (isTRUE(same_state)) preds <- c(preds, sprintf("fips_state = %s", .sql_lit_chr(target$fips_state)))
+
+  peers_sql <- sprintf(
+    "SELECT canonical_govid, gov_name, fips_state, population_acs,
+            population_acs / %.6f AS pop_ratio
+     FROM canonical_fips_xwalk
+     WHERE %s
+     ORDER BY ABS(LN(CAST(population_acs AS DOUBLE) / %.6f))
+     LIMIT %d",
+    target$population_acs,
+    paste(preds, collapse = " AND "),
+    target$population_acs,
+    as.integer(max_peers)
+  )
+  peers <- tibble::as_tibble(DBI::dbGetQuery(con, peers_sql))
+  if (nrow(peers) > 0L) peers$rank <- seq_len(nrow(peers))
+  else peers$rank <- integer(0)
+  peers
+}
+
+#' Compare a target government against a peer set
+#'
+#' Pulls spending for the target plus a peer set (either a
+#' [cog_find_peers()] result or a character vector of `canonical_govid`) and
+#' appends peer-distribution summary rows (`summary_p25`, `summary_p50`,
+#' `summary_p75`) so the result can be faceted by `role` in a single ggplot
+#' call.
+#'
+#' @param target_govid Character scalar.
+#' @param peers A tibble from [cog_find_peers()] or a character vector of
+#'   `canonical_govid`s.
+#' @param category Character scalar or vector.
+#' @param years Integer vector.
+#' @param per_capita Default `TRUE` — peer compare usually normalizes by
+#'   population.
+#' @param adjust_to_year Integer base year for CPI-U conversion or `NULL`.
+#' @return Tibble matching [cog_spending()]'s columns, plus a `role`
+#'   column taking values `"target"`, `"peer"`, `"summary_p25"`,
+#'   `"summary_p50"`, or `"summary_p75"`, and `target_rank` (target's rank
+#'   among target+peers at `max(years)`, NA for other rows). Provenance
+#'   attribute reports `verb = "cog_peer_compare"` and `peer_count`.
+#' @export
+cog_peer_compare <- function(target_govid, peers, category, years,
+                             per_capita = TRUE, adjust_to_year = NULL) {
+  call <- match.call()
+  if (!is.character(target_govid) || length(target_govid) != 1L) {
+    cli::cli_abort("`target_govid` must be a length-1 character string.")
+  }
+  peer_govids <- if (is.data.frame(peers)) {
+    as.character(peers$canonical_govid)
+  } else {
+    as.character(peers)
+  }
+  peer_govids <- peer_govids[!is.na(peer_govids) & nzchar(peer_govids)]
+  all_govids <- unique(c(target_govid, peer_govids))
+
+  r <- cog_spending(all_govids, years, category, per_capita, adjust_to_year)
+  r$role <- ifelse(r$canonical_govid == target_govid, "target", "peer")
+
+  value_col <- .peer_value_col(per_capita, adjust_to_year)
+
+  summary_rows <- .peer_summary_rows(r, value_col)
+  out <- dplyr::bind_rows(r, summary_rows)
+  rank_val <- .peer_target_rank(r, target_govid, years, value_col)
+  out$target_rank <- ifelse(out$role == "target", rank_val, NA_integer_)
+
+  prov <- attr(r, "provenance") %||% list()
+  prov$verb       <- "cog_peer_compare"
+  prov$call       <- paste(deparse(call), collapse = " ")
+  prov$peer_count <- length(peer_govids)
+  prov$target     <- list(
+    canonical_govid = target_govid,
+    gov_name        = unique(r$gov_name[r$role == "target"])
+  )
+  attr(out, "provenance") <- prov
+  out
+}
+
+#' @noRd
+.peer_value_col <- function(per_capita, adjust_to_year) {
+  if (!is.null(adjust_to_year)) {
+    if (isTRUE(per_capita)) "amt_per_capita_real" else "amt_real"
+  } else {
+    if (isTRUE(per_capita)) "amt_per_capita_nominal" else "amt_nominal"
+  }
+}
+
+#' @noRd
+.peer_summary_rows <- function(r, value_col) {
+  peer_rows <- r[r$role == "peer", , drop = FALSE]
+  if (nrow(peer_rows) == 0L) {
+    return(r[integer(0), , drop = FALSE])
+  }
+  s <- peer_rows |>
+    dplyr::group_by(.data$year, .data$spend_subtype, .data$category) |>
+    dplyr::reframe(
+      q     = c("p25", "p50", "p75"),
+      value = stats::quantile(
+        .data[[value_col]], c(0.25, 0.50, 0.75), na.rm = TRUE
+      )
+    )
+  s$role <- paste0("summary_", s$q)
+  s$gov_name <- dplyr::case_when(
+    s$q == "p25" ~ "Peer P25",
+    s$q == "p50" ~ "Peer median",
+    s$q == "p75" ~ "Peer P75",
+    TRUE         ~ NA_character_
+  )
+  s$canonical_govid <- NA_character_
+  out <- s[, c("year", "canonical_govid", "gov_name",
+               "spend_subtype", "category", "role")]
+  out[[value_col]] <- s$value
+  out
+}
+
+#' @noRd
+.peer_target_rank <- function(r, target_govid, years, value_col) {
+  if (nrow(r) == 0L) return(NA_integer_)
+  latest <- max(as.integer(years))
+  latest_rows <- r[r$year == latest &
+                   r$role %in% c("target", "peer"), , drop = FALSE]
+  if (nrow(latest_rows) == 0L) return(NA_integer_)
+  ranked <- dplyr::arrange(latest_rows, dplyr::desc(.data[[value_col]]))
+  tr <- which(ranked$canonical_govid == target_govid)[1]
+  if (length(tr) == 0L || is.na(tr)) NA_integer_ else as.integer(tr)
+}

R/zzz.R

@@ -4,6 +4,11 @@
   invisible(NULL)
 }
 
+# Silence R CMD check "no visible binding" for tidy-eval pronouns used in
+# dplyr verbs. `.data` comes from rlang and is guaranteed to resolve at
+# evaluation time inside dplyr data-masking contexts.
+utils::globalVariables(c(".data"))
+
 .onUnload <- function(libpath) {
   cog_close()
 }

man/cog_find_peers.Rd

@@ -0,0 +1,45 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/peers.R
+\name{cog_find_peers}
+\alias{cog_find_peers}
+\title{Find peer governments by similarity criteria}
+\usage{
+cog_find_peers(
+  target_govid,
+  same_type = TRUE,
+  same_state = FALSE,
+  pop_range = c(0.7, 1.3),
+  is_ratio = TRUE,
+  pop_year = NULL,
+  max_peers = 10L
+)
+}
+\arguments{
+\item{target_govid}{Character scalar — `canonical_govid` of the target.}
+
+\item{same_type}{If `TRUE` (default) restrict peers to the target's
+`govs_type`.}
+
+\item{same_state}{If `TRUE` restrict peers to the target's `fips_state`.
+Default `FALSE`.}
+
+\item{pop_range}{Length-2 numeric vector giving lower/upper bounds.}
+
+\item{is_ratio}{If `TRUE` (default) `pop_range` is multiplied by the
+target's `population_acs` to produce absolute bounds. If `FALSE`,
+`pop_range` is interpreted as absolute population counts.}
+
+\item{pop_year}{Reserved for future use (selecting ACS vintage). Currently
+the corpus has a single snapshot so this argument has no effect.}
+
+\item{max_peers}{Integer cap on the number of peers returned.}
+}
+\value{
+Tibble with columns `canonical_govid`, `gov_name`, `fips_state`,
+  `population_acs`, `pop_ratio`, `rank`.
+}
+\description{
+Selects peer governments from `canonical_fips_xwalk` by combinations of
+government type, state, and population range. Peers are ordered by
+`|log(pop_ratio)|` ascending (closest to the target's population first).
+}

man/cog_peer_compare.Rd

@@ -0,0 +1,44 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/peers.R
+\name{cog_peer_compare}
+\alias{cog_peer_compare}
+\title{Compare a target government against a peer set}
+\usage{
+cog_peer_compare(
+  target_govid,
+  peers,
+  category,
+  years,
+  per_capita = TRUE,
+  adjust_to_year = NULL
+)
+}
+\arguments{
+\item{target_govid}{Character scalar.}
+
+\item{peers}{A tibble from [cog_find_peers()] or a character vector of
+`canonical_govid`s.}
+
+\item{category}{Character scalar or vector.}
+
+\item{years}{Integer vector.}
+
+\item{per_capita}{Default `TRUE` — peer compare usually normalizes by
+population.}
+
+\item{adjust_to_year}{Integer base year for CPI-U conversion or `NULL`.}
+}
+\value{
+Tibble matching [cog_spending()]'s columns, plus a `role`
+  column taking values `"target"`, `"peer"`, `"summary_p25"`,
+  `"summary_p50"`, or `"summary_p75"`, and `target_rank` (target's rank
+  among target+peers at `max(years)`, NA for other rows). Provenance
+  attribute reports `verb = "cog_peer_compare"` and `peer_count`.
+}
+\description{
+Pulls spending for the target plus a peer set (either a
+[cog_find_peers()] result or a character vector of `canonical_govid`) and
+appends peer-distribution summary rows (`summary_p25`, `summary_p50`,
+`summary_p75`) so the result can be faceted by `role` in a single ggplot
+call.
+}

tests/testthat/test-peers.R

@@ -0,0 +1,90 @@
+test_that("cog_find_peers returns same-type peers in the default pop band", {
+  skip_if_no_corpus()
+  peers <- cog_find_peers("101006006")                # Broward County
+  expect_s3_class(peers, "tbl_df")
+  expected_cols <- c("canonical_govid", "gov_name", "fips_state",
+                     "population_acs", "pop_ratio", "rank")
+  expect_true(all(expected_cols %in% names(peers)))
+  expect_true(all(peers$pop_ratio >= 0.7 & peers$pop_ratio <= 1.3))
+  expect_false("101006006" %in% peers$canonical_govid)
+  expect_equal(peers$rank, seq_len(nrow(peers)))
+})
+
+test_that("cog_find_peers respects same_state restriction", {
+  skip_if_no_corpus()
+  peers <- cog_find_peers("101006006", same_state = TRUE,
+                          pop_range = c(0.1, 10))
+  expect_true(all(peers$fips_state == "12"))
+})
+
+test_that("cog_find_peers absolute pop range works", {
+  skip_if_no_corpus()
+  peers <- cog_find_peers("101006006",
+                          pop_range = c(1.5e6, 2.5e6),
+                          is_ratio = FALSE, max_peers = 20L)
+  expect_true(all(peers$population_acs >= 1.5e6 &
+                  peers$population_acs <= 2.5e6))
+})
+
+test_that("cog_find_peers errors cleanly on unknown govid", {
+  skip_if_no_corpus()
+  expect_error(cog_find_peers("XXXINVALID"), "not found")
+})
+
+test_that("cog_peer_compare accepts a cog_find_peers result directly", {
+  skip_if_no_corpus()
+  peers <- cog_find_peers("101006006", max_peers = 4L)
+  r <- cog_peer_compare("101006006", peers, "Police", years = 2020L)
+  expect_s3_class(r, "tbl_df")
+  expect_true("role" %in% names(r))
+  expect_setequal(
+    unique(r$role),
+    c("target", "peer", "summary_p25", "summary_p50", "summary_p75")
+  )
+  expect_equal(sum(r$role == "target" & r$spend_subtype == "operations"), 1L)
+})
+
+test_that("cog_peer_compare accepts a character vector of govids", {
+  skip_if_no_corpus()
+  r <- cog_peer_compare(
+    "101006006",
+    peers = c("441015015", "441220220"),     # Bexar, Tarrant
+    category = "Police", years = 2020L
+  )
+  expect_true("peer" %in% r$role)
+  expect_equal(sum(r$role == "peer" & r$spend_subtype == "operations"), 2L)
+})
+
+test_that("cog_peer_compare summary rows use real per-capita when requested", {
+  skip_if_no_corpus()
+  r <- cog_peer_compare(
+    "101006006",
+    peers = c("441015015", "441220220", "231082082"),
+    category = "Police", years = 2019:2020,
+    per_capita = TRUE, adjust_to_year = 2022L
+  )
+  summaries <- dplyr::filter(r, grepl("^summary_", role))
+  expect_true(all(is.finite(summaries$amt_per_capita_real)))
+  # summary rows have NA canonical_govid and named gov_name
+  expect_true(all(is.na(summaries$canonical_govid)))
+  expect_true(all(grepl("Peer", summaries$gov_name)))
+})
+
+test_that("cog_peer_compare provenance reports the outer verb + peer count", {
+  skip_if_no_corpus()
+  r <- cog_peer_compare("101006006",
+                        peers = c("441015015", "441220220"),
+                        category = "Police", years = 2020L)
+  prov <- attr(r, "provenance")
+  expect_equal(prov$verb, "cog_peer_compare")
+  expect_equal(prov$peer_count, 2L)
+})
+
+test_that("cog_peer_compare handles zero peers gracefully", {
+  skip_if_no_corpus()
+  r <- cog_peer_compare("101006006",
+                        peers = character(0),
+                        category = "Police", years = 2020L)
+  expect_true(all(r$role == "target"))
+  expect_equal(sum(grepl("^summary_", r$role)), 0L)
+})