feat: cog_balances() core verb (#25)

2026-08-03 10:01:40 -04:00
parent 825ac394f2
commit a281a9621f
5 changed files with 219 additions and 0 deletions
@@ -22,6 +22,7 @@ Imports:
    httr2,
    digest
 Suggests:
+    arrow,
    testthat (>= 3.0.0),
    withr,
    knitr,
@@ -1,5 +1,6 @@
 # Generated by roxygen2: do not edit by hand

+export(cog_balances)
 export(cog_basket_resolution)
 export(cog_basket_unresolved)
 export(cog_categories)
@@ -0,0 +1,98 @@
+# R/balances.R
+#
+# Cash and security holdings. A third verb rather than an argument on a money
+# verb because holdings are a STOCK -- a balance at a point in time -- while
+# cog_spending()/cog_revenue() return FLOWS over a fiscal year. The money
+# verbs' whole argument vocabulary (expenditure_concept, revenue_concept,
+# complete=) describes flows and is meaningless here, so this deliberately
+# does NOT route through .verb_spendrev().
+
+#' Cash and security holdings for one or more governments
+#'
+#' Returns Census cash-and-security holdings (`category_type = "balance"`):
+#' fund balances, retirement system holdings and insurance trust balances.
+#'
+#' @section Holdings are not GAAP fund balance:
+#' Census holdings are **gross** -- no liabilities are netted -- so a reserve
+#' ratio built from them overstates what is actually available. They are not
+#' comparable to a GAAP fund balance from an ACFR.
+#'
+#' @param govid Canonical govid(s): a character vector, or a data frame with a
+#'   `canonical_govid` column (e.g. from [cog_gov_search()]).
+#' @param years Integer vector of fiscal years.
+#' @param category Optional character vector of categories to keep. One of
+#'   `"Fund Balances"`, `"Insurance Trust Balances"`,
+#'   `"Retirement System Holdings"`. There is deliberately no `subtype`
+#'   argument: for holdings, `category` is a strict coarsening of
+#'   `balance_subtype` (unlike the money verbs, where the two axes cross), so
+#'   every combination would be either redundant or empty.
+#'   `category = "Fund Balances"` is exactly the `general` family
+#'   (`W01`/`W31`/`W61`). `balance_subtype` is returned, so a finer split is
+#'   one `dplyr::filter()` away.
+#' @param per_capita Divide holdings by population. Note this is a **stock per
+#'   resident** (reserves per person), which is *not* comparable to
+#'   [cog_spending()]'s per-capita figures -- those are a flow per person.
+#' @param adjust_to_year Deflate to this year's dollars (CPI-U).
+#' @param basis Accepted for uniformity with the money verbs, but currently a
+#'   **no-op**: `harmonization_map` carries no balance-code rows, so harmonized
+#'   and raw space are identical for holdings. Reported in
+#'   `provenance$basis_note`.
+#' @param recipe Optional harmonization recipe id (see [cog_recipes()]).
+#'   `"cash_securities_z77_wide"` and `"cash_securities_z78_wide"` bridge the
+#'   wide era to the modern one.
+#'
+#' @return A `tbl_df` with a `provenance` attribute. Amounts are full US
+#'   dollars.
+#' @export
+cog_balances <- function(govid, years, category = NULL,
+                         per_capita = FALSE, adjust_to_year = NULL,
+                         basis = c("harmonized", "raw"), recipe = NULL) {
+  call <- match.call()
+  basis <- match.arg(basis, c("harmonized", "raw"))
+  govid <- .coerce_govid_input(govid)
+  years <- as.integer(years)
+  if (!is.null(adjust_to_year)) adjust_to_year <- as.integer(adjust_to_year)
+
+  con <- .ensure_session()
+  .require_balance_support(con)
+  .check_govids_in_scope(govid)
+
+  basis_note <- paste0(
+    "`basis` has no effect on holdings: harmonization_map carries no ",
+    "balance-code rows, so harmonized and raw space are identical here."
+  )
+
+  sql <- .build_verb_sql("balance_annotated", "balance_subtype",
+                         govid, years, category,
+                         ig_view = NULL, subtype_scope = NULL)
+  result <- tibble::as_tibble(DBI::dbGetQuery(con, sql))
+
+  prov <- .build_provenance(
+    verb = "cog_balances", call = call, govid = govid, years = years,
+    category = category, per_capita = per_capita,
+    adjust_to_year = adjust_to_year, result = result, sql = sql,
+    subtype_col = "balance_subtype",
+    basis = basis, basis_note = basis_note,
+    # Neither concept vocabulary applies to a stock.
+    expenditure_concept = NA_character_,
+    revenue_concept = NA_character_
+  )
+
+  attr(result, "provenance") <- prov
+  result
+}
+
+#' Abort unless the mounted corpus classifies balance codes.
+#'
+#' `balance_subtype` arrived with cog_pipeline #76/#77 without a
+#' schema_version bump, so the check is on the column, not the version.
+#' @noRd
+.require_balance_support <- function(con) {
+  if (.corpus_has_balance_subtype(con)) return(invisible(TRUE))
+  cli::cli_abort(
+    c("This corpus does not classify cash and security holdings.",
+      i = "`summary_categories` has no {.field balance_subtype} column.",
+      i = "Republish from cog_pipeline at #76/#77 or later."),
+    class = "uscogdata_no_balance_support"
+  )
+}
@@ -0,0 +1,62 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/balances.R
+\name{cog_balances}
+\alias{cog_balances}
+\title{Cash and security holdings for one or more governments}
+\usage{
+cog_balances(
+  govid,
+  years,
+  category = NULL,
+  per_capita = FALSE,
+  adjust_to_year = NULL,
+  basis = c("harmonized", "raw"),
+  recipe = NULL
+)
+}
+\arguments{
+\item{govid}{Canonical govid(s): a character vector, or a data frame with a
+`canonical_govid` column (e.g. from [cog_gov_search()]).}
+
+\item{years}{Integer vector of fiscal years.}
+
+\item{category}{Optional character vector of categories to keep. One of
+`"Fund Balances"`, `"Insurance Trust Balances"`,
+`"Retirement System Holdings"`. There is deliberately no `subtype`
+argument: for holdings, `category` is a strict coarsening of
+`balance_subtype` (unlike the money verbs, where the two axes cross), so
+every combination would be either redundant or empty.
+`category = "Fund Balances"` is exactly the `general` family
+(`W01`/`W31`/`W61`). `balance_subtype` is returned, so a finer split is
+one `dplyr::filter()` away.}
+
+\item{per_capita}{Divide holdings by population. Note this is a **stock per
+resident** (reserves per person), which is *not* comparable to
+[cog_spending()]'s per-capita figures -- those are a flow per person.}
+
+\item{adjust_to_year}{Deflate to this year's dollars (CPI-U).}
+
+\item{basis}{Accepted for uniformity with the money verbs, but currently a
+**no-op**: `harmonization_map` carries no balance-code rows, so harmonized
+and raw space are identical for holdings. Reported in
+`provenance$basis_note`.}
+
+\item{recipe}{Optional harmonization recipe id (see [cog_recipes()]).
+`"cash_securities_z77_wide"` and `"cash_securities_z78_wide"` bridge the
+wide era to the modern one.}
+}
+\value{
+A `tbl_df` with a `provenance` attribute. Amounts are full US
+  dollars.
+}
+\description{
+Returns Census cash-and-security holdings (`category_type = "balance"`):
+fund balances, retirement system holdings and insurance trust balances.
+}
+\section{Holdings are not GAAP fund balance}{
+
+Census holdings are **gross** -- no liabilities are netted -- so a reserve
+ratio built from them overstates what is actually available. They are not
+comparable to a GAAP fund balance from an ACFR.
+}
+
@@ -97,3 +97,60 @@ test_that("balance views are skipped on a corpus without balance_subtype", {
    expect_true("revenue_long" %in% views)
  })
 })
+
+test_that("cog_balances returns holdings for a government that has them", {
+  skip_if_no_corpus()
+  with_fixture_corpus({
+    r <- cog_balances("550000227544", 2019)
+    expect_s3_class(r, "tbl_df")
+    expect_true(nrow(r) > 0L)
+    expect_true(all(c("year", "canonical_govid", "gov_name", "balance_subtype",
+                      "category", "amt_nominal") %in% names(r)))
+    expect_identical(sort(unique(r$category)),
+                     c("Fund Balances", "Insurance Trust Balances"))
+    expect_false(is.null(attr(r, "provenance")))
+    expect_identical(attr(r, "provenance")$verb, "cog_balances")
+  })
+})
+
+test_that('category = "Fund Balances" is exactly the general family', {
+  skip_if_no_corpus()
+  with_fixture_corpus({
+    r <- cog_balances("550000227544", 2019, category = "Fund Balances")
+    expect_identical(unique(r$balance_subtype), "general")
+    codes <- sort(unlist(strsplit(paste(r$codes_included, collapse = ","), ",")))
+    expect_identical(codes, c("W01", "W31", "W61"))
+  })
+})
+
+test_that("no flow code can reach cog_balances", {
+  skip_if_no_corpus()
+  with_fixture_corpus({
+    r <- cog_balances("550000227544", c(2011, 2012, 2019, 2020))
+    got <- unique(unlist(strsplit(paste(r$codes_included, collapse = ","), ",")))
+
+    # The expected set is read from the RAW corpus, never from the verb --
+    # verifying an absence through the filter that creates it proves nothing.
+    ds <- arrow::open_dataset(file.path(fixture_corpus_path(), "data", "long"))
+    sc <- arrow::read_parquet(
+      file.path(fixture_corpus_path(), "data", "summary_categories.parquet"))
+    sc <- as.data.frame(sc)
+    balance_codes <- sc$item_code[sc$category_type == "balance"]
+
+    expect_true(all(got %in% balance_codes))
+    expect_true(length(setdiff(got, balance_codes)) == 0L)
+  })
+})
+
+test_that("every balance_subtype maps to exactly one category", {
+  skip_if_no_corpus()
+  # Dropping the `subtype` argument is only safe while this tree holds. If the
+  # pipeline ever gives a balance subtype a second category, `category` becomes
+  # a lossy filter -- fail HERE rather than in a user's analysis.
+  sc <- as.data.frame(arrow::read_parquet(
+    file.path(fixture_corpus_path(), "data", "summary_categories.parquet")))
+  b <- sc[sc$category_type == "balance", ]
+  per_subtype <- tapply(b$category, b$balance_subtype,
+                        function(x) length(unique(x)))
+  expect_true(all(per_subtype == 1L))
+})