Add function to update hub format target data

.Rbuildignore

@@ -1 +1 @@
-^LICENSE\.md$
+^\.github$

.github/.gitignore

@@ -0,0 +1 @@
+*.html

.github/workflows/R-CMD-check.yaml

@@ -0,0 +1,53 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+name: R-CMD-check.yaml
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.ref }}
+  cancel-in-progress: true
+
+permissions: read-all
+
+jobs:
+  R-CMD-check:
+    runs-on: ${{ matrix.config.os }}
+
+    name: ${{ matrix.config.os }} (${{ matrix.config.r }})
+
+    strategy:
+      fail-fast: false
+      matrix:
+        config:
+          - {os: macos-latest,   r: 'release'}
+          - {os: windows-latest, r: 'release'}
+          - {os: ubuntu-latest,  r: 'release'}
+
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      R_KEEP_PKG_SOURCE: yes
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-pandoc@v2
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          r-version: ${{ matrix.config.r }}
+          http-user-agent: ${{ matrix.config.http-user-agent }}
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::rcmdcheck
+          needs: check
+
+      - uses: r-lib/actions/check-r-package@v2
+        with:
+          upload-snapshots: true
+          build_args: 'c("--no-manual","--compact-vignettes=gs+qpdf")'

.github/workflows/test-coverage.yaml

@@ -0,0 +1,62 @@
+# Workflow derived from https://github.com/r-lib/actions/tree/v2/examples
+# Need help debugging build failures? Start at https://github.com/r-lib/actions#where-to-find-help
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+
+name: test-coverage.yaml
+
+permissions: read-all
+
+jobs:
+  test-coverage:
+    runs-on: ubuntu-latest
+    env:
+      GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+
+      - uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          extra-packages: any::covr, any::xml2
+          needs: coverage
+
+      - name: Test coverage
+        run: |
+          cov <- covr::package_coverage(
+            quiet = FALSE,
+            clean = FALSE,
+            install_path = file.path(normalizePath(Sys.getenv("RUNNER_TEMP"), winslash = "/"), "package")
+          )
+          print(cov)
+          covr::to_cobertura(cov)
+        shell: Rscript {0}
+
+      - uses: codecov/codecov-action@v5
+        with:
+          # Fail if error if not on PR, or if on PR and token is given
+          fail_ci_if_error: ${{ github.event_name != 'pull_request' || secrets.CODECOV_TOKEN }}
+          files: ./cobertura.xml
+          plugins: noop
+          disable_search: true
+          token: ${{ secrets.CODECOV_TOKEN }}
+
+      - name: Show testthat output
+        if: always()
+        run: |
+          ## --------------------------------------------------------------------
+          find '${{ runner.temp }}/package' -name 'testthat.Rout*' -exec cat '{}' \; || true
+        shell: bash
+
+      - name: Upload test results
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-test-failures
+          path: ${{ runner.temp }}/package

.gitignore

@@ -379,3 +379,5 @@ docs/site/
 # such, it should not be committed for packages, but should be committed for
 # applications that require a static environment.
 #Manifest.toml
+
+/.quarto/

DESCRIPTION

@@ -17,9 +17,14 @@ Imports:
     glue,
     lubridate,
     readr,
-    stringr
+    stringr,
+    tidyselect
 Remotes:
-    forecasttools=github::cdcgov/forecasttools
+    forecasttools=github::cdcgov/forecasttools,
+    hubUtils=github::hubverse-org/hubUtils
 Suggests:
-    testthat (>= 3.0.0)
-Config/testthat/edition: 3
+    httptest2,
+    testthat (>= 3.0.0),
+    tibble,
+    withr,
+    purrr

NAMESPACE

@@ -1,3 +1,4 @@
 # Generated by roxygen2: do not edit by hand
 
+export(excluded_locations)
 export(update_hub_target_data)

R/constants.R

@@ -0,0 +1,4 @@
+#' Two digits FIPS codes for locations excluded from hubs' target data
+#'
+#' @export
+excluded_locations <- c("78", "74", "69", "66", "60")

R/update_hub_target_data.R

@@ -0,0 +1,118 @@
+nhsn_col_names <- list(
+  covid = "totalconfc19newadm",
+  rsv = "totalconfrsvnewadm"
+)
+nssp_col_names <- list(
+  covid = "percent_visits_covid",
+  rsv = "percent_visits_rsv"
+)
+
+#' Get and process target data for the hub
+#'
+#' This function pulls, formats and save NHSN and NSSP data for use in the hub.
+#'
+#' @param base_hub_path Path to the base hub directory.
+#' @param disease Disease name ("covid" or "rsv").
+#' @param as_of As-of date of the data pull. Default is the system date as determined by [lubridate::today()].
+#' @param excluded_locations Vector of location codes to exclude from the output.
+#' Default value `hubhelpr::excluded_locations`.
+#' @param nhsn_first_weekending_date First week-ending date to include for
+#' the NHSN dataset. Default value is "2024-11-09".
+#' @param legacy_file Logical. Whether to write legacy CSV output (default: FALSE).
+#'
+#' @return Writes `time-series.parquet` and optionally legacy csv target data files
+#' to the target-data directory in the hub.
+#' @export
+update_hub_target_data <- function(
+  base_hub_path,
+  disease,
+  as_of = lubridate::today(),
+  nhsn_first_weekending_date = lubridate::as_date("2024-11-09"),
+  excluded_locations = hubhelpr::excluded_locations,
+  legacy_file = FALSE
+) {
+  if (!disease %in% c("covid", "rsv")) {
+    stop("'disease' must be either 'covid' or 'rsv'")
+  }
+  output_dirpath <- fs::path(base_hub_path, "target-data")
+  fs::dir_create(output_dirpath)
+
+  nhsn_col_name <- nhsn_col_names[[disease]]
+  nssp_col_name <- nssp_col_names[[disease]]
+  hubverse_ts_req_cols <- c(
+    "date",
+    "observation",
+    "location",
+    "as_of",
+    "target"
+  )
+  nhsn_data <- forecasttools::pull_data_cdc_gov_dataset(
+    dataset = "nhsn_hrd_prelim",
+    columns = nhsn_col_name,
+    start_date = nhsn_first_weekending_date
+  ) |>
+    dplyr::mutate(
+      date = lubridate::as_date(.data$weekendingdate),
+      observation = as.numeric(.data[[nhsn_col_name]]),
+      jurisdiction = stringr::str_replace(.data$jurisdiction, "USA", "US"),
+      location = forecasttools::us_location_recode(
+        .data$jurisdiction,
+        "abbr",
+        "code"
+      ),
+      as_of = !!as_of,
+      target = glue::glue("wk inc {disease} hosp")
+    ) |>
+    dplyr::filter(!(.data$location %in% !!excluded_locations))
+
+  hubverse_format_nhsn_data <- nhsn_data |>
+    dplyr::select(tidyselect::all_of(hubverse_ts_req_cols))
+
+  if (legacy_file) {
+    legacy_file_name <- glue::glue(
+      "{disease}-hospital-admissions.csv"
+    )
+    nhsn_data |>
+      dplyr::rename(
+        value = "observation",
+        state = "jurisdiction"
+      ) |>
+      dplyr::arrange(state) |>
+      dplyr::select("state", "date", "value", "location") |>
+      readr::write_csv(
+        fs::path(output_dirpath, legacy_file_name)
+      )
+  }
+
+  hubverse_format_nssp_data <- forecasttools::pull_data_cdc_gov_dataset(
+    dataset = "nssp_prop_ed_visits",
+    columns = c(nssp_col_name, "geography"),
+    locations = "All"
+  ) |>
+    dplyr::mutate(
+      date = lubridate::as_date(.data$week_end),
+      observation = as.numeric(.data[[nssp_col_name]]) / 100,
+      location = forecasttools::us_location_recode(
+        .data$geography,
+        "name",
+        "code"
+      ),
+      as_of = !!as_of,
+      target = glue::glue("wk inc {disease} prop ed visits")
+    ) |>
+    dplyr::select(dplyr::all_of(hubverse_ts_req_cols)) |>
+    dplyr::arrange(date, location)
+
+  output_file <- fs::path(output_dirpath, "time-series", ext = "parquet")
+  if (fs::file_exists(output_file)) {
+    existing_data <- forecasttools::read_tabular_file(output_file)
+  } else {
+    existing_data <- NULL
+  }
+  dplyr::bind_rows(
+    existing_data,
+    hubverse_format_nhsn_data,
+    hubverse_format_nssp_data
+  ) |>
+    forecasttools::write_tabular_file(output_file)
+}

README.md

@@ -1,3 +1,7 @@
+<!-- badges: start -->
+[![R-CMD-check](https://github.com/CDCgov/hubhelpr/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/CDCgov/hubhelpr/actions/workflows/R-CMD-check.yaml)
+<!-- badges: end -->
+
 # hubhelpr
 
 ## Overview

tests/testthat.R

@@ -0,0 +1,12 @@
+# This file is part of the standard setup for testthat.
+# It is recommended that you do not modify it.
+#
+# Where should you do additional test configuration?
+# Learn more about the roles of various files in:
+# * https://r-pkgs.org/testing-design.html#sec-tests-files-overview
+# * https://testthat.r-lib.org/articles/special-files.html
+
+library(testthat)
+library(hubhelpr)
+
+test_check("hubhelpr")