Issue 215: Merge main to spatial

.github/workflows/pkgdown.yaml

@@ -23,6 +23,8 @@ jobs:
       contents: write
       id-token: write
       pages: write
+    outputs:
+      page_artifact_id: ${{ steps.upload-artifact.outputs.artifact_id }}
     steps:
       - uses: actions/checkout@v4
 
@@ -52,6 +54,7 @@ jobs:
         shell: Rscript {0}
 
       - name: Upload artifact for GH pages deployment
+        id: upload-artifact
         uses: actions/upload-pages-artifact@v3
         with:
           path: "docs/"
@@ -72,3 +75,33 @@ jobs:
     steps:
       - name: Deploy to GitHub pages
         uses: actions/deploy-pages@v4
+
+  post-page-artifact:
+    # only comment on PRs
+    if: ${{ github.event_name == 'pull_request' }}
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+        contents: read
+        pull-requests: write
+    env:
+      GH_TOKEN: ${{ github.token }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Find Comment
+        uses: peter-evans/find-comment@v3
+        id: fc
+        with:
+           issue-number: ${{ github.event.pull_request.number }}
+           comment-author: 'github-actions[bot]'
+           body-includes: Your page is ready to preview
+
+      - name: Create or update comment
+        uses: peter-evans/create-or-update-comment@v4
+        with:
+          comment-id: ${{ steps.fc.outputs.comment-id }}
+          issue-number: ${{ github.event.pull_request.number }}
+          body: |
+            Thank you for your contribution, @${{ github.triggering_actor }} :rocket:! Your page is ready to preview [here](https://github.com/${{github.repository}}/actions/runs/${{ github.run_id }}/artifacts/${{ needs.build.outputs.page_artifact_id }})
+          edit-mode: replace

.github/workflows/r-cmd-check.yaml

@@ -7,13 +7,16 @@ on:
 
 jobs:
   check-package:
-    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        r-version: ["4.1.0", "release"]
+        os: [windows-latest, ubuntu-latest]
+    runs-on:  ${{matrix.os}}
     steps:
     - uses: actions/checkout@v4
-    - uses: actions/checkout@v4
     - uses: r-lib/actions/setup-r@v2
       with:
-        r-version: "release"
+        r-version: ${{matrix.r-version}}
         use-public-rspm: true
         extra-repositories: "https://mc-stan.org/r-packages/"
     - name: "Set up dependencies for wwinference"
@@ -24,6 +27,7 @@ jobs:
       uses: epinowcast/actions/install-cmdstan@v1
       with:
         cmdstan-version: "latest"
+        num-cores: 2
     - name: "Check wwinference package"
       uses: r-lib/actions/check-r-package@v2
       with:

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: wwinference
 Title: Jointly infers infection dynamics from wastewater data and epidemiological indicators
-Version: 0.0.0.9000
+Version: 0.1.0
 Authors@R: c(
     person(given = "Kaitlyn",
            family = "Johnson",
@@ -23,7 +23,7 @@ Authors@R: c(
            email = "[email protected]"),
     person(given = "George",
            family = "Vega Yon",
-           role = c("ctb"),
+           role = c("aut"),
            email = "[email protected]",
            comment = c(ORCID = "0000-0002-3171-0844")),
     person(given = "Damon",
@@ -37,7 +37,25 @@ Authors@R: c(
     person(given = "Scott",
            family = "Olesen",
            role = c("aut"),
-           email = "[email protected]")
+           email = "[email protected]"),
+    person(given = "Adam",
+           family = "Howes",
+           role = c("ctb"),
+           email = "[email protected]",
+           comment = c(ORCID = "0000-0003-2386-4031")),
+    person(given = "Chirag",
+           family = "Kumar",
+           role = c("ctb"),
+           email = "[email protected]"),
+    person(given = "Alexander",
+           family = "Keyel",
+           role = c("ctb"),
+           email = "[email protected]",
+           comment = c(ORCID = "000-0001-5256-6274")),
+    person(given = "Hannah",
+           family = "Cohen",
+           role = c("ctb"),
+           email = "[email protected]")
 	)
 Description: An implementation of a hierarchical semi-mechanistic renewal
     approach jointly calibrating to multiple wastewater concentrations datasets from
@@ -54,7 +72,7 @@ License: Apache License (>= 2)
 URL: https://github.com/cdcgov/ww-inference-model/, https://cdcgov.github.io/ww-inference-model/
 BugReports: https://github.com/cdcgov/ww-inference-model/issues/
 Depends:
-    R (>= 4.3.0)
+    R (>= 4.1.0)
 SystemRequirements: CmdStan (>=2.35.0)
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)

NAMESPACE

@@ -1,11 +1,13 @@
 # Generated by roxygen2: do not edit by hand
 
-S3method(get_draws_df,data.frame)
-S3method(get_draws_df,default)
-S3method(get_draws_df,wwinference_fit)
+S3method(get_draws,data.frame)
+S3method(get_draws,default)
+S3method(get_draws,wwinference_fit)
 S3method(get_model_diagnostic_flags,default)
 S3method(get_model_diagnostic_flags,wwinference_fit)
+S3method(plot,wwinference_fit_draws)
 S3method(print,wwinference_fit)
+S3method(print,wwinference_fit_draws)
 S3method(summary,wwinference_fit)
 export(add_pmfs)
 export(add_time_indexing)
@@ -20,10 +22,14 @@ export(generate_simulated_data)
 export(get_count_data_sizes)
 export(get_count_indices)
 export(get_count_values)
+export(get_date_time_spine)
+export(get_draws)
 export(get_draws_df)
 export(get_ind_m)
 export(get_input_count_data_for_stan)
 export(get_input_ww_data_for_stan)
+export(get_lab_site_site_spine)
+export(get_lab_site_subpop_spine)
 export(get_mcmc_options)
 export(get_model_diagnostic_flags)
 export(get_model_spec)
@@ -32,18 +38,18 @@ export(get_plot_forecasted_counts)
 export(get_plot_global_rt)
 export(get_plot_subpop_rt)
 export(get_plot_ww_conc)
+export(get_site_subpop_spine)
 export(get_stan_data)
-export(get_subpop_data)
-export(get_ww_data_indices)
 export(get_ww_data_sizes)
-export(get_ww_values)
+export(get_ww_indices_and_values)
 export(independence_corr_func_r)
 export(indicate_ww_exclusions)
 export(parameter_diagnostics)
 export(preprocess_count_data)
 export(preprocess_ww_data)
 export(rand_corr_matrix_func)
 export(spatial_rt_process)
+export(summary_diagnostics)
 export(to_simplex)
 export(validate_paramlist)
 export(wwinference)

NEWS.md

@@ -1,5 +1,4 @@
-# wwinference 0.0.1 (dev)
-
+# wwinference 0.1.0
 
 This is the first major release, focused on providing an initial version of the package.
 Note the package is still flagged as in development, though the authors plan on using it for production work in the coming weeks.

R/checkers.R

@@ -13,19 +13,26 @@
 #' @param date_vector vector of dates
 #' @param max_date string indicating the maximum date in ISO8601 convention
 #' e.g. YYYY-MM-DD
+#' @param arg_dates string to print the name of the data you are checking the
+#' dates for
+#' @param arg_max_date string to print the name of the maximum date you are
+#' checkign the data for
 #' @param call Calling environment to be passed to [cli::cli_abort()] for
 #' traceback.
 #'
 #' @return NULL, invisibly
 assert_no_dates_after_max <- function(date_vector,
-                                      max_date, call = rlang::caller_env()) {
+                                      max_date,
+                                      arg_dates = "y",
+                                      arg_max_date = "x",
+                                      call = rlang::caller_env()) {
   if (max(date_vector) > max_date) {
     cli::cli_abort(
       c(
-        "The data passed in has observations beyond the specified",
-        "maximum date. Either this is the incorrect vintaged",
-        "data, or the data needs to be filtered to only contain",
-        "observations before the maximum date"
+        "The {.arg_dates {arg_dates}} passed in has observations after the ",
+        "specified {.arg_max_date {arg_max_date}}. Check that this is the ",
+        "dataset you intended to use with the given ",
+        "{.arg_max_date {arg_max_date}}."
       ),
       call = call,
       class = "wwinference_input_data_error"
@@ -211,6 +218,46 @@ assert_no_repeated_elements <- function(x, arg = "x",
   invisible()
 }
 
+#' Check a set of columns in a data frame uniquely identify
+#' data frame rows.
+#'
+#' @description
+#' Equivalently, this checks that when grouping by the columns in question,
+#' each group has a single entry
+#'
+#' @param df the dataframe to check
+#' @param unique_key_columns Columns that, taken together, should
+#' uniquely identify a row in the data frame.
+#' @param arg the name of the unique grouping to check
+#' @param call Calling environment to be passed to [cli::cli_abort()] for
+#' traceback.
+#' @param add_err_msg string containing an additional error message,
+#' default is the empty string (`""`)
+#'
+#' @return NULL, invisibly
+assert_cols_det_unique_row <- function(df,
+                                       unique_key_columns,
+                                       arg = "x",
+                                       call = rlang::caller_env(),
+                                       add_err_msg = "") {
+  duplicated_rows <- df |> dplyr::filter(dplyr::n() > 1,
+    .by = {{ unique_key_columns }}
+  )
+
+  if (nrow(duplicated_rows) != 0) {
+    cli::cli_abort(
+      c("The data has more than one observation per {.arg {arg}}",
+        add_err_msg,
+        "i" = "Multiple observations in a {.arg {arg}} are not",
+        "currently supported."
+      ),
+      call = call,
+      class = "wwinference_input_data_error"
+    )
+  }
+  invisible()
+}
+
 
 
 #' Assert that a vector is either of a vector of integers or a vector of
@@ -347,19 +394,15 @@ assert_req_ww_cols_present <- function(ww_data,
 #' traceback.
 #'
 #' @return NULL, invisibly
-check_req_count_cols_present <- function(count_data,
-                                         count_col_name,
-                                         pop_size_col_name,
-                                         add_req_col_names = c("date"),
-                                         call = rlang::caller_env()) {
+assert_req_count_cols_present <- function(count_data,
+                                          count_col_name,
+                                          pop_size_col_name,
+                                          add_req_col_names = c("date"),
+                                          call = rlang::caller_env()) {
   column_names <- colnames(count_data)
   expected_col_names <- c(
-    {
-      count_col_name
-    },
-    {
-      pop_size_col_name
-    },
+    count_col_name,
+    pop_size_col_name,
     add_req_col_names
   )
 
@@ -491,6 +534,9 @@ assert_daily_data <- function(dates,
 #' calibration time
 #'
 #' @param date_vector the vector of dates to check, must be of Date type
+#' @param data_name What data correspond to the dates in `date_vector`.
+#' Used to make the error message informative (e.g.
+#' "hospital admissions data")
 #' @param calibration_time integer indicating the number of days that
 #' the dates must span
 #' @param call Calling environment to be passed to [cli::cli_abort()] for
@@ -500,6 +546,7 @@ assert_daily_data <- function(dates,
 #'
 #' @return NULL invisible
 assert_sufficient_days_of_data <- function(date_vector,
+                                           data_name,
                                            calibration_time,
                                            call = rlang::caller_env(),
                                            add_err_msg = "") {
@@ -511,7 +558,8 @@ assert_sufficient_days_of_data <- function(date_vector,
   if (!check_sufficient_data) {
     cli::cli_abort(
       c(
-        "Insufficient data for specified calibration time"
+        "Insufficient {.arg {data_name}} for the specified calibration time. ",
+        add_err_msg
       ),
       call = call,
       class = "wwinference_specification_error"
@@ -540,9 +588,8 @@ assert_dates_within_frame <- function(dates1,
   checkmate::assert_date(dates1)
   checkmate::assert_date(dates2)
   check_dates2_win_frame <- min(dates1) <= max(dates2) &
-    min(dates2) >= min(dates1) &
-    max(dates2) <= max_date &
-    max(dates1) <= max_date
+    min(dates2) <= max(dates1)
+
   if (!check_dates2_win_frame) {
     cli::cli_abort(
       c(
@@ -556,6 +603,8 @@ assert_dates_within_frame <- function(dates1,
 
   invisible()
 }
+
+
 #' Assert that two tibbles of date and time mapping align
 #'
 #' @param first_data a tibble containing the columns `date` (with IS08601