add error message for missing strata

DESCRIPTION

@@ -31,7 +31,8 @@ Imports:
     tidyr,
     utils,
     tidyselect,
-    cli
+    cli,
+    purrr
 Suggests:
     parallel,
     knitr,

R/est.incidence.by.R

@@ -1,14 +1,14 @@
 #' Estimate Seroincidence
 #'
 #' @description
 #' Function to estimate seroincidences based on cross-section serology data and longitudinal
 #' response model.
 #'
 #' @param pop_data a [data.frame] with cross-sectional serology data per antibody and age, and additional columns corresponding to each element of the `strata` input
 #' @param strata a [character] vector of stratum-defining variables. Values must be variable names in `pop_data`.
 #' @param curve_strata_varnames A subset of `strata`. Values must be variable names in `curve_params`. Default = "".
 #' @param noise_strata_varnames A subset of `strata`. Values must be variable names in `noise_params`. Default = "".
 #' @param num_cores Number of processor cores to use for calculations when computing by strata. If set to more than 1 and package \pkg{parallel} is available, then the computations are executed in parallel. Default = 1L.
 
 #' @details
 #'
@@ -17,7 +17,7 @@
 #' and then the data will be passed to [est.incidence()].
 #' If for some reason you want to use [est.incidence.by()]
 #' with no strata instead of calling [est.incidence()],
 #' you may use `NA`, `NULL`, or `""` as the `strata` argument to avoid that warning.
 #'
 #'
 #' @inheritParams est.incidence
@@ -26,7 +26,7 @@
 #'
 #' @return
 #' * if `strata` has meaningful inputs:
 #' An object of class `"seroincidence.by"`; i.e., a list of `"seroincidence"` objects from [est.incidence()], one for each stratum, with some meta-data attributes.
 #' * if `strata` is missing, `NULL`, `NA`, or `""`:
 #' An object of class `"seroincidence"`.
 #'
@@ -39,7 +39,7 @@
 #'
 #' curve <- load_curve_params("https://osf.io/download/rtw5k/") %>%
 #'   filter(antigen_iso %in% c("HlyE_IgA", "HlyE_IgG")) %>%
 #'   slice(1:100, .by = antigen_iso) # Reduce dataset for the purposes of this example
 #'
 #' noise <- load_noise_params("https://osf.io/download//hqy4v/")
 #'
@@ -49,13 +49,13 @@
 #'   curve_params = curve,
 #'   noise_params = noise %>% filter(Country == "Pakistan"),
 #'   antigen_isos = c("HlyE_IgG", "HlyE_IgA"),
-#'   #num_cores = 8 # Allow for parallel processing to decrease run time
+#'   # num_cores = 8 # Allow for parallel processing to decrease run time
 #'   iterlim = 5 # limit iterations for the purpose of this example
 #' )
 #'
 #' summary(est2)
 #'
 est.incidence.by <- function(
     pop_data,
     curve_params,
     noise_params,
@@ -101,6 +101,61 @@
     return(to_return)
   }
 
+  if (!all(is.element(strata, pop_data %>% names()))) {
+
+    # find strata with full match
+    present_vars <- purrr::map(.x = strata, .f = function(pattern) {
+      grep(
+        x = pop_data %>% names(),
+        value = TRUE,
+        pattern = paste0("^", pattern, "$"),
+        ignore.case = TRUE
+      )
+    }) %>%
+      purrr::keep(~ length(.x) > 0) %>%
+      unlist()
+
+     # find strata with partial matches
+    present_partial_vars <- purrr::keep(strata,
+       function(pattern) {
+       length(
+         grep(
+           pattern,
+           pop_data %>% names(),
+           ignore.case = TRUE)) > 0
+     }) %>%
+     setdiff(y = present_vars)
+
+    # get partial matches
+    partial_match <- purrr::map(.x = present_partial_vars, .f = function(pattern) {
+      grep(
+        x = pop_data %>% names(),
+        value = TRUE,
+        pattern = pattern,
+        ignore.case = TRUE
+      )
+    }) %>%
+      purrr::keep(~ length(.x) > 0) %>%
+      unlist()
+
+    # strata with no match
+    no_match_vars <- strata %>%
+      setdiff(pop_data %>% names()) %>%
+      setdiff(present_partial_vars)
+
+    cli::cli_abort(
+      class = "missing_var",
+      message = c(
+        "x" = "Can't stratify with the provided strata.",
+        "i" = "The {.var {no_match_vars}} option{?s} for `strata` {?is/are} missing in {.arg pop_data}.",
+        if(length(present_partial_vars) > 0){
+          c( "i" = "The {.var {present_partial_vars}} option for `strata` {?is/are} likely misspelled.",
+             "i" = "Did you mean {.var {partial_match}}?")
+        }
+      )
+    )
+  }
+
   .checkStrata(data = pop_data, strata = strata)
 
   .errorCheck(

tests/testthat/test-est.incidence.by.R

@@ -0,0 +1,54 @@
+
+library(dplyr)
+
+# get pop data
+xs_data <- load_pop_data(
+  file_path = "https://osf.io/download//n6cp3/",
+  age = "Age",
+  value = "result",
+  id = "index_id",
+  standardize = TRUE
+) %>%
+  filter(Country == "Pakistan") %>%
+  slice_head(n = 100)
+
+# get noise data
+noise <- load_noise_params("https://osf.io/download//hqy4v/") %>%
+  filter(Country == "Pakistan")
+
+# get curve data
+curve <- load_curve_params("https://osf.io/download/rtw5k/")
+
+test_that("est.incidence.by() aborts when strata is missing in `pop_data`", {
+
+  expect_error(
+    object = est.incidence.by(
+      strata = c("catch"),
+      pop_data = xs_data %>% filter(Country == "Pakistan"),
+      curve_params = curve,
+      noise_params = noise %>% filter(Country == "Pakistan"),
+      antigen_isos = c("HlyE_IgG", "HlyE_IgA"),
+      # num_cores = 8 # Allow for parallel processing to decrease run time
+      iterlim = 5 # limit iterations for the purpose of this example
+    ),
+    class = "missing_var"
+  )
+})
+
+test_that("est.incidence.by() aborts when multiple elements that don't exactly match the columns of `pop_data` are provided", {
+
+  expect_error(
+    object = est.incidence.by(
+      strata = c("catch","Count"),
+      pop_data = xs_data %>% filter(Country == "Pakistan"),
+      curve_params = curve,
+      noise_params = noise %>% filter(Country == "Pakistan"),
+      antigen_isos = c("HlyE_IgG", "HlyE_IgA"),
+      # num_cores = 8 # Allow for parallel processing to decrease run time
+      iterlim = 5 # limit iterations for the purpose of this example
+    ),
+    class = "missing_var"
+  )
+
+})
+