Added an error for botstrap when Sample.Label not unique across strata

See issue #157
DistanceDevelopment · Dec 20, 2023 · b8d19d9 · b8d19d9
1 parent ce0c77d
commit b8d19d9
Show file tree

Hide file tree

Showing 4 changed files with 23 additions and 1 deletion.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -11,7 +11,7 @@ Description: A simple way of fitting detection functions to distance sampling
     Horvitz-Thompson-like estimator) if survey area information is provided. See
     Miller et al. (2019) <doi:10.18637/jss.v089.i01> for more information on
     methods and <https://examples.distancesampling.org/> for example analyses.
-Version: 1.0.8.9001
+Version: 1.0.8.9002
 URL: https://github.com/DistanceDevelopment/Distance/
 BugReports: https://github.com/DistanceDevelopment/Distance/issues
 Language: en-GB

diff --git a/NEWS b/NEWS
@@ -5,6 +5,7 @@ Distance 1.0.9
 * Fixed bug which produced NA's when stratum names came after 'Total' in the alphabet. (Issue #158)
 * Added additional documentation explaining the adjustment term options when covariates are in the model. (Issue #156)
 * Fixed dht bootstrap to work when distbegin and distend are supplied but not distance. (Issue #147)
+* Added a warning for the dht bootstrap when Sample.Label values are not unique across all strata. (Issue #157)
 
 Distance 1.0.8
 ----------------------

diff --git a/R/bootdht_resample_data.R b/R/bootdht_resample_data.R
@@ -18,6 +18,11 @@ bootdht_resample_data <- function(bootdat, our_resamples,
 
   # get all samples per stratum
   samps_per_strata <- unique(bf[, c(stratum_label, sample_label)])
+  # Check that the sampler names are unique across strata
+  # The number of unique sampler names should be the same as the rows in samps_per_strata
+  if(sample_label %in% our_resamples && !nrow(samps_per_strata) == length(unique(samps_per_strata[[sample_label]]))){
+    stop("Cannot bootstrap on samplers within strata as sampler ID values are not unique across strata. Please ensure all Sample.Label values are unique.", call. = FALSE)
+  }
   samps_per_strata <- by(bf[,c(stratum_label, sample_label)],
                          bf[[stratum_label]],
                          function(x) unique(x[[sample_label]]))

diff --git a/tests/testthat/test_bootdht.R b/tests/testthat/test_bootdht.R
@@ -171,4 +171,20 @@ test_that("Issue #158 is fixed (stratum names > 'Total' bug)", {
   set.seed(225)
   bootout <- bootdht(mod1, flatfile=minke,  nboot=3)
   expect_true(nrow(bootout) > 0)
+})
+
+
+# generate some data to test on
+dat <- data.frame(object = 1:60, Sample.Label = rep(1:10,6),
+                  Area = 100, Effort = 1000)
+dat$Region.Label <- c(rep("StrataA", 30), rep("StrataB", 30))
+dat$distance <- abs(rnorm(nrow(dat), 0, 25))
+dat$size <- rpois(nrow(dat), 20)
+dat$ref.object <- dat$object
+
+test_that("Error raised when sampler ID not unique", {
+
+  set.seed(123)
+  expect_error(bootdht_resample_data(dat, c("Sample.Label")), 
+               "Cannot bootstrap on samplers within strata as sampler ID values are not unique across strata. Please ensure all Sample.Label values are unique.")
 })