(v2.1.1.9129) unit test fix

DESCRIPTION

@@ -1,5 +1,5 @@
 Package: AMR
-Version: 2.1.1.9128
+Version: 2.1.1.9129
 Date: 2025-01-27
 Title: Antimicrobial Resistance Data Analysis
 Description: Functions to simplify and standardise antimicrobial resistance (AMR)
@@ -46,6 +46,7 @@ Suggests:
   rmarkdown,
   rvest,
   skimr,
+  testthat,
   tibble,
   tidymodels,
   tidyselect,

NEWS.md

@@ -1,4 +1,4 @@
-# AMR 2.1.1.9128
+# AMR 2.1.1.9129
 
 *(this beta version will eventually become v3.0. We're happy to reach a new major milestone soon, which will be all about the new One Health support! Install this beta using [the instructions here](https://msberends.github.io/AMR/#latest-development-version).)*
 

PythonPackage/AMR/AMR.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: AMR
-Version: 2.1.1.9128
+Version: 2.1.1.9129
 Summary: A Python wrapper for the AMR R package
 Home-page: https://github.com/msberends/AMR
 Author: Matthijs Berends

PythonPackage/AMR/AMR/datasets.py

@@ -1,7 +1,3 @@
-BLUE = '\033[94m'
-GREEN = '\033[32m'
-RESET = '\033[0m'
-
 import os
 import sys
 from rpy2 import robjects
@@ -17,18 +13,22 @@ venv_path = sys.prefix
 r_lib_path = os.path.join(venv_path, "R_libs")
 # Ensure the R library path exists
 os.makedirs(r_lib_path, exist_ok=True)
-# Set the R library path in .libPaths
-base = importr('base')
-# Turn off warnings
-base.options(warn = -1)
 
-base._libPaths(r_lib_path)
+# Import base and utils
+base = importr('base')
+utils = importr('utils')
+
+# Override R library paths globally for the session
+robjects.r(f'.Library <- "{r_lib_path}"')  # Replace default library
+robjects.r(f'.Library.site <- "{r_lib_path}"')  # Replace site-specific library
+base._libPaths(r_lib_path)  # Override .libPaths() as well
+
+# Get the effective library path
 r_amr_lib_path = base._libPaths()[0]
 
 # Check if the AMR package is installed in R
-if not isinstalled('AMR', lib_loc = r_amr_lib_path):
-    utils = importr('utils')
-    print(f"{BLUE}AMR:{RESET} Installing AMR package to {BLUE}{r_amr_lib_path}/{RESET}...", flush=True)
+if not isinstalled('AMR', lib_loc=r_amr_lib_path):
+    print(f"AMR: Installing latest AMR R package to {r_amr_lib_path}...", flush=True)
     utils.install_packages('AMR', repos='https://msberends.r-universe.dev', quiet=True)
 
 # Python package version of AMR
@@ -43,16 +43,12 @@ r_amr_version = robjects.r(f'as.character(packageVersion("AMR", lib.loc = "{r_li
 # Compare R and Python package versions
 if r_amr_version != python_amr_version:
     try:
-        print(f"{BLUE}AMR:{RESET} Updating AMR package in {BLUE}{r_amr_lib_path}/{RESET}...", flush=True)
-        utils = importr('utils')
+        print(f"AMR: Updating AMR package in {r_amr_lib_path}...", flush=True)
         utils.install_packages('AMR', repos='https://msberends.r-universe.dev', quiet=True)
     except Exception as e:
-        print(f"{BLUE}AMR:{RESET} Could not update: {e}{RESET}", flush=True)
+        print(f"AMR: Could not update: {e}", flush=True)
 
-# Restore warnings to default
-base.options(warn = 0)
-
-print(f"{BLUE}AMR:{RESET} Setting up R environment and AMR datasets...", flush=True)
+print(f"AMR: Setting up R environment and AMR datasets...", flush=True)
 
 # Activate the automatic conversion between R and pandas DataFrames
 pandas2ri.activate()
@@ -77,4 +73,4 @@ microorganisms = pandas2ri.rpy2py(robjects.r('AMR::microorganisms[, !sapply(AMR:
 antibiotics = pandas2ri.rpy2py(robjects.r('AMR::antibiotics[, !sapply(AMR::antibiotics, is.list)]'))
 clinical_breakpoints = pandas2ri.rpy2py(robjects.r('AMR::clinical_breakpoints[, !sapply(AMR::clinical_breakpoints, is.list)]'))
 
-print(f"{BLUE}AMR:{RESET} {GREEN}Done.{RESET}", flush=True)
+print(f"AMR: Done.", flush=True)

PythonPackage/AMR/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name='AMR',
-    version='2.1.1.9128',
+    version='2.1.1.9129',
     packages=find_packages(),
     install_requires=[
         'rpy2',

R/aa_globals.R

@@ -165,6 +165,7 @@ globalVariables(c(
   "lang",
   "language",
   "lookup",
+  "lower",
   "method",
   "mic ",
   "mic",
@@ -198,6 +199,7 @@ globalVariables(c(
   "total",
   "txt",
   "type",
+  "upper",
   "uti_index",
   "value",
   "varname",

R/antibiogram.R

@@ -60,7 +60,7 @@
 #' 
 #' For estimating antimicrobial coverage, especially when creating a WISCA, the outcome might become more reliable by only including the top *n* species encountered in the data. You can filter on this top *n* using [top_n_microorganisms()]. For example, use `top_n_microorganisms(your_data, n = 10)` as a pre-processing step to only include the top 10 species in the data.
 #' 
-#' The numeric values of an antibiogram are stored in a long format as the [attribute] `long_numeric`. You can retrieve them using `attributes(x)$long_numeric`, where `x` is the outcome of [antibiogram()] or [wisca()]. This is ideal for e.g. advanced plotting.
+#' The numeric values of an antibiogram are stored in a long format as the [attribute][attributes()] `long_numeric`. You can retrieve them using `attributes(x)$long_numeric`, where `x` is the outcome of [antibiogram()] or [wisca()]. This is ideal for e.g. advanced plotting.
 #' 
 #' ### Formatting Type
 #' 

R/bug_drug_combinations.R

@@ -36,6 +36,7 @@
 #' @param remove_intrinsic_resistant [logical] to indicate that rows and columns with 100% resistance for all tested antimicrobials must be removed from the table
 #' @param FUN the function to call on the `mo` column to transform the microorganism codes - the default is [mo_shortname()]
 #' @param translate_ab a [character] of length 1 containing column names of the [antibiotics] data set
+#' @param include_n_rows a [logical] to indicate if the total number of rows must be included in the output
 #' @param ... arguments passed on to `FUN`
 #' @inheritParams sir_df
 #' @inheritParams base::formatC
@@ -182,8 +183,8 @@ bug_drug_combinations <- function(x,
     out <- out[, colnames(out)[colnames(out) != "total_rows"], drop = FALSE]
   }
   
-  out <- out %pm>% pm_arrange(mo, ab)
   out <- as_original_data_class(out, class(x.bak)) # will remove tibble groups
+  out <- out %pm>% pm_arrange(mo, ab)
   rownames(out) <- NULL
   structure(out, class = c("bug_drug_combinations", if(data_has_groups) "grouped" else NULL, class(out)))
 }

R/ggplot_pca.R

@@ -261,7 +261,7 @@ ggplot_pca <- function(x,
         type = "open"
       ),
       colour = arrows_colour,
-      size = arrows_size,
+      linewidth = arrows_size,
       alpha = arrows_alpha
     )
     if (arrows_textangled == TRUE) {

R/top_n_microorganisms.R

@@ -36,7 +36,7 @@
 #' @param n_for_each an optional integer specifying the maximum number of rows to retain for each value of the selected property. If `NULL`, all rows within the top *n* groups will be included.
 #' @param col_mo A character string indicating the column in `x` that contains microorganism names or codes. Defaults to the first column of class [`mo`]. Values will be coerced using [as.mo()].
 #' @param ... Additional arguments passed on to [mo_property()] when `property` is not `NULL`.
-#' @details This function is useful for preprocessing data before creating [antibiograms][antibiograms()] or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
+#' @details This function is useful for preprocessing data before creating [antibiograms][antibiogram()] or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
 #' @export
 #' @seealso [mo_property()], [as.mo()], [antibiogram()]
 #' @examples

data-raw/_generate_python_wrapper.sh

@@ -42,10 +42,6 @@ description_file="../DESCRIPTION"
 
 # Write header to the datasets Python file, including the convert_to_python function
 cat <<EOL > "$datasets_file"
-BLUE = '\033[94m'
-GREEN = '\033[32m'
-RESET = '\033[0m'
-
 import os
 import sys
 from rpy2 import robjects
@@ -61,18 +57,22 @@ venv_path = sys.prefix
 r_lib_path = os.path.join(venv_path, "R_libs")
 # Ensure the R library path exists
 os.makedirs(r_lib_path, exist_ok=True)
-# Set the R library path in .libPaths
-base = importr('base')
-# Turn off warnings
-base.options(warn = -1)
 
-base._libPaths(r_lib_path)
+# Import base and utils
+base = importr('base')
+utils = importr('utils')
+
+# Override R library paths globally for the session
+robjects.r(f'.Library <- "{r_lib_path}"')  # Replace default library
+robjects.r(f'.Library.site <- "{r_lib_path}"')  # Replace site-specific library
+base._libPaths(r_lib_path)  # Override .libPaths() as well
+
+# Get the effective library path
 r_amr_lib_path = base._libPaths()[0]
 
 # Check if the AMR package is installed in R
-if not isinstalled('AMR', lib_loc = r_amr_lib_path):
-    utils = importr('utils')
-    print(f"{BLUE}AMR:{RESET} Installing AMR package to {BLUE}{r_amr_lib_path}/{RESET}...", flush=True)
+if not isinstalled('AMR', lib_loc=r_amr_lib_path):
+    print(f"AMR: Installing latest AMR R package to {r_amr_lib_path}...", flush=True)
     utils.install_packages('AMR', repos='https://msberends.r-universe.dev', quiet=True)
 
 # Python package version of AMR
@@ -87,16 +87,12 @@ r_amr_version = robjects.r(f'as.character(packageVersion("AMR", lib.loc = "{r_li
 # Compare R and Python package versions
 if r_amr_version != python_amr_version:
     try:
-        print(f"{BLUE}AMR:{RESET} Updating AMR package in {BLUE}{r_amr_lib_path}/{RESET}...", flush=True)
-        utils = importr('utils')
+        print(f"AMR: Updating AMR package in {r_amr_lib_path}...", flush=True)
         utils.install_packages('AMR', repos='https://msberends.r-universe.dev', quiet=True)
     except Exception as e:
-        print(f"{BLUE}AMR:{RESET} Could not update: {e}{RESET}", flush=True)
+        print(f"AMR: Could not update: {e}", flush=True)
 
-# Restore warnings to default
-base.options(warn = 0)
-
-print(f"{BLUE}AMR:{RESET} Setting up R environment and AMR datasets...", flush=True)
+print(f"AMR: Setting up R environment and AMR datasets...", flush=True)
 
 # Activate the automatic conversion between R and pandas DataFrames
 pandas2ri.activate()
@@ -121,7 +117,7 @@ microorganisms = pandas2ri.rpy2py(robjects.r('AMR::microorganisms[, !sapply(AMR:
 antibiotics = pandas2ri.rpy2py(robjects.r('AMR::antibiotics[, !sapply(AMR::antibiotics, is.list)]'))
 clinical_breakpoints = pandas2ri.rpy2py(robjects.r('AMR::clinical_breakpoints[, !sapply(AMR::clinical_breakpoints, is.list)]'))
 
-print(f"{BLUE}AMR:{RESET} {GREEN}Done.{RESET}", flush=True)
+print(f"AMR: Done.", flush=True)
 EOL
 
 echo "from .datasets import example_isolates" >> $init_file

data-raw/gpt_training_text_v2.1.1.9129.txt

@@ -1,5 +1,5 @@
 This files contains all context you must know about the AMR package for R.
-First and foremost, you are trained on version 2.1.1.9128. Remember this whenever someone asks which AMR package version you’re at.
+First and foremost, you are trained on version 2.1.1.9129. Remember this whenever someone asks which AMR package version you’re at.
 --------------------------------
 
 THE PART HEREAFTER CONTAINS CONTENTS FROM FILE 'NAMESPACE':
@@ -1705,7 +1705,7 @@ This function returns a table with values between 0 and 100 for \emph{susceptibi
 
 For estimating antimicrobial coverage, especially when creating a WISCA, the outcome might become more reliable by only including the top \emph{n} species encountered in the data. You can filter on this top \emph{n} using \code{\link[=top_n_microorganisms]{top_n_microorganisms()}}. For example, use \code{top_n_microorganisms(your_data, n = 10)} as a pre-processing step to only include the top 10 species in the data.
 
-The numeric values of an antibiogram are stored in a long format as the \link{attribute} \code{long_numeric}. You can retrieve them using \code{attributes(x)$long_numeric}, where \code{x} is the outcome of \code{\link[=antibiogram]{antibiogram()}} or \code{\link[=wisca]{wisca()}}. This is ideal for e.g. advanced plotting.
+The numeric values of an antibiogram are stored in a long format as the \link[=attributes]{attribute} \code{long_numeric}. You can retrieve them using \code{attributes(x)$long_numeric}, where \code{x} is the outcome of \code{\link[=antibiogram]{antibiogram()}} or \code{\link[=wisca]{wisca()}}. This is ideal for e.g. advanced plotting.
 \subsection{Formatting Type}{
 
 The formatting of the 'cells' of the table can be set with the argument \code{formatting_type}. In these examples, \code{5} is the susceptibility percentage (for WISCA: \code{4-6} indicates the confidence level), \code{15} the numerator, and \code{300} the denominator:
@@ -3900,6 +3900,8 @@ bug_drug_combinations(x, col_mo = NULL, FUN = mo_shortname,
 
 \item{FUN}{the function to call on the \code{mo} column to transform the microorganism codes - the default is \code{\link[=mo_shortname]{mo_shortname()}}}
 
+\item{include_n_rows}{a \link{logical} to indicate if the total number of rows must be included in the output}
+
 \item{...}{arguments passed on to \code{FUN}}
 
 \item{translate_ab}{a \link{character} of length 1 containing column names of the \link{antibiotics} data set}
@@ -8027,7 +8029,7 @@ top_n_microorganisms(x, n, property = "fullname", n_for_each = NULL,
 This function filters a data set to include only the top \emph{n} microorganisms based on a specified property, such as taxonomic family or genus. For example, it can filter a data set to the top 3 species, or to any species in the top 5 genera, or to the top 3 species in each of the top 5 genera.
 }
 \details{
-This function is useful for preprocessing data before creating \link[=antibiograms]{antibiograms} or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
+This function is useful for preprocessing data before creating \link[=antibiogram]{antibiograms} or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
 }
 \examples{
 # filter to the top 3 species:

data-raw/reproduction_of_microorganisms.R

@@ -2210,6 +2210,6 @@ devtools::load_all(".")
 
 # run the unit tests
 Sys.setenv(NOT_CRAN = "true")
-testthat::test_file("inst/tinytest/test-data.R")
-testthat::test_file("inst/tinytest/test-mo.R")
-testthat::test_file("inst/tinytest/test-mo_property.R")
+testthat::test_file("inst/tests/testthat/test-data.R")
+testthat::test_file("inst/tests/testthat/test-mo.R")
+testthat::test_file("inst/tests/testthat/test-mo_property.R")

inst/tests/test-_misc.R

@@ -27,6 +27,15 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
+tryCatch(!is.function(expect_stout), error = function(e) TRUE) {
+  expect_stout <<- testthat::expect_output
+}
+tryCatch(!is.function(expect_inherits), error = function(e) TRUE) {
+  expect_inherits <<- function(x, y, ...) testthat::expect(inherits(x, y),
+                                                          failure_message = paste0("Expected class ", paste(y, collapse = "/"),
+                                                                                   ", got class ", paste(class(x), collapse = "/")))
+}
+
 expect_equal(AMR:::percentage(0.25), "25%")
 expect_equal(AMR:::percentage(0.5), "50%")
 expect_equal(AMR:::percentage(0.500, digits = 1), "50.0%")

inst/tests/test-ggplot_sir.R

@@ -44,12 +44,14 @@ if (AMR:::pkg_is_available("dplyr", min_version = "1.0.0", also_load = TRUE) &&
       as.double()
   )
   
-  expect_stdout(print(example_isolates %>%
-    select(AMC, CIP) %>%
-    ggplot_sir(x = "interpretation", facet = "antibiotic")))
-  expect_stdout(print(example_isolates %>%
-    select(AMC, CIP) %>%
-    ggplot_sir(x = "antibiotic", facet = "interpretation")))
+  expect_inherits(example_isolates %>%
+                    select(AMC, CIP) %>%
+                    ggplot_sir(x = "interpretation", facet = "antibiotic"),
+                  "gg")
+  expect_inherits(example_isolates %>%
+                    select(AMC, CIP) %>%
+                    ggplot_sir(x = "antibiotic", facet = "interpretation"),
+                  "gg")
 
   expect_equal(
     (example_isolates %>%

man/antibiogram.Rd

@@ -100,7 +100,7 @@ This function returns a table with values between 0 and 100 for \emph{susceptibi
 
 For estimating antimicrobial coverage, especially when creating a WISCA, the outcome might become more reliable by only including the top \emph{n} species encountered in the data. You can filter on this top \emph{n} using \code{\link[=top_n_microorganisms]{top_n_microorganisms()}}. For example, use \code{top_n_microorganisms(your_data, n = 10)} as a pre-processing step to only include the top 10 species in the data.
 
-The numeric values of an antibiogram are stored in a long format as the \link{attribute} \code{long_numeric}. You can retrieve them using \code{attributes(x)$long_numeric}, where \code{x} is the outcome of \code{\link[=antibiogram]{antibiogram()}} or \code{\link[=wisca]{wisca()}}. This is ideal for e.g. advanced plotting.
+The numeric values of an antibiogram are stored in a long format as the \link[=attributes]{attribute} \code{long_numeric}. You can retrieve them using \code{attributes(x)$long_numeric}, where \code{x} is the outcome of \code{\link[=antibiogram]{antibiogram()}} or \code{\link[=wisca]{wisca()}}. This is ideal for e.g. advanced plotting.
 \subsection{Formatting Type}{
 
 The formatting of the 'cells' of the table can be set with the argument \code{formatting_type}. In these examples, \code{5} is the susceptibility percentage (for WISCA: \code{4-6} indicates the confidence level), \code{15} the numerator, and \code{300} the denominator:

man/bug_drug_combinations.Rd

@@ -21,6 +21,8 @@ bug_drug_combinations(x, col_mo = NULL, FUN = mo_shortname,
 
 \item{FUN}{the function to call on the \code{mo} column to transform the microorganism codes - the default is \code{\link[=mo_shortname]{mo_shortname()}}}
 
+\item{include_n_rows}{a \link{logical} to indicate if the total number of rows must be included in the output}
+
 \item{...}{arguments passed on to \code{FUN}}
 
 \item{translate_ab}{a \link{character} of length 1 containing column names of the \link{antibiotics} data set}

man/top_n_microorganisms.Rd

@@ -24,7 +24,7 @@ top_n_microorganisms(x, n, property = "fullname", n_for_each = NULL,
 This function filters a data set to include only the top \emph{n} microorganisms based on a specified property, such as taxonomic family or genus. For example, it can filter a data set to the top 3 species, or to any species in the top 5 genera, or to the top 3 species in each of the top 5 genera.
 }
 \details{
-This function is useful for preprocessing data before creating \link[=antibiograms]{antibiograms} or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
+This function is useful for preprocessing data before creating \link[=antibiogram]{antibiograms} or other analyses that require focused subsets of microbial data. For example, it can filter a data set to only include isolates from the top 10 species.
 }
 \examples{
 # filter to the top 3 species:

tests/tinytest.R

@@ -27,21 +27,25 @@
 # how to conduct AMR data analysis: https://msberends.github.io/AMR/   #
 # ==================================================================== #
 
-# we use {tinytest} instead of {testthat} because it does not rely on recent R versions - we want to test on R >= 3.0.
+# we use {tinytest} for older R versions to allow unit testing in R >= 3.0.0.
 
-# Run them in RStudio using:
-# rstudioapi::jobRunScript("tests/tinytest.R", name = "AMR Unit Tests", workingDir = getwd(), exportEnv = "tinytest_results")
+# use this to quickly use testtthat for more informative errors:
+# testthat::test_dir("inst/tests")
 
-# test only on GitHub Actions and at using RStudio jobs - not on CRAN as tests are lengthy
-if (tryCatch(isTRUE(AMR:::import_fn("isJob", "rstudioapi")()), error = function(e) FALSE) ||
-  identical(Sys.getenv("R_RUN_TINYTEST"), "true")) {
-  # env var 'R_LIBS_USER' got overwritten during 'R CMD check' in GitHub Actions, so:
+# test only on GitHub Actions - not on CRAN as tests are lengthy
+if (identical(Sys.getenv("R_RUN_TINYTEST"), "true")) {
+  # env var 'R_LIBS_USER' gets overwritten during 'R CMD check' in GitHub Actions, so:
   .libPaths(c(Sys.getenv("R_LIBS_USER_GH_ACTIONS"), .libPaths()))
+  
   if (AMR:::pkg_is_available("tinytest", also_load = TRUE)) {
+    
+    # load the package
     library(AMR)
+    
     # set language
     set_AMR_locale("English")
-    # set some functions if on old R
+    
+    # set some functions for older R versions
     if (getRversion() < "3.2.0") {
       anyNA <- AMR:::anyNA
       dir.exists <- AMR:::dir.exists
@@ -65,15 +69,14 @@ if (tryCatch(isTRUE(AMR:::import_fn("isJob", "rstudioapi")()), error = function(
       deparse1 <- AMR:::deparse1
     }
     
-    # start the unit tests
     suppressMessages(
       out <- test_package("AMR",
-        testdir = ifelse(dir.exists("inst/tinytest"),
-          "inst/tinytest",
-          "tinytest"
-        ),
-        verbose = FALSE,
-        color = FALSE
+                          testdir = ifelse(dir.exists("inst/tests"),
+                                           "inst/tests",
+                                           "tests"
+                          ),
+                          verbose = FALSE,
+                          color = FALSE
       )
     )
     cat("\n\nSUMMARY:\n")