AMR/tests/testthat/test-first_isolate.R

212 lines
8.3 KiB
R
Raw Normal View History

# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Analysis #
# #
2019-01-02 23:24:07 +01:00
# SOURCE #
# https://gitlab.com/msberends/AMR #
# #
# LICENCE #
2019-01-02 23:24:07 +01:00
# (c) 2019 Berends MS (m.s.berends@umcg.nl), Luz CF (c.f.luz@umcg.nl) #
# #
2019-01-02 23:24:07 +01:00
# This R package is free software; you can freely use and distribute #
# it for both personal and commercial purposes under the terms of the #
# GNU General Public License version 2.0 (GNU GPL-2), as published by #
# the Free Software Foundation. #
# #
# This R package was created for academic research and was publicly #
# released in the hope that it will be useful, but it comes WITHOUT #
# ANY WARRANTY OR LIABILITY. #
2019-04-05 18:47:39 +02:00
# Visit our website for more info: https://msberends.gitlab.io/AMR. #
# ==================================================================== #
2018-07-23 14:14:03 +02:00
context("first_isolate.R")
2018-03-27 17:43:42 +02:00
test_that("first isolates work", {
2019-02-18 02:33:37 +01:00
# first isolates
2018-04-02 16:05:09 +02:00
expect_equal(
2018-06-19 10:05:38 +02:00
sum(
first_isolate(x = example_isolates,
2018-04-02 16:05:09 +02:00
col_date = "date",
col_patient_id = "patient_id",
2018-08-31 13:36:19 +02:00
col_mo = "mo",
info = TRUE),
2018-07-02 09:34:20 +02:00
na.rm = TRUE),
1317)
2018-06-19 10:05:38 +02:00
2019-02-18 02:33:37 +01:00
# first *weighted* isolates
2018-06-19 10:05:38 +02:00
expect_equal(
suppressWarnings(
sum(
first_isolate(x = example_isolates %>% mutate(keyab = key_antibiotics(.)),
2018-12-14 09:31:53 +01:00
# let syntax determine these automatically:
# col_date = "date",
# col_patient_id = "patient_id",
# col_mo = "mo",
# col_keyantibiotics = "keyab",
type = "keyantibiotics",
info = TRUE),
na.rm = TRUE)),
1413)
2018-12-14 09:31:53 +01:00
# should be same for tibbles
expect_equal(
suppressWarnings(
sum(
first_isolate(x = example_isolates %>% dplyr::as_tibble() %>% mutate(keyab = key_antibiotics(.)),
2018-12-14 07:48:12 +01:00
# let syntax determine these automatically:
# col_date = "date",
# col_patient_id = "patient_id",
# col_mo = "mo",
# col_keyantibiotics = "keyab",
2018-06-19 10:05:38 +02:00
type = "keyantibiotics",
info = TRUE),
na.rm = TRUE)),
1413)
2019-02-18 02:33:37 +01:00
# when not ignoring I
expect_equal(
suppressWarnings(
sum(
first_isolate(x = example_isolates %>% mutate(keyab = key_antibiotics(.)),
col_date = "date",
col_patient_id = "patient_id",
2018-08-31 13:36:19 +02:00
col_mo = "mo",
col_keyantibiotics = "keyab",
ignore_I = FALSE,
type = "keyantibiotics",
info = TRUE),
na.rm = TRUE)),
1436)
2019-02-18 02:33:37 +01:00
# when using points
2018-07-02 09:34:20 +02:00
expect_equal(
suppressWarnings(
sum(
first_isolate(x = example_isolates %>% mutate(keyab = key_antibiotics(.)),
2018-07-02 09:34:20 +02:00
col_date = "date",
col_patient_id = "patient_id",
2018-08-31 13:36:19 +02:00
col_mo = "mo",
2018-07-02 09:34:20 +02:00
col_keyantibiotics = "keyab",
type = "points",
info = TRUE),
na.rm = TRUE)),
1417)
2018-04-03 11:08:31 +02:00
2019-02-18 02:33:37 +01:00
# first non-ICU isolates
2018-04-20 13:45:34 +02:00
expect_equal(
sum(
first_isolate(example_isolates,
2018-08-31 13:36:19 +02:00
col_mo = "mo",
2018-06-19 10:05:38 +02:00
col_date = "date",
col_patient_id = "patient_id",
col_icu = "ward_icu",
info = TRUE,
icu_exclude = TRUE),
na.rm = TRUE),
1163)
2018-04-20 13:45:34 +02:00
2018-04-03 11:08:31 +02:00
# set 1500 random observations to be of specimen type 'Urine'
random_rows <- sample(x = 1:2000, size = 1500, replace = FALSE)
2018-06-19 10:05:38 +02:00
expect_lt(
sum(
first_isolate(x = mutate(example_isolates,
2018-06-19 10:05:38 +02:00
specimen = if_else(row_number() %in% random_rows,
"Urine",
"Other")),
2018-06-19 10:05:38 +02:00
col_date = "date",
col_patient_id = "patient_id",
2018-08-31 13:36:19 +02:00
col_mo = "mo",
2018-06-19 10:05:38 +02:00
col_specimen = "specimen",
filter_specimen = "Urine",
info = TRUE),
na.rm = TRUE),
2018-04-03 11:08:31 +02:00
1501)
2018-07-02 09:34:20 +02:00
# same, but now exclude ICU
expect_lt(
sum(
first_isolate(x = mutate(example_isolates,
2018-07-02 09:34:20 +02:00
specimen = if_else(row_number() %in% random_rows,
"Urine",
"Other")),
2018-07-02 09:34:20 +02:00
col_date = "date",
col_patient_id = "patient_id",
2018-08-31 13:36:19 +02:00
col_mo = "mo",
2018-07-02 09:34:20 +02:00
col_specimen = "specimen",
filter_specimen = "Urine",
col_icu = "ward_icu",
icu_exclude = TRUE,
info = TRUE),
na.rm = TRUE),
1501)
2018-08-23 21:27:15 +02:00
# "No isolates found"
expect_message(example_isolates %>%
2018-08-23 21:27:15 +02:00
mutate(specimen = "test") %>%
mutate(first = first_isolate(., "date", "patient_id",
2018-08-31 13:36:19 +02:00
col_mo = "mo",
col_specimen = "specimen",
2018-12-22 22:39:34 +01:00
filter_specimen = "something_unexisting")))
# printing of exclusion message
expect_output(example_isolates %>%
2018-12-22 22:39:34 +01:00
first_isolate(col_date = "date",
col_mo = "mo",
col_patient_id = "patient_id",
col_testcode = "gender",
testcodes_exclude = "M"))
# errors
2018-08-31 13:36:19 +02:00
expect_error(first_isolate("date", "patient_id", col_mo = "mo"))
expect_error(first_isolate(example_isolates,
col_date = "non-existing col",
2018-08-31 13:36:19 +02:00
col_mo = "mo"))
2018-10-23 11:15:05 +02:00
# look for columns itself
expect_message(first_isolate(example_isolates))
expect_message(first_isolate(example_isolates %>%
2018-12-22 22:39:34 +01:00
mutate(mo = as.character(mo)) %>%
left_join_microorganisms()))
2018-10-23 11:15:05 +02:00
2018-09-01 21:19:46 +02:00
# if mo is not an mo class, result should be the same
expect_identical(example_isolates %>%
2018-12-22 22:39:34 +01:00
mutate(mo = as.character(mo)) %>%
first_isolate(col_date = "date",
col_mo = "mo",
col_patient_id = "patient_id"),
example_isolates %>%
2018-09-01 21:19:46 +02:00
first_isolate(col_date = "date",
col_mo = "mo",
col_patient_id = "patient_id"))
# missing dates should be no problem
df <- example_isolates
2019-05-13 14:56:23 +02:00
df[1:100, "date"] <- NA
expect_equal(
sum(
first_isolate(x = df,
col_date = "date",
col_patient_id = "patient_id",
col_mo = "mo",
info = TRUE),
na.rm = TRUE),
1322)
# unknown MOs
expect_equal(example_isolates %>%
mutate(mo = ifelse(mo == "B_ESCHR_COL", "UNKNOWN", mo)) %>%
mutate(first = first_isolate(., include_unknown = FALSE)) %>%
.$first %>%
sum(),
1062)
expect_equal(example_isolates %>%
mutate(mo = ifelse(mo == "B_ESCHR_COL", "UNKNOWN", mo)) %>%
mutate(first = first_isolate(., include_unknown = TRUE)) %>%
.$first %>%
sum(),
1529)
expect_equal(example_isolates %>%
mutate(mo = ifelse(mo == "B_ESCHR_COL", NA, mo)) %>%
mutate(first = first_isolate(.)) %>%
.$first %>%
sum(),
1062)
2019-05-13 14:56:23 +02:00
2018-03-27 17:43:42 +02:00
})