P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-12 18:21:49 +02:00
Code Releases Activity

New mo algorithm, prepare for 2.0

Browse Source
This commit is contained in:
Dr. Matthijs Berends
2022-10-05 09:12:22 +02:00
committed by GitHub
parent 63fe160322
commit cd2acc4a29
182 changed files with 4054 additions and 90905 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
R/ab_from_text.R
View File

@ -1,12 +1,16 @@
# ==================================================================== #
# TITLE #
# Antimicrobial Resistance (AMR) Data Analysis for R #
# AMR: An R Package for Working with Antimicrobial Resistance Data #
# #
# SOURCE #
# https://github.com/msberends/AMR #
# #
# LICENCE #
# (c) 2018-2022 Berends MS, Luz CF et al. #
# CITE AS #
# Berends MS, Luz CF, Friedrich AW, Sinha BNM, Albers CJ, Glasner C #
# (2022). AMR: An R Package for Working with Antimicrobial Resistance #
# Data. Journal of Statistical Software, 104(3), 1-31. #
# doi:10.18637/jss.v104.i03 #
# #
# Developed at the University of Groningen, the Netherlands, in #
# collaboration with non-profit organisations Certe Medical #
# Diagnostics & Advice, and University Medical Center Groningen. #
@ -110,7 +114,7 @@ ab_from_text <- function(text,
meet_criteria(thorough_search, allow_class = "logical", has_length = 1, allow_NULL = TRUE)
meet_criteria(info, allow_class = "logical", has_length = 1)
type <- tolower(trimws(type))
type <- tolower(trimws2(type))
text <- tolower(as.character(text))
text_split_all <- strsplit(text, "[ ;.,:\\|]")
@ -120,21 +124,21 @@ ab_from_text <- function(text,
if (type %like% "(drug|ab|anti)") {
translate_ab <- get_translate_ab(translate_ab)
if (isTRUE(thorough_search) |
(isTRUE(is.null(thorough_search)) & max(vapply(FUN.VALUE = double(1), text_split_all, length), na.rm = TRUE) <= 3)) {
if (isTRUE(thorough_search) ||
(isTRUE(is.null(thorough_search)) && max(vapply(FUN.VALUE = double(1), text_split_all, length), na.rm = TRUE) <= 3)) {
text_split_all <- text_split_all[nchar(text_split_all) >= 4 & grepl("[a-z]+", text_split_all)]
result <- lapply(text_split_all, function(text_split) {
progress$tick()
suppressWarnings(
out <- as.ab(text_split, ...)
as.ab(text_split, ...)
)
})
} else {
# no thorough search
abbr <- unlist(antibiotics$abbreviations)
abbr <- unlist(AMR::antibiotics$abbreviations)
abbr <- abbr[nchar(abbr) >= 4]
names_atc <- substr(c(antibiotics$name, antibiotics$atc), 1, 5)
synonyms <- unlist(antibiotics$synonyms)
names_atc <- substr(c(AMR::antibiotics$name, AMR::antibiotics$atc), 1, 5)
synonyms <- unlist(AMR::antibiotics$synonyms)
synonyms <- synonyms[nchar(synonyms) >= 4]
# regular expression must not be too long, so split synonyms in two:
synonyms_part1 <- synonyms[seq_len(0.5 * length(synonyms))]
@ -149,7 +153,7 @@ ab_from_text <- function(text,
result <- lapply(text_split_all, function(text_split) {
progress$tick()
suppressWarnings(
out <- as.ab(
as.ab(
unique(c(
text_split[text_split %like_case% to_regex(abbr)],
text_split[text_split %like_case% to_regex(names_atc)],
@ -176,7 +180,7 @@ ab_from_text <- function(text,
}
})
} else if (type %like% "dos") {
text_split_all <- strsplit(text, " ")
text_split_all <- strsplit(text, " ", fixed = TRUE)
result <- lapply(text_split_all, function(text_split) {
text_split <- text_split[text_split %like% "^[0-9]{2,}(/[0-9]+)?[a-z]*$"]
# only left part of "/", like 500 in "500/125"