P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2024-12-25 19:26:13 +01:00
Code Releases Activity

(v1.5.0.9021) improve speed of %like%

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends 2021-02-21 20:15:09 +01:00
parent daa12ced2c
commit 5ef8cb41a7
23 changed files with 137 additions and 126 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/check.yaml vendored
View File

@ -159,7 +159,7 @@ jobs:
_R_CHECK_LENGTH_1_CONDITION_: verbose
_R_CHECK_LENGTH_1_LOGIC2_: verbose
run: |
R CMD check data-raw/AMR_*.tar.gz --no-manual --no-build-vignettes
R CMD check data-raw/AMR_latest.tar.gz --no-manual --no-build-vignettes
- name: Show testthat output
if: always()

4
DESCRIPTION
View File

@ -1,6 +1,6 @@
Package: AMR
Version: 1.5.0.9020
Date: 2021-02-18
Version: 1.5.0.9021
Date: 2021-02-21
Title: Antimicrobial Resistance Data Analysis
Authors@R: c(
person(role = c("aut", "cre"),

5
NEWS.md
View File

@ -1,5 +1,5 @@
# AMR 1.5.0.9020
## <small>Last updated: 18 February 2021</small>
# AMR 1.5.0.9021
## <small>Last updated: 21 February 2021</small>
### New
* Support for EUCAST Clinical Breakpoints v11.0 (2021), effective in the `eucast_rules()` function and in `as.rsi()` to interpret MIC and disk diffusion values. This is now the default guideline in this package.
@ -58,6 +58,7 @@
* Functions `print()` and `summary()` on a Principal Components Analysis object (`pca()`) now print additional group info if the original data was grouped using `dplyr::group_by()`
* Improved speed and reliability of `guess_ab_col()`. As this also internally improves the reliability of `first_isolate()` and `mdro()`, this might have a slight impact on the results of those functions.
* Fix for `mo_name()` when used in other languages than English
* The `like()` function (and its fast alias `%like%`) now always use Perl compatibility, improving speed for many functions in this package
### Other
* Big documentation updates

8
R/aa_helper_functions.R
View File

@ -1077,6 +1077,14 @@ percentage <- function(x, digits = NULL, ...) {
digits = digits, ...)
}
time_start_tracking <- function() {
pkg_env$time_start <- round(as.numeric(Sys.time()) * 1000)
}
time_track <- function(name = NULL) {
paste("(until now:", trimws(round(as.numeric(Sys.time()) * 1000) - pkg_env$time_start), "ms)")
}
# prevent dependency on package 'backports'
# these functions were not available in previous versions of R (last checked: R 4.0.3)
# see here for the full list: https://github.com/r-lib/backports

8
R/eucast_rules.R
View File

@ -896,7 +896,7 @@ eucast_rules <- function(x,
target_value <- eucast_rules_df[i, "to_value", drop = TRUE]
if (is.na(source_antibiotics)) {
rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value),
rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value),
error = function(e) integer(0))
} else {
source_antibiotics <- get_antibiotic_columns(source_antibiotics, x)
@ -906,17 +906,17 @@ eucast_rules <- function(x,
if (length(source_antibiotics) == 0) {
rows <- integer(0)
} else if (length(source_antibiotics) == 1) {
rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value
rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value
& as.rsi_no_warning(x[, source_antibiotics[1L]]) == source_value[1L]),
error = function(e) integer(0))
} else if (length(source_antibiotics) == 2) {
rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value
rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value
& as.rsi_no_warning(x[, source_antibiotics[1L]]) == source_value[1L]
& as.rsi_no_warning(x[, source_antibiotics[2L]]) == source_value[2L]),
error = function(e) integer(0))
# nolint start
# } else if (length(source_antibiotics) == 3) {
# rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like_perl% mo_value
# rows <- tryCatch(which(x[, if_mo_property, drop = TRUE] %like% mo_value
# & as.rsi_no_warning(x[, source_antibiotics[1L]]) == source_value[1L]
# & as.rsi_no_warning(x[, source_antibiotics[2L]]) == source_value[2L]
# & as.rsi_no_warning(x[, source_antibiotics[3L]]) == source_value[3L]),

37
R/like.R
View File

@ -39,7 +39,7 @@
#' * Is case-insensitive (use `%like_case%` for case-sensitive matching)
#' * Supports multiple patterns
#' * Checks if `pattern` is a regular expression and sets `fixed = TRUE` if not, to greatly improve speed
#' * Tries again with `perl = TRUE` if regex fails
#' * Always uses compatibility with Perl
#'
#' Using RStudio? The text `%like%` can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like `Ctrl+Shift+L` or `Cmd+Shift+L` (see `Tools` > `Modify Keyboard Shortcuts...`).
#' @source Idea from the [`like` function from the `data.table` package](https://github.com/Rdatatable/data.table/blob/master/R/like.R)
@ -99,7 +99,7 @@ like <- function(x, pattern, ignore.case = TRUE) {
if (is.factor(x[i])) {
res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed)
} else {
res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed)
res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed, perl = !fixed)
}
}
res <- vapply(FUN.VALUE = logical(1), pattern, function(pttrn) grepl(pttrn, x, ignore.case = FALSE, fixed = fixed))
@ -112,9 +112,9 @@ like <- function(x, pattern, ignore.case = TRUE) {
# x and pattern are of same length, so items with each other
for (i in seq_len(length(res))) {
if (is.factor(x[i])) {
res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed)
res[i] <- as.integer(x[i]) %in% grep(pattern[i], levels(x[i]), ignore.case = FALSE, fixed = fixed, perl = !fixed)
} else {
res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed)
res[i] <- grepl(pattern[i], x[i], ignore.case = FALSE, fixed = fixed, perl = !fixed)
}
}
return(res)
@ -123,22 +123,9 @@ like <- function(x, pattern, ignore.case = TRUE) {
# the regular way how grepl works; just one pattern against one or more x
if (is.factor(x)) {
as.integer(x) %in% grep(pattern, levels(x), ignore.case = FALSE, fixed = fixed)
as.integer(x) %in% grep(pattern, levels(x), ignore.case = FALSE, fixed = fixed, perl = !fixed)
} else {
tryCatch(grepl(pattern, x, ignore.case = FALSE, fixed = fixed),
error = function(e) {
if (grepl("invalid reg(ular )?exp", e$message, ignore.case = TRUE)) {
# try with perl = TRUE:
return(grepl(pattern = pattern,
x = x,
ignore.case = FALSE,
fixed = fixed,
perl = TRUE))
} else {
# stop otherwise
stop(e$message)
}
})
grepl(pattern, x, ignore.case = FALSE, fixed = fixed, perl = !fixed)
}
}
@ -157,15 +144,3 @@ like <- function(x, pattern, ignore.case = TRUE) {
meet_criteria(pattern, allow_NA = FALSE)
like(x, pattern, ignore.case = FALSE)
}
"%like_perl%" <- function(x, pattern) {
meet_criteria(x, allow_NA = TRUE)
meet_criteria(pattern, allow_NA = FALSE)
# convenient for e.g. matching all Klebsiella and Raoultella, but not
# K. aerogenes: fullname %like_perl% "^(Klebsiella(?! aerogenes)|Raoultella)"
grepl(x = tolower(x),
pattern = tolower(pattern),
perl = TRUE,
fixed = FALSE,
ignore.case = TRUE)
}

36
R/mo.R
View File

@ -277,6 +277,10 @@ exec_as.mo <- function(x,
check_dataset_integrity()
if (isTRUE(debug) && initial_search == TRUE) {
time_start_tracking()
}
lookup <- function(needle,
column = property,
haystack = reference_data_to_use,
@ -295,7 +299,8 @@ exec_as.mo <- function(x,
# `column` can be NULL for all columns, or a selection
# returns a character (vector) - if `column` > length 1 then with columns as names
if (isTRUE(debug_mode)) {
cat(font_silver("looking up: ", substitute(needle), collapse = ""))
cat(font_silver("Looking up: ", substitute(needle), collapse = ""),
"\n ", time_track())
}
if (length(column) == 1) {
res_df <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE]
@ -313,7 +318,7 @@ exec_as.mo <- function(x,
NA_character_
} else {
if (isTRUE(debug_mode)) {
cat(font_green(paste0(" **MATCH** (", NROW(res_df), " results)\n")))
cat(font_green(paste0(" MATCH (", NROW(res_df), " results)\n")))
}
if ((length(res) > n | uncertainty > 1) & uncertainty != -1) {
# save the other possible results as well, but not for forced certain results (then uncertainty == -1)
@ -327,16 +332,20 @@ exec_as.mo <- function(x,
res[seq_len(min(n, length(res)))]
}
} else {
if (isTRUE(debug_mode)) {
cat("\n")
}
if (is.null(column)) {
column <- names(haystack)
}
res <- haystack[which(eval(substitute(needle), envir = haystack, enclos = parent.frame())), , drop = FALSE]
res <- res[seq_len(min(n, nrow(res))), column, drop = TRUE]
if (NROW(res) == 0) {
if (isTRUE(debug_mode)) {
cat(font_red(" (no rows)\n"))
}
res <- rep(NA_character_, length(column))
} else {
if (isTRUE(debug_mode)) {
cat(font_green(paste0(" MATCH (", NROW(res), " rows)\n")))
}
}
res <- as.character(res)
names(res) <- column
@ -471,10 +480,10 @@ exec_as.mo <- function(x,
x_backup[x_backup_untouched == "Fungi"] <- "Fungi" # is literally the kingdom
# Fill in fullnames and MO codes at once
known_names <- x_backup %in% MO_lookup$fullname
x[known_names] <- MO_lookup[match(x_backup[known_names], MO_lookup$fullname), property, drop = TRUE]
known_codes <- x_backup %in% MO_lookup$mo
x[known_codes] <- MO_lookup[match(x_backup[known_codes], MO_lookup$mo), property, drop = TRUE]
known_names <- tolower(x_backup) %in% MO_lookup$fullname_lower
x[known_names] <- MO_lookup[match(tolower(x_backup)[known_names], MO_lookup$fullname), property, drop = TRUE]
known_codes <- toupper(x_backup) %in% MO_lookup$mo
x[known_codes] <- MO_lookup[match(toupper(x_backup)[known_codes], MO_lookup$mo), property, drop = TRUE]
already_known <- known_names | known_codes
# now only continue where the right taxonomic output is not already known
@ -975,6 +984,7 @@ exec_as.mo <- function(x,
g.x_backup_without_spp %pm>% substr(1, x_length / 2),
".* ",
g.x_backup_without_spp %pm>% substr((x_length / 2) + 1, x_length))
print(x_split)
found <- lookup(fullname_lower %like_case% x_split,
haystack = data_to_check)
if (!is.na(found)) {
@ -1414,6 +1424,10 @@ exec_as.mo <- function(x,
close(progress)
}
if (isTRUE(debug) && initial_search == TRUE) {
cat("Ended search", time_track(), "\n")
}
# handling failures ----
failures <- failures[!failures %in% c(NA, NULL, NaN)]
@ -1571,6 +1585,10 @@ exec_as.mo <- function(x,
}
}
if (isTRUE(debug) && initial_search == TRUE) {
cat("Finished function", time_track(), "\n")
}
x
}

BIN
data-raw/AMR_latest.tar.gz
View File

Binary file not shown.

2
docs/404.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="https://msberends.github.io/AMR//index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

2
docs/LICENSE-text.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

123
docs/articles/benchmarks.html
View File

@ -39,7 +39,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>
@ -192,6 +192,7 @@
<div class="page-header toc-ignore">
<h1 data-toc-skip>Benchmarks</h1>
<h4 class="date">21 February 2021</h4>
<small class="dont-index">Source: <a href="https://github.com/msberends/AMR/blob/master/vignettes/benchmarks.Rmd"><code>vignettes/benchmarks.Rmd</code></a></small>
<div class="hidden name"><code>benchmarks.Rmd</code></div>
@ -225,36 +226,42 @@
<span class="fu"><a href="../reference/as.mo.html">as.mo</a></span><span class="op">(</span><span class="st">"VISA"</span><span class="op">)</span>, <span class="co"># Vancomycin Intermediate S. aureus</span>
<span class="fu"><a href="../reference/as.mo.html">as.mo</a></span><span class="op">(</span><span class="st">"VRSA"</span><span class="op">)</span>, <span class="co"># Vancomycin Resistant S. aureus</span>
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max</span>
<span class="co"># as.mo("sau") 13.0 14.0 25.0 15.0 44.0 65</span>
<span class="co"># as.mo("stau") 120.0 130.0 140.0 140.0 160.0 160</span>
<span class="co"># as.mo("STAU") 120.0 130.0 150.0 160.0 160.0 180</span>
<span class="co"># as.mo("staaur") 13.0 13.0 14.0 14.0 14.0 15</span>
<span class="co"># as.mo("STAAUR") 13.0 14.0 17.0 15.0 15.0 43</span>
<span class="co"># as.mo("S. aureus") 30.0 32.0 45.0 34.0 62.0 68</span>
<span class="co"># as.mo("S aureus") 31.0 34.0 42.0 35.0 61.0 63</span>
<span class="co"># as.mo("Staphylococcus aureus") 2.5 2.6 2.8 2.8 2.9 3</span>
<span class="co"># as.mo("Staphylococcus aureus (MRSA)") 1200.0 1200.0 1200.0 1200.0 1200.0 1200</span>
<span class="co"># as.mo("Sthafilokkockus aaureuz") 550.0 560.0 570.0 560.0 570.0 610</span>
<span class="co"># as.mo("MRSA") 13.0 13.0 17.0 15.0 15.0 42</span>
<span class="co"># as.mo("VISA") 21.0 22.0 26.0 23.0 23.0 52</span>
<span class="co"># as.mo("VRSA") 21.0 23.0 35.0 24.0 52.0 54</span>
<span class="co"># neval</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span></code></pre></div>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># as.mo("sau") 12.0 12.0 13.0 14.0 14.0 16 10</span>
<span class="co"># as.mo("stau") 55.0 67.0 88.0 95.0 98.0 120 10</span>
<span class="co"># as.mo("STAU") 57.0 66.0 110.0 100.0 130.0 250 10</span>
<span class="co"># as.mo("staaur") 12.0 12.0 17.0 13.0 14.0 54 10</span>
<span class="co"># as.mo("STAAUR") 11.0 12.0 17.0 13.0 14.0 61 10</span>
<span class="co"># as.mo("S. aureus") 30.0 32.0 62.0 69.0 93.0 95 10</span>
<span class="co"># as.mo("S aureus") 29.0 33.0 43.0 37.0 53.0 71 10</span>
<span class="co"># as.mo("Staphylococcus aureus") 2.2 2.4 2.6 2.6 2.8 3 10</span>
<span class="co"># as.mo("Staphylococcus aureus (MRSA)") 270.0 290.0 330.0 310.0 380.0 430 10</span>
<span class="co"># as.mo("Sthafilokkockus aaureuz") 190.0 210.0 240.0 250.0 270.0 290 10</span>
<span class="co"># as.mo("MRSA") 12.0 12.0 14.0 13.0 15.0 16 10</span>
<span class="co"># as.mo("VISA") 21.0 22.0 29.0 24.0 25.0 79 10</span>
<span class="co"># as.mo("VRSA") 21.0 24.0 35.0 28.0 56.0 58 10</span></code></pre></div>
<p><img src="benchmarks_files/figure-html/unnamed-chunk-4-1.png" width="562.5"></p>
<p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 100 milliseconds, this is only 10 input values per second. It is clear that accepted taxonomic names are extremely fast, but some variations can take up to 500-1000 times as much time.</p>
<p>To improve performance, two important calculations take almost no time at all: <strong>repetitive results</strong> and <strong>already precalculated results</strong>.</p>
@ -281,11 +288,11 @@
<span class="co"># now let's see:</span>
<span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu">microbenchmark</span><span class="op">(</span><span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="va">x</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># mo_name(x) 141 180 218 207 245 312 10</span></code></pre></div>
<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.207 seconds. You only lose time on your unique input values.</p>
<span class="co"># mo_name(x) 125 144 182 171 186 298 10</span></code></pre></div>
<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.171 seconds. You only lose time on your unique input values.</p>
</div>
<div id="precalculated-results" class="section level3">
<h3 class="hasAnchor">
@ -296,13 +303,13 @@
B <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"S. aureus"</span><span class="op">)</span>,
C <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"Staphylococcus aureus"</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 8.76 8.96 9.39 9.31 9.86 10.10 10</span>
<span class="co"># B 27.60 28.20 33.00 28.90 29.40 71.20 10</span>
<span class="co"># C 2.28 2.32 2.47 2.45 2.48 2.85 10</span></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0025 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 7.08 7.37 15.90 7.94 9.02 48.9 10</span>
<span class="co"># B 23.50 24.00 25.20 24.10 26.20 30.1 10</span>
<span class="co"># C 1.54 1.62 1.76 1.71 1.81 2.3 10</span></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0017 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<div class="sourceCode" id="cb5"><pre class="downlit sourceCode r">
<code class="sourceCode R"><span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu">microbenchmark</span><span class="op">(</span>A <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_species</a></span><span class="op">(</span><span class="st">"aureus"</span><span class="op">)</span>,
B <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_genus</a></span><span class="op">(</span><span class="st">"Staphylococcus"</span><span class="op">)</span>,
@ -313,17 +320,17 @@
G <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_phylum</a></span><span class="op">(</span><span class="st">"Firmicutes"</span><span class="op">)</span>,
H <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_kingdom</a></span><span class="op">(</span><span class="st">"Bacteria"</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 1.91 1.95 2.06 1.99 2.09 2.62 10</span>
<span class="co"># B 1.83 1.91 2.09 2.04 2.20 2.45 10</span>
<span class="co"># C 1.79 1.90 2.03 1.99 2.22 2.30 10</span>
<span class="co"># D 1.90 2.01 2.18 2.12 2.25 2.71 10</span>
<span class="co"># E 1.91 2.02 2.14 2.08 2.15 2.81 10</span>
<span class="co"># F 1.86 1.92 2.00 2.01 2.06 2.16 10</span>
<span class="co"># G 1.81 1.96 2.09 2.08 2.22 2.41 10</span>
<span class="co"># H 1.90 1.93 2.05 2.00 2.22 2.29 10</span></code></pre></div>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 1.63 1.92 1.99 2.01 2.11 2.29 10</span>
<span class="co"># B 1.67 1.89 2.01 1.96 2.12 2.62 10</span>
<span class="co"># C 1.86 1.87 1.96 1.97 2.04 2.13 10</span>
<span class="co"># D 1.63 1.82 1.90 1.94 2.00 2.06 10</span>
<span class="co"># E 1.60 1.94 3.05 1.97 2.24 12.60 10</span>
<span class="co"># F 1.66 1.90 2.18 1.95 2.01 4.33 10</span>
<span class="co"># G 1.84 1.89 1.99 1.98 2.02 2.24 10</span>
<span class="co"># H 1.79 1.95 2.08 2.06 2.25 2.36 10</span></code></pre></div>
<p>Of course, when running <code><a href="../reference/mo_property.html">mo_phylum("Firmicutes")</a></code> the function has zero knowledge about the actual microorganism, namely <em>S. aureus</em>. But since the result would be <code>"Firmicutes"</code> anyway, there is no point in calculating the result. And because this package ‘knows’ all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.</p>
</div>
<div id="results-in-other-languages" class="section level3">
@ -348,16 +355,16 @@
fr <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"CoNS"</span>, language <span class="op">=</span> <span class="st">"fr"</span><span class="op">)</span>,
pt <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"CoNS"</span>, language <span class="op">=</span> <span class="st">"pt"</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">100</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># en 17.45 18.01 19.69 18.53 19.14 55.30 100</span>
<span class="co"># de 20.58 21.54 26.69 22.08 23.96 67.16 100</span>
<span class="co"># nl 33.79 34.67 39.13 35.39 36.72 74.60 100</span>
<span class="co"># es 20.71 21.42 24.36 21.88 22.65 58.57 100</span>
<span class="co"># it 20.65 21.18 26.50 21.53 22.68 61.96 100</span>
<span class="co"># fr 20.68 21.27 25.05 21.64 22.37 58.82 100</span>
<span class="co"># pt 20.69 21.44 24.36 21.94 22.99 59.66 100</span></code></pre></div>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># en 17.21 17.88 21.68 18.14 19.20 71.64 100</span>
<span class="co"># de 20.08 20.74 26.58 21.26 22.41 159.80 100</span>
<span class="co"># nl 24.88 25.81 31.01 26.32 27.03 74.57 100</span>
<span class="co"># es 19.91 20.80 26.33 21.28 22.60 80.34 100</span>
<span class="co"># it 19.96 20.63 25.21 21.20 22.25 76.35 100</span>
<span class="co"># fr 19.61 20.38 26.62 21.15 22.59 80.90 100</span>
<span class="co"># pt 19.87 20.58 27.65 20.92 23.22 80.73 100</span></code></pre></div>
<p>Currently supported are German, Dutch, Spanish, Italian, French and Portuguese.</p>
</div>
</div>

BIN
docs/articles/benchmarks_files/figure-html/unnamed-chunk-4-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 69 KiB

After

Width:  |  Height:  |  Size: 68 KiB

2
docs/articles/index.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

2
docs/authors.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

2
docs/index.html
View File

@ -43,7 +43,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

13
docs/news/index.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>
@ -236,13 +236,13 @@
<small>Source: <a href='https://github.com/msberends/AMR/blob/master/NEWS.md'><code>NEWS.md</code></a></small>
</div>
<div id="amr-1509020" class="section level1">
<h1 class="page-header" data-toc-text="1.5.0.9020">
<a href="#amr-1509020" class="anchor"></a>AMR 1.5.0.9020<small> Unreleased </small>
<div id="amr-1509021" class="section level1">
<h1 class="page-header" data-toc-text="1.5.0.9021">
<a href="#amr-1509021" class="anchor"></a>AMR 1.5.0.9021<small> Unreleased </small>
</h1>
<div id="last-updated-18-february-2021" class="section level2">
<div id="last-updated-21-february-2021" class="section level2">
<h2 class="hasAnchor">
<a href="#last-updated-18-february-2021" class="anchor"></a><small>Last updated: 18 February 2021</small>
<a href="#last-updated-21-february-2021" class="anchor"></a><small>Last updated: 21 February 2021</small>
</h2>
<div id="new" class="section level3">
<h3 class="hasAnchor">
@ -326,6 +326,7 @@
</li>
<li>Improved speed and reliability of <code><a href="../reference/guess_ab_col.html">guess_ab_col()</a></code>. As this also internally improves the reliability of <code><a href="../reference/first_isolate.html">first_isolate()</a></code> and <code><a href="../reference/mdro.html">mdro()</a></code>, this might have a slight impact on the results of those functions.</li>
<li>Fix for <code><a href="../reference/mo_property.html">mo_name()</a></code> when used in other languages than English</li>
<li>The <code><a href="../reference/like.html">like()</a></code> function (and its fast alias <code><a href="../reference/like.html">%like%</a></code>) now always use Perl compatibility, improving speed for many functions in this package</li>
</ul>
</div>
<div id="other" class="section level3">

2
docs/pkgdown.yml
View File

@ -12,7 +12,7 @@ articles:
datasets: datasets.html
resistance_predict: resistance_predict.html
welcome_to_AMR: welcome_to_AMR.html
last_built: 2021-02-18T22:21Z
last_built: 2021-02-21T19:14Z
urls:
reference: https://msberends.github.io/AMR//reference
article: https://msberends.github.io/AMR//articles

2
docs/reference/antibiotic_class_selectors.html
View File

@ -83,7 +83,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9019</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

2
docs/reference/index.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

4
docs/reference/like.html
View File

@ -82,7 +82,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9016</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>
@ -277,7 +277,7 @@
<li><p>Is case-insensitive (use <code>%like_case%</code> for case-sensitive matching)</p></li>
<li><p>Supports multiple patterns</p></li>
<li><p>Checks if <code>pattern</code> is a regular expression and sets <code>fixed = TRUE</code> if not, to greatly improve speed</p></li>
<li><p>Tries again with <code>perl = TRUE</code> if regex fails</p></li>
<li><p>Always uses compatibility with Perl</p></li>
</ul>
<p>Using RStudio? The text <code>%like%</code> can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like <code>Ctrl+Shift+L</code> or <code>Cmd+Shift+L</code> (see <code>Tools</code> &gt; <code>Modify Keyboard Shortcuts...</code>).</p>

2
docs/survey.html
View File

@ -81,7 +81,7 @@
</button>
<span class="navbar-brand">
<a class="navbar-link" href="index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9020</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>

2
man/like.Rd
View File

@ -34,7 +34,7 @@ The \verb{\%like\%} function:
\item Is case-insensitive (use \verb{\%like_case\%} for case-sensitive matching)
\item Supports multiple patterns
\item Checks if \code{pattern} is a regular expression and sets \code{fixed = TRUE} if not, to greatly improve speed
\item Tries again with \code{perl = TRUE} if regex fails
\item Always uses compatibility with Perl
}
Using RStudio? The text \verb{\%like\%} can also be directly inserted in your code from the Addins menu and can have its own Keyboard Shortcut like \code{Ctrl+Shift+L} or \code{Cmd+Shift+L} (see \code{Tools} > \verb{Modify Keyboard Shortcuts...}).

1
vignettes/benchmarks.Rmd
View File

@ -1,5 +1,6 @@
---
title: "Benchmarks"
date: '`r format(Sys.Date(), "%d %B %Y")`'
output:
rmarkdown::html_vignette:
toc: true