P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2024-12-25 18:46:11 +01:00
Code Releases Activity

as.mo improvements

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends 2019-02-25 15:52:32 +01:00
parent 0ec76cfa98
commit c506d2893b
13 changed files with 390 additions and 376 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
R/mo.R
View File

@ -97,7 +97,7 @@
#' The artificial intelligence takes into account microbial prevalence of pathogens in humans. It uses three groups and every (sub)species is in the group it matches first. These groups are:
#' \itemize{
#' \item{1 (most prevalent): class is Gammaproteobacteria \strong{or} genus is one of: \emph{Enterococcus}, \emph{Staphylococcus}, \emph{Streptococcus}.}
#' \item{2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora \strong{or} genus is one of: \emph{Aspergillus}, \emph{Bacteroides}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Chryseobacterium}, \emph{Cryptococcus}, \emph{Elisabethkingia}, \emph{Flavobacterium}, \emph{Fusobacterium}, \emph{Giardia}, \emph{Leptotrichia}, \emph{Mycoplasma}, \emph{Prevotella}, \emph{Rhodotorula}, \emph{Treponema}, \emph{Trichophyton}.}
#' \item{2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora \strong{or} genus is one of: \emph{Aspergillus}, \emph{Bacteroides}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Chryseobacterium}, \emph{Cryptococcus}, \emph{Elisabethkingia}, \emph{Flavobacterium}, \emph{Fusobacterium}, \emph{Giardia}, \emph{Leptotrichia}, \emph{Mycoplasma}, \emph{Prevotella}, \emph{Rhodotorula}, \emph{Treponema}, \emph{Trichophyton}, \emph{Ureaplasma}.}
#' \item{3 (least prevalent): all others.}
#' }
#'
@ -167,10 +167,9 @@
#' }
as.mo <- function(x, Becker = FALSE, Lancefield = FALSE, allow_uncertain = TRUE, reference_df = get_mo_source()) {
# will be checked for mo class in validation
mo <- mo_validate(x = x, property = "mo",
Becker = Becker, Lancefield = Lancefield,
allow_uncertain = allow_uncertain, reference_df = reference_df)
structure(.Data = mo, class = "mo")
mo_validate(x = x, property = "mo",
Becker = Becker, Lancefield = Lancefield,
allow_uncertain = allow_uncertain, reference_df = reference_df)
}
#' @rdname as.mo
@ -229,7 +228,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
x <- x[!is.na(x) & !is.null(x) & !identical(x, "")]
# conversion of old MO codes from v0.5.0 (ITIS) to later versions (Catalogue of Life)
if (any(x %like% "^[BFP]_[A-Z]{3,7}")) {
if (any(x %like% "^[BFP]_[A-Z]{3,7}") & !all(x %in% microorganisms$mo)) {
leftpart <- gsub("^([BFP]_[A-Z]{3,7}).*", "\\1", x)
if (any(leftpart %in% names(mo_codes_v0.5.0))) {
rightpart <- gsub("^[BFP]_[A-Z]{3,7}(.*)", "\\1", x)
@ -256,40 +255,52 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# all empty
if (all(identical(trimws(x_input), "") | is.na(x_input))) {
if (property == "mo") {
return(structure(rep(NA_character_, length(x_input)), class = "mo"))
return(structure(rep(NA_character_, length(x_input)),
class = "mo"))
} else {
return(rep(NA_character_, length(x_input)))
}
} else if (all(x %in% reference_df[, 1])
& all(reference_df[, "mo"] %in% microorganismsDT[, "mo"][[1]])) {
& all(reference_df[, "mo"] %in% AMR::microorganisms$mo)) {
# all in reference df
colnames(reference_df)[1] <- "x"
suppressWarnings(
x <- data.frame(x = x, stringsAsFactors = FALSE) %>%
left_join(reference_df, by = "x") %>%
left_join(microorganisms, by = "mo") %>%
left_join(AMR::microorganisms, by = "mo") %>%
pull(property)
)
} else if (all(x %in% microorganismsDT[, "mo"][[1]])) {
} else if (all(x %in% AMR::microorganisms$mo)) {
# existing mo codes when not looking for property "mo", like mo_genus("B_ESCHR_COL")
x <- microorganismsDT[data.table(mo = x), on = "mo", ..property][[1]]
y <- microorganismsDT[prevalence == 1][data.table(mo = x), on = "mo", ..property][[1]]
if (any(is.na(y))) {
y[is.na(y)] <- microorganismsDT[prevalence == 2][data.table(mo = x[is.na(y)]), on = "mo", ..property][[1]]
}
if (any(is.na(y))) {
y[is.na(y)] <- microorganismsDT[prevalence == 3][data.table(mo = x[is.na(y)]), on = "mo", ..property][[1]]
}
x <- y
} else if (all(x %in% microorganismsDT[prevalence == 1, "fullname"][[1]])) {
} else if (all(x %in% AMR::microorganisms$fullname)) {
# we need special treatment for very prevalent full names, they are likely!
# e.g. as.mo("Staphylococcus aureus")
x <- microorganismsDT[prevalence == 1][data.table(fullname = x), on = "fullname", ..property][[1]]
} else if (all(x %in% microorganismsDT[prevalence == 2, "fullname"][[1]])) {
# same for common full names, they are also likely
x <- microorganismsDT[prevalence == 2][data.table(fullname = x), on = "fullname", ..property][[1]]
y <- microorganismsDT[prevalence == 1][data.table(fullname = x), on = "fullname", ..property][[1]]
if (any(is.na(y))) {
y[is.na(y)] <- microorganismsDT[prevalence == 2][data.table(fullname = x[is.na(y)]), on = "fullname", ..property][[1]]
}
if (any(is.na(y))) {
y[is.na(y)] <- microorganismsDT[prevalence == 3][data.table(fullname = x[is.na(y)]), on = "fullname", ..property][[1]]
}
x <- y
} else if (all(toupper(x) %in% microorganisms.codes[, "code"])) {
} else if (all(toupper(x) %in% AMR::microorganisms.codes$code)) {
# commonly used MO codes
y <- as.data.table(microorganisms.codes)[data.table(code = toupper(x)), on = "code", ]
y <- as.data.table(AMR::microorganisms.codes)[data.table(code = toupper(x)), on = "code", ]
x <- microorganismsDT[data.table(mo = y[["mo"]]), on = "mo", ..property][[1]]
} else if (!all(x %in% microorganismsDT[, ..property][[1]])) {
} else if (!all(x %in% AMR::microorganisms[, property])) {
x_backup <- x
@ -504,8 +515,8 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
}
# TRY OTHER SOURCES ----
if (toupper(x_backup[i]) %in% microorganisms.codes[, 1]) {
mo_found <- microorganisms.codes[toupper(x_backup[i]) == microorganisms.codes[, 1], "mo"][1L]
if (toupper(x_backup[i]) %in% AMR::microorganisms.codes[, 1]) {
mo_found <- AMR::microorganisms.codes[toupper(x_backup[i]) == AMR::microorganisms.codes[, 1], "mo"][1L]
if (length(mo_found) > 0) {
x[i] <- microorganismsDT[mo == mo_found, ..property][[1]][1L]
next

2
R/mo_property.R
View File

@ -494,7 +494,7 @@ mo_validate <- function(x, property, ...) {
# check onLoad() in R/zzz.R: data tables are created there.
}
if (!all(x %in% microorganismsDT[, ..property][[1]])
if (!all(x %in% microorganisms[, property])
| Becker %in% c(TRUE, "all")
| Lancefield %in% c(TRUE, "all")) {
exec_as.mo(x, property = property, ...)

20
R/zzz.R
View File

@ -30,6 +30,10 @@
microorganisms.oldDT <- as.data.table(AMR::microorganisms.old)
setkey(microorganisms.oldDT, col_id, fullname)
assign(x = "microorganisms",
value = make(),
envir = asNamespace("AMR"))
assign(x = "microorganismsDT",
value = make_DT(),
envir = asNamespace("AMR"))
@ -45,9 +49,8 @@
}
#' @importFrom dplyr mutate case_when
#' @importFrom data.table as.data.table setkey
make_DT <- function() {
microorganismsDT <- AMR::microorganisms %>%
make <- function() {
AMR::microorganisms %>%
mutate(prevalence = case_when(
class == "Gammaproteobacteria"
| genus %in% c("Enterococcus", "Staphylococcus", "Streptococcus")
@ -71,11 +74,16 @@ make_DT <- function() {
"Prevotella",
"Rhodotorula",
"Treponema",
"Trichophyton")
"Trichophyton",
"Ureaplasma")
~ 2,
TRUE ~ 3
)) %>%
as.data.table()
))
}
#' @importFrom data.table as.data.table setkey
make_DT <- function() {
microorganismsDT <- as.data.table(make())
setkey(microorganismsDT,
kingdom,
prevalence,

477
docs/articles/AMR.html
View File

@ -327,70 +327,70 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2016-10-19</td>
<td align="center">U5</td>
<td align="center">2010-07-18</td>
<td align="center">Z5</td>
<td align="center">Hospital B</td>
<td align="center">Streptococcus pneumoniae</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2017-01-13</td>
<td align="center">P8</td>
<td align="center">Hospital C</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2016-05-27</td>
<td align="center">C10</td>
<td align="center">Hospital A</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2014-11-05</td>
<td align="center">A2</td>
<td align="center">Hospital A</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2017-03-21</td>
<td align="center">N6</td>
<td align="center">Hospital B</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="odd">
<td align="center">2010-03-02</td>
<td align="center">X6</td>
<td align="center">2014-07-31</td>
<td align="center">K5</td>
<td align="center">Hospital B</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2015-08-17</td>
<td align="center">B8</td>
<td align="center">Hospital D</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">2017-07-12</td>
<td align="center">U8</td>
<td align="center">Hospital B</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="odd">
<td align="center">2013-09-10</td>
<td align="center">Y1</td>
<td align="center">Hospital B</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2017-07-30</td>
<td align="center">X10</td>
<td align="center">Hospital C</td>
<td align="center">Streptococcus pneumoniae</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
</tbody>
</table>
@ -411,8 +411,8 @@
#&gt;
#&gt; Item Count Percent Cum. Count Cum. Percent
#&gt; --- ----- ------- -------- ----------- -------------
#&gt; 1 M 10,390 52.0% 10,390 52.0%
#&gt; 2 F 9,610 48.1% 20,000 100.0%</code></pre>
#&gt; 1 M 10,383 51.9% 10,383 51.9%
#&gt; 2 F 9,617 48.1% 20,000 100.0%</code></pre>
<p>So, we can draw at least two conclusions immediately. From a data scientist perspective, the data looks clean: only values <code>M</code> and <code>F</code>. From a researcher perspective: there are slightly more men. Nothing we didn’t already know.</p>
<p>The data is already quite clean, but we still need to transform some variables. The <code>bacteria</code> column now consists of text, and we want to add more variables based on microbial IDs later on. So, we will transform this column to valid IDs. The <code><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate()</a></code> function of the <code>dplyr</code> package makes this really easy:</p>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb12-1" title="1">data &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span></a>
@ -443,10 +443,10 @@
<a class="sourceLine" id="cb14-19" title="19"><span class="co">#&gt; Kingella kingae (no changes)</span></a>
<a class="sourceLine" id="cb14-20" title="20"><span class="co">#&gt; </span></a>
<a class="sourceLine" id="cb14-21" title="21"><span class="co">#&gt; EUCAST Expert Rules, Intrinsic Resistance and Exceptional Phenotypes (v3.1, 2016)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1369 changes)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1340 changes)</span></a>
<a class="sourceLine" id="cb14-23" title="23"><span class="co">#&gt; Table 2: Intrinsic resistance in non-fermentative Gram-negative bacteria (no changes)</span></a>
<a class="sourceLine" id="cb14-24" title="24"><span class="co">#&gt; Table 3: Intrinsic resistance in other Gram-negative bacteria (no changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2815 changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2699 changes)</span></a>
<a class="sourceLine" id="cb14-26" title="26"><span class="co">#&gt; Table 8: Interpretive rules for B-lactam agents and Gram-positive cocci (no changes)</span></a>
<a class="sourceLine" id="cb14-27" title="27"><span class="co">#&gt; Table 9: Interpretive rules for B-lactam agents and Gram-negative rods (no changes)</span></a>
<a class="sourceLine" id="cb14-28" title="28"><span class="co">#&gt; Table 10: Interpretive rules for B-lactam agents and other Gram-negative bacteria (no changes)</span></a>
@ -462,9 +462,9 @@
<a class="sourceLine" id="cb14-38" title="38"><span class="co">#&gt; Non-EUCAST: piperacillin/tazobactam = S where piperacillin = S (no changes)</span></a>
<a class="sourceLine" id="cb14-39" title="39"><span class="co">#&gt; Non-EUCAST: trimethoprim/sulfa = S where trimethoprim = S (no changes)</span></a>
<a class="sourceLine" id="cb14-40" title="40"><span class="co">#&gt; </span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,563 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,406 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-42" title="42"><span class="co">#&gt; -&gt; added 0 test results</span></a>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,184 test results (0 to S; 0 to I; 4,184 to R)</span></a></code></pre></div>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,039 test results (0 to S; 0 to I; 4,039 to R)</span></a></code></pre></div>
</div>
<div id="adding-new-variables" class="section level1">
<h1 class="hasAnchor">
@ -489,8 +489,8 @@
<a class="sourceLine" id="cb16-3" title="3"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `bacteria` as input for `col_mo`.</span></a>
<a class="sourceLine" id="cb16-4" title="4"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `date` as input for `col_date`.</span></a>
<a class="sourceLine" id="cb16-5" title="5"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `patient_id` as input for `col_patient_id`.</span></a>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,780 first isolates (28.9% of total)</span></a></code></pre></div>
<p>So only 28.9% is suitable for resistance analysis! We can now filter on it with the <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> function, also from the <code>dplyr</code> package:</p>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,676 first isolates (28.4% of total)</span></a></code></pre></div>
<p>So only 28.4% is suitable for resistance analysis! We can now filter on it with the <code><a href="https://dplyr.tidyverse.org/reference/filter.html">filter()</a></code> function, also from the <code>dplyr</code> package:</p>
<div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb17-1" title="1">data_1st &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb17-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/filter.html">filter</a></span>(first <span class="op">==</span><span class="st"> </span><span class="ot">TRUE</span>)</a></code></pre></div>
<p>For future use, the above two syntaxes can be shortened with the <code><a href="../reference/first_isolate.html">filter_first_isolate()</a></code> function:</p>
@ -516,8 +516,8 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-01-05</td>
<td align="center">G4</td>
<td align="center">2010-03-12</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -527,19 +527,19 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-03-10</td>
<td align="center">G4</td>
<td align="center">2010-04-30</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-07-15</td>
<td align="center">G4</td>
<td align="center">2010-06-28</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -549,8 +549,8 @@
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-09-07</td>
<td align="center">G4</td>
<td align="center">2010-07-08</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -560,67 +560,67 @@
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-11-10</td>
<td align="center">G4</td>
<td align="center">2010-08-22</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2011-01-23</td>
<td align="center">G4</td>
<td align="center">2010-09-04</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2011-02-21</td>
<td align="center">G4</td>
<td align="center">2010-11-16</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2011-02-25</td>
<td align="center">G4</td>
<td align="center">2011-03-31</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2011-02-28</td>
<td align="center">G4</td>
<td align="center">2011-05-25</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-04-03</td>
<td align="center">G4</td>
<td align="center">2011-08-25</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
@ -637,7 +637,7 @@
<a class="sourceLine" id="cb19-7" title="7"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `patient_id` as input for `col_patient_id`.</span></a>
<a class="sourceLine" id="cb19-8" title="8"><span class="co">#&gt; </span><span class="al">NOTE</span><span class="co">: Using column `keyab` as input for `col_keyantibiotics`. Use col_keyantibiotics = FALSE to prevent this.</span></a>
<a class="sourceLine" id="cb19-9" title="9"><span class="co">#&gt; [Criterion] Inclusion based on key antibiotics, ignoring I.</span></a>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,963 first weighted isolates (79.8% of total)</span></a></code></pre></div>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,935 first weighted isolates (79.7% of total)</span></a></code></pre></div>
<table class="table">
<thead><tr class="header">
<th align="center">isolate</th>
@ -654,8 +654,8 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-01-05</td>
<td align="center">G4</td>
<td align="center">2010-03-12</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -666,8 +666,20 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-03-10</td>
<td align="center">G4</td>
<td align="center">2010-04-30</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-06-28</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -676,22 +688,10 @@
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-07-15</td>
<td align="center">G4</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-09-07</td>
<td align="center">G4</td>
<td align="center">2010-07-08</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -702,11 +702,11 @@
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-11-10</td>
<td align="center">G4</td>
<td align="center">2010-08-22</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
@ -714,23 +714,23 @@
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2011-01-23</td>
<td align="center">G4</td>
<td align="center">2010-09-04</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">TRUE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2011-02-21</td>
<td align="center">G4</td>
<td align="center">2010-11-16</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
@ -738,47 +738,47 @@
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2011-02-25</td>
<td align="center">G4</td>
<td align="center">2011-03-31</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2011-02-28</td>
<td align="center">G4</td>
<td align="center">2011-05-25</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-04-03</td>
<td align="center">G4</td>
<td align="center">2011-08-25</td>
<td align="center">I7</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
</tbody>
</table>
<p>Instead of 2, now 8 isolates are flagged. In total, 79.8% of all isolates are marked ‘first weighted’ - 50.9% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.</p>
<p>Instead of 2, now 7 isolates are flagged. In total, 79.7% of all isolates are marked ‘first weighted’ - 51.3% more than when using the CLSI guideline. In real life, this novel algorithm will yield 5-10% more isolates than the classic CLSI guideline.</p>
<p>As with <code><a href="../reference/first_isolate.html">filter_first_isolate()</a></code>, there’s a shortcut for this new algorithm too:</p>
<div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb20-1" title="1">data_1st &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb20-2" title="2"><span class="st"> </span><span class="kw"><a href="../reference/first_isolate.html">filter_first_weighted_isolate</a></span>()</a></code></pre></div>
<p>So we end up with 15,963 isolates for analysis.</p>
<p>So we end up with 15,935 isolates for analysis.</p>
<p>We can remove unneeded columns:</p>
<div class="sourceCode" id="cb21"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb21-1" title="1">data_1st &lt;-<span class="st"> </span>data_1st <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb21-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/select.html">select</a></span>(<span class="op">-</span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(first, keyab))</a></code></pre></div>
@ -786,7 +786,6 @@
<div class="sourceCode" id="cb22"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb22-1" title="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/utils/topics/head">head</a></span>(data_1st)</a></code></pre></div>
<table class="table">
<thead><tr class="header">
<th></th>
<th align="center">date</th>
<th align="center">patient_id</th>
<th align="center">hospital</th>
@ -803,101 +802,95 @@
</tr></thead>
<tbody>
<tr class="odd">
<td>1</td>
<td align="center">2016-10-19</td>
<td align="center">U5</td>
<td align="center">2010-07-18</td>
<td align="center">Z5</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">B_STRPT_PNE</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">Gram positive</td>
<td align="center">Streptococcus</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>3</td>
<td align="center">2014-11-05</td>
<td align="center">A2</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>5</td>
<td align="center">2010-03-02</td>
<td align="center">X6</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>6</td>
<td align="center">2015-08-17</td>
<td align="center">B8</td>
<td align="center">Hospital D</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>7</td>
<td align="center">2013-01-25</td>
<td align="center">M3</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>8</td>
<td align="center">2013-07-27</td>
<td align="center">E2</td>
<td align="center">2017-01-13</td>
<td align="center">P8</td>
<td align="center">Hospital C</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">2014-07-31</td>
<td align="center">K5</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">Gram negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">2017-07-12</td>
<td align="center">U8</td>
<td align="center">Hospital B</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Klebsiella</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">2013-09-10</td>
<td align="center">Y1</td>
<td align="center">Hospital B</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">Gram negative</td>
<td align="center">Klebsiella</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">2017-07-30</td>
<td align="center">X10</td>
<td align="center">Hospital C</td>
<td align="center">B_STRPT_PNE</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">F</td>
<td align="center">Gram positive</td>
<td align="center">Streptococcus</td>
<td align="center">pneumoniae</td>
<td align="center">TRUE</td>
</tr>
</tbody>
</table>
<p>Time for the analysis!</p>
@ -915,9 +908,9 @@
<div class="sourceCode" id="cb23"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb23-1" title="1"><span class="kw"><a href="../reference/freq.html">freq</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/paste">paste</a></span>(data_1st<span class="op">$</span>genus, data_1st<span class="op">$</span>species))</a></code></pre></div>
<p>Or can be used like the <code>dplyr</code> way, which is easier readable:</p>
<div class="sourceCode" id="cb24"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb24-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/freq.html">freq</a></span>(genus, species)</a></code></pre></div>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,963 x 13)</strong></p>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,935 x 13)</strong></p>
<p>Columns: 2<br>
Length: 15,963 (of which NA: 0 = 0.00%)<br>
Length: 15,935 (of which NA: 0 = 0.00%)<br>
Unique: 4</p>
<p>Shortest: 16<br>
Longest: 24</p>
@ -934,33 +927,33 @@ Longest: 24</p>
<tr class="odd">
<td align="left">1</td>
<td align="left">Escherichia coli</td>
<td align="right">7,910</td>
<td align="right">7,898</td>
<td align="right">49.6%</td>
<td align="right">7,910</td>
<td align="right">7,898</td>
<td align="right">49.6%</td>
</tr>
<tr class="even">
<td align="left">2</td>
<td align="left">Staphylococcus aureus</td>
<td align="right">3,889</td>
<td align="right">24.4%</td>
<td align="right">11,799</td>
<td align="right">73.9%</td>
<td align="right">4,017</td>
<td align="right">25.2%</td>
<td align="right">11,915</td>
<td align="right">74.8%</td>
</tr>
<tr class="odd">
<td align="left">3</td>
<td align="left">Streptococcus pneumoniae</td>
<td align="right">2,480</td>
<td align="right">15.5%</td>
<td align="right">14,279</td>
<td align="right">89.5%</td>
<td align="right">2,449</td>
<td align="right">15.4%</td>
<td align="right">14,364</td>
<td align="right">90.1%</td>
</tr>
<tr class="even">
<td align="left">4</td>
<td align="left">Klebsiella pneumoniae</td>
<td align="right">1,684</td>
<td align="right">10.5%</td>
<td align="right">15,963</td>
<td align="right">1,571</td>
<td align="right">9.9%</td>
<td align="right">15,935</td>
<td align="right">100.0%</td>
</tr>
</tbody>
@ -971,7 +964,7 @@ Longest: 24</p>
<a href="#resistance-percentages" class="anchor"></a>Resistance percentages</h2>
<p>The functions <code>portion_R</code>, <code>portion_RI</code>, <code>portion_I</code>, <code>portion_IS</code> and <code>portion_S</code> can be used to determine the portion of a specific antimicrobial outcome. They can be used on their own:</p>
<div class="sourceCode" id="cb25"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb25-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span><span class="kw"><a href="../reference/portion.html">portion_IR</a></span>(amox)</a>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4748481</span></a></code></pre></div>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4776279</span></a></code></pre></div>
<p>Or can be used in conjuction with <code><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by()</a></code> and <code><a href="https://dplyr.tidyverse.org/reference/summarise.html">summarise()</a></code>, both from the <code>dplyr</code> package:</p>
<div class="sourceCode" id="cb26"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb26-1" title="1">data_1st <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb26-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/group_by.html">group_by</a></span>(hospital) <span class="op">%&gt;%</span><span class="st"> </span></a>
@ -984,19 +977,19 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4765396</td>
<td align="center">0.4740616</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4750632</td>
<td align="center">0.4748265</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4830405</td>
<td align="center">0.4910305</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4657107</td>
<td align="center">0.4777953</td>
</tr>
</tbody>
</table>
@ -1014,23 +1007,23 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4765396</td>
<td align="center">4774</td>
<td align="center">0.4740616</td>
<td align="center">4742</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4750632</td>
<td align="center">5534</td>
<td align="center">0.4748265</td>
<td align="center">5621</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4830405</td>
<td align="center">2447</td>
<td align="center">0.4910305</td>
<td align="center">2397</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4657107</td>
<td align="center">3208</td>
<td align="center">0.4777953</td>
<td align="center">3175</td>
</tr>
</tbody>
</table>
@ -1050,27 +1043,27 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Escherichia</td>
<td align="center">0.7353982</td>
<td align="center">0.8972187</td>
<td align="center">0.9734513</td>
<td align="center">0.7295518</td>
<td align="center">0.9013674</td>
<td align="center">0.9772094</td>
</tr>
<tr class="even">
<td align="center">Klebsiella</td>
<td align="center">0.7369359</td>
<td align="center">0.9014252</td>
<td align="center">0.9786223</td>
<td align="center">0.7517505</td>
<td align="center">0.9000637</td>
<td align="center">0.9789943</td>
</tr>
<tr class="odd">
<td align="center">Staphylococcus</td>
<td align="center">0.7413217</td>
<td align="center">0.9161738</td>
<td align="center">0.9763435</td>
<td align="center">0.7353747</td>
<td align="center">0.9168534</td>
<td align="center">0.9788399</td>
</tr>
<tr class="even">
<td align="center">Streptococcus</td>
<td align="center">0.7181452</td>
<td align="center">0.7390772</td>
<td align="center">0.0000000</td>
<td align="center">0.7181452</td>
<td align="center">0.7390772</td>
</tr>
</tbody>
</table>

BIN
docs/articles/AMR_files/figure-html/plot 1-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 33 KiB

After

Width:  |  Height:  |  Size: 33 KiB

BIN
docs/articles/AMR_files/figure-html/plot 3-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 21 KiB

After

Width:  |  Height:  |  Size: 21 KiB

BIN
docs/articles/AMR_files/figure-html/plot 4-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 68 KiB

After

Width:  |  Height:  |  Size: 68 KiB

BIN
docs/articles/AMR_files/figure-html/plot 5-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 50 KiB

After

Width:  |  Height:  |  Size: 50 KiB

163
docs/articles/benchmarks.html
View File

@ -210,56 +210,47 @@
<div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb2-1" title="1">S.aureus &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"sau"</span>),</a>
<a class="sourceLine" id="cb2-2" title="2"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"stau"</span>),</a>
<a class="sourceLine" id="cb2-3" title="3"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"staaur"</span>),</a>
<a class="sourceLine" id="cb2-4" title="4"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S. aureus"</span>),</a>
<a class="sourceLine" id="cb2-5" title="5"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S. aureus"</span>),</a>
<a class="sourceLine" id="cb2-6" title="6"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"STAAUR"</span>),</a>
<a class="sourceLine" id="cb2-4" title="4"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"STAAUR"</span>),</a>
<a class="sourceLine" id="cb2-5" title="5"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S. aureus"</span>),</a>
<a class="sourceLine" id="cb2-6" title="6"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"S. aureus"</span>),</a>
<a class="sourceLine" id="cb2-7" title="7"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Staphylococcus aureus"</span>),</a>
<a class="sourceLine" id="cb2-8" title="8"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb2-9" title="9"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(S.aureus, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb2-10" title="10"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb2-11" title="11"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb2-12" title="12"><span class="co">#&gt; as.mo("sau") 16.4 16.5 28.4 16.8 54.9 55.8 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 86.0 86.5 97.3 88.9 100.0 132.0 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.3 16.6 23.0 16.8 21.0 56.8 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("S. aureus") 25.3 25.9 39.4 27.2 64.0 74.5 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 25.2 25.3 29.7 25.6 27.0 64.3 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("STAAUR") 16.3 16.7 21.1 17.0 18.0 56.8 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 13.5 13.9 20.5 14.4 17.5 51.2 10</span></a></code></pre></div>
<a class="sourceLine" id="cb2-12" title="12"><span class="co">#&gt; as.mo("sau") 12.1 12.2 12.3 12.2 12.3 12.6 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 81.3 81.9 97.3 82.7 120.0 155.0 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 12.2 12.3 12.7 12.6 13.2 13.5 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 12.2 12.3 16.5 12.6 13.4 50.7 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 20.1 20.1 25.2 20.1 20.2 69.9 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 20.1 20.2 20.7 20.3 21.6 22.0 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 11.2 11.3 11.5 11.3 11.5 12.4 10</span></a></code></pre></div>
<p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 10 milliseconds means it can determine 100 input values per second. It case of 50 milliseconds, this is only 20 input values per second. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first is a WHONET code) or common laboratory codes, or common full organism names like the last one.</p>
<p>To achieve this speed, the <code>as.mo</code> function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of <em>Mycoplasma leonicaptivi</em> (<code>B_MYCPL_LEO</code>), a bug probably never found before in humans:</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb3-1" title="1">M.leonicaptivi &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"myle"</span>),</a>
<a class="sourceLine" id="cb3-2" title="2"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"mycleo"</span>),</a>
<a class="sourceLine" id="cb3-3" title="3"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"M. leonicaptivi"</span>),</a>
<a class="sourceLine" id="cb3-4" title="4"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"M. leonicaptivi"</span>),</a>
<a class="sourceLine" id="cb3-5" title="5"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"MYCLEO"</span>),</a>
<a class="sourceLine" id="cb3-6" title="6"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Mycoplasma leonicaptivi"</span>),</a>
<a class="sourceLine" id="cb3-7" title="7"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb3-8" title="8"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(M.leonicaptivi, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb3-9" title="9"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; expr min lq mean median uq max</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("myle") 135.0 135.0 147.0 135.0 174.0 176.0</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("mycleo") 211.0 213.0 233.0 232.0 251.0 262.0</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("M. leonicaptivi") 59.2 59.2 63.6 59.4 59.6 98.7</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("M. leonicaptivi") 59.0 59.1 59.3 59.3 59.3 59.7</span></a>
<a class="sourceLine" id="cb3-15" title="15"><span class="co">#&gt; as.mo("MYCLEO") 211.0 211.0 220.0 211.0 222.0 250.0</span></a>
<a class="sourceLine" id="cb3-16" title="16"><span class="co">#&gt; as.mo("Mycoplasma leonicaptivi") 22.5 22.5 26.5 22.6 22.7 61.0</span></a>
<a class="sourceLine" id="cb3-17" title="17"><span class="co">#&gt; neval</span></a>
<a class="sourceLine" id="cb3-18" title="18"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-19" title="19"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-20" title="20"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-21" title="21"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-22" title="22"><span class="co">#&gt; 10</span></a>
<a class="sourceLine" id="cb3-23" title="23"><span class="co">#&gt; 10</span></a></code></pre></div>
<p>That takes 3.4 times as much time on average! A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance.</p>
<p>In the figure below, we compare <em>Escherichia coli</em> (which is very common) with <em>Prevotella brevis</em> (which is moderately common) and with <em>Mycoplasma leonicaptivi</em> (which is very uncommon):</p>
<p>To achieve this speed, the <code>as.mo</code> function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of <em>Thermus islandicus</em> (<code>B_THERMS_ISL</code>), a bug probably never found before in humans:</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb3-1" title="1">T.islandicus &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"theisl"</span>),</a>
<a class="sourceLine" id="cb3-2" title="2"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"THEISL"</span>),</a>
<a class="sourceLine" id="cb3-3" title="3"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"T. islandicus"</span>),</a>
<a class="sourceLine" id="cb3-4" title="4"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"T. islandicus"</span>),</a>
<a class="sourceLine" id="cb3-5" title="5"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Thermus islandicus"</span>),</a>
<a class="sourceLine" id="cb3-6" title="6"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb3-7" title="7"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(T.islandicus, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb3-8" title="8"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb3-9" title="9"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; as.mo("theisl") 446.0 452.0 478.0 486.0 488.0 506 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 446.0 446.0 471.0 467.0 489.0 528 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 76.5 77.1 87.4 77.2 85.4 127 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 76.9 76.9 81.4 77.1 79.1 116 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 67.6 67.7 80.0 67.9 106.0 112 10</span></a></code></pre></div>
<p>That takes 8.5 times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like <em>Thermus islandicus</em>) are almost fast - these are the most probable input from most data sets.</p>
<p>In the figure below, we compare <em>Escherichia coli</em> (which is very common) with <em>Prevotella brevis</em> (which is moderately common) and with <em>Thermus islandicus</em> (which is very uncommon):</p>
<div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb4-1" title="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/graphics/topics/par">par</a></span>(<span class="dt">mar =</span> <span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/c">c</a></span>(<span class="dv">5</span>, <span class="dv">16</span>, <span class="dv">4</span>, <span class="dv">2</span>)) <span class="co"># set more space for left margin text (16)</span></a>
<a class="sourceLine" id="cb4-2" title="2"></a>
<a class="sourceLine" id="cb4-3" title="3"><span class="kw"><a href="https://www.rdocumentation.org/packages/graphics/topics/boxplot">boxplot</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"M. leonicaptivi"</span>),</a>
<a class="sourceLine" id="cb4-4" title="4"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Mycoplasma leonicaptivi"</span>),</a>
<a class="sourceLine" id="cb4-5" title="5"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"P. brevis"</span>),</a>
<a class="sourceLine" id="cb4-6" title="6"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Prevotella brevis"</span>),</a>
<a class="sourceLine" id="cb4-7" title="7"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"E. coli"</span>),</a>
<a class="sourceLine" id="cb4-8" title="8"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Escherichia coli"</span>),</a>
<a class="sourceLine" id="cb4-3" title="3"><span class="kw"><a href="https://www.rdocumentation.org/packages/graphics/topics/boxplot">boxplot</a></span>(<span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Thermus islandicus"</span>),</a>
<a class="sourceLine" id="cb4-4" title="4"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Prevotella brevis"</span>),</a>
<a class="sourceLine" id="cb4-5" title="5"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"Escherichia coli"</span>),</a>
<a class="sourceLine" id="cb4-6" title="6"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"T. islandicus"</span>),</a>
<a class="sourceLine" id="cb4-7" title="7"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"P. brevis"</span>),</a>
<a class="sourceLine" id="cb4-8" title="8"> <span class="kw"><a href="../reference/as.mo.html">as.mo</a></span>(<span class="st">"E. coli"</span>),</a>
<a class="sourceLine" id="cb4-9" title="9"> <span class="dt">times =</span> <span class="dv">50</span>),</a>
<a class="sourceLine" id="cb4-10" title="10"> <span class="dt">horizontal =</span> <span class="ot">TRUE</span>, <span class="dt">las =</span> <span class="dv">1</span>, <span class="dt">unit =</span> <span class="st">"s"</span>, <span class="dt">log =</span> <span class="ot">FALSE</span>,</a>
<a class="sourceLine" id="cb4-11" title="11"> <span class="dt">xlab =</span> <span class="st">""</span>, <span class="dt">ylab =</span> <span class="st">"Time in seconds"</span>,</a>
@ -271,27 +262,33 @@
<a href="#repetitive-results" class="anchor"></a>Repetitive results</h3>
<p>Repetitive results mean that unique values are present more than once. Unique values will only be calculated once by <code><a href="../reference/as.mo.html">as.mo()</a></code>. We will use <code><a href="../reference/mo_property.html">mo_fullname()</a></code> for this test - a helper function that returns the full microbial name (genus, species and possibly subspecies) which uses <code><a href="../reference/as.mo.html">as.mo()</a></code> internally.</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb5-1" title="1"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/library">library</a></span>(dplyr)</a>
<a class="sourceLine" id="cb5-2" title="2"><span class="co"># take 500,000 random MO codes from the septic_patients data set</span></a>
<a class="sourceLine" id="cb5-3" title="3">x =<span class="st"> </span>septic_patients <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-4" title="4"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/sample.html">sample_n</a></span>(<span class="dv">500000</span>, <span class="dt">replace =</span> <span class="ot">TRUE</span>) <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-5" title="5"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/pull.html">pull</a></span>(mo)</a>
<a class="sourceLine" id="cb5-6" title="6"> </a>
<a class="sourceLine" id="cb5-7" title="7"><span class="co"># got the right length?</span></a>
<a class="sourceLine" id="cb5-8" title="8"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/length">length</a></span>(x)</a>
<a class="sourceLine" id="cb5-9" title="9"><span class="co">#&gt; [1] 500000</span></a>
<a class="sourceLine" id="cb5-10" title="10"></a>
<a class="sourceLine" id="cb5-11" title="11"><span class="co"># and how many unique values do we have?</span></a>
<a class="sourceLine" id="cb5-12" title="12"><span class="kw"><a href="https://dplyr.tidyverse.org/reference/n_distinct.html">n_distinct</a></span>(x)</a>
<a class="sourceLine" id="cb5-13" title="13"><span class="co">#&gt; [1] 95</span></a>
<a class="sourceLine" id="cb5-14" title="14"></a>
<a class="sourceLine" id="cb5-15" title="15"><span class="co"># now let's see:</span></a>
<a class="sourceLine" id="cb5-16" title="16">run_it &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(x),</a>
<a class="sourceLine" id="cb5-17" title="17"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb5-18" title="18"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb5-19" title="19"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb5-20" title="20"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb5-21" title="21"><span class="co">#&gt; mo_fullname(x) 610 641 644 644 657 665 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!) of 95 unique values only takes 0.64 seconds (644 ms). You only lose time on your unique input values.</p>
<a class="sourceLine" id="cb5-2" title="2"><span class="co"># take all MO codes from the septic_patients data set</span></a>
<a class="sourceLine" id="cb5-3" title="3">x &lt;-<span class="st"> </span>septic_patients<span class="op">$</span>mo <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-4" title="4"><span class="st"> </span><span class="co"># keep only the unique ones</span></a>
<a class="sourceLine" id="cb5-5" title="5"><span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/unique">unique</a></span>() <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-6" title="6"><span class="st"> </span><span class="co"># pick 50 of them at random</span></a>
<a class="sourceLine" id="cb5-7" title="7"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/sample.html">sample</a></span>(<span class="dv">50</span>) <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-8" title="8"><span class="st"> </span><span class="co"># paste that 10,000 times</span></a>
<a class="sourceLine" id="cb5-9" title="9"><span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/rep">rep</a></span>(<span class="dv">10000</span>) <span class="op">%&gt;%</span></a>
<a class="sourceLine" id="cb5-10" title="10"><span class="st"> </span><span class="co"># scramble it</span></a>
<a class="sourceLine" id="cb5-11" title="11"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/sample.html">sample</a></span>()</a>
<a class="sourceLine" id="cb5-12" title="12"> </a>
<a class="sourceLine" id="cb5-13" title="13"><span class="co"># got indeed 50 times 10,000 = half a million?</span></a>
<a class="sourceLine" id="cb5-14" title="14"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/length">length</a></span>(x)</a>
<a class="sourceLine" id="cb5-15" title="15"><span class="co">#&gt; [1] 500000</span></a>
<a class="sourceLine" id="cb5-16" title="16"></a>
<a class="sourceLine" id="cb5-17" title="17"><span class="co"># and how many unique values do we have?</span></a>
<a class="sourceLine" id="cb5-18" title="18"><span class="kw"><a href="https://dplyr.tidyverse.org/reference/n_distinct.html">n_distinct</a></span>(x)</a>
<a class="sourceLine" id="cb5-19" title="19"><span class="co">#&gt; [1] 50</span></a>
<a class="sourceLine" id="cb5-20" title="20"></a>
<a class="sourceLine" id="cb5-21" title="21"><span class="co"># now let's see:</span></a>
<a class="sourceLine" id="cb5-22" title="22">run_it &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(x),</a>
<a class="sourceLine" id="cb5-23" title="23"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb5-24" title="24"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb5-25" title="25"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb5-26" title="26"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb5-27" title="27"><span class="co">#&gt; mo_fullname(x) 679 731 768 762 779 886 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!!) of 50 unique values only takes 0.76 seconds (762 ms). You only lose time on your unique input values.</p>
</div>
<div id="precalculated-results" class="section level3">
<h3 class="hasAnchor">
@ -303,11 +300,11 @@
<a class="sourceLine" id="cb6-4" title="4"> <span class="dt">times =</span> <span class="dv">10</span>)</a>
<a class="sourceLine" id="cb6-5" title="5"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb6-6" title="6"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb6-7" title="7"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb6-8" title="8"><span class="co">#&gt; A 7.500 7.540 7.720 7.610 7.710 8.750 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 25.800 26.200 27.100 27.800 27.800 27.900 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.604 0.628 0.704 0.729 0.755 0.791 10</span></a></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_fullname("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0007 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>
<a class="sourceLine" id="cb6-7" title="7"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb6-8" title="8"><span class="co">#&gt; A 10.200 10.400 10.800 10.700 10.900 12.00 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 20.700 20.800 21.000 20.900 21.100 22.30 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.305 0.313 0.454 0.441 0.568 0.72 10</span></a></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_fullname("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0004 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="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb7-1" title="1">run_it &lt;-<span class="st"> </span><span class="kw"><a href="https://www.rdocumentation.org/packages/microbenchmark/topics/microbenchmark">microbenchmark</a></span>(<span class="dt">A =</span> <span class="kw"><a href="../reference/mo_property.html">mo_species</a></span>(<span class="st">"aureus"</span>),</a>
<a class="sourceLine" id="cb7-2" title="2"> <span class="dt">B =</span> <span class="kw"><a href="../reference/mo_property.html">mo_genus</a></span>(<span class="st">"Staphylococcus"</span>),</a>
<a class="sourceLine" id="cb7-3" title="3"> <span class="dt">C =</span> <span class="kw"><a href="../reference/mo_property.html">mo_fullname</a></span>(<span class="st">"Staphylococcus aureus"</span>),</a>
@ -320,14 +317,14 @@
<a class="sourceLine" id="cb7-10" title="10"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">3</span>)</a>
<a class="sourceLine" id="cb7-11" title="11"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb7-12" title="12"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.704 0.806 0.897 0.867 1.040 1.130 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.671 0.722 0.841 0.807 0.903 1.110 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.702 0.768 0.856 0.816 0.967 1.160 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.641 0.695 0.746 0.746 0.755 0.976 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.627 0.702 0.781 0.762 0.789 1.100 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.651 0.694 0.779 0.733 0.761 1.220 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.552 0.745 0.801 0.764 0.815 1.090 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.637 0.661 0.722 0.724 0.766 0.803 10</span></a></code></pre></div>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.366 0.446 0.563 0.523 0.681 0.785 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.365 0.453 0.598 0.661 0.682 0.859 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.369 0.477 0.633 0.646 0.674 1.150 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.283 0.337 0.455 0.464 0.609 0.611 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.309 0.333 0.422 0.393 0.527 0.606 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.280 0.316 0.457 0.466 0.557 0.676 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.283 0.328 0.422 0.359 0.535 0.638 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.295 0.339 0.402 0.368 0.460 0.562 10</span></a></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> too, 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">
@ -354,13 +351,13 @@
<a class="sourceLine" id="cb8-18" title="18"><span class="kw"><a href="https://www.rdocumentation.org/packages/base/topics/print">print</a></span>(run_it, <span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">signif =</span> <span class="dv">4</span>)</a>
<a class="sourceLine" id="cb8-19" title="19"><span class="co">#&gt; Unit: milliseconds</span></a>
<a class="sourceLine" id="cb8-20" title="20"><span class="co">#&gt; expr min lq mean median uq max neval</span></a>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 18.95 18.99 19.59 19.04 19.49 23.47 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 27.13 27.26 27.69 27.63 27.88 29.05 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 26.95 27.62 34.90 27.99 32.35 61.05 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 27.42 27.55 38.05 27.75 60.86 61.40 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 26.99 27.30 34.13 27.48 27.70 61.28 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 27.35 27.52 30.95 27.58 27.72 61.11 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 27.26 27.33 27.67 27.53 27.91 28.44 10</span></a></code></pre></div>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 13.28 13.65 27.39 31.90 36.32 47.03 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 21.46 22.08 32.62 22.15 45.37 80.16 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 21.54 22.09 29.93 22.23 44.86 55.15 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 21.53 22.09 28.80 22.10 22.16 57.05 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 22.00 22.16 23.19 22.28 23.35 27.89 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 22.15 22.17 26.42 22.34 23.48 45.54 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 22.05 22.09 28.13 22.31 23.76 55.38 10</span></a></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-5-1.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 32 KiB

After

Width:  |  Height:  |  Size: 29 KiB

2
docs/reference/as.mo.html
View File

@ -334,7 +334,7 @@ When using <code>allow_uncertain = TRUE</code> (which is the default setting), i
<p>The artificial intelligence takes into account microbial prevalence of pathogens in humans. It uses three groups and every (sub)species is in the group it matches first. These groups are:</p><ul>
<li><p>1 (most prevalent): class is Gammaproteobacteria <strong>or</strong> genus is one of: <em>Enterococcus</em>, <em>Staphylococcus</em>, <em>Streptococcus</em>.</p></li>
<li><p>2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora <strong>or</strong> genus is one of: <em>Aspergillus</em>, <em>Bacteroides</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Chryseobacterium</em>, <em>Cryptococcus</em>, <em>Elisabethkingia</em>, <em>Flavobacterium</em>, <em>Fusobacterium</em>, <em>Giardia</em>, <em>Leptotrichia</em>, <em>Mycoplasma</em>, <em>Prevotella</em>, <em>Rhodotorula</em>, <em>Treponema</em>, <em>Trichophyton</em>.</p></li>
<li><p>2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora <strong>or</strong> genus is one of: <em>Aspergillus</em>, <em>Bacteroides</em>, <em>Candida</em>, <em>Capnocytophaga</em>, <em>Chryseobacterium</em>, <em>Cryptococcus</em>, <em>Elisabethkingia</em>, <em>Flavobacterium</em>, <em>Fusobacterium</em>, <em>Giardia</em>, <em>Leptotrichia</em>, <em>Mycoplasma</em>, <em>Prevotella</em>, <em>Rhodotorula</em>, <em>Treponema</em>, <em>Trichophyton</em>, <em>Ureaplasma</em>.</p></li>
<li><p>3 (least prevalent): all others.</p></li>
</ul>
<p>Group 1 contains all common Gram negatives, like all Enterobacteriaceae and e.g. <em>Pseudomonas</em> and <em>Legionella</em>.</p>

2
man/as.mo.Rd
View File

@ -105,7 +105,7 @@ Use \code{mo_renamed()} to get a vector with all values that could be coerced ba
The artificial intelligence takes into account microbial prevalence of pathogens in humans. It uses three groups and every (sub)species is in the group it matches first. These groups are:
\itemize{
\item{1 (most prevalent): class is Gammaproteobacteria \strong{or} genus is one of: \emph{Enterococcus}, \emph{Staphylococcus}, \emph{Streptococcus}.}
\item{2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora \strong{or} genus is one of: \emph{Aspergillus}, \emph{Bacteroides}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Chryseobacterium}, \emph{Cryptococcus}, \emph{Elisabethkingia}, \emph{Flavobacterium}, \emph{Fusobacterium}, \emph{Giardia}, \emph{Leptotrichia}, \emph{Mycoplasma}, \emph{Prevotella}, \emph{Rhodotorula}, \emph{Treponema}, \emph{Trichophyton}.}
\item{2: phylum is one of: Proteobacteria, Firmicutes, Actinobacteria, Sarcomastigophora \strong{or} genus is one of: \emph{Aspergillus}, \emph{Bacteroides}, \emph{Candida}, \emph{Capnocytophaga}, \emph{Chryseobacterium}, \emph{Cryptococcus}, \emph{Elisabethkingia}, \emph{Flavobacterium}, \emph{Fusobacterium}, \emph{Giardia}, \emph{Leptotrichia}, \emph{Mycoplasma}, \emph{Prevotella}, \emph{Rhodotorula}, \emph{Treponema}, \emph{Trichophyton}, \emph{Ureaplasma}.}
\item{3 (least prevalent): all others.}
}

47
vignettes/benchmarks.Rmd
View File

@ -44,9 +44,9 @@ But the calculation time differs a lot. Here, the AI effect can be reviewed best
S.aureus <- microbenchmark(as.mo("sau"),
as.mo("stau"),
as.mo("staaur"),
as.mo("STAAUR"),
as.mo("S. aureus"),
as.mo("S. aureus"),
as.mo("STAAUR"),
as.mo("Staphylococcus aureus"),
times = 10)
print(S.aureus, unit = "ms", signif = 3)
@ -54,32 +54,31 @@ print(S.aureus, unit = "ms", signif = 3)
In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 10 milliseconds means it can determine 100 input values per second. It case of 50 milliseconds, this is only 20 input values per second. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first is a WHONET code) or common laboratory codes, or common full organism names like the last one.
To achieve this speed, the `as.mo` function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of *Mycoplasma leonicaptivi* (`B_MYCPL_LEO`), a bug probably never found before in humans:
To achieve this speed, the `as.mo` function also takes into account the prevalence of human pathogenic microorganisms. The downside is of course that less prevalent microorganisms will be determined less fast. See this example for the ID of *Thermus islandicus* (`B_THERMS_ISL`), a bug probably never found before in humans:
```{r}
M.leonicaptivi <- microbenchmark(as.mo("myle"),
as.mo("mycleo"),
as.mo("M. leonicaptivi"),
as.mo("M. leonicaptivi"),
as.mo("MYCLEO"),
as.mo("Mycoplasma leonicaptivi"),
T.islandicus <- microbenchmark(as.mo("theisl"),
as.mo("THEISL"),
as.mo("T. islandicus"),
as.mo("T. islandicus"),
as.mo("Thermus islandicus"),
times = 10)
print(M.leonicaptivi, unit = "ms", signif = 3)
print(T.islandicus, unit = "ms", signif = 3)
```
That takes `r round(mean(M.leonicaptivi$time, na.rm = TRUE) / mean(S.aureus$time, na.rm = TRUE), 1)` times as much time on average! A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance.
That takes `r round(mean(T.islandicus$time, na.rm = TRUE) / mean(S.aureus$time, na.rm = TRUE), 1)` times as much time on average. A value of 100 milliseconds means it can only determine ~10 different input values per second. We can conclude that looking up arbitrary codes of less prevalent microorganisms is the worst way to go, in terms of calculation performance. Full names (like *Thermus islandicus*) are almost fast - these are the most probable input from most data sets.
In the figure below, we compare *Escherichia coli* (which is very common) with *Prevotella brevis* (which is moderately common) and with *Mycoplasma leonicaptivi* (which is very uncommon):
In the figure below, we compare *Escherichia coli* (which is very common) with *Prevotella brevis* (which is moderately common) and with *Thermus islandicus* (which is very uncommon):
```{r}
par(mar = c(5, 16, 4, 2)) # set more space for left margin text (16)
boxplot(microbenchmark(as.mo("M. leonicaptivi"),
as.mo("Mycoplasma leonicaptivi"),
as.mo("P. brevis"),
boxplot(microbenchmark(as.mo("Thermus islandicus"),
as.mo("Prevotella brevis"),
as.mo("E. coli"),
as.mo("Escherichia coli"),
as.mo("T. islandicus"),
as.mo("P. brevis"),
as.mo("E. coli"),
times = 50),
horizontal = TRUE, las = 1, unit = "s", log = FALSE,
xlab = "", ylab = "Time in seconds",
@ -94,12 +93,18 @@ Repetitive results mean that unique values are present more than once. Unique va
```{r, message = FALSE}
library(dplyr)
# take 500,000 random MO codes from the septic_patients data set
x = septic_patients %>%
sample_n(500000, replace = TRUE) %>%
pull(mo)
# take all MO codes from the septic_patients data set
x <- septic_patients$mo %>%
# keep only the unique ones
unique() %>%
# pick 50 of them at random
sample(50) %>%
# paste that 10,000 times
rep(10000) %>%
# scramble it
sample()
# got the right length?
# got indeed 50 times 10,000 = half a million?
length(x)
# and how many unique values do we have?
@ -111,7 +116,7 @@ run_it <- microbenchmark(mo_fullname(x),
print(run_it, unit = "ms", signif = 3)
```
So transforming 500,000 values (!) of `r n_distinct(x)` unique values only takes `r round(median(run_it$time, na.rm = TRUE) / 1e9, 2)` seconds (`r as.integer(median(run_it$time, na.rm = TRUE) / 1e6)` ms). You only lose time on your unique input values.
So transforming 500,000 values (!!) of `r n_distinct(x)` unique values only takes `r round(median(run_it$time, na.rm = TRUE) / 1e9, 2)` seconds (`r as.integer(median(run_it$time, na.rm = TRUE) / 1e6)` ms). You only lose time on your unique input values.
### Precalculated results