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 fix

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends 2019-02-27 14:22:07 +01:00
parent 54162522bd
commit 642f6571fe
11 changed files with 291 additions and 273 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
NAMESPACE
View File

@ -217,6 +217,7 @@ importFrom(dplyr,bind_cols)
importFrom(dplyr,bind_rows)
importFrom(dplyr,case_when)
importFrom(dplyr,desc)
importFrom(dplyr,distinct)
importFrom(dplyr,everything)
importFrom(dplyr,filter)
importFrom(dplyr,filter_all)

2
R/freq.R
View File

@ -682,7 +682,7 @@ format_header <- function(x, markdown = FALSE, decimal.mark = ".", big.mark = ",
# numeric values
if (has_length == TRUE & any(x_class %in% c("double", "integer", "numeric", "raw", "single"))) {
header$sd <- paste0(header$sd, " (CV: ", header$cv, ", MAD: ", header$mad, ")")
header$fivenum <- paste0(paste(header$fivenum, collapse = " | "), " (IQR: ", header$IQR, ", CQV: ", header$cqv, ")")
header$fivenum <- paste0(paste(trimws(header$fivenum), collapse = " | "), " (IQR: ", header$IQR, ", CQV: ", header$cqv, ")")
header$outliers_total <- paste0(header$outliers_total, " (unique count: ", header$outliers_unique, ")")
header <- header[!names(header) %in% c("cv", "mad", "IQR", "cqv", "outliers_unique")]
}

64
R/mo.R
View File

@ -165,30 +165,44 @@
#' mutate(mo = as.mo(paste(genus, species)))
#' }
as.mo <- function(x, Becker = FALSE, Lancefield = FALSE, allow_uncertain = TRUE, reference_df = get_mo_source()) {
if (!"AMR" %in% base::.packages()) {
library("AMR")
# check onLoad() in R/zzz.R: data tables are created there.
}
if (all(x %in% AMR::microorganisms$mo)
& isFALSE(Becker)
& isFALSE(Lancefield)
& is.null(reference_df)) {
y <- x
} else if (all(x %in% AMR::microorganisms$fullname)
& isFALSE(Becker)
& isFALSE(Lancefield)
& is.null(reference_df)) {
# we need special treatment for very prevalent full names, they are likely!
} else if (all(tolower(x) %in% microorganismsDT$fullname_lower)
& isFALSE(Becker)
& isFALSE(Lancefield)
& is.null(reference_df)) {
# we need special treatment for very prevalent full names, they are likely! (case insensitive)
# e.g. as.mo("Staphylococcus aureus")
y <- microorganismsDT[prevalence == 1][data.table(fullname = x), on = "fullname", "mo"][[1]]
y <- microorganismsDT[prevalence == 1][data.table(fullname_lower = tolower(x)),
on = "fullname_lower",
"mo"][[1]]
if (any(is.na(y))) {
y[is.na(y)] <- microorganismsDT[prevalence == 2][data.table(fullname = x[is.na(y)]), on = "fullname", "mo"][[1]]
y[is.na(y)] <- microorganismsDT[prevalence == 2][data.table(fullname_lower = tolower(x[is.na(y)])),
on = "fullname_lower",
"mo"][[1]]
}
if (any(is.na(y))) {
y[is.na(y)] <- microorganismsDT[prevalence == 3][data.table(fullname = x[is.na(y)]), on = "fullname", "mo"][[1]]
y[is.na(y)] <- microorganismsDT[prevalence == 3][data.table(fullname_lower = tolower(x[is.na(y)])),
on = "fullname_lower",
"mo"][[1]]
}
} else {
# will be checked for mo class in validation and uses exec_as.mo internally if necessary
y <- mo_validate(x = x, property = "mo",
Becker = Becker, Lancefield = Lancefield,
allow_uncertain = allow_uncertain, reference_df = reference_df)
}
structure(.Data = y, class = "mo")
}
@ -198,7 +212,7 @@ is.mo <- function(x) {
identical(class(x), "mo")
}
#' @importFrom dplyr %>% pull left_join n_distinct progress_estimated filter
#' @importFrom dplyr %>% pull left_join n_distinct progress_estimated filter distinct
#' @importFrom data.table data.table as.data.table setkey
#' @importFrom crayon magenta red blue silver italic has_color
exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
@ -298,22 +312,30 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# existing mo codes when not looking for property "mo", like mo_genus("B_ESCHR_COL")
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]]
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]]
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% AMR::microorganisms$fullname)) {
} else if (all(tolower(x) %in% microorganismsDT$fullname_lower)) {
# we need special treatment for very prevalent full names, they are likely!
# e.g. as.mo("Staphylococcus aureus")
y <- microorganismsDT[prevalence == 1][data.table(fullname = x), on = "fullname", ..property][[1]]
y <- microorganismsDT[prevalence == 1][data.table(fullname_lower = tolower(x)), on = "fullname_lower", ..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]]
y[is.na(y)] <- microorganismsDT[prevalence == 2][data.table(fullname_lower = tolower(x[is.na(y)])),
on = "fullname_lower",
..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]]
y[is.na(y)] <- microorganismsDT[prevalence == 3][data.table(fullname_lower = tolower(x[is.na(y)])),
on = "fullname_lower",
..property][[1]]
}
x <- y
@ -521,13 +543,13 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# FIRST TRY FULLNAMES AND CODES
# if only genus is available, return only genus
if (all(!c(x[i], x_trimmed[i]) %like% " ")) {
found <- microorganismsDT[tolower(fullname) %in% tolower(c(x_species[i], x_trimmed_species[i])), ..property][[1]]
found <- microorganismsDT[fullname_lower %in% tolower(c(x_species[i], x_trimmed_species[i])), ..property][[1]]
if (length(found) > 0) {
x[i] <- found[1L]
next
}
if (nchar(x_trimmed[i]) >= 6) {
found <- microorganismsDT[tolower(fullname) %like% paste0(x_withspaces_start_only[i], "[a-z]+ species"), ..property][[1]]
found <- microorganismsDT[fullname_lower %like% paste0(x_withspaces_start_only[i], "[a-z]+ species"), ..property][[1]]
if (length(found) > 0) {
x[i] <- found[1L]
next
@ -564,13 +586,13 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
e.x_withspaces_start_only,
f.x_withspaces_end_only) {
found <- data_to_check[tolower(fullname) %in% tolower(c(a.x_backup, b.x_trimmed)), ..property][[1]]
found <- data_to_check[fullname_lower %in% tolower(c(a.x_backup, b.x_trimmed)), ..property][[1]]
# most probable: is exact match in fullname
if (length(found) > 0) {
return(found[1L])
}
found <- data_to_check[tolower(fullname) == tolower(c.x_trimmed_without_group), ..property][[1]]
found <- data_to_check[fullname_lower == tolower(c.x_trimmed_without_group), ..property][[1]]
if (length(found) > 0) {
return(found[1L])
}
@ -664,7 +686,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
# MISCELLANEOUS ----
# look for old taxonomic names ----
found <- microorganisms.oldDT[tolower(fullname) == tolower(x_backup[i])
found <- microorganisms.oldDT[fullname_lower == tolower(x_backup[i])
| fullname %like% x_withspaces_start_end[i],]
if (NROW(found) > 0) {
col_id_new <- found[1, col_id_new]
@ -693,7 +715,7 @@ exec_as.mo <- function(x, Becker = FALSE, Lancefield = FALSE,
if (nchar(b.x_trimmed) > 4 & !b.x_trimmed %like% " ") {
if (!grepl("^[A-Z][a-z]+", b.x_trimmed, ignore.case = FALSE)) {
# not when input is like Genustext, because then Neospora would lead to Actinokineospora
found <- microorganismsDT[tolower(fullname) %like% paste(b.x_trimmed, "species"), ..property][[1]]
found <- microorganismsDT[fullname_lower %like% paste(b.x_trimmed, "species"), ..property][[1]]
if (length(found) > 0) {
x[i] <- found[1L]
uncertainties <<- rbind(uncertainties,

2
R/zzz.R
View File

@ -28,6 +28,7 @@
if (!all(c("microorganismsDT", "microorganisms.oldDT") %in% ls(envir = asNamespace("AMR")))) {
microorganisms.oldDT <- as.data.table(AMR::microorganisms.old)
microorganisms.oldDT$fullname_lower <- tolower(microorganisms.oldDT$fullname)
setkey(microorganisms.oldDT, col_id, fullname)
assign(x = "microorganisms",
@ -84,6 +85,7 @@ make <- function() {
#' @importFrom data.table as.data.table setkey
make_DT <- function() {
microorganismsDT <- as.data.table(make())
microorganismsDT$fullname_lower <- tolower(microorganismsDT$fullname)
setkey(microorganismsDT,
kingdom,
prevalence,

421
docs/articles/AMR.html
View File

@ -327,68 +327,68 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2015-01-18</td>
<td align="center">F9</td>
<td align="center">Hospital B</td>
<td align="center">Escherichia coli</td>
<td align="center">2011-10-07</td>
<td align="center">O2</td>
<td align="center">Hospital C</td>
<td align="center">Streptococcus pneumoniae</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">M</td>
<td align="center">S</td>
<td align="center">F</td>
</tr>
<tr class="even">
<td align="center">2017-12-07</td>
<td align="center">H7</td>
<td align="center">2013-10-20</td>
<td align="center">C10</td>
<td align="center">Hospital A</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">R</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2016-02-14</td>
<td align="center">J4</td>
<td align="center">2014-08-25</td>
<td align="center">O4</td>
<td align="center">Hospital A</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2010-12-25</td>
<td align="center">P2</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="odd">
<td align="center">2016-12-26</td>
<td align="center">S8</td>
<td align="center">Hospital A</td>
<tr class="even">
<td align="center">2011-10-28</td>
<td align="center">E3</td>
<td align="center">Hospital B</td>
<td align="center">Streptococcus pneumoniae</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>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="odd">
<td align="center">2010-08-31</td>
<td align="center">H1</td>
<td align="center">Hospital A</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">R</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">2010-03-27</td>
<td align="center">R7</td>
<td align="center">Hospital D</td>
<td align="center">Klebsiella pneumoniae</td>
<td align="center">S</td>
<td align="center">2014-11-03</td>
<td align="center">U7</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">F</td>
</tr>
@ -411,8 +411,8 @@
#&gt;
#&gt; Item Count Percent Cum. Count Cum. Percent
#&gt; --- ----- ------- -------- ----------- -------------
#&gt; 1 M 10,386 51.9% 10,386 51.9%
#&gt; 2 F 9,614 48.1% 20,000 100.0%</code></pre>
#&gt; 1 M 10,303 51.5% 10,303 51.5%
#&gt; 2 F 9,697 48.5% 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 (1291 changes)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1256 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 (2787 changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2821 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 7,442 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,457 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 4,078 test results (0 to S; 0 to I; 4,078 to R)</span></a></code></pre></div>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,077 test results (0 to S; 0 to I; 4,077 to R)</span></a></code></pre></div>
</div>
<div id="adding-new-variables" class="section level1">
<h1 class="hasAnchor">
@ -489,7 +489,7 @@
<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 5,707 first isolates (28.5% of total)</span></a></code></pre></div>
<a class="sourceLine" id="cb16-6" title="6"><span class="co">#&gt; =&gt; Found 5,704 first isolates (28.5% of total)</span></a></code></pre></div>
<p>So only 28.5% 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>
@ -516,96 +516,96 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-02-12</td>
<td align="center">I9</td>
<td align="center">2010-01-18</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-02-12</td>
<td align="center">I9</td>
<td align="center">2010-03-30</td>
<td align="center">I8</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="odd">
<td align="center">3</td>
<td align="center">2010-02-22</td>
<td align="center">I9</td>
<td align="center">2010-10-05</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-03-05</td>
<td align="center">I9</td>
<td align="center">2011-01-26</td>
<td align="center">I8</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">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2010-03-08</td>
<td align="center">I9</td>
<td align="center">2011-02-01</td>
<td align="center">I8</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">R</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">2010-03-17</td>
<td align="center">I9</td>
<td align="center">2011-03-08</td>
<td align="center">I8</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">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2010-05-03</td>
<td align="center">I9</td>
<td align="center">2011-04-11</td>
<td align="center">I8</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">FALSE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2010-07-03</td>
<td align="center">I9</td>
<td align="center">2011-04-23</td>
<td align="center">I8</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="odd">
<td align="center">9</td>
<td align="center">2010-09-11</td>
<td align="center">I9</td>
<td align="center">2011-06-21</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -615,18 +615,18 @@
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2010-09-24</td>
<td align="center">I9</td>
<td align="center">2011-07-06</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</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>
</tbody>
</table>
<p>Only 1 isolates are marked as ‘first’ according to CLSI guideline. But when reviewing the antibiogram, it is obvious that some isolates are absolutely different strains and should be included too. This is why we weigh isolates, based on their antibiogram. The <code><a href="../reference/key_antibiotics.html">key_antibiotics()</a></code> function adds a vector with 18 key antibiotics: 6 broad spectrum ones, 6 small spectrum for Gram negatives and 6 small spectrum for Gram positives. These can be defined by the user.</p>
<p>Only 2 isolates are marked as ‘first’ according to CLSI guideline. But when reviewing the antibiogram, it is obvious that some isolates are absolutely different strains and should be included too. This is why we weigh isolates, based on their antibiogram. The <code><a href="../reference/key_antibiotics.html">key_antibiotics()</a></code> function adds a vector with 18 key antibiotics: 6 broad spectrum ones, 6 small spectrum for Gram negatives and 6 small spectrum for Gram positives. These can be defined by the user.</p>
<p>If a column exists with a name like ‘key(…)ab’ the <code><a href="../reference/first_isolate.html">first_isolate()</a></code> function will automatically use it and determine the first weighted isolates. Mind the NOTEs in below output:</p>
<div class="sourceCode" id="cb19"><pre class="sourceCode r"><code class="sourceCode r"><a class="sourceLine" id="cb19-1" title="1">data &lt;-<span class="st"> </span>data <span class="op">%&gt;%</span><span class="st"> </span></a>
<a class="sourceLine" id="cb19-2" title="2"><span class="st"> </span><span class="kw"><a href="https://dplyr.tidyverse.org/reference/mutate.html">mutate</a></span>(<span class="dt">keyab =</span> <span class="kw"><a href="../reference/key_antibiotics.html">key_antibiotics</a></span>(.)) <span class="op">%&gt;%</span><span class="st"> </span></a>
@ -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 15,861 first weighted isolates (79.3% of total)</span></a></code></pre></div>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,909 first weighted isolates (79.5% of total)</span></a></code></pre></div>
<table class="table">
<thead><tr class="header">
<th align="center">isolate</th>
@ -654,104 +654,104 @@
<tbody>
<tr class="odd">
<td align="center">1</td>
<td align="center">2010-02-12</td>
<td align="center">I9</td>
<td align="center">2010-01-18</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">TRUE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-02-12</td>
<td align="center">I9</td>
<td align="center">2010-03-30</td>
<td align="center">I8</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>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-02-22</td>
<td align="center">I9</td>
<td align="center">2010-10-05</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-03-05</td>
<td align="center">I9</td>
<td align="center">2011-01-26</td>
<td align="center">I8</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">R</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">5</td>
<td align="center">2010-03-08</td>
<td align="center">I9</td>
<td align="center">2011-02-01</td>
<td align="center">I8</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">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2010-03-17</td>
<td align="center">I9</td>
<td align="center">2011-03-08</td>
<td align="center">I8</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">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">7</td>
<td align="center">2010-05-03</td>
<td align="center">I9</td>
<td align="center">2011-04-11</td>
<td align="center">I8</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">FALSE</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2010-07-03</td>
<td align="center">I9</td>
<td align="center">2011-04-23</td>
<td align="center">I8</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">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2010-09-11</td>
<td align="center">I9</td>
<td align="center">2011-06-21</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -762,11 +762,11 @@
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2010-09-24</td>
<td align="center">I9</td>
<td align="center">2011-07-06</td>
<td align="center">I8</td>
<td align="center">B_ESCHR_COL</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>
@ -774,11 +774,11 @@
</tr>
</tbody>
</table>
<p>Instead of 1, now 8 isolates are flagged. In total, 79.3% of all isolates are marked ‘first weighted’ - 50.8% 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 9 isolates are flagged. In total, 79.5% of all isolates are marked ‘first weighted’ - 51% 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 15,861 isolates for analysis.</p>
<p>So we end up with 15,909 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>
@ -803,44 +802,11 @@
</tr></thead>
<tbody>
<tr class="odd">
<td>1</td>
<td align="center">2015-01-18</td>
<td align="center">F9</td>
<td align="center">Hospital B</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</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 negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>3</td>
<td align="center">2016-02-14</td>
<td align="center">J4</td>
<td align="center">Hospital A</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">I</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="odd">
<td>4</td>
<td align="center">2010-12-25</td>
<td align="center">P2</td>
<td align="center">Hospital B</td>
<td align="center">2011-10-07</td>
<td align="center">O2</td>
<td align="center">Hospital C</td>
<td align="center">B_STRPT_PNE</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">R</td>
@ -851,51 +817,78 @@
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>5</td>
<td align="center">2016-12-26</td>
<td align="center">S8</td>
<td align="center">2013-10-20</td>
<td align="center">C10</td>
<td align="center">Hospital A</td>
<td align="center">B_STRPT_PNE</td>
<td align="center">S</td>
<td align="center">I</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</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 negative</td>
<td align="center">Escherichia</td>
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td align="center">2014-08-25</td>
<td align="center">O4</td>
<td align="center">Hospital A</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 align="center">2011-10-28</td>
<td align="center">E3</td>
<td align="center">Hospital B</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">M</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="odd">
<td>6</td>
<td align="center">2010-03-27</td>
<td align="center">R7</td>
<td align="center">Hospital D</td>
<td align="center">2010-08-31</td>
<td align="center">H1</td>
<td align="center">Hospital A</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">F</td>
<td align="center">M</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>8</td>
<td align="center">2016-08-08</td>
<td align="center">K8</td>
<td align="center">Hospital B</td>
<td align="center">B_KLBSL_PNE</td>
<td align="center">2014-11-03</td>
<td align="center">U7</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">I</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">Klebsiella</td>
<td align="center">pneumoniae</td>
<td align="center">F</td>
<td align="center">Gram positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
</tbody>
@ -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> (15,861 x 13)</strong></p>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,909 x 13)</strong></p>
<p>Columns: 2<br>
Length: 15,861 (of which NA: 0 = 0.00%)<br>
Length: 15,909 (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">7,879</td>
<td align="right">49.7%</td>
<td align="right">7,879</td>
<td align="right">49.7%</td>
<td align="right">7,837</td>
<td align="right">49.3%</td>
<td align="right">7,837</td>
<td align="right">49.3%</td>
</tr>
<tr class="even">
<td align="left">2</td>
<td align="left">Staphylococcus aureus</td>
<td align="right">3,915</td>
<td align="right">24.7%</td>
<td align="right">11,794</td>
<td align="right">74.4%</td>
<td align="right">3,940</td>
<td align="right">24.8%</td>
<td align="right">11,777</td>
<td align="right">74.0%</td>
</tr>
<tr class="odd">
<td align="left">3</td>
<td align="left">Streptococcus pneumoniae</td>
<td align="right">2,482</td>
<td align="right">15.6%</td>
<td align="right">14,276</td>
<td align="right">90.0%</td>
<td align="right">2,554</td>
<td align="right">16.1%</td>
<td align="right">14,331</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">1,585</td>
<td align="right">10.0%</td>
<td align="right">15,861</td>
<td align="right">1,578</td>
<td align="right">9.9%</td>
<td align="right">15,909</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] 0.4744341</span></a></code></pre></div>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4787856</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">0.4759916</td>
<td align="center">0.4717819</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4808997</td>
<td align="center">0.4802632</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4682779</td>
<td align="center">0.4870184</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4651015</td>
<td align="center">0.4804169</td>
</tr>
</tbody>
</table>
@ -1014,23 +1007,23 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4759916</td>
<td align="center">4790</td>
<td align="center">0.4717819</td>
<td align="center">4731</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4808997</td>
<td align="center">5602</td>
<td align="center">0.4802632</td>
<td align="center">5624</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4682779</td>
<td align="center">2317</td>
<td align="center">0.4870184</td>
<td align="center">2388</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4651015</td>
<td align="center">3152</td>
<td align="center">0.4804169</td>
<td align="center">3166</td>
</tr>
</tbody>
</table>
@ -1050,27 +1043,27 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Escherichia</td>
<td align="center">0.7292804</td>
<td align="center">0.8975758</td>
<td align="center">0.9772814</td>
<td align="center">0.7256603</td>
<td align="center">0.8983029</td>
<td align="center">0.9729488</td>
</tr>
<tr class="even">
<td align="center">Klebsiella</td>
<td align="center">0.7438486</td>
<td align="center">0.9015773</td>
<td align="center">0.9741325</td>
<td align="center">0.7338403</td>
<td align="center">0.8935361</td>
<td align="center">0.9689480</td>
</tr>
<tr class="odd">
<td align="center">Staphylococcus</td>
<td align="center">0.7315453</td>
<td align="center">0.9154534</td>
<td align="center">0.9793103</td>
<td align="center">0.7309645</td>
<td align="center">0.9233503</td>
<td align="center">0.9794416</td>
</tr>
<tr class="even">
<td align="center">Streptococcus</td>
<td align="center">0.7352941</td>
<td align="center">0.7372749</td>
<td align="center">0.0000000</td>
<td align="center">0.7352941</td>
<td align="center">0.7372749</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

74
docs/articles/benchmarks.html
View File

@ -217,14 +217,14 @@
<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") 15.40 15.50 22.70 15.60 15.90 53.3 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 84.20 84.30 86.60 84.60 86.60 102.0 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 15.40 15.40 19.70 15.50 15.60 57.1 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 15.40 15.40 15.50 15.50 15.60 15.9 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 23.50 23.50 31.10 23.50 23.60 61.7 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 23.50 23.50 36.50 23.50 61.60 74.3 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 7.19 7.27 9.01 7.44 7.67 23.2 10</span></a></code></pre></div>
<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") 16.30 16.40 20.9 16.60 18.70 55.6 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 33.70 33.70 37.9 33.80 33.90 74.4 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.30 16.30 16.6 16.40 16.70 17.8 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 16.30 16.30 25.6 16.40 16.50 63.9 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 24.20 24.30 27.2 24.60 26.70 45.2 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 24.20 24.20 39.1 24.90 64.00 85.6 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 7.28 7.33 11.1 7.36 7.44 40.6 10</span></a></code></pre></div>
<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. The second input is the only one that has to be looked up thoroughly. All the others are known codes (the first one is a WHONET code) or common laboratory codes, or common full organism names like the last one. Full organism names are always preferred.</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>
@ -235,13 +235,13 @@
<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") 444.0 449.0 479.0 488.0 493.0 506.0 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 444.0 484.0 488.0 491.0 507.0 514.0 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 80.5 80.8 87.8 81.3 89.9 118.0 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 79.8 80.4 82.0 80.7 81.2 93.5 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 63.4 63.5 72.3 64.0 64.5 107.0 10</span></a></code></pre></div>
<p>That takes 7.7 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>
<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") 287.0 296.0 329.0 330.0 334.0 432 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 286.0 292.0 333.0 329.0 366.0 433 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 72.9 73.1 90.1 75.7 94.1 161 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 72.8 73.5 89.4 79.7 115.0 125 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 65.8 66.0 76.8 67.7 85.2 107 10</span></a></code></pre></div>
<p>That takes 7.2 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>
@ -287,8 +287,8 @@
<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) 743 771 805 798 844 886 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!!) of 50 unique values only takes 0.8 seconds (798 ms). You only lose time on your unique input values.</p>
<a class="sourceLine" id="cb5-27" title="27"><span class="co">#&gt; mo_fullname(x) 716 738 778 763 778 899 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">
@ -300,11 +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 10.900 11.100 11.200 11.200 11.300 11.400 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 21.300 21.400 21.600 21.600 21.700 22.000 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.302 0.313 0.492 0.532 0.569 0.725 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 0.0005 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 10.90 11.600 26.700 21.200 47.80 51.000 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 22.00 22.500 26.900 22.900 25.70 49.800 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.32 0.557 0.565 0.565 0.59 0.828 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 0.0006 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>
@ -317,14 +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 0.330 0.399 0.444 0.425 0.480 0.599 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.343 0.362 0.386 0.376 0.425 0.439 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.327 0.454 0.550 0.571 0.640 0.816 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.273 0.306 0.329 0.319 0.366 0.392 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.246 0.266 0.295 0.286 0.323 0.364 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.260 0.265 0.320 0.312 0.364 0.407 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.238 0.252 0.281 0.270 0.319 0.339 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.251 0.278 0.316 0.320 0.358 0.381 10</span></a></code></pre></div>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.297 0.343 0.399 0.388 0.457 0.518 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.330 0.349 0.397 0.394 0.430 0.496 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.345 0.365 0.521 0.519 0.689 0.697 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.250 0.257 0.321 0.345 0.354 0.372 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.270 0.315 0.339 0.329 0.362 0.444 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.256 0.272 0.328 0.307 0.321 0.580 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.237 0.277 0.299 0.304 0.320 0.349 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.243 0.268 0.318 0.321 0.350 0.415 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">
@ -351,13 +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 14.37 14.43 17.91 14.64 14.82 47.42 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 22.59 22.88 27.57 23.00 23.55 67.95 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 22.50 22.91 26.39 22.94 23.01 57.05 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 22.56 22.76 26.83 23.05 24.02 57.31 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 22.53 22.86 29.52 22.97 23.29 56.11 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 22.49 22.92 23.06 23.01 23.18 23.99 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 22.49 22.86 23.21 23.06 23.62 24.09 10</span></a></code></pre></div>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 14.79 15.17 16.14 15.30 15.69 22.59 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 23.40 23.86 28.56 23.94 25.25 64.07 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 23.27 23.75 35.29 24.41 26.41 92.65 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 23.64 23.85 31.38 24.29 24.87 63.61 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 23.47 23.82 25.22 24.91 27.04 27.69 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 23.57 23.74 27.93 23.82 23.90 64.43 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 23.74 23.88 28.84 24.74 34.01 44.33 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: 29 KiB

After

Width:  |  Height:  |  Size: 27 KiB