P281424
/
AMR
mirror of https://github.com/msberends/AMR.git
1
0
Fork 0
Code Releases Activity

mo_source improvement

This commit is contained in:
dr. M.S. (Matthijs) Berends 2019-03-01 09:34:04 +01:00
parent 2565b60024
commit c5efb272fd
21 changed files with 324 additions and 294 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.gitlab-ci.yml
View File

@ -64,6 +64,7 @@ R:
variables:
WARNINGS_ARE_ERRORS: 1
script:
- export WARNINGS_ARE_ERRORS=1
# remove vignettes folder and get VignetteBuilder field out of DESCRIPTION file
- rm -rf vignettes
- Rscript -e 'd <- read.dcf("DESCRIPTION"); d[, colnames(d) == "VignetteBuilder"] <- NA; write.dcf(d, "DESCRIPTION")'
@ -81,6 +82,7 @@ coverage:
allow_failure: true
when: on_success
only:
- premaster
- master
script:
- apt-get install --yes git

2
DESCRIPTION
View File

@ -1,6 +1,6 @@
Package: AMR
Version: 0.5.0.9020
Date: 2019-02-28
Date: 2019-03-01
Title: Antimicrobial Resistance Analysis
Authors@R: c(
person(

21
R/mo.R
View File

@ -117,6 +117,7 @@
#' @seealso \code{\link{microorganisms}} for the \code{data.frame} that is being used to determine ID's. \cr
#' The \code{\link{mo_property}} functions (like \code{\link{mo_genus}}, \code{\link{mo_gramstain}}) to get properties based on the returned code.
#' @inheritSection AMR Read more on our website!
#' @importFrom dplyr %>% pull left_join
#' @examples
#' # These examples all return "B_STPHY_AUR", the ID of S. aureus:
#' as.mo("stau")
@ -171,16 +172,28 @@ as.mo <- function(x, Becker = FALSE, Lancefield = FALSE, allow_uncertain = TRUE,
# check onLoad() in R/zzz.R: data tables are created there.
}
if (all(x %in% AMR::microorganisms$mo)
if (deparse(substitute(reference_df)) == "get_mo_source()"
& isFALSE(Becker)
& isFALSE(Lancefield)
& is.null(reference_df)) {
& !is.null(reference_df)
& all(x %in% reference_df[,1])) {
# has valid own reference_df
# (data.table not faster here)
colnames(reference_df)[1] <- "x"
suppressWarnings(
y <- data.frame(x = x, stringsAsFactors = FALSE) %>%
left_join(reference_df, by = "x") %>%
pull("mo")
)
} else if (all(x %in% AMR::microorganisms$mo)
& isFALSE(Becker)
& isFALSE(Lancefield)) {
y <- x
} else if (all(tolower(x) %in% microorganismsDT$fullname_lower)
& isFALSE(Becker)
& isFALSE(Lancefield)
& is.null(reference_df)) {
& isFALSE(Lancefield)) {
# 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_lower = tolower(x)),

24
R/mo_source.R
View File

@ -52,15 +52,19 @@
#' # Created mo_source file '~/.mo_source.rds' from 'home/me/ourcodes.xlsx'.
#' }
#'
#' It has now created a file "~/.mo_source.rds" with the contents of our Excel file. It it an R specific format with great compression.
#' It has now created a file "~/.mo_source.rds" with the contents of our Excel file, but only the first column with foreign values and the 'mo' column will be kept.
#'
#' And now we can use it in our functions:
#' \preformatted{
#' as.mo("lab_mo_ecoli")
#' # B_ESCHR_COL
#' [1] B_ESCHR_COL
#'
#' mo_genus("lab_mo_kpneumoniae")
#' # "Klebsiella"
#' [1] "Klebsiella"
#'
#' # other input values still work too
#' as.mo(c("Escherichia coli", "E. coli", "lab_mo_ecoli"))
#' [1] B_ESCHR_COL B_ESCHR_COL B_ESCHR_COL
#' }
#'
#' If we edit the Excel file to, let's say, this:
@ -78,10 +82,10 @@
#' \preformatted{
#' as.mo("lab_mo_ecoli")
#' # Updated mo_source file '~/.mo_source.rds' from 'home/me/ourcodes.xlsx'.
#' # B_ESCHR_COL
#' [1] B_ESCHR_COL
#'
#' mo_genus("lab_Staph_aureus")
#' # "Staphylococcus"
#' [1] "Staphylococcus"
#' }
#'
#' To remove the reference completely, just use any of these:
@ -119,7 +123,9 @@ set_mo_source <- function(path) {
valid <- FALSE
} else if (!"mo" %in% colnames(df)) {
valid <- FALSE
} else if (!all(df$mo %in% AMR::microorganisms$mo)) {
} else if (all(as.data.frame(df)[, 1] == "")) {
valid <- FALSE
} else if (!all(df$mo %in% c("", AMR::microorganisms$mo))) {
valid <- FALSE
} else if (NCOL(df) < 2) {
valid <- FALSE
@ -163,9 +169,11 @@ set_mo_source <- function(path) {
stop("File must contain a column with self-defined values and a reference column `mo` with valid values from the `microorganisms` data set.")
}
# keep only first two columns, second must be mo
if (colnames(df)[1] == "mo") {
# put mo to the end
df <- df %>% select(-"mo", everything(), "mo")
df <- df[, c(2, 1)]
} else {
df <- df[, c(1, 2)]
}
df <- as.data.frame(df, stringAsFactors = FALSE)

4
appveyor.yml
View File

@ -55,8 +55,8 @@ on_failure:
- 7z a failure.zip *.Rcheck\*
- appveyor PushArtifact failure.zip
on_success:
- Rscript -e "library(covr); cc <- package_coverage(); codecov(coverage = cc, token = '50ffa0aa-fee0-4f8b-a11d-8c7edc6d32ca'); cat('Code coverage:', percent_coverage(cc))"
#on_success:
# - Rscript -e "library(covr); cc <- package_coverage(); codecov(coverage = cc, token = '50ffa0aa-fee0-4f8b-a11d-8c7edc6d32ca'); cat('Code coverage:', percent_coverage(cc))"
artifacts:
- path: '*.Rcheck\**\*.log'

452
docs/articles/AMR.html
View File

@ -192,7 +192,7 @@
<h1>How to conduct AMR analysis</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>AMR.Rmd</code></div>
@ -201,7 +201,7 @@
<p><strong>Note:</strong> values on this page will change with every website update since they are based on randomly created values and the page was written in <a href="https://rmarkdown.rstudio.com/">RMarkdown</a>. However, the methodology remains unchanged. This page was generated on 28 February 2019.</p>
<p><strong>Note:</strong> values on this page will change with every website update since they are based on randomly created values and the page was written in <a href="https://rmarkdown.rstudio.com/">RMarkdown</a>. However, the methodology remains unchanged. This page was generated on 01 March 2019.</p>
<div id="introduction" class="section level1">
<h1 class="hasAnchor">
<a href="#introduction" class="anchor"></a>Introduction</h1>
@ -217,21 +217,21 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2019-02-28</td>
<td align="center">2019-03-01</td>
<td align="center">abcd</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">S</td>
</tr>
<tr class="even">
<td align="center">2019-02-28</td>
<td align="center">2019-03-01</td>
<td align="center">abcd</td>
<td align="center">Escherichia coli</td>
<td align="center">S</td>
<td align="center">R</td>
</tr>
<tr class="odd">
<td align="center">2019-02-28</td>
<td align="center">2019-03-01</td>
<td align="center">efgh</td>
<td align="center">Escherichia coli</td>
<td align="center">R</td>
@ -327,71 +327,71 @@
</tr></thead>
<tbody>
<tr class="odd">
<td align="center">2015-09-11</td>
<td align="center">C6</td>
<td align="center">2017-06-13</td>
<td align="center">Z3</td>
<td align="center">Hospital D</td>
<td align="center">Staphylococcus aureus</td>
<td align="center">Escherichia coli</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>
</tr>
<tr class="even">
<td align="center">2015-05-10</td>
<td align="center">N2</td>
<td align="center">Hospital A</td>
<td align="center">2013-09-13</td>
<td align="center">A1</td>
<td align="center">Hospital D</td>
<td align="center">Escherichia coli</td>
<td align="center">I</td>
<td align="center">I</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">2012-03-06</td>
<td align="center">C2</td>
<td align="center">Hospital C</td>
<td align="center">Escherichia coli</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="even">
<td align="center">2011-11-09</td>
<td align="center">X3</td>
<td align="center">2015-06-10</td>
<td align="center">L8</td>
<td align="center">Hospital B</td>
<td align="center">Staphylococcus aureus</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">2017-02-01</td>
<td align="center">O6</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">Escherichia coli</td>
<td align="center">S</td>
<td align="center">R</td>
<td align="center">F</td>
<td align="center">S</td>
<td align="center">S</td>
<td align="center">M</td>
</tr>
<tr class="even">
<td align="center">2017-02-26</td>
<td align="center">X1</td>
<td align="center">2010-08-05</td>
<td align="center">A7</td>
<td align="center">Hospital D</td>
<td align="center">Klebsiella pneumoniae</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">2011-08-25</td>
<td align="center">X4</td>
<td align="center">Hospital C</td>
<td align="center">Staphylococcus aureus</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">2011-03-09</td>
<td align="center">B7</td>
<td align="center">Hospital D</td>
<td align="center">Escherichia coli</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>
</tbody>
</table>
<p>Now, let’s start the cleaning and the analysis!</p>
@ -411,8 +411,8 @@
#&gt;
#&gt; Item Count Percent Cum. Count Cum. Percent
#&gt; --- ----- ------- -------- ----------- -------------
#&gt; 1 M 10,244 51.2% 10,244 51.2%
#&gt; 2 F 9,756 48.8% 20,000 100.0%</code></pre>
#&gt; 1 M 10,311 51.6% 10,311 51.6%
#&gt; 2 F 9,689 48.4% 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 (1275 changes)</span></a>
<a class="sourceLine" id="cb14-22" title="22"><span class="co">#&gt; Table 1: Intrinsic resistance in Enterobacteriaceae (1364 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 (2727 changes)</span></a>
<a class="sourceLine" id="cb14-25" title="25"><span class="co">#&gt; Table 4: Intrinsic resistance in Gram-positive bacteria (2659 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 7,427 out of 20,000 rows</span></a>
<a class="sourceLine" id="cb14-41" title="41"><span class="co">#&gt; =&gt; EUCAST rules affected 7,366 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 4,002 test results (0 to S; 0 to I; 4,002 to R)</span></a></code></pre></div>
<a class="sourceLine" id="cb14-43" title="43"><span class="co">#&gt; -&gt; changed 4,023 test results (0 to S; 0 to I; 4,023 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 5,650 first isolates (28.3% of total)</span></a></code></pre></div>
<p>So only 28.3% 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 5,641 first isolates (28.2% of total)</span></a></code></pre></div>
<p>So only 28.2% 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">2010-04-26</td>
<td align="center">H9</td>
<td align="center">2010-01-14</td>
<td align="center">K8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -527,10 +527,10 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-05-27</td>
<td align="center">H9</td>
<td align="center">2010-02-17</td>
<td align="center">K8</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">R</td>
<td align="center">S</td>
@ -538,19 +538,19 @@
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-07-20</td>
<td align="center">H9</td>
<td align="center">2010-03-01</td>
<td align="center">K8</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">R</td>
<td align="center">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">4</td>
<td align="center">2010-11-25</td>
<td align="center">H9</td>
<td align="center">2010-03-11</td>
<td align="center">K8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -560,54 +560,54 @@
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2011-01-19</td>
<td align="center">H9</td>
<td align="center">2010-04-13</td>
<td align="center">K8</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">S</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2011-01-24</td>
<td align="center">H9</td>
<td align="center">2010-08-30</td>
<td align="center">K8</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">7</td>
<td align="center">2011-03-09</td>
<td align="center">H9</td>
<td align="center">2010-11-05</td>
<td align="center">K8</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">S</td>
<td align="center">FALSE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2011-06-07</td>
<td align="center">H9</td>
<td align="center">2010-12-21</td>
<td align="center">K8</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">TRUE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2011-07-30</td>
<td align="center">H9</td>
<td align="center">2010-12-21</td>
<td align="center">K8</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>
@ -615,14 +615,14 @@
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-08-01</td>
<td align="center">H9</td>
<td align="center">2011-03-20</td>
<td align="center">K8</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">TRUE</td>
</tr>
</tbody>
</table>
@ -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 15,814 first weighted isolates (79.1% of total)</span></a></code></pre></div>
<a class="sourceLine" id="cb19-10" title="10"><span class="co">#&gt; =&gt; Found 15,738 first weighted isolates (78.7% 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">2010-04-26</td>
<td align="center">H9</td>
<td align="center">2010-01-14</td>
<td align="center">K8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
<td align="center">S</td>
@ -666,10 +666,10 @@
</tr>
<tr class="even">
<td align="center">2</td>
<td align="center">2010-05-27</td>
<td align="center">H9</td>
<td align="center">2010-02-17</td>
<td align="center">K8</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">R</td>
<td align="center">S</td>
@ -678,20 +678,20 @@
</tr>
<tr class="odd">
<td align="center">3</td>
<td align="center">2010-07-20</td>
<td align="center">H9</td>
<td align="center">2010-03-01</td>
<td align="center">K8</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">R</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">2010-11-25</td>
<td align="center">H9</td>
<td align="center">2010-03-11</td>
<td align="center">K8</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">S</td>
<td align="center">S</td>
@ -702,83 +702,83 @@
</tr>
<tr class="odd">
<td align="center">5</td>
<td align="center">2011-01-19</td>
<td align="center">H9</td>
<td align="center">2010-04-13</td>
<td align="center">K8</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">S</td>
<td align="center">FALSE</td>
<td align="center">R</td>
<td align="center">R</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">6</td>
<td align="center">2011-01-24</td>
<td align="center">H9</td>
<td align="center">2010-08-30</td>
<td align="center">K8</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">7</td>
<td align="center">2011-03-09</td>
<td align="center">H9</td>
<td align="center">2010-11-05</td>
<td align="center">K8</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">S</td>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">8</td>
<td align="center">2011-06-07</td>
<td align="center">H9</td>
<td align="center">2010-12-21</td>
<td align="center">K8</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">TRUE</td>
<td align="center">TRUE</td>
<td align="center">FALSE</td>
<td align="center">FALSE</td>
</tr>
<tr class="odd">
<td align="center">9</td>
<td align="center">2011-07-30</td>
<td align="center">H9</td>
<td align="center">2010-12-21</td>
<td align="center">K8</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>
<td align="center">FALSE</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td align="center">10</td>
<td align="center">2011-08-01</td>
<td align="center">H9</td>
<td align="center">2011-03-20</td>
<td align="center">K8</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>
<td align="center">TRUE</td>
</tr>
</tbody>
</table>
<p>Instead of 2, now 6 isolates are flagged. In total, 79.1% 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, 78.7% of all isolates are marked ‘first weighted’ - 50.5% 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 15,814 isolates for analysis.</p>
<p>So we end up with 15,738 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>
@ -804,24 +804,72 @@
<tbody>
<tr class="odd">
<td>1</td>
<td align="center">2015-09-11</td>
<td align="center">C6</td>
<td align="center">2017-06-13</td>
<td align="center">Z3</td>
<td align="center">Hospital D</td>
<td align="center">B_STPHY_AUR</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="even">
<td>3</td>
<td align="center">2015-06-10</td>
<td align="center">L8</td>
<td align="center">Hospital B</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>6</td>
<td align="center">2011-03-09</td>
<td align="center">B7</td>
<td align="center">Hospital D</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">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>8</td>
<td align="center">2015-03-15</td>
<td align="center">O1</td>
<td align="center">Hospital A</td>
<td align="center">B_STPHY_AUR</td>
<td align="center">R</td>
<td align="center">I</td>
<td align="center">S</td>
<td align="center">S</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>
<tr class="even">
<td>3</td>
<td align="center">2012-03-06</td>
<td align="center">C2</td>
<tr class="odd">
<td>9</td>
<td align="center">2012-09-07</td>
<td align="center">K5</td>
<td align="center">Hospital C</td>
<td align="center">B_ESCHR_COL</td>
<td align="center">R</td>
@ -834,65 +882,17 @@
<td align="center">coli</td>
<td align="center">TRUE</td>
</tr>
<tr class="odd">
<td>4</td>
<td align="center">2011-11-09</td>
<td align="center">X3</td>
<td align="center">Hospital B</td>
<td align="center">B_STPHY_AUR</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 positive</td>
<td align="center">Staphylococcus</td>
<td align="center">aureus</td>
<td align="center">TRUE</td>
</tr>
<tr class="even">
<td>6</td>
<td align="center">2017-02-26</td>
<td align="center">X1</td>
<td align="center">Hospital D</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">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>7</td>
<td align="center">2010-02-15</td>
<td align="center">P3</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>
<tr class="even">
<td>8</td>
<td align="center">2012-10-20</td>
<td align="center">H4</td>
<td>10</td>
<td align="center">2015-08-09</td>
<td align="center">R5</td>
<td align="center">Hospital D</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">F</td>
<td align="center">Gram positive</td>
<td align="center">Streptococcus</td>
<td align="center">pneumoniae</td>
@ -915,9 +915,9 @@
<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> (15,814 x 13)</strong></p>
<p><strong>Frequency table of <code>genus</code> and <code>species</code> from a <code>data.frame</code> (15,738 x 13)</strong></p>
<p>Columns: 2<br>
Length: 15,814 (of which NA: 0 = 0.00%)<br>
Length: 15,738 (of which NA: 0 = 0.00%)<br>
Unique: 4</p>
<p>Shortest: 16<br>
Longest: 24</p>
@ -934,33 +934,33 @@ Longest: 24</p>
<tr class="odd">
<td align="left">1</td>
<td align="left">Escherichia coli</td>
<td align="right">7,918</td>
<td align="right">50.1%</td>
<td align="right">7,918</td>
<td align="right">50.1%</td>
<td align="right">7,875</td>
<td align="right">50.0%</td>
<td align="right">7,875</td>
<td align="right">50.0%</td>
</tr>
<tr class="even">
<td align="left">2</td>
<td align="left">Staphylococcus aureus</td>
<td align="right">3,865</td>
<td align="right">24.4%</td>
<td align="right">11,783</td>
<td align="right">74.5%</td>
<td align="right">3,897</td>
<td align="right">24.8%</td>
<td align="right">11,772</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">2,458</td>
<td align="right">15.5%</td>
<td align="right">14,241</td>
<td align="right">90.1%</td>
<td align="right">2,400</td>
<td align="right">15.2%</td>
<td align="right">14,172</td>
<td align="right">90.0%</td>
</tr>
<tr class="even">
<td align="left">4</td>
<td align="left">Klebsiella pneumoniae</td>
<td align="right">1,573</td>
<td align="right">9.9%</td>
<td align="right">15,814</td>
<td align="right">1,566</td>
<td align="right">10.0%</td>
<td align="right">15,738</td>
<td align="right">100.0%</td>
</tr>
</tbody>
@ -971,7 +971,7 @@ Longest: 24</p>
<a href="#resistance-percentages" class="anchor"></a>Resistance percentages</h2>
<p>The functions <code><a href="../reference/portion.html">portion_R()</a></code>, <code>portion_RI()</code>, <code><a href="../reference/portion.html">portion_I()</a></code>, <code>portion_IS()</code> and <code><a href="../reference/portion.html">portion_S()</a></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] 0.4762868</span></a></code></pre></div>
<a class="sourceLine" id="cb25-2" title="2"><span class="co">#&gt; [1] 0.4757911</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 +984,19 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4752371</td>
<td align="center">0.4800594</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4825898</td>
<td align="center">0.4737983</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4705631</td>
<td align="center">0.4763514</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4711928</td>
<td align="center">0.4724536</td>
</tr>
</tbody>
</table>
@ -1014,23 +1014,23 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Hospital A</td>
<td align="center">0.4752371</td>
<td align="center">4745</td>
<td align="center">0.4800594</td>
<td align="center">4714</td>
</tr>
<tr class="even">
<td align="center">Hospital B</td>
<td align="center">0.4825898</td>
<td align="center">5514</td>
<td align="center">0.4737983</td>
<td align="center">5534</td>
</tr>
<tr class="odd">
<td align="center">Hospital C</td>
<td align="center">0.4705631</td>
<td align="center">2344</td>
<td align="center">0.4763514</td>
<td align="center">2368</td>
</tr>
<tr class="even">
<td align="center">Hospital D</td>
<td align="center">0.4711928</td>
<td align="center">3211</td>
<td align="center">0.4724536</td>
<td align="center">3122</td>
</tr>
</tbody>
</table>
@ -1050,27 +1050,27 @@ Longest: 24</p>
<tbody>
<tr class="odd">
<td align="center">Escherichia</td>
<td align="center">0.7346552</td>
<td align="center">0.8993433</td>
<td align="center">0.9744885</td>
<td align="center">0.7283810</td>
<td align="center">0.9015873</td>
<td align="center">0.9751111</td>
</tr>
<tr class="even">
<td align="center">Klebsiella</td>
<td align="center">0.7406230</td>
<td align="center">0.9020979</td>
<td align="center">0.9726637</td>
<td align="center">0.7311622</td>
<td align="center">0.9157088</td>
<td align="center">0.9750958</td>
</tr>
<tr class="odd">
<td align="center">Staphylococcus</td>
<td align="center">0.7322122</td>
<td align="center">0.9210867</td>
<td align="center">0.9785252</td>
<td align="center">0.7251732</td>
<td align="center">0.9230177</td>
<td align="center">0.9799846</td>
</tr>
<tr class="even">
<td align="center">Streptococcus</td>
<td align="center">0.7135883</td>
<td align="center">0.7345833</td>
<td align="center">0.0000000</td>
<td align="center">0.7135883</td>
<td align="center">0.7345833</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: 35 KiB

After

Width:  |  Height:  |  Size: 35 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

2
docs/articles/EUCAST.html
View File

@ -192,7 +192,7 @@
<h1>How to apply EUCAST rules</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>EUCAST.Rmd</code></div>

2
docs/articles/G_test.html
View File

@ -192,7 +192,7 @@
<h1>How to use the <em>G</em>-test</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>G_test.Rmd</code></div>

2
docs/articles/WHONET.html
View File

@ -192,7 +192,7 @@
<h1>How to work with WHONET data</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>WHONET.Rmd</code></div>

2
docs/articles/atc_property.html
View File

@ -192,7 +192,7 @@
<h1>How to get properties of an antibiotic</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>atc_property.Rmd</code></div>

72
docs/articles/benchmarks.html
View File

@ -192,7 +192,7 @@
<h1>Benchmarks</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>benchmarks.Rmd</code></div>
@ -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") 16.70 16.80 17.10 16.90 17.20 18.4 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 31.70 31.80 48.90 31.90 73.00 117.0 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.70 16.80 23.10 16.90 17.90 76.0 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 16.80 17.00 33.20 18.20 56.00 58.6 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 24.60 24.70 29.00 24.70 25.30 65.8 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 24.60 24.70 29.20 24.80 25.10 67.4 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 7.02 7.11 7.73 7.26 7.33 11.9 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") 16.6 16.70 25.10 16.70 18.30 58.00 10</span></a>
<a class="sourceLine" id="cb2-13" title="13"><span class="co">#&gt; as.mo("stau") 31.8 31.90 36.20 31.90 31.90 74.90 10</span></a>
<a class="sourceLine" id="cb2-14" title="14"><span class="co">#&gt; as.mo("staaur") 16.7 16.80 30.70 16.90 57.80 72.20 10</span></a>
<a class="sourceLine" id="cb2-15" title="15"><span class="co">#&gt; as.mo("STAAUR") 16.7 16.70 16.80 16.80 16.80 17.30 10</span></a>
<a class="sourceLine" id="cb2-16" title="16"><span class="co">#&gt; as.mo("S. aureus") 24.6 24.70 33.60 24.70 25.00 70.40 10</span></a>
<a class="sourceLine" id="cb2-17" title="17"><span class="co">#&gt; as.mo("S. aureus") 24.6 24.70 29.10 24.70 24.80 67.20 10</span></a>
<a class="sourceLine" id="cb2-18" title="18"><span class="co">#&gt; as.mo("Staphylococcus aureus") 7.5 7.51 7.67 7.58 7.91 7.97 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>
@ -236,12 +236,12 @@
<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") 262.0 292.0 296.0 304.0 310 312 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 261.0 263.0 286.0 288.0 307 311 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 142.0 143.0 164.0 165.0 184 187 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 142.0 143.0 170.0 163.0 192 229 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 67.7 68.1 94.3 89.4 117 132 10</span></a></code></pre></div>
<p>That takes 7.5 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>
<a class="sourceLine" id="cb3-10" title="10"><span class="co">#&gt; as.mo("theisl") 262.0 264.0 297.0 306 310 376 10</span></a>
<a class="sourceLine" id="cb3-11" title="11"><span class="co">#&gt; as.mo("THEISL") 262.0 265.0 292.0 290 308 355 10</span></a>
<a class="sourceLine" id="cb3-12" title="12"><span class="co">#&gt; as.mo("T. islandicus") 142.0 142.0 161.0 148 185 186 10</span></a>
<a class="sourceLine" id="cb3-13" title="13"><span class="co">#&gt; as.mo("T. islandicus") 141.0 142.0 184.0 174 188 340 10</span></a>
<a class="sourceLine" id="cb3-14" title="14"><span class="co">#&gt; as.mo("Thermus islandicus") 68.4 68.8 96.3 110 115 125 10</span></a></code></pre></div>
<p>That takes 8 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) 732 739 818 819 837 1040 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!!) of 50 unique values only takes 0.82 seconds (818 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) 723 731 797 785 807 1010 10</span></a></code></pre></div>
<p>So transforming 500,000 values (!!) of 50 unique values only takes 0.78 seconds (784 ms). You only lose time on your unique input values.</p>
</div>
<div id="precalculated-results" class="section level3">
<h3 class="hasAnchor">
@ -300,10 +300,10 @@
<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 11.100 11.300 11.500 11.500 11.600 11.700 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 22.200 22.500 22.800 22.900 23.000 23.500 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.325 0.566 0.571 0.579 0.599 0.704 10</span></a></code></pre></div>
<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 11.20 11.300 12.100 11.800 12.200 15.500 10</span></a>
<a class="sourceLine" id="cb6-9" title="9"><span class="co">#&gt; B 22.20 22.700 26.900 23.900 24.200 57.600 10</span></a>
<a class="sourceLine" id="cb6-10" title="10"><span class="co">#&gt; C 0.53 0.552 0.652 0.591 0.781 0.803 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>
@ -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 0.308 0.392 0.419 0.406 0.478 0.524 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.377 0.406 0.424 0.418 0.442 0.486 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.359 0.516 0.580 0.574 0.664 0.730 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.266 0.326 0.337 0.342 0.350 0.383 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.254 0.281 0.332 0.336 0.359 0.446 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.237 0.315 0.329 0.340 0.360 0.374 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.261 0.295 0.318 0.323 0.341 0.390 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.271 0.290 0.321 0.317 0.343 0.403 10</span></a></code></pre></div>
<a class="sourceLine" id="cb7-13" title="13"><span class="co">#&gt; A 0.318 0.329 0.414 0.431 0.464 0.532 10</span></a>
<a class="sourceLine" id="cb7-14" title="14"><span class="co">#&gt; B 0.346 0.355 0.414 0.405 0.456 0.528 10</span></a>
<a class="sourceLine" id="cb7-15" title="15"><span class="co">#&gt; C 0.347 0.357 0.507 0.489 0.608 0.778 10</span></a>
<a class="sourceLine" id="cb7-16" title="16"><span class="co">#&gt; D 0.280 0.306 0.348 0.343 0.378 0.453 10</span></a>
<a class="sourceLine" id="cb7-17" title="17"><span class="co">#&gt; E 0.241 0.298 0.333 0.329 0.401 0.408 10</span></a>
<a class="sourceLine" id="cb7-18" title="18"><span class="co">#&gt; F 0.253 0.295 0.320 0.308 0.330 0.415 10</span></a>
<a class="sourceLine" id="cb7-19" title="19"><span class="co">#&gt; G 0.271 0.279 0.309 0.284 0.363 0.379 10</span></a>
<a class="sourceLine" id="cb7-20" title="20"><span class="co">#&gt; H 0.218 0.260 0.328 0.341 0.366 0.426 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 15.06 15.54 22.29 15.71 31.46 40.83 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 23.57 23.91 28.72 24.04 26.24 47.77 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 23.46 23.87 33.14 24.71 45.69 68.77 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 23.76 23.98 37.40 24.72 46.85 90.39 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 23.98 24.07 30.76 24.49 25.18 67.52 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 24.03 24.04 27.06 24.14 26.51 47.08 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 23.66 24.00 30.90 24.17 25.84 65.76 10</span></a></code></pre></div>
<a class="sourceLine" id="cb8-21" title="21"><span class="co">#&gt; en 15.12 15.39 19.60 15.47 15.63 57.02 10</span></a>
<a class="sourceLine" id="cb8-22" title="22"><span class="co">#&gt; de 23.37 23.62 24.02 24.01 24.09 25.10 10</span></a>
<a class="sourceLine" id="cb8-23" title="23"><span class="co">#&gt; nl 23.44 23.94 24.05 24.02 24.14 25.02 10</span></a>
<a class="sourceLine" id="cb8-24" title="24"><span class="co">#&gt; es 23.71 24.03 28.36 24.08 24.29 65.92 10</span></a>
<a class="sourceLine" id="cb8-25" title="25"><span class="co">#&gt; it 23.65 23.94 24.08 24.03 24.07 25.12 10</span></a>
<a class="sourceLine" id="cb8-26" title="26"><span class="co">#&gt; fr 23.94 23.99 32.58 24.17 25.14 66.00 10</span></a>
<a class="sourceLine" id="cb8-27" title="27"><span class="co">#&gt; pt 23.30 23.63 28.51 24.06 24.78 68.87 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: 27 KiB

After

Width:  |  Height:  |  Size: 28 KiB

2
docs/articles/freq.html
View File

@ -192,7 +192,7 @@
<h1>How to create frequency tables</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>freq.Rmd</code></div>

2
docs/articles/mo_property.html
View File

@ -192,7 +192,7 @@
<h1>How to get properties of a microorganism</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>mo_property.Rmd</code></div>

2
docs/articles/resistance_predict.html
View File

@ -192,7 +192,7 @@
<h1>How to predict antimicrobial resistance</h1>
<h4 class="author">Matthijs S. Berends</h4>
<h4 class="date">28 February 2019</h4>
<h4 class="date">01 March 2019</h4>
<div class="hidden name"><code>resistance_predict.Rmd</code></div>

13
docs/reference/mo_source.html
View File

@ -278,12 +278,15 @@ This is the fastest way to have your organisation (or analysis) specific codes p
set_mo_source("home/me/ourcodes.xlsx")
# Created mo_source file '~/.mo_source.rds' from 'home/me/ourcodes.xlsx'.
</pre>
<p>It has now created a file "~/.mo_source.rds" with the contents of our Excel file. It it an R specific format with great compression.</p>
<p>It has now created a file "~/.mo_source.rds" with the contents of our Excel file, but only the first column with foreign values and the 'mo' column will be kept.</p>
<p>And now we can use it in our functions:</p><pre>
as.mo("lab_mo_ecoli")
# B_ESCHR_COL
[1] B_ESCHR_COL
mo_genus("lab_mo_kpneumoniae")
# "Klebsiella"
[1] "Klebsiella"
# other input values still work too
as.mo(c("Escherichia coli", "E. coli", "lab_mo_ecoli"))
[1] B_ESCHR_COL B_ESCHR_COL B_ESCHR_COL
</pre>
<p>If we edit the Excel file to, let's say, this:</p><pre>
| A | B |
@ -297,9 +300,9 @@ as.mo("lab_mo_ecoli")
<p>...any new usage of an MO function in this package will update your data:</p><pre>
as.mo("lab_mo_ecoli")
# Updated mo_source file '~/.mo_source.rds' from 'home/me/ourcodes.xlsx'.
# B_ESCHR_COL
[1] B_ESCHR_COL
mo_genus("lab_Staph_aureus")
# "Staphylococcus"
[1] "Staphylococcus"
</pre>
<p>To remove the reference completely, just use any of these:</p><pre>
set_mo_source("")

14
man/mo_source.Rd
View File

@ -45,15 +45,19 @@ set_mo_source("home/me/ourcodes.xlsx")
# Created mo_source file '~/.mo_source.rds' from 'home/me/ourcodes.xlsx'.
}
It has now created a file "~/.mo_source.rds" with the contents of our Excel file. It it an R specific format with great compression.
It has now created a file "~/.mo_source.rds" with the contents of our Excel file, but only the first column with foreign values and the 'mo' column will be kept.
And now we can use it in our functions:
\preformatted{
as.mo("lab_mo_ecoli")
# B_ESCHR_COL
[1] B_ESCHR_COL
mo_genus("lab_mo_kpneumoniae")
# "Klebsiella"
[1] "Klebsiella"
# other input values still work too
as.mo(c("Escherichia coli", "E. coli", "lab_mo_ecoli"))
[1] B_ESCHR_COL B_ESCHR_COL B_ESCHR_COL
}
If we edit the Excel file to, let's say, this:
@ -71,10 +75,10 @@ If we edit the Excel file to, let's say, this:
\preformatted{
as.mo("lab_mo_ecoli")
# Updated mo_source file '~/.mo_source.rds' from 'home/me/ourcodes.xlsx'.
# B_ESCHR_COL
[1] B_ESCHR_COL
mo_genus("lab_Staph_aureus")
# "Staphylococcus"
[1] "Staphylococcus"
}
To remove the reference completely, just use any of these: