added vignette of freq

2026-10-01 04:13:33 +02:00 · 2018-05-09 11:44:46 +02:00
1 parent 25b3346d9a
commit f05e7178cb
@@ -4,3 +4,4 @@
 .Ruserdata
 AMR.Rproj
 tests/testthat/Rplots.pdf
+inst/doc
@@ -1,6 +1,6 @@
 Package: AMR
-Version: 0.2.0
-Date: 2018-05-02
+Version: 0.2.0.9000
+Date: 2018-05-09
 Title: Antimicrobial Resistance Analysis
 Authors@R: c(
    person(
@@ -37,7 +37,10 @@ Imports:
    tibble
 Suggests:
    testthat (>= 1.0.2),
-    covr (>= 3.0.1)
+    covr (>= 3.0.1),
+    knitr,
+    rmarkdown
+VignetteBuilder: knitr
 URL: https://github.com/msberends/AMR
 BugReports: https://github.com/msberends/AMR/issues
 License: GPL-2 | file LICENSE
@@ -1,4 +1,13 @@
-# 0.2.0
+# 0.2.9000 (development version)
+#### New
+* Vignettes about frequency tables: [vignettes/freq.html](vignettes/freq.html)
+* Possibility to globally set the default for the amount of items to print in frequency tables (`freq` function), with `options(max.print.freq = n)`
+
+#### Changed
+* Renamed `toConsole` parameter of `freq` to `as.data.frame`
+* Small translational improvements to the `septic_patients` dataset
+
+# 0.2.0 (latest stable version)
 #### New
 * Full support for Windows, Linux and macOS
 * Full support for old R versions, only R-3.0.0 (April 2013) or later is needed (needed packages may have other dependencies)
@@ -21,10 +21,10 @@
 #' Create a frequency table of a vector of data, a single column or a maximum of 9 columns of a data frame. Supports markdown for reports.
 #' @param x data
 #' @param sort.count Sort on count. Use \code{FALSE} to sort alphabetically on item.
-#' @param nmax number of row to print. Use \code{nmax = 0} or \code{nmax = NA} to print all rows.
-#' @param na.rm a logical value indicating whether NA values should be removed from the frequency table. The header will always print the amount of\code{NA}s.
+#' @param nmax number of row to print. The default, \code{15}, uses \code{\link[base]{getOption}("max.print.freq")}. Use \code{nmax = 0} or \code{nmax = NA} to print all rows.
+#' @param na.rm a logical value indicating whether NA values should be removed from the frequency table. The header will always print the amount of \code{NA}s.
 #' @param markdown print table in markdown format (this forces \code{nmax = NA})
-#' @param toConsole Print table to the console. Use \code{FALSE} to assign the table to an object.
+#' @param as.data.frame return frequency table without header as a \code{data.frame} (e.g. to assign the table to an object)
 #' @param digits how many significant digits are to be used for numeric values (not for the items themselves, that depends on \code{\link{getOption}("digits")})
 #' @param sep a character string to separate the terms when selecting multiple columns
 #' @details For numeric values, the next values will be calculated and shown into the header:
@@ -32,7 +32,7 @@
 #'   \item{Mean, using \code{\link[base]{mean}}}
 #'   \item{Standard deviation, using \code{\link[stats]{sd}}}
 #'   \item{Five numbers of Tukey (min, Q1, median, Q3, max), using \code{\link[stats]{fivenum}}}
-#'   \item{Outliers (count and list), using \code{\link{boxplot.stats}}}
+#'   \item{Outliers (total count and unique count), using \code{\link{boxplot.stats}}}
 #'   \item{Coefficient of variation (CV), the standard deviation divided by the mean}
 #'   \item{Coefficient of quartile variation (CQV, sometimes called coefficient of dispersion), calculated as \code{(Q3 - Q1) / (Q3 + Q1)} using \code{\link{quantile}} with \code{type = 6} as quantile algorithm to comply with SPSS standards}
 #' }
@@ -63,13 +63,13 @@
 #' years <- septic_patients %>%
 #'   mutate(year = format(date, "%Y")) %>%
 #'   select(year) %>%
-#'   freq(toConsole = FALSE)
+#'   freq(as.data.frame = TRUE)
 freq <- function(x,
                 sort.count = TRUE,
-                 nmax = 15,
+                 nmax = getOption("max.print.freq"),
                 na.rm = TRUE,
                 markdown = FALSE,
-                 toConsole = TRUE,
+                 as.data.frame = FALSE,
                 digits = 2,
                 sep = " ") {

@@ -156,8 +156,8 @@ freq <- function(x,
      stop('A maximum of 9 columns can be analysed at the same time.', call. = FALSE)
    }
  }
-  if (markdown == TRUE & toConsole == FALSE) {
-    warning('`toConsole = FALSE` will be ignored when `markdown = TRUE`.')
+  if (markdown == TRUE & as.data.frame == TRUE) {
+    warning('`as.data.frame = TRUE` will be ignored when `markdown = TRUE`.')
  }

  if (mult.columns > 1) {
@@ -232,7 +232,7 @@ freq <- function(x,
    x <- x %>% format(formatdates)
  }

-  if (toConsole == TRUE) {
+  if (as.data.frame == FALSE) {
    cat(header)
  }

@@ -244,22 +244,30 @@ freq <- function(x,
    warning('All observations are unique.', call. = FALSE)
  }

-  if (nmax == 0 | is.na(nmax)) {
+  nmax.set <- !missing(nmax)
+  if (is.null(nmax) & is.null(base::getOption("max.print.freq", default = NULL))) {
+    # default for max print setting
+    nmax <- 15
+  }
+
+  if (nmax == 0 | is.na(nmax) | is.null(nmax)) {
    nmax <- length(x)
  }
  nmax.1 <- min(length(x), nmax + 1)

  # create table with counts and percentages
+  column_names <- c('Item', 'Count', 'Percent', 'Cum. Count', 'Cum. Percent', '(Factor Level)')
+  column_names_df <- c('item', 'count', 'percent', 'cum_count', 'cum_percent', 'factor_level')
  if (any(class(x) == 'factor')) {
    df <- tibble::tibble(Item = x,
                         Fctlvl = x %>% as.integer()) %>%
      group_by(Item, Fctlvl)
-    column_names <- c('Item', 'Count', 'Percent', 'Cum. Count', 'Cum. Percent', '(Factor Level)')
    column_align <- c('l', 'r', 'r', 'r', 'r', 'r')
  } else {
    df <- tibble::tibble(Item = x) %>%
      group_by(Item)
-    column_names <- c('Item', 'Count', 'Percent', 'Cum. Count', 'Cum. Percent')
+    column_names <- column_names[1:5] # strip factor lvl
+    column_names_df <- column_names_df[1:5] # strip factor lvl
    column_align <- c(x_align, 'r', 'r', 'r', 'r')
  }
  df <- df %>%
@@ -276,10 +284,10 @@ freq <- function(x,

  # sort according to setting
  if (sort.count == TRUE) {
-    df <- df %>% arrange(desc(Count))
+    df <- df %>% arrange(desc(Count), Item)
  } else {
    if (any(class(x) == 'factor')) {
-      df <- df %>% arrange(Fctlvl)
+      df <- df %>% arrange(Fctlvl, Item)
    } else {
      df <- df %>% arrange(Item)
    }
@@ -295,65 +303,68 @@ freq <- function(x,
    df <- df %>% select(Item, Count, Percent, Cum, CumTot, Fctlvl)
  }

+  if (as.data.frame == TRUE) {
+    # assign to object
+    df[, 3] <- df[, 2] / sum(df[, 2], na.rm = TRUE)
+    df[, 4] <- cumsum(df[, 2])
+    df[, 5] <- df[, 4] / sum(df[, 2], na.rm = TRUE)
+    colnames(df) <- column_names_df
+    return(as.data.frame(df, stringsAsFactors = FALSE))
+  }
+
  if (markdown == TRUE) {
    tblformat <- 'markdown'
  } else {
    tblformat <- 'pandoc'
  }

-  if (toConsole == FALSE) {
-    # assign to object
-    df[, 3] <- df[, 2] / sum(df[, 2], na.rm = TRUE)
-    df[, 4] <- cumsum(df[, 2])
-    df[, 5] <- df[, 4] / sum(df[, 2], na.rm = TRUE)
-    return(df)
+  # save old NA setting for kable
+  opt.old <- options()$knitr.kable.NA
+  options(knitr.kable.NA = "<NA>")

-  } else {
+  Count.rest <- sum(df[nmax.1:nrow(df), 'Count'], na.rm = TRUE)
+  if (any(class(x) %in% c('double', 'integer', 'numeric', 'raw', 'single'))) {
+    df <- df %>% mutate(Item = format(Item))
+  }
+  df <- df %>% mutate(Count = format(Count))

-    # save old NA setting for kable
-    opt.old <- options()$knitr.kable.NA
-    options(knitr.kable.NA = "<NA>")
-
-    Count.rest <- sum(df[nmax.1:nrow(df), 'Count'], na.rm = TRUE)
-    if (any(class(x) %in% c('double', 'integer', 'numeric', 'raw', 'single'))) {
-      df <- df %>% mutate(Item = format(Item))
-    }
-    df <- df %>% mutate(Count = format(Count))
-
-    if (nrow(df) > nmax.1 & markdown == FALSE) {
-      df2 <- df[1:nmax,]
-      print(
-        knitr::kable(df2,
-                     format = tblformat,
-                     col.names = column_names,
-                     align = column_align,
-                     padding = 1)
-      )
-      cat('... and ',
-          format(nrow(df) - nmax),
-          ' more ',
-          paste0('(n = ',
-                 format(Count.rest),
-                 '; ',
-                 (Count.rest / length(x)) %>% percent(force_zero = TRUE),
-                 ')'),
-          '. Use `nmax` to show more rows.\n', sep = '')
-
-    } else {
-      print(
-        knitr::kable(df,
-                     format = tblformat,
-                     col.names = column_names,
-                     align = column_align,
-                     padding = 1)
-      )
+  if (nrow(df) > nmax.1 & markdown == FALSE) {
+    df2 <- df[1:nmax,]
+    print(
+      knitr::kable(df2,
+                   format = tblformat,
+                   col.names = column_names,
+                   align = column_align,
+                   padding = 1)
+    )
+    cat('... and ',
+        format(nrow(df) - nmax),
+        ' more ',
+        paste0('(n = ',
+               format(Count.rest),
+               '; ',
+               (Count.rest / length(x)) %>% percent(force_zero = TRUE),
+               ')'),
+        '.', sep = '')
+    if (nmax.set == FALSE) {
+      cat(' Use `nmax` to show more or less rows.')
    }
    cat('\n')

-    # reset old kable setting
-    options(knitr.kable.NA = opt.old)
-    return(invisible())
+  } else {
+    print(
+      knitr::kable(df,
+                   format = tblformat,
+                   col.names = column_names,
+                   align = column_align,
+                   padding = 1)
+    )
  }
+  cat('\n')
+
+  # reset old kable setting
+  options(knitr.kable.NA = opt.old)
+  return(invisible())
 }

 #' @rdname freq
@@ -3,7 +3,7 @@

 [![logo_rug](man/figures/logo_rug.png)](https://www.rug.nl)[![logo_umcg](man/figures/logo_umcg.png)](https://www.umcg.nl)

-This R package was created for academic research by PhD students of the Faculty of Medical Sciences of the [University of Groningen)](https://www.rug.nl) and the Medical Microbiology & Infection Prevention (MMBI) department of the [University Medical Center Groningen (UMCG)](https://www.umcg.nl). See [Authors](#authors).
+This R package was created for academic research by PhD students of the Faculty of Medical Sciences of the [University of Groningen](https://www.rug.nl) and the Medical Microbiology & Infection Prevention (MMBI) department of the [University Medical Center Groningen (UMCG)](https://www.umcg.nl). See [Authors](#authors).

 ## Why this package?
 This R package contains functions to make **microbiological, epidemiological data analysis easier**. It allows the use of some new classes to work with MIC values and antimicrobial interpretations (i.e. values S, I and R).
@@ -5,24 +5,26 @@
 \alias{frequency_tbl}
 \title{Frequency table}
 \usage{
-freq(x, sort.count = TRUE, nmax = 15, na.rm = TRUE, markdown = FALSE,
-  toConsole = TRUE, digits = 2, sep = " ")
+freq(x, sort.count = TRUE, nmax = getOption("max.print.freq"),
+  na.rm = TRUE, markdown = FALSE, as.data.frame = FALSE, digits = 2,
+  sep = " ")

-frequency_tbl(x, sort.count = TRUE, nmax = 15, na.rm = TRUE,
-  markdown = FALSE, toConsole = TRUE, digits = 2, sep = " ")
+frequency_tbl(x, sort.count = TRUE, nmax = getOption("max.print.freq"),
+  na.rm = TRUE, markdown = FALSE, as.data.frame = FALSE, digits = 2,
+  sep = " ")
 }
 \arguments{
 \item{x}{data}

 \item{sort.count}{Sort on count. Use \code{FALSE} to sort alphabetically on item.}

-\item{nmax}{number of row to print. Use \code{nmax = 0} or \code{nmax = NA} to print all rows.}
+\item{nmax}{number of row to print. The default, \code{15}, uses \code{\link[base]{getOption}("max.print.freq")}. Use \code{nmax = 0} or \code{nmax = NA} to print all rows.}

-\item{na.rm}{a logical value indicating whether NA values should be removed from the frequency table. The header will always print the amount of\code{NA}s.}
+\item{na.rm}{a logical value indicating whether NA values should be removed from the frequency table. The header will always print the amount of \code{NA}s.}

 \item{markdown}{print table in markdown format (this forces \code{nmax = NA})}

-\item{toConsole}{Print table to the console. Use \code{FALSE} to assign the table to an object.}
+\item{as.data.frame}{return frequency table without header as a \code{data.frame} (e.g. to assign the table to an object)}

 \item{digits}{how many significant digits are to be used for numeric values (not for the items themselves, that depends on \code{\link{getOption}("digits")})}

@@ -37,7 +39,7 @@ For numeric values, the next values will be calculated and shown into the header
  \item{Mean, using \code{\link[base]{mean}}}
  \item{Standard deviation, using \code{\link[stats]{sd}}}
  \item{Five numbers of Tukey (min, Q1, median, Q3, max), using \code{\link[stats]{fivenum}}}
-  \item{Outliers (count and list), using \code{\link{boxplot.stats}}}
+  \item{Outliers (total count and unique count), using \code{\link{boxplot.stats}}}
  \item{Coefficient of variation (CV), the standard deviation divided by the mean}
  \item{Coefficient of quartile variation (CQV, sometimes called coefficient of dispersion), calculated as \code{(Q3 - Q1) / (Q3 + Q1)} using \code{\link{quantile}} with \code{type = 6} as quantile algorithm to comply with SPSS standards}
 }
@@ -63,7 +65,7 @@ septic_patients \%>\%
 years <- septic_patients \%>\%
  mutate(year = format(date, "\%Y")) \%>\%
  select(year) \%>\%
-  freq(toConsole = FALSE)
+  freq(as.data.frame = TRUE)
 }
 \keyword{freq}
 \keyword{frequency}
@@ -1,7 +1,7 @@
 context("eucast.R")

 test_that("EUCAST rules work", {
-  a <- EUCAST_rules(septic_patients)
+  a <- suppressWarnings(EUCAST_rules(septic_patients))

  a <- data.frame(bactid = c("KLEPNE",  # Klebsiella pneumoniae
                             "PSEAER",  # Pseudomonas aeruginosa
@@ -1,12 +1,12 @@
 context("freq.R")

 test_that("frequency table works", {
-  expect_equal(nrow(freq(c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5), toConsole = FALSE)), 5)
-  expect_equal(nrow(frequency_tbl(c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5), toConsole = FALSE)), 5)
+  expect_equal(nrow(freq(c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5), as.data.frame = TRUE)), 5)
+  expect_equal(nrow(frequency_tbl(c(1, 1, 2, 2, 3, 3, 4, 4, 5, 5), as.data.frame = TRUE)), 5)

  # date column of septic_patients should contain 1662 unique dates
-  expect_equal(nrow(freq(septic_patients$date, toConsole = FALSE)), 1662)
-  expect_equal(nrow(freq(septic_patients$date, toConsole = FALSE)),
+  expect_equal(nrow(freq(septic_patients$date, as.data.frame = TRUE)), 1662)
+  expect_equal(nrow(freq(septic_patients$date, as.data.frame = TRUE)),
               length(unique(septic_patients$date)))

  expect_output(freq(septic_patients$age))
@@ -13,7 +13,7 @@ test_that("MDRO works", {
  expect_equal(outcome %>% class(), c('ordered', 'factor'))

  # septic_patients should have these finding using Dutch guidelines
-  expect_equal(outcome %>% freq(toConsole = FALSE) %>% pull(Count), c(3, 21))
+  expect_equal(outcome %>% freq(as.data.frame = TRUE) %>% pull(count), c(3, 21))

  expect_equal(BRMO(septic_patients, info = FALSE), MDRO(septic_patients, "nl", info = FALSE))

@@ -0,0 +1,91 @@
+## ----setup, include = FALSE, results = 'markup'--------------------------
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#"
+)
+library(dplyr)
+library(AMR)
+
+## ---- echo = TRUE, results = 'hide'--------------------------------------
+# # just using base R
+freq(septic_patients$sex)
+
+# # using base R to select the variable and pass it on with a pipe
+septic_patients$sex %>% freq()
+
+# # do it all with pipes, using the `select` function of the dplyr package
+septic_patients %>%
+  select(sex) %>%
+  freq()
+
+## ---- echo = TRUE--------------------------------------------------------
+freq(septic_patients$sex)
+
+## ---- echo = TRUE, results = 'hide'--------------------------------------
+my_patients <- septic_patients %>% 
+  left_join_microorganisms()
+
+## ---- echo = TRUE--------------------------------------------------------
+colnames(microorganisms)
+
+## ---- echo = TRUE--------------------------------------------------------
+dim(septic_patients)
+dim(my_patients)
+
+## ---- echo = TRUE--------------------------------------------------------
+my_patients %>%
+  select(genus, species) %>%
+  freq()
+
+## ---- echo = TRUE--------------------------------------------------------
+# # get age distribution of unique patients
+septic_patients %>% 
+  distinct(patient_id, .keep_all = TRUE) %>% 
+  select(age) %>% 
+  freq(nmax = 5)
+
+## ---- echo = TRUE--------------------------------------------------------
+septic_patients %>%
+  select(hospital_id) %>% 
+  freq()
+
+## ---- echo = TRUE--------------------------------------------------------
+septic_patients %>%
+  select(hospital_id) %>% 
+  freq(sort.count = TRUE)
+
+## ---- echo = TRUE--------------------------------------------------------
+septic_patients %>%
+  select(amox) %>% 
+  freq()
+
+## ---- echo = TRUE--------------------------------------------------------
+septic_patients %>%
+  select(date) %>% 
+  freq(nmax = 5)
+
+## ---- echo = TRUE--------------------------------------------------------
+septic_patients %>%
+  select(amox) %>% 
+  freq(na.rm = FALSE)
+
+## ---- echo = TRUE--------------------------------------------------------
+septic_patients %>%
+  select(hospital_id) %>% 
+  freq(markdown = TRUE)
+
+## ---- echo = TRUE--------------------------------------------------------
+my_df <- septic_patients %>%
+  select(hospital_id) %>% 
+  freq(as.data.frame = TRUE)
+
+my_df
+
+class(my_df)
+
+## ---- echo = FALSE-------------------------------------------------------
+# this will print "2018" in 2018, and "2018-yyyy" after 2018.
+yrs <- c(2018:format(Sys.Date(), "%Y"))
+yrs <- c(min(yrs), max(yrs))
+yrs <- paste(unique(yrs), collapse = "-")
+
@@ -0,0 +1,183 @@
+---
+title: "Creating Frequency Tables"
+author: "Matthijs S. Berends"
+output: 
+  rmarkdown::html_vignette:
+    toc: true
+vignette: >
+  %\VignetteIndexEntry{Vignette Title}
+  %\VignetteEngine{knitr::rmarkdown}
+  %\VignetteEncoding{UTF-8}
+---
+
+```{r setup, include = FALSE, results = 'markup'}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#"
+)
+library(dplyr)
+library(AMR)
+```
+
+## Introduction
+
+Frequency tables (or frequency distributions) are summaries of the distribution of values in a sample. With the `freq` function, you can create univariate frequency tables. Multiple variables will be pasted into one variable, so it forces a univariate distribution. We take the `septic_patients` dataset (included in this AMR package) as example.
+
+## Frequencies of one variable
+
+To only show and quickly review the content of one variable, you can just select this variable in various ways. Let's say we want to get the frequencies of the `sex` variable of the `septic_patients` dataset:
+```{r, echo = TRUE, results = 'hide'}
+# # just using base R
+freq(septic_patients$sex)
+
+# # using base R to select the variable and pass it on with a pipe
+septic_patients$sex %>% freq()
+
+# # do it all with pipes, using the `select` function of the dplyr package
+septic_patients %>%
+  select(sex) %>%
+  freq()
+```
+This will all lead to the following table:
+```{r, echo = TRUE}
+freq(septic_patients$sex)
+```
+This immediately shows the class of the variable, its length and availability (i.e. the amount of `NA`), the amount of unique values and (most importantly) that among septic patients men are more prevalent than women.
+
+## Frequencies of more than one variable
+
+Multiple variables will be pasted into one variable to review individual cases, keeping a univariate frequency table.
+
+For illustration, we could add some more variables to the `septic_patients` dataset to learn about bacterial properties:
+```{r, echo = TRUE, results = 'hide'}
+my_patients <- septic_patients %>% 
+  left_join_microorganisms()
+```
+Now all variables of the `microorganisms` dataset have been joined to the `septic_patients` dataset. The `microorganisms` dataset consists of the following variables:
+```{r, echo = TRUE}
+colnames(microorganisms)
+```
+
+If we compare the dimensions between the old and new dataset, we can see that these `r ncol(my_patients) - ncol(septic_patients)` variables were added:
+```{r, echo = TRUE}
+dim(septic_patients)
+dim(my_patients)
+```
+
+So now the `genus` and `species` variables are available. A frequency table of these combined variables can be created like this:
+```{r, echo = TRUE}
+my_patients %>%
+  select(genus, species) %>%
+  freq()
+```
+
+## Frequencies of numeric values
+
+Frequency tables can be created of any input.
+
+In case of numeric values (like integers, doubles, etc.) additional descriptive statistics will be calculated and shown into the header:
+
+```{r, echo = TRUE}
+# # get age distribution of unique patients
+septic_patients %>% 
+  distinct(patient_id, .keep_all = TRUE) %>% 
+  select(age) %>% 
+  freq(nmax = 5)
+```
+
+So the following properties are determined, where `NA` values are always ignored:
+
+* **Mean**
+
+* **Standard deviation**
+
+* **Coefficient of variation** (CV), the standard deviation divided by the mean
+
+* **Five numbers of Tukey** (min, Q1, median, Q3, max)
+
+* **Coefficient of quartile variation** (CQV, sometimes called coefficient of dispersion), calculated as (Q3 - Q1) / (Q3 + Q1) using quantile with `type = 6` as quantile algorithm to comply with SPSS standards
+
+* **Outliers** (total count and unique count)
+
+So for example, the above frequency table quickly shows the median age of patients being `r my_patients %>% distinct(patient_id, .keep_all = TRUE) %>% pull(age) %>% median(na.rm = TRUE)`.
+
+## Frequencies of factors
+
+Frequencies of factors will be sorted on factor level instead of item count by default. This can be changed with the `sort.count` parameter. Frequency tables of factors always show the factor level as an additional last column.
+
+`sort.count` is `TRUE` by default, except for factors. Compare this default behaviour:
+
+```{r, echo = TRUE}
+septic_patients %>%
+  select(hospital_id) %>% 
+  freq()
+```
+
+To this, where items are now sorted on item count:
+
+```{r, echo = TRUE}
+septic_patients %>%
+  select(hospital_id) %>% 
+  freq(sort.count = TRUE)
+```
+
+All classes will be printed into the header. Variables with the new `rsi` class of this AMR package are actually ordered factors and have three classes (look at `Class` in the header):
+
+```{r, echo = TRUE}
+septic_patients %>%
+  select(amox) %>% 
+  freq()
+```
+
+## Frequencies of dates
+
+Frequencies of dates will show the oldest and newest date in the data, and the amount of days between them:
+
+```{r, echo = TRUE}
+septic_patients %>%
+  select(date) %>% 
+  freq(nmax = 5)
+```
+
+## Additional parameters
+
+### Parameter `na.rm`
+With the `na.rm` parameter (defaults to `TRUE`, but they will always be shown into the header), you can include `NA` values in the frequency table:
+```{r, echo = TRUE}
+septic_patients %>%
+  select(amox) %>% 
+  freq(na.rm = FALSE)
+```
+
+### Parameter `markdown`
+The `markdown` parameter can be used in reports created with R Markdown. This will always print all rows:
+
+```{r, echo = TRUE}
+septic_patients %>%
+  select(hospital_id) %>% 
+  freq(markdown = TRUE)
+```
+
+### Parameter `as.data.frame`
+With the `as.data.frame` parameter you can assign the frequency table to an object, or just print it as a `data.frame` to the console:
+
+```{r, echo = TRUE}
+my_df <- septic_patients %>%
+  select(hospital_id) %>% 
+  freq(as.data.frame = TRUE)
+
+my_df
+
+class(my_df)
+```
+
+----
+```{r, echo = FALSE}
+# this will print "2018" in 2018, and "2018-yyyy" after 2018.
+yrs <- c(2018:format(Sys.Date(), "%Y"))
+yrs <- c(min(yrs), max(yrs))
+yrs <- paste(unique(yrs), collapse = "-")
+```
+AMR, (c) `r yrs`, `r packageDescription("AMR")$URL`
+
+Licensed under the [GNU General Public License v2.0](https://github.com/msberends/AMR/blob/master/LICENSE).
@@ -0,0 +1,344 @@
+<!DOCTYPE html>
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+
+<head>
+
+<meta charset="utf-8" />
+<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+<meta name="generator" content="pandoc" />
+
+<meta name="viewport" content="width=device-width, initial-scale=1">
+
+<meta name="author" content="Matthijs S. Berends" />
+
+
+<title>Creating Frequency Tables</title>
+
+
+
+<style type="text/css">code{white-space: pre;}</style>
+<style type="text/css">
+div.sourceCode { overflow-x: auto; }
+table.sourceCode, tr.sourceCode, td.lineNumbers, td.sourceCode {
+  margin: 0; padding: 0; vertical-align: baseline; border: none; }
+table.sourceCode { width: 100%; line-height: 100%; }
+td.lineNumbers { text-align: right; padding-right: 4px; padding-left: 4px; color: #aaaaaa; border-right: 1px solid #aaaaaa; }
+td.sourceCode { padding-left: 5px; }
+code > span.kw { color: #007020; font-weight: bold; } /* Keyword */
+code > span.dt { color: #902000; } /* DataType */
+code > span.dv { color: #40a070; } /* DecVal */
+code > span.bn { color: #40a070; } /* BaseN */
+code > span.fl { color: #40a070; } /* Float */
+code > span.ch { color: #4070a0; } /* Char */
+code > span.st { color: #4070a0; } /* String */
+code > span.co { color: #60a0b0; font-style: italic; } /* Comment */
+code > span.ot { color: #007020; } /* Other */
+code > span.al { color: #ff0000; font-weight: bold; } /* Alert */
+code > span.fu { color: #06287e; } /* Function */
+code > span.er { color: #ff0000; font-weight: bold; } /* Error */
+code > span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */
+code > span.cn { color: #880000; } /* Constant */
+code > span.sc { color: #4070a0; } /* SpecialChar */
+code > span.vs { color: #4070a0; } /* VerbatimString */
+code > span.ss { color: #bb6688; } /* SpecialString */
+code > span.im { } /* Import */
+code > span.va { color: #19177c; } /* Variable */
+code > span.cf { color: #007020; font-weight: bold; } /* ControlFlow */
+code > span.op { color: #666666; } /* Operator */
+code > span.bu { } /* BuiltIn */
+code > span.ex { } /* Extension */
+code > span.pp { color: #bc7a00; } /* Preprocessor */
+code > span.at { color: #7d9029; } /* Attribute */
+code > span.do { color: #ba2121; font-style: italic; } /* Documentation */
+code > span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */
+code > span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */
+code > span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */
+</style>
+
+
+
+<link href="data:text/css;charset=utf-8,body%20%7B%0Abackground%2Dcolor%3A%20%23fff%3B%0Amargin%3A%201em%20auto%3B%0Amax%2Dwidth%3A%20700px%3B%0Aoverflow%3A%20visible%3B%0Apadding%2Dleft%3A%202em%3B%0Apadding%2Dright%3A%202em%3B%0Afont%2Dfamily%3A%20%22Open%20Sans%22%2C%20%22Helvetica%20Neue%22%2C%20Helvetica%2C%20Arial%2C%20sans%2Dserif%3B%0Afont%2Dsize%3A%2014px%3B%0Aline%2Dheight%3A%201%2E35%3B%0A%7D%0A%23header%20%7B%0Atext%2Dalign%3A%20center%3B%0A%7D%0A%23TOC%20%7B%0Aclear%3A%20both%3B%0Amargin%3A%200%200%2010px%2010px%3B%0Apadding%3A%204px%3B%0Awidth%3A%20400px%3B%0Aborder%3A%201px%20solid%20%23CCCCCC%3B%0Aborder%2Dradius%3A%205px%3B%0Abackground%2Dcolor%3A%20%23f6f6f6%3B%0Afont%2Dsize%3A%2013px%3B%0Aline%2Dheight%3A%201%2E3%3B%0A%7D%0A%23TOC%20%2Etoctitle%20%7B%0Afont%2Dweight%3A%20bold%3B%0Afont%2Dsize%3A%2015px%3B%0Amargin%2Dleft%3A%205px%3B%0A%7D%0A%23TOC%20ul%20%7B%0Apadding%2Dleft%3A%2040px%3B%0Amargin%2Dleft%3A%20%2D1%2E5em%3B%0Amargin%2Dtop%3A%205px%3B%0Amargin%2Dbottom%3A%205px%3B%0A%7D%0A%23TOC%20ul%20ul%20%7B%0Amargin%2Dleft%3A%20%2D2em%3B%0A%7D%0A%23TOC%20li%20%7B%0Aline%2Dheight%3A%2016px%3B%0A%7D%0Atable%20%7B%0Amargin%3A%201em%20auto%3B%0Aborder%2Dwidth%3A%201px%3B%0Aborder%2Dcolor%3A%20%23DDDDDD%3B%0Aborder%2Dstyle%3A%20outset%3B%0Aborder%2Dcollapse%3A%20collapse%3B%0A%7D%0Atable%20th%20%7B%0Aborder%2Dwidth%3A%202px%3B%0Apadding%3A%205px%3B%0Aborder%2Dstyle%3A%20inset%3B%0A%7D%0Atable%20td%20%7B%0Aborder%2Dwidth%3A%201px%3B%0Aborder%2Dstyle%3A%20inset%3B%0Aline%2Dheight%3A%2018px%3B%0Apadding%3A%205px%205px%3B%0A%7D%0Atable%2C%20table%20th%2C%20table%20td%20%7B%0Aborder%2Dleft%2Dstyle%3A%20none%3B%0Aborder%2Dright%2Dstyle%3A%20none%3B%0A%7D%0Atable%20thead%2C%20table%20tr%2Eeven%20%7B%0Abackground%2Dcolor%3A%20%23f7f7f7%3B%0A%7D%0Ap%20%7B%0Amargin%3A%200%2E5em%200%3B%0A%7D%0Ablockquote%20%7B%0Abackground%2Dcolor%3A%20%23f6f6f6%3B%0Apadding%3A%200%2E25em%200%2E75em%3B%0A%7D%0Ahr%20%7B%0Aborder%2Dstyle%3A%20solid%3B%0Aborder%3A%20none%3B%0Aborder%2Dtop%3A%201px%20solid%20%23777%3B%0Amargin%3A%2028px%200%3B%0A%7D%0Adl%20%7B%0Amargin%2Dleft%3A%200%3B%0A%7D%0Adl%20dd%20%7B%0Amargin%2Dbottom%3A%2013px%3B%0Amargin%2Dleft%3A%2013px%3B%0A%7D%0Adl%20dt%20%7B%0Afont%2Dweight%3A%20bold%3B%0A%7D%0Aul%20%7B%0Amargin%2Dtop%3A%200%3B%0A%7D%0Aul%20li%20%7B%0Alist%2Dstyle%3A%20circle%20outside%3B%0A%7D%0Aul%20ul%20%7B%0Amargin%2Dbottom%3A%200%3B%0A%7D%0Apre%2C%20code%20%7B%0Abackground%2Dcolor%3A%20%23f7f7f7%3B%0Aborder%2Dradius%3A%203px%3B%0Acolor%3A%20%23333%3B%0Awhite%2Dspace%3A%20pre%2Dwrap%3B%20%0A%7D%0Apre%20%7B%0Aborder%2Dradius%3A%203px%3B%0Amargin%3A%205px%200px%2010px%200px%3B%0Apadding%3A%2010px%3B%0A%7D%0Apre%3Anot%28%5Bclass%5D%29%20%7B%0Abackground%2Dcolor%3A%20%23f7f7f7%3B%0A%7D%0Acode%20%7B%0Afont%2Dfamily%3A%20Consolas%2C%20Monaco%2C%20%27Courier%20New%27%2C%20monospace%3B%0Afont%2Dsize%3A%2085%25%3B%0A%7D%0Ap%20%3E%20code%2C%20li%20%3E%20code%20%7B%0Apadding%3A%202px%200px%3B%0A%7D%0Adiv%2Efigure%20%7B%0Atext%2Dalign%3A%20center%3B%0A%7D%0Aimg%20%7B%0Abackground%2Dcolor%3A%20%23FFFFFF%3B%0Apadding%3A%202px%3B%0Aborder%3A%201px%20solid%20%23DDDDDD%3B%0Aborder%2Dradius%3A%203px%3B%0Aborder%3A%201px%20solid%20%23CCCCCC%3B%0Amargin%3A%200%205px%3B%0A%7D%0Ah1%20%7B%0Amargin%2Dtop%3A%200%3B%0Afont%2Dsize%3A%2035px%3B%0Aline%2Dheight%3A%2040px%3B%0A%7D%0Ah2%20%7B%0Aborder%2Dbottom%3A%204px%20solid%20%23f7f7f7%3B%0Apadding%2Dtop%3A%2010px%3B%0Apadding%2Dbottom%3A%202px%3B%0Afont%2Dsize%3A%20145%25%3B%0A%7D%0Ah3%20%7B%0Aborder%2Dbottom%3A%202px%20solid%20%23f7f7f7%3B%0Apadding%2Dtop%3A%2010px%3B%0Afont%2Dsize%3A%20120%25%3B%0A%7D%0Ah4%20%7B%0Aborder%2Dbottom%3A%201px%20solid%20%23f7f7f7%3B%0Amargin%2Dleft%3A%208px%3B%0Afont%2Dsize%3A%20105%25%3B%0A%7D%0Ah5%2C%20h6%20%7B%0Aborder%2Dbottom%3A%201px%20solid%20%23ccc%3B%0Afont%2Dsize%3A%20105%25%3B%0A%7D%0Aa%20%7B%0Acolor%3A%20%230033dd%3B%0Atext%2Ddecoration%3A%20none%3B%0A%7D%0Aa%3Ahover%20%7B%0Acolor%3A%20%236666ff%3B%20%7D%0Aa%3Avisited%20%7B%0Acolor%3A%20%23800080%3B%20%7D%0Aa%3Avisited%3Ahover%20%7B%0Acolor%3A%20%23BB00BB%3B%20%7D%0Aa%5Bhref%5E%3D%22http%3A%22%5D%20%7B%0Atext%2Ddecoration%3A%20underline%3B%20%7D%0Aa%5Bhref%5E%3D%22https%3A%22%5D%20%7B%0Atext%2Ddecoration%3A%20underline%3B%20%7D%0A%0Acode%20%3E%20span%2Ekw%20%7B%20color%3A%20%23555%3B%20font%2Dweight%3A%20bold%3B%20%7D%20%0Acode%20%3E%20span%2Edt%20%7B%20color%3A%20%23902000%3B%20%7D%20%0Acode%20%3E%20span%2Edv%20%7B%20color%3A%20%2340a070%3B%20%7D%20%0Acode%20%3E%20span%2Ebn%20%7B%20color%3A%20%23d14%3B%20%7D%20%0Acode%20%3E%20span%2Efl%20%7B%20color%3A%20%23d14%3B%20%7D%20%0Acode%20%3E%20span%2Ech%20%7B%20color%3A%20%23d14%3B%20%7D%20%0Acode%20%3E%20span%2Est%20%7B%20color%3A%20%23d14%3B%20%7D%20%0Acode%20%3E%20span%2Eco%20%7B%20color%3A%20%23888888%3B%20font%2Dstyle%3A%20italic%3B%20%7D%20%0Acode%20%3E%20span%2Eot%20%7B%20color%3A%20%23007020%3B%20%7D%20%0Acode%20%3E%20span%2Eal%20%7B%20color%3A%20%23ff0000%3B%20font%2Dweight%3A%20bold%3B%20%7D%20%0Acode%20%3E%20span%2EfuLine truncated
+
+</head>
+
+<body>
+
+
+
+
+<h1 class="title toc-ignore">Creating Frequency Tables</h1>
+<h4 class="author"><em>Matthijs S. Berends</em></h4>
+
+
+<div id="TOC">
+<ul>
+<li><a href="#introduction">Introduction</a></li>
+<li><a href="#frequencies-of-one-variable">Frequencies of one variable</a></li>
+<li><a href="#frequencies-of-more-than-one-variable">Frequencies of more than one variable</a></li>
+<li><a href="#frequencies-of-numeric-values">Frequencies of numeric values</a></li>
+<li><a href="#frequencies-of-factors">Frequencies of factors</a></li>
+<li><a href="#frequencies-of-dates">Frequencies of dates</a></li>
+<li><a href="#additional-parameters">Additional parameters</a><ul>
+<li><a href="#parameter-na.rm">Parameter <code>na.rm</code></a></li>
+<li><a href="#parameter-markdown">Parameter <code>markdown</code></a></li>
+<li><a href="#parameter-as.data.frame">Parameter <code>as.data.frame</code></a></li>
+</ul></li>
+</ul>
+</div>
+
+<div id="introduction" class="section level2">
+<h2>Introduction</h2>
+<p>Frequency tables (or frequency distributions) are summaries of the distribution of values in a sample. With the <code>freq</code> function, you can create univariate frequency tables. Multiple variables will be pasted into one variable, so it forces a univariate distribution. We take the <code>septic_patients</code> dataset (included in this AMR package) as example.</p>
+</div>
+<div id="frequencies-of-one-variable" class="section level2">
+<h2>Frequencies of one variable</h2>
+<p>To only show and quickly review the content of one variable, you can just select this variable in various ways. Let’s say we want to get the frequencies of the <code>sex</code> variable of the <code>septic_patients</code> dataset:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r"><span class="co"># # just using base R</span>
+<span class="kw">freq</span>(septic_patients$sex)
+
+<span class="co"># # using base R to select the variable and pass it on with a pipe</span>
+septic_patients$sex %&gt;%<span class="st"> </span><span class="kw">freq</span>()
+
+<span class="co"># # do it all with pipes, using the `select` function of the dplyr package</span>
+septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(sex) %&gt;%
+<span class="st">  </span><span class="kw">freq</span>()</code></pre></div>
+<p>This will all lead to the following table:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r"><span class="kw">freq</span>(septic_patients$sex)
+<span class="co"># Class:     character</span>
+<span class="co"># Length:    2000 (of which NA: 0 = 0.0%)</span>
+<span class="co"># Unique:    2</span>
+<span class="co"># </span>
+<span class="co"># Item    Count   Percent   Cum. Count   Cum. Percent</span>
+<span class="co"># -----  ------  --------  -----------  -------------</span>
+<span class="co"># M        1112     55.6%         1112          55.6%</span>
+<span class="co"># F         888     44.4%         2000         100.0%</span></code></pre></div>
+<p>This immediately shows the class of the variable, its length and availability (i.e. the amount of <code>NA</code>), the amount of unique values and (most importantly) that among septic patients men are more prevalent than women.</p>
+</div>
+<div id="frequencies-of-more-than-one-variable" class="section level2">
+<h2>Frequencies of more than one variable</h2>
+<p>Multiple variables will be pasted into one variable to review individual cases, keeping a univariate frequency table.</p>
+<p>For illustration, we could add some more variables to the <code>septic_patients</code> dataset to learn about bacterial properties:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">my_patients &lt;-<span class="st"> </span>septic_patients %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">left_join_microorganisms</span>()</code></pre></div>
+<p>Now all variables of the <code>microorganisms</code> dataset have been joined to the <code>septic_patients</code> dataset. The <code>microorganisms</code> dataset consists of the following variables:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r"><span class="kw">colnames</span>(microorganisms)
+<span class="co">#  [1] &quot;bactid&quot;       &quot;bactsys&quot;      &quot;family&quot;       &quot;genus&quot;       </span>
+<span class="co">#  [5] &quot;species&quot;      &quot;subspecies&quot;   &quot;fullname&quot;     &quot;type&quot;        </span>
+<span class="co">#  [9] &quot;gramstain&quot;    &quot;aerobic&quot;      &quot;type_nl&quot;      &quot;gramstain_nl&quot;</span></code></pre></div>
+<p>If we compare the dimensions between the old and new dataset, we can see that these 11 variables were added:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r"><span class="kw">dim</span>(septic_patients)
+<span class="co"># [1] 2000   47</span>
+<span class="kw">dim</span>(my_patients)
+<span class="co"># [1] 2000   58</span></code></pre></div>
+<p>So now the <code>genus</code> and <code>species</code> variables are available. A frequency table of these combined variables can be created like this:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">my_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(genus, species) %&gt;%
+<span class="st">  </span><span class="kw">freq</span>()
+<span class="co"># Columns:   2</span>
+<span class="co"># Length:    2000 (of which NA: 0 = 0.0%)</span>
+<span class="co"># Unique:    137</span>
+<span class="co"># </span>
+<span class="co"># Item                                 Count   Percent   Cum. Count   Cum. Percent</span>
+<span class="co"># ----------------------------------  ------  --------  -----------  -------------</span>
+<span class="co"># Escherichia coli                       485     24.2%          485          24.2%</span>
+<span class="co"># Staphylococcus coagulase negatief      297     14.8%          782          39.1%</span>
+<span class="co"># Staphylococcus aureus                  200     10.0%          982          49.1%</span>
+<span class="co"># Staphylococcus epidermidis             150      7.5%         1132          56.6%</span>
+<span class="co"># Streptococcus pneumoniae                97      4.9%         1229          61.5%</span>
+<span class="co"># Staphylococcus hominis                  67      3.4%         1296          64.8%</span>
+<span class="co"># Klebsiella pneumoniae                   65      3.2%         1361          68.0%</span>
+<span class="co"># Enterococcus faecalis                   44      2.2%         1405          70.2%</span>
+<span class="co"># Proteus mirabilis                       33      1.7%         1438          71.9%</span>
+<span class="co"># Pseudomonas aeruginosa                  31      1.6%         1469          73.5%</span>
+<span class="co"># Streptococcus pyogenes                  30      1.5%         1499          75.0%</span>
+<span class="co"># Enterococcus faecium                    27      1.4%         1526          76.3%</span>
+<span class="co"># Bacteroides fragilis                    26      1.3%         1552          77.6%</span>
+<span class="co"># Enterobacter cloacae                    25      1.2%         1577          78.8%</span>
+<span class="co"># Klebsiella oxytoca                      23      1.1%         1600          80.0%</span>
+<span class="co"># ... and 122 more (n = 400; 20.0%). Use `nmax` to show more or less rows.</span></code></pre></div>
+</div>
+<div id="frequencies-of-numeric-values" class="section level2">
+<h2>Frequencies of numeric values</h2>
+<p>Frequency tables can be created of any input.</p>
+<p>In case of numeric values (like integers, doubles, etc.) additional descriptive statistics will be calculated and shown into the header:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r"><span class="co"># # get age distribution of unique patients</span>
+septic_patients %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">distinct</span>(patient_id, <span class="dt">.keep_all =</span> <span class="ot">TRUE</span>) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">select</span>(age) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>(<span class="dt">nmax =</span> <span class="dv">5</span>)
+<span class="co"># Class:     integer</span>
+<span class="co"># Length:    1920 (of which NA: 0 = 0.0%)</span>
+<span class="co"># Unique:    94</span>
+<span class="co">#   </span>
+<span class="co"># Mean:      68</span>
+<span class="co"># Std. dev.: 18 (CV: 0.27)</span>
+<span class="co"># Five-Num:  0  |  61  |  72  |  80  |  101 (CQV: 0.13)</span>
+<span class="co"># Outliers:  94 (unique: 26)</span>
+<span class="co"># </span>
+<span class="co">#  Item   Count   Percent   Cum. Count   Cum. Percent</span>
+<span class="co"># -----  ------  --------  -----------  -------------</span>
+<span class="co">#     0      34      1.8%           34           1.8%</span>
+<span class="co">#     1       5      0.3%           39           2.0%</span>
+<span class="co">#     2       5      0.3%           44           2.3%</span>
+<span class="co">#     3       2      0.1%           46           2.4%</span>
+<span class="co">#     4       1      0.1%           47           2.4%</span>
+<span class="co"># ... and 89 more (n = 1873; 97.6%).</span></code></pre></div>
+<p>So the following properties are determined, where <code>NA</code> values are always ignored:</p>
+<ul>
+<li><p><strong>Mean</strong></p></li>
+<li><p><strong>Standard deviation</strong></p></li>
+<li><p><strong>Coefficient of variation</strong> (CV), the standard deviation divided by the mean</p></li>
+<li><p><strong>Five numbers of Tukey</strong> (min, Q1, median, Q3, max)</p></li>
+<li><p><strong>Coefficient of quartile variation</strong> (CQV, sometimes called coefficient of dispersion), calculated as (Q3 - Q1) / (Q3 + Q1) using quantile with <code>type = 6</code> as quantile algorithm to comply with SPSS standards</p></li>
+<li><p><strong>Outliers</strong> (total count and unique count)</p></li>
+</ul>
+<p>So for example, the above frequency table quickly shows the median age of patients being 72.</p>
+</div>
+<div id="frequencies-of-factors" class="section level2">
+<h2>Frequencies of factors</h2>
+<p>Frequencies of factors will be sorted on factor level instead of item count by default. This can be changed with the <code>sort.count</code> parameter. Frequency tables of factors always show the factor level as an additional last column.</p>
+<p><code>sort.count</code> is <code>TRUE</code> by default, except for factors. Compare this default behaviour:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(hospital_id) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>()
+<span class="co"># Class:     factor</span>
+<span class="co"># Length:    2000 (of which NA: 0 = 0.0%)</span>
+<span class="co"># Unique:    5</span>
+<span class="co"># </span>
+<span class="co"># Item    Count   Percent   Cum. Count   Cum. Percent   (Factor Level)</span>
+<span class="co"># -----  ------  --------  -----------  -------------  ---------------</span>
+<span class="co"># A         233     11.7%          233          11.7%                1</span>
+<span class="co"># B         583     29.1%          816          40.8%                2</span>
+<span class="co"># C         221     11.1%         1037          51.8%                3</span>
+<span class="co"># D         650     32.5%         1687          84.4%                4</span>
+<span class="co"># E         313     15.7%         2000         100.0%                5</span></code></pre></div>
+<p>To this, where items are now sorted on item count:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(hospital_id) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>(<span class="dt">sort.count =</span> <span class="ot">TRUE</span>)
+<span class="co"># Class:     factor</span>
+<span class="co"># Length:    2000 (of which NA: 0 = 0.0%)</span>
+<span class="co"># Unique:    5</span>
+<span class="co"># </span>
+<span class="co"># Item    Count   Percent   Cum. Count   Cum. Percent   (Factor Level)</span>
+<span class="co"># -----  ------  --------  -----------  -------------  ---------------</span>
+<span class="co"># D         650     32.5%          650          32.5%                4</span>
+<span class="co"># B         583     29.1%         1233          61.7%                2</span>
+<span class="co"># E         313     15.7%         1546          77.3%                5</span>
+<span class="co"># A         233     11.7%         1779          88.9%                1</span>
+<span class="co"># C         221     11.1%         2000         100.0%                3</span></code></pre></div>
+<p>All classes will be printed into the header. Variables with the new <code>rsi</code> class of this AMR package are actually ordered factors and have three classes (look at <code>Class</code> in the header):</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(amox) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>()
+<span class="co"># Class:     factor &gt; ordered &gt; rsi</span>
+<span class="co"># Length:    2000 (of which NA: 678 = 33.9%)</span>
+<span class="co"># Unique:    3</span>
+<span class="co"># </span>
+<span class="co"># Item    Count   Percent   Cum. Count   Cum. Percent   (Factor Level)</span>
+<span class="co"># -----  ------  --------  -----------  -------------  ---------------</span>
+<span class="co"># S         561     42.4%          561          42.4%                1</span>
+<span class="co"># I          49      3.7%          610          46.1%                2</span>
+<span class="co"># R         712     53.9%         1322         100.0%                3</span></code></pre></div>
+</div>
+<div id="frequencies-of-dates" class="section level2">
+<h2>Frequencies of dates</h2>
+<p>Frequencies of dates will show the oldest and newest date in the data, and the amount of days between them:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(date) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>(<span class="dt">nmax =</span> <span class="dv">5</span>)
+<span class="co"># Class:     Date</span>
+<span class="co"># Length:    2000 (of which NA: 0 = 0.0%)</span>
+<span class="co"># Unique:    1662</span>
+<span class="co"># </span>
+<span class="co"># Oldest:    2 januari 2001</span>
+<span class="co"># Newest:    18 oktober 2017 (+6133)</span>
+<span class="co"># </span>
+<span class="co"># Item          Count   Percent   Cum. Count   Cum. Percent</span>
+<span class="co"># -----------  ------  --------  -----------  -------------</span>
+<span class="co"># 2008-12-24        5      0.2%            5           0.2%</span>
+<span class="co"># 2010-12-10        4      0.2%            9           0.4%</span>
+<span class="co"># 2011-03-03        4      0.2%           13           0.6%</span>
+<span class="co"># 2013-06-24        4      0.2%           17           0.8%</span>
+<span class="co"># 2017-09-01        4      0.2%           21           1.1%</span>
+<span class="co"># ... and 1657 more (n = 1979; 99.0%).</span></code></pre></div>
+</div>
+<div id="additional-parameters" class="section level2">
+<h2>Additional parameters</h2>
+<div id="parameter-na.rm" class="section level3">
+<h3>Parameter <code>na.rm</code></h3>
+<p>With the <code>na.rm</code> parameter (defaults to <code>TRUE</code>, but they will always be shown into the header), you can include <code>NA</code> values in the frequency table:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(amox) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>(<span class="dt">na.rm =</span> <span class="ot">FALSE</span>)
+<span class="co"># Class:     factor &gt; ordered &gt; rsi</span>
+<span class="co"># Length:    2678 (of which NA: 678 = 25.3%)</span>
+<span class="co"># Unique:    4</span>
+<span class="co"># </span>
+<span class="co"># Item    Count   Percent   Cum. Count   Cum. Percent   (Factor Level)</span>
+<span class="co"># -----  ------  --------  -----------  -------------  ---------------</span>
+<span class="co"># S         561     28.1%          561          28.1%                1</span>
+<span class="co"># I          49      2.5%          610          30.5%                2</span>
+<span class="co"># R         712     35.6%         1322          66.1%                3</span>
+<span class="co"># &lt;NA&gt;      678     33.9%         2000         100.0%             &lt;NA&gt;</span></code></pre></div>
+</div>
+<div id="parameter-markdown" class="section level3">
+<h3>Parameter <code>markdown</code></h3>
+<p>The <code>markdown</code> parameter can be used in reports created with R Markdown. This will always print all rows:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(hospital_id) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>(<span class="dt">markdown =</span> <span class="ot">TRUE</span>)
+<span class="co"># </span>
+<span class="co"># Class:     factor</span>
+<span class="co"># </span>
+<span class="co"># Length:    2000 (of which NA: 0 = 0.0%)</span>
+<span class="co"># </span>
+<span class="co"># Unique:    5</span>
+<span class="co"># </span>
+<span class="co"># |Item | Count| Percent| Cum. Count| Cum. Percent| (Factor Level)|</span>
+<span class="co"># |:----|-----:|-------:|----------:|------------:|--------------:|</span>
+<span class="co"># |A    |   233|   11.7%|        233|        11.7%|              1|</span>
+<span class="co"># |B    |   583|   29.1%|        816|        40.8%|              2|</span>
+<span class="co"># |C    |   221|   11.1%|       1037|        51.8%|              3|</span>
+<span class="co"># |D    |   650|   32.5%|       1687|        84.4%|              4|</span>
+<span class="co"># |E    |   313|   15.7%|       2000|       100.0%|              5|</span></code></pre></div>
+</div>
+<div id="parameter-as.data.frame" class="section level3">
+<h3>Parameter <code>as.data.frame</code></h3>
+<p>With the <code>as.data.frame</code> parameter you can assign the frequency table to an object, or just print it as a <code>data.frame</code> to the console:</p>
+<div class="sourceCode"><pre class="sourceCode r"><code class="sourceCode r">my_df &lt;-<span class="st"> </span>septic_patients %&gt;%
+<span class="st">  </span><span class="kw">select</span>(hospital_id) %&gt;%<span class="st"> </span>
+<span class="st">  </span><span class="kw">freq</span>(<span class="dt">as.data.frame =</span> <span class="ot">TRUE</span>)
+
+my_df
+<span class="co">#   item count percent cum_count cum_percent factor_level</span>
+<span class="co"># 1    A   233  0.1165       233      0.1165            1</span>
+<span class="co"># 2    B   583  0.2915       816      0.4080            2</span>
+<span class="co"># 3    C   221  0.1105      1037      0.5185            3</span>
+<span class="co"># 4    D   650  0.3250      1687      0.8435            4</span>
+<span class="co"># 5    E   313  0.1565      2000      1.0000            5</span>
+
+<span class="kw">class</span>(my_df)
+<span class="co"># [1] &quot;data.frame&quot;</span></code></pre></div>
+<hr />
+<p>AMR, (c) 2018, <a href="https://github.com/msberends/AMR" class="uri">https://github.com/msberends/AMR</a></p>
+<p>Licensed under the <a href="https://github.com/msberends/AMR/blob/master/LICENSE">GNU General Public License v2.0</a>.</p>
+</div>
+</div>
+
+
+
+<!-- dynamically load mathjax for compatibility with self-contained -->
+<script>
+  (function () {
+    var script = document.createElement("script");
+    script.type = "text/javascript";
+    script.src  = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML";
+    document.getElementsByTagName("head")[0].appendChild(script);
+  })();
+</script>
+
+</body>
+</html>