mirror of https://github.com/msberends/AMR.git
235 lines
8.8 KiB
R
Executable File
235 lines
8.8 KiB
R
Executable File
% Generated by roxygen2: do not edit by hand
|
|
% Please edit documentation in R/freq.R
|
|
\name{freq}
|
|
\alias{freq}
|
|
\alias{frequency_tbl}
|
|
\alias{top_freq}
|
|
\alias{header}
|
|
\alias{print.freq}
|
|
\title{Frequency table}
|
|
\usage{
|
|
freq(x, ..., sort.count = TRUE, nmax = getOption("max.print.freq"),
|
|
na.rm = TRUE, row.names = TRUE, markdown = !interactive(),
|
|
digits = 2, quote = FALSE, header = TRUE, title = NULL,
|
|
na = "<NA>", droplevels = TRUE, sep = " ",
|
|
decimal.mark = getOption("OutDec"), big.mark = ifelse(decimal.mark !=
|
|
",", ",", "."))
|
|
|
|
frequency_tbl(x, ..., sort.count = TRUE,
|
|
nmax = getOption("max.print.freq"), na.rm = TRUE, row.names = TRUE,
|
|
markdown = !interactive(), digits = 2, quote = FALSE,
|
|
header = TRUE, title = NULL, na = "<NA>", droplevels = TRUE,
|
|
sep = " ", decimal.mark = getOption("OutDec"),
|
|
big.mark = ifelse(decimal.mark != ",", ",", "."))
|
|
|
|
top_freq(f, n)
|
|
|
|
header(f, property = NULL)
|
|
|
|
\method{print}{freq}(x, nmax = getOption("max.print.freq", default = 15),
|
|
markdown = !interactive(), header = TRUE,
|
|
decimal.mark = getOption("OutDec"), big.mark = ifelse(decimal.mark !=
|
|
",", ",", "."), ...)
|
|
}
|
|
\arguments{
|
|
\item{x}{vector of any class or a \code{\link{data.frame}}, \code{\link{tibble}} (may contain a grouping variable) or \code{\link{table}}}
|
|
|
|
\item{...}{up to nine different columns of \code{x} when \code{x} is a \code{data.frame} or \code{tibble}, to calculate frequencies from - see Examples. Also supports quasiquotion.}
|
|
|
|
\item{sort.count}{sort on count, i.e. frequencies. This will be \code{TRUE} at default for everything except when using grouping variables.}
|
|
|
|
\item{nmax}{number of row to print. The default, \code{15}, uses \code{\link{getOption}("max.print.freq")}. Use \code{nmax = 0}, \code{nmax = Inf}, \code{nmax = NULL} or \code{nmax = NA} to print all rows.}
|
|
|
|
\item{na.rm}{a logical value indicating whether \code{NA} values should be removed from the frequency table. The header (if set) will always print the amount of \code{NA}s.}
|
|
|
|
\item{row.names}{a logical value indicating whether row indices should be printed as \code{1:nrow(x)}}
|
|
|
|
\item{markdown}{a logical value indicating whether the frequency table should be printed in markdown format. This will print all rows (except when \code{nmax} is defined) and is default behaviour in non-interactive R sessions (like when knitting RMarkdown files).}
|
|
|
|
\item{digits}{how many significant digits are to be used for numeric values in the header (not for the items themselves, that depends on \code{\link{getOption}("digits")})}
|
|
|
|
\item{quote}{a logical value indicating whether or not strings should be printed with surrounding quotes}
|
|
|
|
\item{header}{a logical value indicating whether an informative header should be printed}
|
|
|
|
\item{title}{text to show above frequency table, at default to tries to coerce from the variables passed to \code{x}}
|
|
|
|
\item{na}{a character string that should be used to show empty (\code{NA}) values (only useful when \code{na.rm = FALSE})}
|
|
|
|
\item{droplevels}{a logical value indicating whether in factors empty levels should be dropped}
|
|
|
|
\item{sep}{a character string to separate the terms when selecting multiple columns}
|
|
|
|
\item{decimal.mark}{%
|
|
used for prettying (longish) numerical and complex sequences.
|
|
Passed to \code{\link{prettyNum}}: that help page explains the details.}
|
|
|
|
\item{big.mark}{%
|
|
used for prettying (longish) numerical and complex sequences.
|
|
Passed to \code{\link{prettyNum}}: that help page explains the details.}
|
|
|
|
\item{f}{a frequency table}
|
|
|
|
\item{n}{number of top \emph{n} items to return, use -n for the bottom \emph{n} items. It will include more than \code{n} rows if there are ties.}
|
|
|
|
\item{property}{property in header to return this value directly}
|
|
}
|
|
\value{
|
|
A \code{data.frame} (with an additional class \code{"freq"}) with five columns: \code{item}, \code{count}, \code{percent}, \code{cum_count} and \code{cum_percent}.
|
|
}
|
|
\description{
|
|
Create a frequency table of a vector with items or a \code{data.frame}. Supports quasiquotation and markdown for reports. Best practice is: \code{data \%>\% freq(var)}.\cr
|
|
\code{top_freq} can be used to get the top/bottom \emph{n} items of a frequency table, with counts as names.
|
|
}
|
|
\details{
|
|
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. This package also has a vignette available to explain the use of this function further, run \code{browseVignettes("AMR")} to read it.
|
|
|
|
For numeric values of any class, these additional values will all be calculated with \code{na.rm = TRUE} and shown into the header:
|
|
\itemize{
|
|
\item{Mean, using \code{\link[base]{mean}}}
|
|
\item{Standard Deviation, using \code{\link[stats]{sd}}}
|
|
\item{Coefficient of Variation (CV), the standard deviation divided by the mean}
|
|
\item{Mean Absolute Deviation (MAD), using \code{\link[stats]{mad}}}
|
|
\item{Tukey Five-Number Summaries (minimum, Q1, median, Q3, maximum), using \code{\link[stats]{fivenum}}}
|
|
\item{Interquartile Range (IQR) calculated as \code{Q3 - Q1} using the Tukey Five-Number Summaries, i.e. \strong{not} using the \code{\link[stats]{quantile}} function}
|
|
\item{Coefficient of Quartile Variation (CQV, sometimes called coefficient of dispersion), calculated as \code{(Q3 - Q1) / (Q3 + Q1)} using the Tukey Five-Number Summaries}
|
|
\item{Outliers (total count and unique count), using \code{\link[grDevices]{boxplot.stats}}}
|
|
}
|
|
|
|
For dates and times of any class, these additional values will be calculated with \code{na.rm = TRUE} and shown into the header:
|
|
\itemize{
|
|
\item{Oldest, using \code{\link{min}}}
|
|
\item{Newest, using \code{\link{max}}, with difference between newest and oldest}
|
|
\item{Median, using \code{\link[stats]{median}}, with percentage since oldest}
|
|
}
|
|
|
|
In factors, all factor levels that are not existing in the input data will be dropped.
|
|
|
|
The function \code{top_freq} uses \code{\link[dplyr]{top_n}} internally and will include more than \code{n} rows if there are ties.
|
|
}
|
|
\section{Read more on our website!}{
|
|
|
|
On our website \url{https://msberends.gitlab.io/AMR} you can find \href{https://msberends.gitlab.io/AMR/articles/AMR.html}{a comprehensive tutorial} about how to conduct AMR analysis, the \href{https://msberends.gitlab.io/AMR/reference}{complete documentation of all functions} (which reads a lot easier than here in R) and \href{https://msberends.gitlab.io/AMR/articles/WHONET.html}{an example analysis using WHONET data}.
|
|
}
|
|
|
|
\examples{
|
|
library(dplyr)
|
|
|
|
# this all gives the same result:
|
|
freq(septic_patients$hospital_id)
|
|
freq(septic_patients[, "hospital_id"])
|
|
septic_patients$hospital_id \%>\% freq()
|
|
septic_patients[, "hospital_id"] \%>\% freq()
|
|
septic_patients \%>\% freq("hospital_id")
|
|
septic_patients \%>\% freq(hospital_id) #<- easiest to remember (tidyverse)
|
|
|
|
|
|
# you could also use `select` or `pull` to get your variables
|
|
septic_patients \%>\%
|
|
filter(hospital_id == "A") \%>\%
|
|
select(mo) \%>\%
|
|
freq()
|
|
|
|
|
|
# multiple selected variables will be pasted together
|
|
septic_patients \%>\%
|
|
left_join_microorganisms \%>\%
|
|
freq(genus, species)
|
|
|
|
# functions as quasiquotation are also supported
|
|
septic_patients \%>\%
|
|
freq(mo_genus(mo), mo_species(mo))
|
|
|
|
|
|
# group a variable and analyse another
|
|
septic_patients \%>\%
|
|
group_by(hospital_id) \%>\%
|
|
freq(gender)
|
|
|
|
|
|
# get top 10 bugs of hospital A as a vector
|
|
septic_patients \%>\%
|
|
filter(hospital_id == "A") \%>\%
|
|
freq(mo) \%>\%
|
|
top_freq(10)
|
|
|
|
|
|
# save frequency table to an object
|
|
years <- septic_patients \%>\%
|
|
mutate(year = format(date, "\%Y")) \%>\%
|
|
freq(year)
|
|
|
|
|
|
# show only the top 5
|
|
years \%>\% print(nmax = 5)
|
|
|
|
|
|
# save to an object with formatted percentages
|
|
years <- format(years)
|
|
|
|
|
|
# print a histogram of numeric values
|
|
septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
hist()
|
|
|
|
# or a boxplot of numeric values
|
|
septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
boxplot()
|
|
|
|
# or even a boxplot per group
|
|
septic_patients \%>\%
|
|
group_by(hospital_id) \%>\%
|
|
freq(age) \%>\%
|
|
boxplot()
|
|
|
|
# or print all points to a regular plot
|
|
septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
plot()
|
|
|
|
|
|
# transform to a data.frame or tibble
|
|
septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
as.data.frame()
|
|
|
|
|
|
# or transform (back) to a vector
|
|
septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
as.vector()
|
|
|
|
identical(septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
as.vector() \%>\%
|
|
sort(),
|
|
sort(septic_patients$age)) # TRUE
|
|
|
|
|
|
# it also supports `table` objects
|
|
table(septic_patients$gender,
|
|
septic_patients$age) \%>\%
|
|
freq(sep = " **sep** ")
|
|
|
|
|
|
# only get selected columns
|
|
septic_patients \%>\%
|
|
freq(hospital_id) \%>\%
|
|
select(item, percent)
|
|
|
|
septic_patients \%>\%
|
|
freq(hospital_id) \%>\%
|
|
select(-count, -cum_count)
|
|
|
|
|
|
# check differences between frequency tables
|
|
diff(freq(septic_patients$TMP),
|
|
freq(septic_patients$SXT))
|
|
}
|
|
\keyword{freq}
|
|
\keyword{frequency}
|
|
\keyword{summarise}
|
|
\keyword{summary}
|