mirror of https://github.com/msberends/AMR.git
128 lines
5.2 KiB
R
Executable File
128 lines
5.2 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{print.frequency_tbl}
|
|
\title{Frequency table}
|
|
\usage{
|
|
frequency_tbl(x, ..., sort.count = TRUE, nmax = getOption("max.print.freq"),
|
|
na.rm = TRUE, row.names = TRUE, markdown = FALSE, digits = 2,
|
|
sep = " ")
|
|
|
|
freq(x, ..., sort.count = TRUE, nmax = getOption("max.print.freq"),
|
|
na.rm = TRUE, row.names = TRUE, markdown = FALSE, digits = 2,
|
|
sep = " ")
|
|
|
|
top_freq(f, n)
|
|
|
|
\method{print}{frequency_tbl}(x, nmax = getOption("max.print.freq", default =
|
|
15), ...)
|
|
}
|
|
\arguments{
|
|
\item{x}{vector with items, or a \code{data.frame}}
|
|
|
|
\item{...}{up to nine different columns of \code{x} to calculate frequencies from, see Examples}
|
|
|
|
\item{sort.count}{sort on count, i.e. frequencies. This will be \code{TRUE} at default for everything except for factors.}
|
|
|
|
\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 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}{print table in markdown format (this forces \code{nmax = NA})}
|
|
|
|
\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{sep}{a character string to separate the terms when selecting multiple columns}
|
|
|
|
\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.}
|
|
}
|
|
\value{
|
|
A \code{data.frame} with an additional class \code{"frequency_tbl"}
|
|
}
|
|
\description{
|
|
Create a frequency table of a vector with items or a data frame. Supports quasiquotation and markdown for reports. \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}
|
|
}
|
|
|
|
|
|
The function \code{top_freq} uses \code{\link[dplyr]{top_n}} internally and will include more than \code{n} rows if there are ties.
|
|
}
|
|
\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 when used to tidyverse
|
|
|
|
# you could use `select`...
|
|
septic_patients \%>\%
|
|
filter(hospital_id == "A") \%>\%
|
|
select(bactid) \%>\%
|
|
freq()
|
|
|
|
# ... or you use `freq` to select it immediately
|
|
septic_patients \%>\%
|
|
filter(hospital_id == "A") \%>\%
|
|
freq(bactid)
|
|
|
|
# select multiple columns; they will be pasted together
|
|
septic_patients \%>\%
|
|
left_join_microorganisms \%>\%
|
|
filter(hospital_id == "A") \%>\%
|
|
freq(genus, species)
|
|
|
|
# get top 10 bugs of hospital A as a vector
|
|
septic_patients \%>\%
|
|
filter(hospital_id == "A") \%>\%
|
|
freq(bactid) \%>\%
|
|
top_freq(10)
|
|
|
|
# save frequency table to an object
|
|
years <- septic_patients \%>\%
|
|
mutate(year = format(date, "\%Y")) \%>\%
|
|
freq(year)
|
|
|
|
# print only top 5
|
|
years \%>\% print(nmax = 5)
|
|
|
|
# transform to plain data.frame
|
|
septic_patients \%>\%
|
|
freq(age) \%>\%
|
|
as.data.frame()
|
|
}
|
|
\keyword{freq}
|
|
\keyword{frequency}
|
|
\keyword{summarise}
|
|
\keyword{summary}
|