1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
|
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/data_tabulate.R
\name{data_tabulate}
\alias{data_tabulate}
\alias{data_tabulate.default}
\alias{data_tabulate.data.frame}
\title{Create frequency tables of variables}
\usage{
data_tabulate(x, ...)
\method{data_tabulate}{default}(x, drop_levels = FALSE, name = NULL, verbose = TRUE, ...)
\method{data_tabulate}{data.frame}(
x,
select = NULL,
exclude = NULL,
ignore_case = FALSE,
regex = FALSE,
collapse = FALSE,
drop_levels = FALSE,
verbose = TRUE,
...
)
}
\arguments{
\item{x}{A (grouped) data frame, a vector or factor.}
\item{...}{not used.}
\item{drop_levels}{Logical, if \code{TRUE}, factor levels that do not occur in
the data are included in the table (with frequency of zero), else unused
factor levels are dropped from the frequency table.}
\item{name}{Optional character string, which includes the name that is used
for printing.}
\item{verbose}{Toggle warnings.}
\item{select}{Variables that will be included when performing the required
tasks. Can be either
\itemize{
\item a variable specified as a literal variable name (e.g., \code{column_name}),
\item a string with the variable name (e.g., \code{"column_name"}), or a character
vector of variable names (e.g., \code{c("col1", "col2", "col3")}),
\item a formula with variable names (e.g., \code{~column_1 + column_2}),
\item a vector of positive integers, giving the positions counting from the left
(e.g. \code{1} or \code{c(1, 3, 5)}),
\item a vector of negative integers, giving the positions counting from the
right (e.g., \code{-1} or \code{-1:-3}),
\item one of the following select-helpers: \code{starts_with()}, \code{ends_with()},
\code{contains()}, a range using \code{:} or \code{regex("")}. \code{starts_with()},
\code{ends_with()}, and \code{contains()} accept several patterns, e.g
\code{starts_with("Sep", "Petal")}.
\item or a function testing for logical conditions, e.g. \code{is.numeric()} (or
\code{is.numeric}), or any user-defined function that selects the variables
for which the function returns \code{TRUE} (like: \code{foo <- function(x) mean(x) > 3}),
\item ranges specified via literal variable names, select-helpers (except
\code{regex()}) and (user-defined) functions can be negated, i.e. return
non-matching elements, when prefixed with a \code{-}, e.g. \code{-ends_with("")},
\code{-is.numeric} or \code{-Sepal.Width:Petal.Length}. \strong{Note:} Negation means
that matches are \emph{excluded}, and thus, the \code{exclude} argument can be
used alternatively. For instance, \code{select=-ends_with("Length")} (with
\code{-}) is equivalent to \code{exclude=ends_with("Length")} (no \code{-}). In case
negation should not work as expected, use the \code{exclude} argument instead.
}
If \code{NULL}, selects all columns. Patterns that found no matches are silently
ignored, e.g. \code{find_columns(iris, select = c("Species", "Test"))} will just
return \code{"Species"}.}
\item{exclude}{See \code{select}, however, column names matched by the pattern
from \code{exclude} will be excluded instead of selected. If \code{NULL} (the default),
excludes no columns.}
\item{ignore_case}{Logical, if \code{TRUE} and when one of the select-helpers or
a regular expression is used in \code{select}, ignores lower/upper case in the
search pattern when matching against variable names.}
\item{regex}{Logical, if \code{TRUE}, the search pattern from \code{select} will be
treated as regular expression. When \code{regex = TRUE}, select \emph{must} be a
character string (or a variable containing a character string) and is not
allowed to be one of the supported select-helpers or a character vector
of length > 1. \code{regex = TRUE} is comparable to using one of the two
select-helpers, \code{select = contains("")} or \code{select = regex("")}, however,
since the select-helpers may not work when called from inside other
functions (see 'Details'), this argument may be used as workaround.}
\item{collapse}{Logical, if \code{TRUE} collapses multiple tables into one larger
table for printing. This affects only printing, not the returned object.}
}
\value{
A data frame, or a list of data frames, with one frequency table
as data frame per variable.
}
\description{
This function creates frequency tables of variables, including
the number of levels/values as well as the distribution of raw, valid and
cumulative percentages.
}
\examples{
\dontshow{if (requireNamespace("poorman")) (if (getRversion() >= "3.4") withAutoprint else force)(\{ # examplesIf}
data(efc)
# vector/factor
data_tabulate(efc$c172code)
# data frame
data_tabulate(efc, c("e42dep", "c172code"))
# grouped data frame
suppressPackageStartupMessages(library(poorman, quietly = TRUE))
efc \%>\%
group_by(c172code) \%>\%
data_tabulate("e16sex")
# collapse tables
efc \%>\%
group_by(c172code) \%>\%
data_tabulate("e16sex", collapse = TRUE)
# for larger N's (> 100000), a big mark is automatically added
set.seed(123)
x <- sample(1:3, 1e6, TRUE)
data_tabulate(x, name = "Large Number")
# to remove the big mark, use "print(..., big_mark = "")"
print(data_tabulate(x), big_mark = "")
\dontshow{\}) # examplesIf}
}
|
