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
|
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/comparedf.control.R
\name{comparedf.control}
\alias{comparedf.control}
\title{Control settings for \code{comparedf} function}
\usage{
comparedf.control(
tol.logical = "none",
tol.num = c("absolute", "percent", "pct"),
tol.num.val = sqrt(.Machine$double.eps),
int.as.num = FALSE,
tol.char = c("none", "trim", "case", "both"),
tol.factor = c("none", "levels", "labels"),
factor.as.char = FALSE,
tol.date = "absolute",
tol.date.val = 0,
tol.other = "none",
tol.vars = "none",
max.print.vars = NA,
max.print.obs = NA,
max.print.diffs.per.var = 10,
max.print.diffs = 50,
max.print.attrs = NA,
...,
max.print.diff = 10
)
}
\arguments{
\item{tol.logical, tol.num, tol.char, tol.factor, tol.date, tol.other}{A function or one of the shortcut character strings or a list thereof,
denoting the tolerance function to use for a given data type. See "details", below.}
\item{tol.num.val}{Numeric; maximum value of differences allowed in numerics (fed to the function given in \code{tol.num}).}
\item{int.as.num}{Logical; should integers be coerced to numeric before comparison? Default FALSE.}
\item{factor.as.char}{Logical; should factors be coerced to character before comparison? Default FALSE.}
\item{tol.date.val}{Numeric; maximum value of differences allowed in dates (fed to the function given in \code{tol.date}).}
\item{tol.vars}{Either \code{"none"} (the default), denoting that variable names are to be matched as-is,
a named vector manually specifying variable names to compare (where the names correspond to columns of
\code{x} and the values correspond to columns of \code{y}), or a
character vector denoting equivalence classes for characters in the variable names. See "details", below.}
\item{max.print.vars}{Integer denoting maximum number of variables to report in the "variables not shared" and "variables not compared"
output. \code{NA} will print all differences.}
\item{max.print.obs}{Integer denoting maximum number of not-shared observations to report. \code{NA} will print all differences.}
\item{max.print.diffs.per.var, max.print.diffs}{Integers denoting the maximum number of differences to report for each variable or overall.
\code{NA} will print all differences for each variable or overall.}
\item{max.print.attrs}{Integers denoting the maximum number of non-identical attributes to report.\code{NA} will print all differences.}
\item{...}{Other arguments (not in use at this time).}
\item{max.print.diff}{Deprecated.}
}
\value{
A list containing the necessary parameters for the \code{\link{comparedf}} function.
}
\description{
Control tolerance definitions for the \code{\link{comparedf}} function.
}
\details{
The following character strings are accepted:
\itemize{
\item{\code{tol.logical = "none"}: compare logicals exactly as they are.}
\item{\code{tol.num = "absolute"}: compare absolute differences in numerics.}
\item{\code{tol.num = "percent"}, \code{tol.num = "pct"} compare percent differences in numerics.}
\item{\code{tol.char = "none"}: compare character strings exactly as they are.}
\item{\code{tol.char = "trim"}: left-justify and trim all trailing white space.}
\item{\code{tol.char = "case"}: allow differences in upper/lower case.}
\item{\code{tol.char = "both"}: combine \code{"trim"} and \code{"case"}.}
\item{\code{tol.factor = "none"}: match both character labels and numeric levels.}
\item{\code{tol.factor = "levels"}: match only the numeric levels.}
\item{\code{tol.factor = "labels"}: match only the labels.}
\item{\code{tol.date = "absolute"}: compare absolute differences in dates.}
\item{\code{tol.other = "none"}: expect objects of other classes to be exactly identical.}
}
A list with names mapped to \code{x} can be used to specify tolerances by variable. One unnamed element is supported
as the default.
\code{tol.vars}: If not set to \code{"none"} (the default) or a named vector,
the \code{tol.vars} argument is a character vector denoting equivalence classes
for the characters in the variable names. A single character in this vector means to replace that character
with \code{""}. All other strings in this vector are split by character and replaced by the first character in the string.
E.g., a character vector \code{c("._", "aA", " ")} would denote that the dot and underscore are equivalent (to be translated to a dot),
that "a" and "A" are equivalent (to be translated to "a"), and that spaces should be removed.
The special character string \code{"case"} in this vector is the same as specifying \code{paste0(letters, LETTERS)}.
}
\examples{
cntl <- comparedf.control(
tol.num = "pct", # calculate percent differences
tol.vars = c("case", # ignore case
"._", # set all underscores to dots.
"e") # remove all letter e's
)
cntl <- comparedf.control(tol.char = list(
"none", # the default
x1 = "case", # be case-insensitive for the variable "x1"
x2 = function(x, y) tol.NA(x, y, x != y | y == "NA") # a custom-defined tolerance
))
}
\seealso{
\code{\link{comparedf}}, \code{\link{comparedf.tolerances}}, \code{\link{summary.comparedf}}
}
\author{
Ethan Heinzen
}
|
