% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/recode_values.R
\name{recode_values}
\alias{recode_values}
\alias{recode_values.numeric}
\alias{recode_values.data.frame}
\title{Recode old values of variables into new values}
\usage{
recode_values(x, ...)

\method{recode_values}{numeric}(
  x,
  recode = NULL,
  default = NULL,
  preserve_na = TRUE,
  verbose = TRUE,
  ...
)

\method{recode_values}{data.frame}(
  x,
  select = NULL,
  exclude = NULL,
  recode = NULL,
  default = NULL,
  preserve_na = TRUE,
  append = FALSE,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)
}
\arguments{
\item{x}{A data frame, numeric or character vector, or factor.}

\item{...}{not used.}

\item{recode}{A list of named vectors, which indicate the recode pairs.
The \emph{names} of the list-elements (i.e. the left-hand side) represent the
\emph{new} values, while the values of the list-elements indicate the original
(old) values that should be replaced. When recoding numeric vectors,
element names have to be surrounded in backticks. For example,
\code{recode=list(`0`=1)} would recode all \code{1} into \code{0} in a numeric
vector. See also 'Examples' and 'Details'.}

\item{default}{Defines the default value for all values that have
no match in the recode-pairs. Note that, if \code{preserve_na=FALSE}, missing
values (\code{NA}) are also captured by the \code{default} argument, and thus will
also be recoded into the specified value. See 'Examples' and 'Details'.}

\item{preserve_na}{Logical, if \code{TRUE}, \code{NA} (missing values) are preserved.
This overrides any other arguments, including \code{default}. Hence, if
\code{preserve_na=TRUE}, \code{default} will no longer convert \code{NA} into the specified
default value.}

\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"}), a character
vector of variable names (e.g., \code{c("col1", "col2", "col3")}), or a
character vector of variable names including ranges specified via \code{:}
(e.g., \code{c("col1:col3", "col5")}),
\item for some functions, like \code{data_select()} or \code{data_rename()}, \code{select} can
be a named character vector. In this case, the names are used to rename
the columns in the output data frame. See 'Details' in the related
functions to see where this option applies.
\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")}. \code{regex()} can be used to define regular
expression patterns.
\item 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{extract_column_names(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{append}{Logical or string. If \code{TRUE}, recoded or converted variables
get new column names and are appended (column bind) to \code{x}, thus returning
both the original and the recoded variables. The new columns get a suffix,
based on the calling function: \code{"_r"} for recode functions, \code{"_n"} for
\code{to_numeric()}, \code{"_f"} for \code{to_factor()}, or \code{"_s"} for
\code{slide()}. If \code{append=FALSE}, original variables in \code{x} will be
overwritten by their recoded versions. If a character value, recoded
variables are appended with new column names (using the defined suffix) to
the original data frame.}

\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.}
}
\value{
\code{x}, where old values are replaced by new values.
}
\description{
This functions recodes old values into new values and can be used to to
recode numeric or character vectors, or factors.
}
\details{
This section describes the pattern of the \code{recode} arguments, which also
provides some shortcuts, in particular when recoding numeric values.
\itemize{
\item Single values

Single values either need to be wrapped in backticks (in case of numeric
values) or "as is" (for character or factor levels). Example:
\code{recode=list(`0`=1,`1`=2)} would recode 1 into 0, and 2 into 1.
For factors or character vectors, an example is:
\code{recode=list(x="a",y="b")} (recode "a" into "x" and "b" into "y").
\item Multiple values

Multiple values that should be recoded into a new value can be separated
with comma. Example: \code{recode=list(`1`=c(1,4),`2`=c(2,3))} would recode the
values 1 and 4 into 1, and 2 and 3 into 2. It is also possible to define  the
old values as a character string, like:  \code{recode=list(`1`="1,4",`2`="2,3")}
For factors or character vectors, an example is:
\code{recode=list(x=c("a","b"),y=c("c","d"))}.
\item Value range

Numeric value ranges can be defined using the \code{:}. Example:
\code{recode=list(`1`=1:3,`2`=4:6)} would recode all values from 1 to 3 into
1, and 4 to 6 into 2.
\item \code{min} and \code{max}

placeholder to use the minimum or maximum value of the
(numeric) variable. Useful, e.g., when recoding ranges of values.
Example: \code{recode=list(`1`="min:10",`2`="11:max")}.
\item \code{default} values

The \code{default} argument defines the default value for all values that have
no match in the recode-pairs. For example,
\verb{recode=list(`1`=c(1,2),`2`=c(3,4)), default=9} would
recode values 1 and 2 into 1, 3 and 4 into 2, and all other values into 9.
If \code{preserve_na} is set to \code{FALSE}, \code{NA} (missing values) will also be
recoded into the specified default value.
\item Reversing and rescaling

See \code{\link[=reverse]{reverse()}} and \code{\link[=rescale]{rescale()}}.
}
}
\note{
You can use \code{options(data_recode_pattern = "old=new")} to switch the
behaviour of the \code{recode}-argument, i.e. recode-pairs are now following the
pattern \verb{old values = new values}, e.g. if \code{getOption("data_recode_pattern")}
is set to \code{"old=new"}, then \code{recode(`1`=0)} would recode all 1 into 0.
The default for \code{recode(`1`=0)} is to recode all 0 into 1.
}
\section{Selection of variables - the \code{select} argument}{

For most functions that have a \code{select} argument (including this function),
the complete input data frame is returned, even when \code{select} only selects
a range of variables. That is, the function is only applied to those variables
that have a match in \code{select}, while all other variables remain unchanged.
In other words: for this function, \code{select} will not omit any non-included
variables, so that the returned data frame will include all variables
from the input data frame.
}

\examples{
# numeric ----------
set.seed(123)
x <- sample(c(1:4, NA), 15, TRUE)
table(x, useNA = "always")

out <- recode_values(x, list(`0` = 1, `1` = 2:3, `2` = 4))
out
table(out, useNA = "always")

# to recode NA values, set preserve_na to FALSE
out <- recode_values(
  x,
  list(`0` = 1, `1` = 2:3, `2` = 4, `9` = NA),
  preserve_na = FALSE
)
out
table(out, useNA = "always")

# preserve na ----------
out <- recode_values(x, list(`0` = 1, `1` = 2:3), default = 77)
out
table(out, useNA = "always")

# recode na into default ----------
out <- recode_values(
  x,
  list(`0` = 1, `1` = 2:3),
  default = 77,
  preserve_na = FALSE
)
out
table(out, useNA = "always")


# factors (character vectors are similar) ----------
set.seed(123)
x <- as.factor(sample(c("a", "b", "c"), 15, TRUE))
table(x)

out <- recode_values(x, list(x = "a", y = c("b", "c")))
out
table(out)

out <- recode_values(x, list(x = "a", y = "b", z = "c"))
out
table(out)

out <- recode_values(x, list(y = "b,c"), default = 77)
# same as
# recode_values(x, list(y = c("b", "c")), default = 77)
out
table(out)


# data frames ----------
set.seed(123)
d <- data.frame(
  x = sample(c(1:4, NA), 12, TRUE),
  y = as.factor(sample(c("a", "b", "c"), 12, TRUE)),
  stringsAsFactors = FALSE
)

recode_values(
  d,
  recode = list(`0` = 1, `1` = 2:3, `2` = 4, x = "a", y = c("b", "c")),
  append = TRUE
)


# switch recode pattern to "old=new" ----------
options(data_recode_pattern = "old=new")

# numeric
set.seed(123)
x <- sample(c(1:4, NA), 15, TRUE)
table(x, useNA = "always")

out <- recode_values(x, list(`1` = 0, `2:3` = 1, `4` = 2))
table(out, useNA = "always")

# factors (character vectors are similar)
set.seed(123)
x <- as.factor(sample(c("a", "b", "c"), 15, TRUE))
table(x)

out <- recode_values(x, list(a = "x", `b, c` = "y"))
table(out)

# reset options
options(data_recode_pattern = NULL)
}
\seealso{
\itemize{
\item Add a prefix or suffix to column names: \code{\link[=data_addprefix]{data_addprefix()}}, \code{\link[=data_addsuffix]{data_addsuffix()}}
\item Functions to reorder or remove columns: \code{\link[=data_reorder]{data_reorder()}}, \code{\link[=data_relocate]{data_relocate()}},
\code{\link[=data_remove]{data_remove()}}
\item Functions to reshape, pivot or rotate data frames: \code{\link[=data_to_long]{data_to_long()}},
\code{\link[=data_to_wide]{data_to_wide()}}, \code{\link[=data_rotate]{data_rotate()}}
\item Functions to recode data: \code{\link[=rescale]{rescale()}}, \code{\link[=reverse]{reverse()}}, \code{\link[=categorize]{categorize()}},
\code{\link[=recode_values]{recode_values()}}, \code{\link[=slide]{slide()}}
\item Functions to standardize, normalize, rank-transform: \code{\link[=center]{center()}}, \code{\link[=standardize]{standardize()}},
\code{\link[=normalize]{normalize()}}, \code{\link[=ranktransform]{ranktransform()}}, \code{\link[=winsorize]{winsorize()}}
\item Split and merge data frames: \code{\link[=data_partition]{data_partition()}}, \code{\link[=data_merge]{data_merge()}}
\item Functions to find or select columns: \code{\link[=data_select]{data_select()}}, \code{\link[=extract_column_names]{extract_column_names()}}
\item Functions to filter rows: \code{\link[=data_match]{data_match()}}, \code{\link[=data_filter]{data_filter()}}
}
}