Create new variables or modify existing variables in a data frame. Unlike base::transform(), data_modify()
can be used on grouped data frames, and newly created variables can be directly
used.
Usage
data_modify(data, ...)
# S3 method for data.frame
data_modify(data, ..., .if = NULL, .at = NULL, .modify = NULL)Arguments
- data
A data frame
- ...
One or more expressions that define the new variable name and the values or recoding of those new variables. These expressions can be one of:
A sequence of named, literal expressions, where the left-hand side refers to the name of the new variable, while the right-hand side represent the values of the new variable. Example:
Sepal.Width = center(Sepal.Width).A sequence of string values, representing expressions.
A variable that contains a string representation of the expression. Example:
a <- "2 * Sepal.Width" data_modify(iris, a)A character vector of expressions. Example:
c("SW_double = 2 * Sepal.Width", "SW_fraction = SW_double / 10"). This type of expression cannot be mixed with other expressions, i.e. if a character vector is provided, you may not add further elements to....Using
NULLas right-hand side removes a variable from the data frame. Example:Petal.Width = NULL.
Note that newly created variables can be used in subsequent expressions, including
.ator.if. See also 'Examples'.- .if
A function that returns
TRUEfor columns in the data frame where.ifapplies. This argument is used in combination with the.modifyargument. Note that only one of.ator.ifcan be provided, but not both at the same time. Newly created variables in...can also be selected, see 'Examples'.- .at
A character vector of variable names that should be modified. This argument is used in combination with the
.modifyargument. Note that only one of.ator.ifcan be provided, but not both at the same time. Newly created variables in...can also be selected, see 'Examples'.- .modify
A function that modifies the variables defined in
.ator.if. This argument is used in combination with either the.ator the.ifargument. Note that the modified variable (i.e. the result from.modify) must be either of length 1 or of same length as the input variable.
Note
data_modify() can also be used inside functions. However, it is
recommended to pass the recode-expression as character vector or list of
characters.
Examples
data(efc)
new_efc <- data_modify(
efc,
c12hour_c = center(c12hour),
c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE),
c12hour_z2 = standardize(c12hour)
)
head(new_efc)
#> c12hour e16sex e42dep c172code neg_c_7 c12hour_c c12hour_z c12hour_z2
#> 1 16 2 3 2 12 -69.65306 -1.0466657 -1.0466657
#> 2 148 2 3 2 20 62.34694 0.9368777 0.9368777
#> 3 70 2 3 1 11 -15.65306 -0.2352161 -0.2352161
#> 4 NA 2 <NA> 2 10 NA NA NA
#> 5 168 2 4 2 12 82.34694 1.2374146 1.2374146
#> 6 16 2 4 2 19 -69.65306 -1.0466657 -1.0466657
# using strings instead of literal expressions
new_efc <- data_modify(
efc,
"c12hour_c = center(c12hour)",
"c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE)",
"c12hour_z2 = standardize(c12hour)"
)
head(new_efc)
#> c12hour e16sex e42dep c172code neg_c_7 c12hour_c c12hour_z c12hour_z2
#> 1 16 2 3 2 12 -69.65306 -1.0466657 -1.0466657
#> 2 148 2 3 2 20 62.34694 0.9368777 0.9368777
#> 3 70 2 3 1 11 -15.65306 -0.2352161 -0.2352161
#> 4 NA 2 <NA> 2 10 NA NA NA
#> 5 168 2 4 2 12 82.34694 1.2374146 1.2374146
#> 6 16 2 4 2 19 -69.65306 -1.0466657 -1.0466657
# using character strings, provided as variable
stand <- "c12hour_c / sd(c12hour, na.rm = TRUE)"
new_efc <- data_modify(
efc,
c12hour_c = center(c12hour),
c12hour_z = stand
)
head(new_efc)
#> c12hour e16sex e42dep c172code neg_c_7 c12hour_c c12hour_z
#> 1 16 2 3 2 12 -69.65306 -1.0466657
#> 2 148 2 3 2 20 62.34694 0.9368777
#> 3 70 2 3 1 11 -15.65306 -0.2352161
#> 4 NA 2 <NA> 2 10 NA NA
#> 5 168 2 4 2 12 82.34694 1.2374146
#> 6 16 2 4 2 19 -69.65306 -1.0466657
# providing expressions as character vector
new_exp <- c(
"c12hour_c = center(c12hour)",
"c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE)"
)
new_efc <- data_modify(efc, new_exp)
head(new_efc)
#> c12hour e16sex e42dep c172code neg_c_7 c12hour_c c12hour_z
#> 1 16 2 3 2 12 -69.65306 -1.0466657
#> 2 148 2 3 2 20 62.34694 0.9368777
#> 3 70 2 3 1 11 -15.65306 -0.2352161
#> 4 NA 2 <NA> 2 10 NA NA
#> 5 168 2 4 2 12 82.34694 1.2374146
#> 6 16 2 4 2 19 -69.65306 -1.0466657
# attributes - in this case, value and variable labels - are preserved
str(new_efc)
#> 'data.frame': 100 obs. of 7 variables:
#> $ c12hour : num 16 148 70 NA 168 16 161 110 28 40 ...
#> ..- attr(*, "label")= chr "average number of hours of care per week"
#> $ e16sex : num 2 2 2 2 2 2 1 2 2 2 ...
#> ..- attr(*, "label")= chr "elder's gender"
#> ..- attr(*, "labels")= Named num [1:2] 1 2
#> .. ..- attr(*, "names")= chr [1:2] "male" "female"
#> $ e42dep : Factor w/ 4 levels "1","2","3","4": 3 3 3 NA 4 4 4 4 4 4 ...
#> ..- attr(*, "labels")= Named num [1:4] 1 2 3 4
#> .. ..- attr(*, "names")= chr [1:4] "independent" "slightly dependent" "moderately dependent" "severely dependent"
#> ..- attr(*, "label")= chr "elder's dependency"
#> $ c172code : num 2 2 1 2 2 2 2 2 NA 2 ...
#> ..- attr(*, "label")= chr "carer's level of education"
#> ..- attr(*, "labels")= Named num [1:3] 1 2 3
#> .. ..- attr(*, "names")= chr [1:3] "low level of education" "intermediate level of education" "high level of education"
#> $ neg_c_7 : num 12 20 11 10 12 19 15 11 15 10 ...
#> ..- attr(*, "label")= chr "Negative impact with 7 items"
#> $ c12hour_c: 'dw_transformer' num -69.7 62.3 -15.7 NA 82.3 ...
#> ..- attr(*, "center")= num 85.7
#> ..- attr(*, "scale")= num 1
#> ..- attr(*, "robust")= logi FALSE
#> ..- attr(*, "label")= chr "average number of hours of care per week"
#> $ c12hour_z: 'dw_transformer' num -1.047 0.937 -0.235 NA 1.237 ...
#> ..- attr(*, "center")= num 85.7
#> ..- attr(*, "scale")= num 1
#> ..- attr(*, "robust")= logi FALSE
#> ..- attr(*, "label")= chr "average number of hours of care per week"
# overwrite existing variable, remove old variable
out <- data_modify(iris, Petal.Length = 1 / Sepal.Length, Sepal.Length = NULL)
head(out)
#> Sepal.Width Petal.Length Petal.Width Species
#> 1 3.5 0.1960784 0.2 setosa
#> 2 3.0 0.2040816 0.2 setosa
#> 3 3.2 0.2127660 0.2 setosa
#> 4 3.1 0.2173913 0.2 setosa
#> 5 3.6 0.2000000 0.2 setosa
#> 6 3.9 0.1851852 0.4 setosa
# works on grouped data
grouped_efc <- data_group(efc, "c172code")
new_efc <- data_modify(
grouped_efc,
c12hour_c = center(c12hour),
c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE),
c12hour_z2 = standardize(c12hour)
)
head(new_efc)
#> # A tibble: 6 × 8
#> # Groups: c172code [2]
#> c12hour e16sex e42dep c172code neg_c_7 c12hour_c c12hour_z c12hour_z2
#> <dbl> <dbl> <fct> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 16 2 3 2 12 -78.0 -1.16 -1.16
#> 2 148 2 3 2 20 54.0 0.804 0.804
#> 3 70 2 3 1 11 -17.1 -0.250 -0.250
#> 4 NA 2 NA 2 10 NA NA NA
#> 5 168 2 4 2 12 74.0 1.10 1.10
#> 6 16 2 4 2 19 -78.0 -1.16 -1.16
# works from inside functions
foo <- function(data, z) {
head(data_modify(data, z))
}
foo(iris, "var_a = Sepal.Width / 10")
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species var_a
#> 1 5.1 3.5 1.4 0.2 setosa 0.35
#> 2 4.9 3.0 1.4 0.2 setosa 0.30
#> 3 4.7 3.2 1.3 0.2 setosa 0.32
#> 4 4.6 3.1 1.5 0.2 setosa 0.31
#> 5 5.0 3.6 1.4 0.2 setosa 0.36
#> 6 5.4 3.9 1.7 0.4 setosa 0.39
new_exp <- c("SW_double = 2 * Sepal.Width", "SW_fraction = SW_double / 10")
foo(iris, new_exp)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species SW_double
#> 1 5.1 3.5 1.4 0.2 setosa 7.0
#> 2 4.9 3.0 1.4 0.2 setosa 6.0
#> 3 4.7 3.2 1.3 0.2 setosa 6.4
#> 4 4.6 3.1 1.5 0.2 setosa 6.2
#> 5 5.0 3.6 1.4 0.2 setosa 7.2
#> 6 5.4 3.9 1.7 0.4 setosa 7.8
#> SW_fraction
#> 1 0.70
#> 2 0.60
#> 3 0.64
#> 4 0.62
#> 5 0.72
#> 6 0.78
# modify at specific positions or if condition is met
d <- iris[1:5, ]
data_modify(d, .at = "Species", .modify = as.numeric)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#> 1 5.1 3.5 1.4 0.2 1
#> 2 4.9 3.0 1.4 0.2 1
#> 3 4.7 3.2 1.3 0.2 1
#> 4 4.6 3.1 1.5 0.2 1
#> 5 5.0 3.6 1.4 0.2 1
data_modify(d, .if = is.factor, .modify = as.numeric)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species
#> 1 5.1 3.5 1.4 0.2 1
#> 2 4.9 3.0 1.4 0.2 1
#> 3 4.7 3.2 1.3 0.2 1
#> 4 4.6 3.1 1.5 0.2 1
#> 5 5.0 3.6 1.4 0.2 1
# can be combined with dots
data_modify(d, new_length = Petal.Length * 2, .at = "Species", .modify = as.numeric)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species new_length
#> 1 5.1 3.5 1.4 0.2 1 2.8
#> 2 4.9 3.0 1.4 0.2 1 2.8
#> 3 4.7 3.2 1.3 0.2 1 2.6
#> 4 4.6 3.1 1.5 0.2 1 3.0
#> 5 5.0 3.6 1.4 0.2 1 2.8
# new variables used in `.at` or `.if`
data_modify(
d,
new_length = Petal.Length * 2,
.at = c("Petal.Length", "new_length"),
.modify = round
)
#> Sepal.Length Sepal.Width Petal.Length Petal.Width Species new_length
#> 1 5.1 3.5 1 0.2 setosa 3
#> 2 4.9 3.0 1 0.2 setosa 3
#> 3 4.7 3.2 1 0.2 setosa 3
#> 4 4.6 3.1 2 0.2 setosa 3
#> 5 5.0 3.6 1 0.2 setosa 3
# combine "data_find()" and ".at" argument
out <- data_modify(
d,
.at = data_find(d, select = starts_with("Sepal")),
.modify = as.factor
)
# "Sepal.Length" and "Sepal.Width" are now factors
str(out)
#> 'data.frame': 5 obs. of 5 variables:
#> $ Sepal.Length: Factor w/ 5 levels "4.6","4.7","4.9",..: 5 3 2 1 4
#> $ Sepal.Width : Factor w/ 5 levels "3","3.1","3.2",..: 4 1 3 2 5
#> $ Petal.Length: num 1.4 1.4 1.3 1.5 1.4
#> $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2
#> $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1