add_columns() combines two or more data frames, but unlike
cbind or dplyr::bind_cols(), this function
binds data as last columns of a data frame (i.e., behind columns
specified in ...). This can be useful in a "pipe"-workflow, where
a data frame returned by a previous function should be appended
at the end of another data frame that is processed in
add_colums().
replace_columns() replaces all columns in data with
identically named columns in ..., and adds remaining (non-duplicated)
columns from ... to data.
add_id() simply adds an ID-column to the data frame, with values
from 1 to nrow(data), respectively for grouped data frames, values
from 1 to group size. See 'Examples'.
add_columns(data, ..., replace = TRUE)
replace_columns(data, ..., add.unique = TRUE)
add_id(data, var = "ID")A data frame. For add_columns(), will be bound after data
frames specified in .... For replace_columns(), duplicated
columns in data will be replaced by columns in ....
More data frames to combine, resp. more data frames with columns
that should replace columns in data.
Logical, if TRUE (default), columns in ... with
identical names in data will replace the columns in data.
The order of columns after replacing is preserved.
Logical, if TRUE (default), remaining columns in
... that did not replace any column in data, are appended
as new columns to data.
Name of new the ID-variable.
For add_columns(), a data frame, where columns of data are appended after columns of ....
For replace_columns(), a data frame where columns in data will be replaced by identically named columns in ..., and remaining
columns from ... will be appended to data (if
add.unique = TRUE).
For add_id(), a new column with ID numbers. This column is always
the first column in the returned data frame.
For add_columns(), by default, columns in data with
identical names like columns in one of the data frames in ...
will be dropped (i.e. variables with identical names in ... will
replace existing variables in data). Use replace = FALSE to
keep all columns. Identical column names will then be renamed, to ensure
unique column names (which happens by default when using
dplyr::bind_cols()). When replacing columns, replaced columns
are not added to the end of the data frame. Rather, the original order of
columns will be preserved.
data(efc)
d1 <- efc[, 1:3]
d2 <- efc[, 4:6]
library(dplyr)
#>
#> Attaching package: ‘dplyr’
#> The following objects are masked from ‘package:stats’:
#>
#> filter, lag
#> The following objects are masked from ‘package:base’:
#>
#> intersect, setdiff, setequal, union
head(bind_cols(d1, d2))
#> c12hour e15relat e16sex e17age e42dep c82cop1
#> 1 16 2 2 83 3 3
#> 2 148 2 2 88 3 3
#> 3 70 1 2 82 3 2
#> 4 168 1 2 67 4 4
#> 5 168 2 2 84 4 3
#> 6 16 2 2 85 4 2
add_columns(d1, d2) %>% head()
#> e17age e42dep c82cop1 c12hour e15relat e16sex
#> 1 83 3 3 16 2 2
#> 2 88 3 3 148 2 2
#> 3 82 3 2 70 1 2
#> 4 67 4 4 168 1 2
#> 5 84 4 3 168 2 2
#> 6 85 4 2 16 2 2
d1 <- efc[, 1:3]
d2 <- efc[, 2:6]
add_columns(d1, d2, replace = TRUE) %>% head()
#> c12hour e15relat e17age e42dep c82cop1 e16sex
#> 1 16 2 83 3 3 2
#> 2 148 2 88 3 3 2
#> 3 70 1 82 3 2 2
#> 4 168 1 67 4 4 2
#> 5 168 2 84 4 3 2
#> 6 16 2 85 4 2 2
add_columns(d1, d2, replace = FALSE) %>% head()
#> New names:
#> • `e15relat` -> `e15relat...1`
#> • `e16sex` -> `e16sex...2`
#> • `e15relat` -> `e15relat...7`
#> • `e16sex` -> `e16sex...8`
#> e15relat...1 e16sex...2 e17age e42dep c82cop1 c12hour e15relat...7 e16sex...8
#> 1 2 2 83 3 3 16 2 2
#> 2 2 2 88 3 3 148 2 2
#> 3 1 2 82 3 2 70 1 2
#> 4 1 2 67 4 4 168 1 2
#> 5 2 2 84 4 3 168 2 2
#> 6 2 2 85 4 2 16 2 2
# use case: we take the original data frame, select specific
# variables and do some transformations or recodings
# (standardization in this example) and add the new, transformed
# variables *to the end* of the original data frame
efc %>%
select(e17age, c160age) %>%
std() %>%
add_columns(efc) %>%
head()
#> c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3 c85cop4 c86cop5
#> 1 16 2 2 83 3 3 2 2 2 1
#> 2 148 2 2 88 3 3 3 3 3 4
#> 3 70 1 2 82 3 2 2 1 4 1
#> 4 168 1 2 67 4 4 1 3 1 1
#> 5 168 2 2 84 4 3 2 1 2 2
#> 6 16 2 2 85 4 2 2 3 3 3
#> c87cop6 c88cop7 c89cop8 c90cop9 c160age c161sex c172code c175empl barthtot
#> 1 1 2 3 3 56 2 2 1 75
#> 2 1 3 2 2 54 2 2 1 75
#> 3 1 1 4 3 80 1 1 0 35
#> 4 1 1 2 4 69 1 2 0 0
#> 5 2 1 4 4 47 2 2 0 25
#> 6 2 2 1 1 56 1 2 1 60
#> neg_c_7 pos_v_4 quol_5 resttotn tot_sc_e n4pstu nur_pst e17age_z
#> 1 12 12 14 0 4 0 NA 0.4791992
#> 2 20 11 10 4 0 0 NA 1.0969170
#> 3 11 13 7 0 1 2 2 0.3556557
#> 4 10 15 12 2 0 3 3 -1.4974976
#> 5 12 15 19 2 1 2 2 0.6027428
#> 6 19 9 8 1 3 2 2 0.7262864
#> c160age_z
#> 1 0.19002509
#> 2 0.04023278
#> 3 1.98753275
#> 4 1.16367507
#> 5 -0.48404028
#> 6 0.19002509
# new variables with same name will overwrite old variables
# in "efc". order of columns is not changed.
efc %>%
select(e16sex, e42dep) %>%
to_factor() %>%
add_columns(efc) %>%
head()
#> c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3 c85cop4 c86cop5
#> 1 16 2 2 83 3 3 2 2 2 1
#> 2 148 2 2 88 3 3 3 3 3 4
#> 3 70 1 2 82 3 2 2 1 4 1
#> 4 168 1 2 67 4 4 1 3 1 1
#> 5 168 2 2 84 4 3 2 1 2 2
#> 6 16 2 2 85 4 2 2 3 3 3
#> c87cop6 c88cop7 c89cop8 c90cop9 c160age c161sex c172code c175empl barthtot
#> 1 1 2 3 3 56 2 2 1 75
#> 2 1 3 2 2 54 2 2 1 75
#> 3 1 1 4 3 80 1 1 0 35
#> 4 1 1 2 4 69 1 2 0 0
#> 5 2 1 4 4 47 2 2 0 25
#> 6 2 2 1 1 56 1 2 1 60
#> neg_c_7 pos_v_4 quol_5 resttotn tot_sc_e n4pstu nur_pst
#> 1 12 12 14 0 4 0 NA
#> 2 20 11 10 4 0 0 NA
#> 3 11 13 7 0 1 2 2
#> 4 10 15 12 2 0 3 3
#> 5 12 15 19 2 1 2 2
#> 6 19 9 8 1 3 2 2
# keep both old and new variables, automatically
# rename variables with identical name
efc %>%
select(e16sex, e42dep) %>%
to_factor() %>%
add_columns(efc, replace = FALSE) %>%
head()
#> New names:
#> • `e16sex` -> `e16sex...3`
#> • `e42dep` -> `e42dep...5`
#> • `e16sex` -> `e16sex...27`
#> • `e42dep` -> `e42dep...28`
#> c12hour e15relat e16sex...3 e17age e42dep...5 c82cop1 c83cop2 c84cop3 c85cop4
#> 1 16 2 2 83 3 3 2 2 2
#> 2 148 2 2 88 3 3 3 3 3
#> 3 70 1 2 82 3 2 2 1 4
#> 4 168 1 2 67 4 4 1 3 1
#> 5 168 2 2 84 4 3 2 1 2
#> 6 16 2 2 85 4 2 2 3 3
#> c86cop5 c87cop6 c88cop7 c89cop8 c90cop9 c160age c161sex c172code c175empl
#> 1 1 1 2 3 3 56 2 2 1
#> 2 4 1 3 2 2 54 2 2 1
#> 3 1 1 1 4 3 80 1 1 0
#> 4 1 1 1 2 4 69 1 2 0
#> 5 2 2 1 4 4 47 2 2 0
#> 6 3 2 2 1 1 56 1 2 1
#> barthtot neg_c_7 pos_v_4 quol_5 resttotn tot_sc_e n4pstu nur_pst e16sex...27
#> 1 75 12 12 14 0 4 0 NA 2
#> 2 75 20 11 10 4 0 0 NA 2
#> 3 35 11 13 7 0 1 2 2 2
#> 4 0 10 15 12 2 0 3 3 2
#> 5 25 12 15 19 2 1 2 2 2
#> 6 60 19 9 8 1 3 2 2 2
#> e42dep...28
#> 1 3
#> 2 3
#> 3 3
#> 4 4
#> 5 4
#> 6 4
# create sample data frames
d1 <- efc[, 1:10]
d2 <- efc[, 2:3]
d3 <- efc[, 7:8]
d4 <- efc[, 10:12]
# show original
head(d1)
#> c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3 c85cop4 c86cop5
#> 1 16 2 2 83 3 3 2 2 2 1
#> 2 148 2 2 88 3 3 3 3 3 4
#> 3 70 1 2 82 3 2 2 1 4 1
#> 4 168 1 2 67 4 4 1 3 1 1
#> 5 168 2 2 84 4 3 2 1 2 2
#> 6 16 2 2 85 4 2 2 3 3 3
library(sjlabelled)
#>
#> Attaching package: ‘sjlabelled’
#> The following object is masked from ‘package:dplyr’:
#>
#> as_label
# slightly change variables, to see effect
d2 <- as_label(d2)
d3 <- as_label(d3)
# replace duplicated columns, append remaining
replace_columns(d1, d2, d3, d4) %>% head()
#> c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3
#> 1 16 child female 83 3 3 Sometimes Sometimes
#> 2 148 child female 88 3 3 Often Often
#> 3 70 spouse/partner female 82 3 2 Sometimes Never
#> 4 168 spouse/partner female 67 4 4 Never Often
#> 5 168 child female 84 4 3 Sometimes Never
#> 6 16 child female 85 4 2 Sometimes Often
#> c85cop4 c86cop5 c87cop6 c88cop7
#> 1 2 1 1 2
#> 2 3 4 1 3
#> 3 4 1 1 1
#> 4 1 1 1 1
#> 5 2 2 2 1
#> 6 3 3 2 2
# replace duplicated columns, omit remaining
replace_columns(d1, d2, d3, d4, add.unique = FALSE) %>% head()
#> c12hour e15relat e16sex e17age e42dep c82cop1 c83cop2 c84cop3
#> 1 16 child female 83 3 3 Sometimes Sometimes
#> 2 148 child female 88 3 3 Often Often
#> 3 70 spouse/partner female 82 3 2 Sometimes Never
#> 4 168 spouse/partner female 67 4 4 Never Often
#> 5 168 child female 84 4 3 Sometimes Never
#> 6 16 child female 85 4 2 Sometimes Often
#> c85cop4 c86cop5
#> 1 2 1
#> 2 3 4
#> 3 4 1
#> 4 1 1
#> 5 2 2
#> 6 3 3
# add ID to dataset
library(dplyr)
data(mtcars)
add_id(mtcars)
#> ID mpg cyl disp hp drat wt qsec vs am gear carb
#> Mazda RX4 1 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
#> Mazda RX4 Wag 2 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
#> Datsun 710 3 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
#> Hornet 4 Drive 4 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
#> Hornet Sportabout 5 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
#> Valiant 6 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
#> Duster 360 7 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
#> Merc 240D 8 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
#> Merc 230 9 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
#> Merc 280 10 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
#> Merc 280C 11 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
#> Merc 450SE 12 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
#> Merc 450SL 13 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
#> Merc 450SLC 14 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
#> Cadillac Fleetwood 15 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
#> Lincoln Continental 16 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
#> Chrysler Imperial 17 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
#> Fiat 128 18 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
#> Honda Civic 19 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
#> Toyota Corolla 20 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
#> Toyota Corona 21 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
#> Dodge Challenger 22 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
#> AMC Javelin 23 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
#> Camaro Z28 24 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
#> Pontiac Firebird 25 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
#> Fiat X1-9 26 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
#> Porsche 914-2 27 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
#> Lotus Europa 28 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
#> Ford Pantera L 29 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
#> Ferrari Dino 30 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
#> Maserati Bora 31 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
#> Volvo 142E 32 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2
mtcars %>%
group_by(gear) %>%
add_id() %>%
arrange(gear, ID) %>%
print(n = 100)
#> # A tibble: 32 × 12
#> ID mpg cyl disp hp drat wt qsec vs am gear carb
#> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 21.4 6 258 110 3.08 3.22 19.4 1 0 3 1
#> 2 2 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2
#> 3 3 18.1 6 225 105 2.76 3.46 20.2 1 0 3 1
#> 4 4 14.3 8 360 245 3.21 3.57 15.8 0 0 3 4
#> 5 5 16.4 8 276. 180 3.07 4.07 17.4 0 0 3 3
#> 6 6 17.3 8 276. 180 3.07 3.73 17.6 0 0 3 3
#> 7 7 15.2 8 276. 180 3.07 3.78 18 0 0 3 3
#> 8 8 10.4 8 472 205 2.93 5.25 18.0 0 0 3 4
#> 9 9 10.4 8 460 215 3 5.42 17.8 0 0 3 4
#> 10 10 14.7 8 440 230 3.23 5.34 17.4 0 0 3 4
#> 11 11 21.5 4 120. 97 3.7 2.46 20.0 1 0 3 1
#> 12 12 15.5 8 318 150 2.76 3.52 16.9 0 0 3 2
#> 13 13 15.2 8 304 150 3.15 3.44 17.3 0 0 3 2
#> 14 14 13.3 8 350 245 3.73 3.84 15.4 0 0 3 4
#> 15 15 19.2 8 400 175 3.08 3.84 17.0 0 0 3 2
#> 16 1 21 6 160 110 3.9 2.62 16.5 0 1 4 4
#> 17 2 21 6 160 110 3.9 2.88 17.0 0 1 4 4
#> 18 3 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1
#> 19 4 24.4 4 147. 62 3.69 3.19 20 1 0 4 2
#> 20 5 22.8 4 141. 95 3.92 3.15 22.9 1 0 4 2
#> 21 6 19.2 6 168. 123 3.92 3.44 18.3 1 0 4 4
#> 22 7 17.8 6 168. 123 3.92 3.44 18.9 1 0 4 4
#> 23 8 32.4 4 78.7 66 4.08 2.2 19.5 1 1 4 1
#> 24 9 30.4 4 75.7 52 4.93 1.62 18.5 1 1 4 2
#> 25 10 33.9 4 71.1 65 4.22 1.84 19.9 1 1 4 1
#> 26 11 27.3 4 79 66 4.08 1.94 18.9 1 1 4 1
#> 27 12 21.4 4 121 109 4.11 2.78 18.6 1 1 4 2
#> 28 1 26 4 120. 91 4.43 2.14 16.7 0 1 5 2
#> 29 2 30.4 4 95.1 113 3.77 1.51 16.9 1 1 5 2
#> 30 3 15.8 8 351 264 4.22 3.17 14.5 0 1 5 4
#> 31 4 19.7 6 145 175 3.62 2.77 15.5 0 1 5 6
#> 32 5 15 8 301 335 3.54 3.57 14.6 0 1 5 8