Skip to contents

Overview

Base R functions that provide a grammar of data manipulation similar to the functions found in the tidyverse. Think of it as the namespace of dplyr, but the internal code of plyr.

Installation

Browse the code at https://bitbucket.org/bklamer/bkdat.

devtools::install_bitbucket("bklamer/bkdat")

Examples

arrange() - ordering rows of a data frame

library(bkdat)
#> 
#> Attaching package: 'bkdat'
#> The following object is masked from 'package:stats':
#> 
#>     filter
arrange_(data = mtcars, x = "cyl")
#>     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#> 1  22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
#> 2  24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
#> 3  22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
#> 4  32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
#> 5  30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
#> 6  33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
#> 7  21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
#> 8  27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
#> 9  26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
#> 10 30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
#> 11 21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2
#> 12 21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
#> 13 21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
#> 14 21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
#> 15 18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
#> 16 19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
#> 17 17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
#> 18 19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
#> 19 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
#> 20 14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
#> 21 16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
#> 22 17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
#> 23 15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
#> 24 10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
#> 25 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
#> 26 14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
#> 27 15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
#> 28 15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
#> 29 13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
#> 30 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
#> 31 15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
#> 32 15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8

filter() - subsetting rows of a data frame

filter(.data = mtcars, cyl == 4)
#>                 mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#> Datsun 710     22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
#> Merc 240D      24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
#> Merc 230       22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
#> Fiat 128       32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
#> Honda Civic    30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
#> Toyota Corolla 33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
#> Toyota Corona  21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
#> Fiat X1-9      27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
#> Porsche 914-2  26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
#> Lotus Europa   30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
#> Volvo 142E     21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

select() - subsetting columns of a data frame

select(data = mtcars, x = c("mpg", "cyl"))
#>                      mpg cyl
#> Mazda RX4           21.0   6
#> Mazda RX4 Wag       21.0   6
#> Datsun 710          22.8   4
#> Hornet 4 Drive      21.4   6
#> Hornet Sportabout   18.7   8
#> Valiant             18.1   6
#> Duster 360          14.3   8
#> Merc 240D           24.4   4
#> Merc 230            22.8   4
#> Merc 280            19.2   6
#> Merc 280C           17.8   6
#> Merc 450SE          16.4   8
#> Merc 450SL          17.3   8
#> Merc 450SLC         15.2   8
#> Cadillac Fleetwood  10.4   8
#> Lincoln Continental 10.4   8
#> Chrysler Imperial   14.7   8
#> Fiat 128            32.4   4
#> Honda Civic         30.4   4
#> Toyota Corolla      33.9   4
#> Toyota Corona       21.5   4
#> Dodge Challenger    15.5   8
#> AMC Javelin         15.2   8
#> Camaro Z28          13.3   8
#> Pontiac Firebird    19.2   8
#> Fiat X1-9           27.3   4
#> Porsche 914-2       26.0   4
#> Lotus Europa        30.4   4
#> Ford Pantera L      15.8   8
#> Ferrari Dino        19.7   6
#> Maserati Bora       15.0   8
#> Volvo 142E          21.4   4

mutate() - adding new variables to a data frame

mutate(.data = mtcars, wt_pounds = wt*1000)
#>                      mpg cyl  disp  hp drat    wt  qsec vs am gear carb wt_pounds
#> Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4      2620
#> Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4      2875
#> Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1      2320
#> Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1      3215
#> Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2      3440
#> Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1      3460
#> Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4      3570
#> Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2      3190
#> Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2      3150
#> Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4      3440
#> Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4      3440
#> Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3      4070
#> Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3      3730
#> Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3      3780
#> Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4      5250
#> Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4      5424
#> Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4      5345
#> Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1      2200
#> Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2      1615
#> Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1      1835
#> Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1      2465
#> Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2      3520
#> AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2      3435
#> Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4      3840
#> Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2      3845
#> Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1      1935
#> Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2      2140
#> Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2      1513
#> Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4      3170
#> Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6      2770
#> Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8      3570
#> Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2      2780

summarise() - grouped summaries of a data frame

mtcars |>
  group_by(group_cols = "cyl") |>
  summarise(mean_hp = mean(hp))
#>   cyl   mean_hp
#> 1   4  82.63636
#> 2   6 122.28571
#> 3   8 209.21429

Functions

The following functions are implemented:

Tidyverse function bkdat function
tibble::add_column() add_column()
tibble::add_row() add_row()
dplyr::arrange() arrange()
NA as_df()
dplyr::bind_cols() bind_cols()
dplyr::bind_rows() bind_fill_rows()
dplyr::bind_rows() bind_rows()
dplyr::desc() desc()
dplyr::do() do()
dplyr::slice() & dplyr::filter() filter()
tidyr::gather() gather()
dplyr::group_by() group_by()
rlang::is_atomic() is_atomic()
NA is_date()
rlang::is_integer() is_integer()
rlang::is_string() is_string()
dplyr::full_join() join_full()
dplyr::inner_join() join_inner()
dplyr::left_join() join_left()
dplyr::right_join() join_right()
purrr::map() map()
purrr::map_chr() map_chr()
purrr::map_dbl() map_dbl()
purrr::map_df() map_df()
purrr::map_int() map_int()
dplyr::mutate() mutate()
dplyr::nest_by() nest_by()
dplyr::pull() pull()
dplyr::rename() rename()
tibble::remove_rownames() reset_row_names()
tibble::rownames_to_column() ronames_to_column()
dplyr::select() select()
tidyr::separate() separate()
tidyr::spread() spread()
dplyr::summarise() summarise()
tidyr::unite() unite()

Changes were made to unify the naming scheme and remove base R naming conflicts: