maditr: Pipe-Style Interface for 'data.table'

Source: R/maditr.R

Package provides pipe-style interface for data.table. It preserves all data.table features without significant impact on performance. 'let' and 'take' functions are simplified interfaces for most common data manipulation tasks.

  • To select rows from data: take_if(mtcars, am==0)

  • To select columns from data: take(mtcars, am, vs, mpg)

  • To aggregate data: take(mtcars, mean_mpg = mean(mpg), by = am)

  • To aggregate all non-grouping columns: take(mtcars, fun = mean, by = am)

  • To aggregate several columns with one summary: take(mtcars, mpg, hp, fun = mean, by = am)

  • To get total summary skip 'by' argument: take(mtcars, fun = mean)

  • Use magrittr pipe '%>%' to chain several operations: 

         mtcars %>%
        let(mpg_hp = mpg/hp) %>%
        take(mean(mpg_hp), by = am)

  • To modify variables or add new variables: 

          mtcars %>%
         let(new_var = 42,
             new_var2 = new_var*hp) %>%
          head()

  • To drop variable assign NULL: let(mtcars, am = NULL) %>% head()

  • For parametric assignment use ':=': 

         new_var = "my_var"
     old_var = "mpg"
     mtcars %>%
         let((new_var) := get(old_var)*2) %>%
         head()

  • For more sophisticated operations see 'query'/'query_if': these functions translates its arguments one-to-one to '[.data.table' method. Additionally there are some conveniences such as automatic 'data.frame' conversion to 'data.table'.

Examples

# examples form 'dplyr' package
data(mtcars)

# Newly created variables are available immediately
mtcars %>%
    let(
        cyl2 = cyl * 2,
        cyl4 = cyl2 * 2
    ) %>% head()
#>     mpg cyl disp  hp drat    wt  qsec vs am gear carb cyl2 cyl4
#> 1: 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4   12   24
#> 2: 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4   12   24
#> 3: 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1    8   16
#> 4: 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1   12   24
#> 5: 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2   16   32
#> 6: 18.1   6  225 105 2.76 3.460 20.22  1  0    3    1   12   24

# You can also use let() to remove variables and
# modify existing variables
mtcars %>%
    let(
        mpg = NULL,
        disp = disp * 0.0163871 # convert to litres
    ) %>% head()
#>    cyl     disp  hp drat    wt  qsec vs am gear carb
#> 1:   6 2.621936 110 3.90 2.620 16.46  0  1    4    4
#> 2:   6 2.621936 110 3.90 2.875 17.02  0  1    4    4
#> 3:   4 1.769807  93 3.85 2.320 18.61  1  1    4    1
#> 4:   6 4.227872 110 3.08 3.215 19.44  1  0    3    1
#> 5:   8 5.899356 175 3.15 3.440 17.02  0  0    3    2
#> 6:   6 3.687098 105 2.76 3.460 20.22  1  0    3    1


# window functions are useful for grouped computations
mtcars %>%
    let(rank = rank(-mpg, ties.method = "min"),
        by = cyl) %>%
    head()
#>     mpg cyl disp  hp drat    wt  qsec vs am gear carb rank
#> 1: 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4    2
#> 2: 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4    2
#> 3: 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1    8
#> 4: 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1    1
#> 5: 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2    2
#> 6: 18.1   6  225 105 2.76 3.460 20.22  1  0    3    1    6

# You can drop variables by setting them to NULL
mtcars %>%
    let(cyl = NULL) %>%
    head()
#>     mpg disp  hp drat    wt  qsec vs am gear carb
#> 1: 21.0  160 110 3.90 2.620 16.46  0  1    4    4
#> 2: 21.0  160 110 3.90 2.875 17.02  0  1    4    4
#> 3: 22.8  108  93 3.85 2.320 18.61  1  1    4    1
#> 4: 21.4  258 110 3.08 3.215 19.44  1  0    3    1
#> 5: 18.7  360 175 3.15 3.440 17.02  0  0    3    2
#> 6: 18.1  225 105 2.76 3.460 20.22  1  0    3    1

# keeps all existing variables
mtcars %>%
    let(displ_l = disp / 61.0237) %>%
    head()
#>     mpg cyl disp  hp drat    wt  qsec vs am gear carb  displ_l
#> 1: 21.0   6  160 110 3.90 2.620 16.46  0  1    4    4 2.621932
#> 2: 21.0   6  160 110 3.90 2.875 17.02  0  1    4    4 2.621932
#> 3: 22.8   4  108  93 3.85 2.320 18.61  1  1    4    1 1.769804
#> 4: 21.4   6  258 110 3.08 3.215 19.44  1  0    3    1 4.227866
#> 5: 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2 5.899347
#> 6: 18.1   6  225 105 2.76 3.460 20.22  1  0    3    1 3.687092

# keeps only the variables you create
mtcars %>%
    take(displ_l = disp / 61.0237)
#>      displ_l
#>  1: 2.621932
#>  2: 2.621932
#>  3: 1.769804
#>  4: 4.227866
#>  5: 5.899347
#>  6: 3.687092
#>  7: 5.899347
#>  8: 2.403984
#>  9: 2.307300
#> 10: 2.746474
#> 11: 2.746474
#> 12: 4.519556
#> 13: 4.519556
#> 14: 4.519556
#> 15: 7.734700
#> 16: 7.538055
#> 17: 7.210313
#> 18: 1.289663
#> 19: 1.240502
#> 20: 1.165121
#> 21: 1.968088
#> 22: 5.211090
#> 23: 4.981671
#> 24: 5.735477
#> 25: 6.554830
#> 26: 1.294579
#> 27: 1.971365
#> 28: 1.558411
#> 29: 5.751864
#> 30: 2.376126
#> 31: 4.932510
#> 32: 1.982836
#>      displ_l


# can refer to both contextual variables and variable names:
var = 100
mtcars %>%
    let(cyl = cyl * var) %>%
    head()
#> Error in cyl * var: non-numeric argument to binary operator

# filter by condition
mtcars %>%
    take_if(am==0)
#>      mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#>  1: 21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
#>  2: 18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
#>  3: 18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
#>  4: 14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
#>  5: 24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
#>  6: 22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
#>  7: 19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
#>  8: 17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
#>  9: 16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
#> 10: 17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
#> 11: 15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
#> 12: 10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
#> 13: 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
#> 14: 14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
#> 15: 21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
#> 16: 15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
#> 17: 15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
#> 18: 13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
#> 19: 19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2

# filter by compound condition
mtcars %>%
    take_if(am==0 & mpg>mean(mpg))
#>     mpg cyl  disp  hp drat    wt  qsec vs am gear carb
#> 1: 21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    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: 21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1


# A 'take' with summary functions applied without 'by' argument returns an aggregated data
mtcars %>%
    take(mean = mean(disp), n = .N)
#>        mean  n
#> 1: 230.7219 32

# Usually, you'll want to group first
mtcars %>%
    take(mean = mean(disp), n = .N, by = am)
#>    am     mean  n
#> 1:  1 143.5308 13
#> 2:  0 290.3789 19

# grouping by multiple variables
mtcars %>%
    take(mean = mean(disp), n = .N, by = list(am, vs))
#>    am vs     mean  n
#> 1:  1  0 206.2167  6
#> 2:  1  1  89.8000  7
#> 3:  0  1 175.1143  7
#> 4:  0  0 357.6167 12

# parametric evaluation:
var = quote(mean(cyl))
take(mtcars, eval(var))
#>    eval(var)
#> 1:    6.1875


# You can group by expressions:
mtcars %>%
    take(
        fun = mean,
        by = list(vsam = vs + am)
    )
#>    vsam      mpg      cyl     disp        hp     drat       wt     qsec
#> 1:    1 20.28462 5.692308 189.4692 138.46154 3.738462 3.038846 18.04231
#> 2:    2 28.37143 4.000000  89.8000  80.57143 4.148571 2.028286 18.70000
#> 3:    0 15.05000 8.000000 357.6167 194.16667 3.120833 4.104083 17.14250
#>        gear     carb
#> 1: 4.076923 3.307692
#> 2: 4.142857 1.428571
#> 3: 3.000000 3.083333