Syntax

All operators have the same form composed of two distinct parts: %<operation><type>%.

• [operation] specifies the performed functionality and can be one of in, out, [in, [out.
• [type] specifies the type of operation and can be one of {}, [], (), [), (], ~, ~p, ~f, #.

Value Types

1. sets

 %in{}%
%out{}%

Work with the same values as %in% does but provide a more consistent behaviour for data.frames and NA values.

letters <- letters[1:10]
letters
#>  [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j"

# sets

letters %in{}% c("a", "b", "c", "e")
#>  [1]  TRUE  TRUE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE

letters %out{}% c("a", "b", "c", "e")
#>  [1] FALSE FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE

2. ranges

 %in()%   %in[]%   %in[)%   %in(]%
%out()%  %out[]%  %out[)%  %out(]%

1:10
#>  [1]  1  2  3  4  5  6  7  8  9 10

# closed interval

1:10 %in()% c(3,6)
#>  [1] FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE

1:10 %out()% c(3,6)
#>  [1]  TRUE  TRUE  TRUE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE

# open interval

1:10 %in[]% c(3,6)
#>  [1] FALSE FALSE  TRUE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE

1:10 %out[]% c(3,6)
#>  [1]  TRUE  TRUE FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE

# open on the right

1:10 %in(]% c(3,6)
#>  [1] FALSE FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE

1:10 %out(]% c(3,6)
#>  [1]  TRUE  TRUE  TRUE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE

# open on the left

1:10 %in[)% c(3,6)
#>  [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE

1:10 %out[)% c(3,6)
#>  [1]  TRUE  TRUE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE

3. patterns

 %in~%   %in~f%   %in~p%
%out~%  %out~f%  %out~p%

month.name
#>  [1] "January"   "February"  "March"     "April"     "May"      
#>  [6] "June"      "July"      "August"    "September" "October"  
#> [11] "November"  "December"

# regular expressions

month.name %in~% "^M.*"
#>  [1] FALSE FALSE  TRUE FALSE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE
#> [12] FALSE

month.name %out~% "^M.*"
#>  [1]  TRUE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE
#> [12]  TRUE

# fixed string regular expressions

month.name %in~f% "^M.*"
#>  [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
#> [12] FALSE

month.name %out~f% "^M.*"
#>  [1]  TRUE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE
#> [12]  TRUE

# perl regular expressions

month.name %in~p% "^(?=.*r)(?!.*er)"
#>  [1]  TRUE  TRUE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
#> [12] FALSE

month.name %out~p% "^(?=.*r)(?!.*er)"
#>  [1] FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE
#> [12]  TRUE

4. counts

 %in#%
%out#%

values <- c("a", "a", "b", "b", "b", "c")
values
#> [1] "a" "a" "b" "b" "b" "c"

# number of occurances

values %in#% 1:2
#> [1]  TRUE  TRUE FALSE FALSE FALSE  TRUE

values %out#% 1:2
#> [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE

Operations

1. detection

Same form as examples shown above.

month.name
#>  [1] "January"   "February"  "March"     "April"     "May"      
#>  [6] "June"      "July"      "August"    "September" "October"  
#> [11] "November"  "December"

month.name %in~% c("^A", "^M")
#>  [1] FALSE FALSE  TRUE  TRUE  TRUE FALSE FALSE  TRUE FALSE FALSE FALSE
#> [12] FALSE

2. subsetting

Used for obtaining actual values.
Starts with [.

month.name
#>  [1] "January"   "February"  "March"     "April"     "May"      
#>  [6] "June"      "July"      "August"    "September" "October"  
#> [11] "November"  "December"

month.name %[in~% c("^A", "^M")
#> [1] "March"  "April"  "May"    "August"

3. replacement

Used for replacing the matched elements with new values.
Called with assignment <- at the end.

month.name
#>  [1] "January"   "February"  "March"     "April"     "May"      
#>  [6] "June"      "July"      "August"    "September" "October"  
#> [11] "November"  "December"

month.name %in~% c("^A", "^M") <- "A or M"

month.name
#>  [1] "January"   "February"  "A or M"    "A or M"    "A or M"   
#>  [6] "June"      "July"      "A or M"    "September" "October"  
#> [11] "November"  "December"

Behaviour

The operators implemented here try to be consistent with the default comparison operators like == and <.
Therefore in some scenarios their behaviour differs from %in%.
For instance:

1. %in{}% can be used on on data frames.

df1 <- data.frame(a = 1:3, b = 2:4, c=letters[1:3])

df1 == 2
#>          a     b     c
#> [1,] FALSE  TRUE FALSE
#> [2,]  TRUE FALSE FALSE
#> [3,] FALSE FALSE FALSE

df1 %in% 2
#> [1] FALSE FALSE FALSE

df1 %in{}% 2
#>          a     b     c
#> [1,] FALSE  TRUE FALSE
#> [2,]  TRUE FALSE FALSE
#> [3,] FALSE FALSE FALSE

df1 %in{}% 2:3
#>          a     b     c
#> [1,] FALSE  TRUE FALSE
#> [2,]  TRUE  TRUE FALSE
#> [3,]  TRUE FALSE FALSE

2. missing values are not considered as not matching.

NA == 1
#> [1] NA

NA %in% 1
#> [1] FALSE

NA %in{}% 1
#> [1] NA

NA %in% NA
#> [1] TRUE

NA %in{}% NA
#> [1] NA

c(1, NA, 3) %in{}% 1:10
#> [1] TRUE   NA TRUE

Additional Examples

Simple examples for illustration.

Selecting flight records from the flights dataset that:

1. Departed and Landed between noon and 5 p.m.
2. Were not traveling to “LEX”, “PSP”, nor “HDN”
3. Travelled distance was either very short (below 100) or very long (above 3000)
4. Had a tail number starting with “N1” or “N3”

library(nycflights13)
library(dplyr)
library(inops)

flights <- select(flights, origin, dest, tailnum, dep_time, arr_time, distance)
flights
#> # A tibble: 336,776 x 6
#>    origin dest  tailnum dep_time arr_time distance
#>    <chr>  <chr> <chr>      <int>    <int>    <dbl>
#>  1 EWR    IAH   N14228       517      830     1400
#>  2 LGA    IAH   N24211       533      850     1416
#>  3 JFK    MIA   N619AA       542      923     1089
#>  4 JFK    BQN   N804JB       544     1004     1576
#>  5 LGA    ATL   N668DN       554      812      762
#>  6 EWR    ORD   N39463       554      740      719
#>  7 EWR    FLL   N516JB       555      913     1065
#>  8 LGA    IAD   N829AS       557      709      229
#>  9 JFK    MCO   N593JB       557      838      944
#> 10 LGA    ORD   N3ALAA       558      753      733
#> # ... with 336,766 more rows

filter(flights,
       dep_time %in()%  c(1200, 1700),
       arr_time %in()%  c(1200, 1700),
       dest     %out%   c("LEX", "PSP", "HDN"),
       distance %out[]% c(100, 3000),
       tailnum  %in~%   c("^N1", "^N3")
       )
#> # A tibble: 2 x 6
#>   origin dest  tailnum dep_time arr_time distance
#>   <chr>  <chr> <chr>      <int>    <int>    <dbl>
#> 1 EWR    PHL   N14972      1240     1333       80
#> 2 JFK    HNL   N391HA      1214     1645     4983

Cleaning up planes dataset in order to:

1. Standardize names of “AIRBUS”, “CANADAIR” and “MCDONNELL” manufacturers.
2. Obtain plane counts for each of the 3 manufacturers mentioned above.

library(nycflights13)
library(inops)

table(planes$manufacturer %[in~% c("AIRBUS", "CANADAIR", "MCDONNELL"))
#> 
#>                        AIRBUS              AIRBUS INDUSTRIE 
#>                           336                           400 
#>                      CANADAIR                  CANADAIR LTD 
#>                             9                             1 
#>             MCDONNELL DOUGLAS MCDONNELL DOUGLAS AIRCRAFT CO 
#>                           120                           103 
#> MCDONNELL DOUGLAS CORPORATION 
#>                            14

planes$manufacturer %in~% "AIRBUS"    <- "AIRBUS"
planes$manufacturer %in~% "CANADAIR"  <- "CANADAIR"
planes$manufacturer %in~% "MCDONNELL" <- "MCDONNELL"

table(planes$manufacturer %[in~% c("AIRBUS", "CANADAIR", "MCDONNELL"))
#> 
#>    AIRBUS  CANADAIR MCDONNELL 
#>       736        10       237

Combine engine models that in the dataset occur less than 6 times under the “Other” group.

library(nycflights13)
library(inops)

table(planes$engine)
#> 
#>       4 Cycle Reciprocating     Turbo-fan     Turbo-jet    Turbo-prop 
#>             2            28          2750           535             2 
#>   Turbo-shaft 
#>             5

planes$engine %in#% 1:5 <- "Other"

table(planes$engine)
#> 
#>         Other Reciprocating     Turbo-fan     Turbo-jet 
#>             9            28          2750           535

Full List

Below is a full list of all the implemented operators along with their usage examples.

Notes

To give an assignment counterpart to < we had to overload the <<- operator, which explains the message when attaching the package. This doesn’t affect the behavior of the <<- assignments.