Useful R functions (preview)

← Vectors (introduction) Vectors (practicing) →

Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers

 [1] 462 264 331 595 219 153 796 675 710 912 440  26 367 940 426 554 373 239 576 420

manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA

 [1] 239 554 153 912 367 420 264 373 710 219  NA 595 940 576  NA 675 426 462  26 331 796  NA 440

duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers

 [1] 5 1 5 2 5 2 1 2 4 3

letters

 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"

LETTERS

 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"

mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters

 [1] "d" "g" "z" "t" "v" "J" "X" "S" "T" "C"

Are all/any elements TRUE

• Input: logical vector
• Output: single logical value
• Task: try, understand what happens when you use manyNumbersWithNA instead of manyNumbers.

all( manyNumbers <= 1000 )

[1] TRUE

all( manyNumbers <= 500 )

[1] FALSE

any( manyNumbers > 1000 )

[1] FALSE

any( manyNumbers > 500 )

[1] TRUE

all( !is.na( manyNumbers ) )

[1] TRUE

any( is.na( manyNumbers ) )

[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )

[1] 10 14

which( manyNumbersWithNA > 900 )

[1]  4 13

which( is.na( manyNumbersWithNA ) )

[1] 11 15 22

Filtering vector elements

• Input: any vector and filtering condition
• Output: elements of the input vector
• Note: several ways to get the same effect

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector

[1] 912 940

manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions

[1] 912 940

somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]

[1] 912 940

Are some elements among other elements

• Input: two vectors
• Output: a logical vector corresponding to the first input vector

"A" %in% LETTERS

[1] TRUE

c( "X", "Y", "Z" ) %in% LETTERS

[1] TRUE TRUE TRUE

all( c( "X", "Y", "Z" ) %in% LETTERS )

[1] TRUE

all( mixedLetters %in% LETTERS )

[1] FALSE

any( mixedLetters %in% LETTERS )

[1] TRUE

mixedLetters[ mixedLetters %in% LETTERS ]

[1] "J" "X" "S" "T" "C"

mixedLetters[ !( mixedLetters %in% LETTERS ) ]

[1] "d" "g" "z" "t" "v"

manyNumbers %in% 300:600

 [1]  TRUE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE  TRUE FALSE  TRUE  TRUE  TRUE FALSE  TRUE  TRUE

which( manyNumbers %in% 300:600 )

 [1]  1  3  4 11 13 15 16 17 19 20

sum( manyNumbers %in% 300:600 )

[1] 10

Pick one of two (three) depending on condition

• Input: a logical vector and two vectors additional vectors (for TRUE, for FALSE)
• Output: elements of the additional vectors
• Note: it can take care of NAs

if_else( manyNumbersWithNA >= 500, "large", "small" )

 [1] "small" "large" "small" "large" "small" "small" "small" "small" "large" "small" NA      "large" "large" "large" NA      "large" "small" "small" "small" "small"
[21] "large" NA      "small"

if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )

 [1] "small"   "large"   "small"   "large"   "small"   "small"   "small"   "small"   "large"   "small"   "UNKNOWN" "large"   "large"   "large"   "UNKNOWN" "large"  
[17] "small"   "small"   "small"   "small"   "large"   "UNKNOWN" "small"  

# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 

 [1]   0 554   0 912   0   0   0   0 710   0  NA 595 940 576  NA 675   0   0   0   0 796  NA   0

Duplicates and unique elements

• Input: a vector

unique( duplicatedNumbers )

[1] 5 1 2 4 3

unique( c( NA, duplicatedNumbers, NA ) )

[1] NA  5  1  2  4  3

duplicated( duplicatedNumbers )

 [1] FALSE FALSE  TRUE FALSE  TRUE  TRUE  TRUE  TRUE FALSE FALSE

Positions of max/min elements

which.max( manyNumbersWithNA )

[1] 13

manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]

[1] 940

which.min( manyNumbersWithNA )

[1] 19

manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]

[1] 26

range( manyNumbersWithNA, na.rm = TRUE )

[1]  26 940

Sorting/ordering of vectors

manyNumbersWithNA

 [1] 239 554 153 912 367 420 264 373 710 219  NA 595 940 576  NA 675 426 462  26 331 796  NA 440

sort( manyNumbersWithNA )

 [1]  26 153 219 239 264 331 367 373 420 426 440 462 554 576 595 675 710 796 912 940

sort( manyNumbersWithNA, na.last = TRUE )

 [1]  26 153 219 239 264 331 367 373 420 426 440 462 554 576 595 675 710 796 912 940  NA  NA  NA

sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )

 [1] 940 912 796 710 675 595 576 554 462 440 426 420 373 367 331 264 239 219 153  26  NA  NA  NA

manyNumbersWithNA[1:5]

[1] 239 554 153 912 367

order( manyNumbersWithNA[1:5] )

[1] 3 1 5 2 4

rank( manyNumbersWithNA[1:5] )

[1] 2 4 1 5 3

sort( mixedLetters )

 [1] "C" "d" "g" "J" "S" "t" "T" "v" "X" "z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )

 [1] 3.5 6.0 9.5 7.5 7.5 5.0 3.5 9.5 1.5 1.5

rank( manyDuplicates, ties.method = "min" )

 [1] 3 6 9 7 7 5 3 9 1 1

rank( manyDuplicates, ties.method = "random" )

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

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v

 [1] -1.0000000 -0.5000000  0.0000000  0.5000000  1.0000000 -2.0830695 -1.0206006 -1.0683954  0.6300673 -1.5662845  2.6260376 -0.5703566 -0.9490789 -1.1015691
[15] -0.5448783

round( v, 0 )

 [1] -1  0  0  0  1 -2 -1 -1  1 -2  3 -1 -1 -1 -1

round( v, 1 )

 [1] -1.0 -0.5  0.0  0.5  1.0 -2.1 -1.0 -1.1  0.6 -1.6  2.6 -0.6 -0.9 -1.1 -0.5

round( v, 2 )

 [1] -1.00 -0.50  0.00  0.50  1.00 -2.08 -1.02 -1.07  0.63 -1.57  2.63 -0.57 -0.95 -1.10 -0.54

floor( v )

 [1] -1 -1  0  0  1 -3 -2 -2  0 -2  2 -1 -1 -2 -1

ceiling( v )

 [1] -1  0  0  1  1 -2 -1 -1  1 -1  3  0  0 -1  0

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights

Amy Eve Bob 
166 170 177 

names( heights )

[1] "Amy" "Eve" "Bob"

names( heights ) <- c( "AMY", "EVE", "BOB" )
heights

AMY EVE BOB 
166 170 177 

heights[[ "EVE" ]]

[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )

# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )

     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  

combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )

     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  

← Vectors (introduction) Vectors (practicing) →

---

Copyright © 2024 Biomedical Data Sciences (BDS) | LUMC