Hash Table/Dictionary Lookup

Usage

lookup(terms, key.match, key.reassign = NULL, missing = NA)
"lookup"(terms, key.match, key.reassign = NULL, missing = NA)
"lookup"(terms, key.match, key.reassign = NULL, missing = NA)
"lookup"(terms, key.match, key.reassign = NULL, missing = NA)
"lookup"(terms, key.match, key.reassign, missing = NA)
"lookup"(terms, key.match, key.reassign, missing = NA)
"lookup"(terms, key.match, key.reassign, missing = NA)
terms %l% key.match
terms %l+% key.match
terms %lc% key.match
terms %lc+% key.match

Arguments

terms

A vector of terms to undergo a lookup.

key.match

Takes one of the following: (1) a two column data.frame of a match key and reassignment column, (2) a named list of vectors (Note: if data.frame or named list supplied no key reassign needed) or (3) a single vector match key.

key.reassign

A single reassignment vector supplied if key.match is not a two column data.frame/named list.

missing

Value to assign to terms not matching the key.match. If set to NULL the original values in terms corresponding to the missing elements are retained.

Examples

## Supply a dataframe to key.match

lookup(1:5, data.frame(1:4, 11:14))

[1] 11 12 13 14 NA


## Retain original values for missing
lookup(1:5, data.frame(1:4, 11:14), missing=NULL)

[1] 11 12 13 14  5


lookup(LETTERS[1:5], data.frame(LETTERS[1:5], 100:104))

[1] 100 101 102 103 104

lookup(LETTERS[1:5], factor(LETTERS[1:5]), 100:104)

[1] 100 101 102 103 104


## Supply a named list of vectors to key.match

codes <- list(
    A = c(1, 2, 4),
    B = c(3, 5),
    C = 7,
    D = c(6, 8:10)
)

lookup(1:10, codes)

 [1] "A" "A" "B" "A" "B" "D" "C" "D" "D" "D"


## Supply a single vector to key.match and key.reassign

lookup(mtcars$carb, sort(unique(mtcars$carb)),
    c("one", "two", "three", "four", "six", "eight"))

 [1] "four"  "four"  "one"   "one"   "two"   "one"   "four"  "two"   "two"   "four"  "four"  "three" "three" "three" "four" 
[16] "four"  "four"  "one"   "two"   "one"   "one"   "two"   "two"   "four"  "two"   "one"   "two"   "two"   "four"  "six"  
[31] "eight" "two"  


lookup(mtcars$carb, sort(unique(mtcars$carb)),
    seq(10, 60, by=10))

 [1] 40 40 10 10 20 10 40 20 20 40 40 30 30 30 40 40 40 10 20 10 10 20 20 40 20 10 20 20 40 50 60 20


## %l%, a binary operator version of lookup
1:5 %l% data.frame(1:4, 11:14)

[1] 11 12 13 14 NA

1:10 %l% codes

 [1] "A" "A" "B" "A" "B" "D" "C" "D" "D" "D"


1:12 %l% codes

 [1] "A" "A" "B" "A" "B" "D" "C" "D" "D" "D" NA  NA 

1:12 %l+% codes

 [1] "A"  "A"  "B"  "A"  "B"  "D"  "C"  "D"  "D"  "D"  "11" "12"


(key <- data.frame(a=1:3, b=factor(paste0("l", 1:3))))

  a  b
1 1 l1
2 2 l2
3 3 l3

1:3 %l% key

[1] l1 l2 l3
Levels: l1 l2 l3


##Larger Examples
key <- data.frame(x=1:2, y=c("A", "B"))
big.vec <- sample(1:2, 3000000, TRUE)
out <- lookup(big.vec, key)
out[1:20]

 [1] B B B B A A A B A A A A A B A B A A A B
Levels: A B


## A big string to recode with variation
## means a bigger dictionary
recode_me <- sample(1:(length(LETTERS)*10), 10000000, TRUE)

## Time it
tic <- Sys.time()

output <- recode_me %l% split(1:(length(LETTERS)*10), LETTERS)
difftime(Sys.time(), tic)

Time difference of 0.726522 secs


## view it
sample(output, 100)

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

See also