Counting frequencies of each letter for multiple column [duplicate]

I have a data frame as below:

> dfnew

   C1 C2 C3 C4   C5   C6
1   A  A  G  A    G    A
2   A  T  T  T    G    G
3   T  A  G  A    T    A
4   C  A  A  A    A    G
5   C  A  T  T    T    C
6   C  A  A  A    T    A
7   T  C  T  G    A    A
8   G  A  G  C    T    A
9   C  T  A  T    G    A
10  G  A  A  A    G    G
11  G  G  T  T    T    A
12  G  A  C  T    T    A
13  T  T  C  T    T    T
14  A  T  A  G    C    T
15  A  C  A  A    A    A
16  A  A  C  A    A    A
17  T  G  G  A    A    T
18  A  A  A  A    G    T
19  G  T  G  G <NA> <NA>

I want to get answer as below in one line of code in R without looping:

A   6   10  7   9   5   10
C   4   2   3   1   1   1
G   5   2   5   3   5   3
T   4   5   4   6   7   4

Asked By: Tanmay

Source

Answer #1:

We can use sapply to loop over the columns, convert it to factor with levels specified and get the frequency with table

sapply(dfnew, function(x) table(factor(x, levels = c("A", "C", "G", "T"))))

Or using tidyverse

library(dplyr)
library(tidyr)
dfnew %>% 
    gather(key, val, na.rm = TRUE) %>% 
    count(key, val) %>% 
    spread(key, n)

Answered By: akrun

Answer #2:

If you use stack to reshape everything to long form, you can call table on the result:

dfnew <- data.frame(C1 = c("A", "A", "T", "C", "C", "C", "T", "G", "C", "G", "G", "G", "T", "A", "A", "A", "T", "A", "G"), 
                    C2 = c("A", "T", "A", "A", "A", "A", "C", "A", "T", "A", "G", "A", "T", "T", "C", "A", "G", "A", "T"), 
                    C3 = c("G", "T", "G", "A", "T", "A", "T", "G", "A", "A", "T", "C", "C", "A", "A", "C", "G", "A", "G"), 
                    C4 = c("A", "T", "A", "A", "T", "A", "G", "C", "T", "A", "T", "T", "T", "G", "A", "A", "A", "A", "G"), 
                    C5 = c("G", "G", "T", "A", "T", "T", "A", "T", "G", "G", "T", "T", "T", "C", "A", "A", "A", "G", NA), 
                    C6 = c("A", "G", "A", "G", "C", "A", "A", "A", "A", "G", "A", "A", "T", "T", "A", "A", "T", "T", NA),
                    stringsAsFactors = FALSE)

table(stack(dfnew))
#>       ind
#> values C1 C2 C3 C4 C5 C6
#>      A  6 10  7  9  5 10
#>      C  4  2  3  1  1  1
#>      G  5  2  5  3  5  3
#>      T  4  5  4  6  7  4

Answered By: alistaire

Answer #3:

using data.table and its pipe worflow with [:

library(data.table)
tab <- fread("
C1 C2 C3 C4   C5   C6
A  A  G  A    G    A
A  T  T  T    G    G
T  A  G  A    T    A
C  A  A  A    A    G
C  A  T  T    T    C
C  A  A  A    T    A
T  C  T  G    A    A
G  A  G  C    T    A
C  T  A  T    G    A
G  A  A  A    G    G
G  G  T  T    T    A
G  A  C  T    T    A
T  T  C  T    T    T
A  T  A  G    C    T
A  C  A  A    A    A
A  A  C  A    A    A
T  G  G  A    A    T
A  A  A  A    G    T
G  T  G  G NA NA")

tab[, melt(.SD, measure.vars = paste0("C", 1:6), na.rm = TRUE)][
    , dcast(.SD, value ~ variable, fun = length, drop = TRUE)
  ]
#>    value C1 C2 C3 C4 C5 C6
#> 1:     A  6 10  7  9  5 10
#> 2:     C  4  2  3  1  1  1
#> 3:     G  5  2  5  3  5  3
#> 4:     T  4  5  4  6  7  4

Answered By: cderv

The answers/resolutions are collected from stackoverflow, are licensed under cc by-sa 2.5 , cc by-sa 3.0 and cc by-sa 4.0 .