## Usage

remove_NA(x, ...)

replace_NA(x, ...)

# S4 method for ANY
remove_NA(x, margin = 1, all = FALSE)

# S4 method for matrix
replace_NA(x, value = 0)

## Arguments

x

An object (should be a matrix or a data.frame).

...

Currently not used.

margin

A vector giving the subscripts which the function will be applied over (1 indicates rows, 2 indicates columns).

all

A logical scalar. If TRUE, only the rows/columns whose values all meet the condition defined by f are considered. If FALSE (the default), only rows/columns where at least one value validates the condition defined by f are considered.

value

A possible replacement value.

Other data cleaning tools: compact(), count(), detect(), discard(), infinite, keep(), zero

N. Frerebeau

## Examples

## Create a count data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

k <- sample(1:25, 3, FALSE)
X[k] <- NA
X
#>      [,1] [,2] [,3] [,4] [,5]
#> [1,]    2    5    9   10    6
#> [2,]    3    1    5    7   NA
#> [3,]    4    5    8   NA    8
#> [4,]   10    7    1    3    9
#> [5,]    2   NA    8    4    1

## Count missing values in rows
count(X, f = is.na, margin = 1)
#> [1] 0 1 1 0 1
## Count non-missing values in columns
count(X, f = is.na, margin = 2, negate = TRUE)
#> [1] 5 4 5 4 4

## Find row with NA
detect(X, f = is.na, margin = 1)
#> [1] FALSE  TRUE  TRUE FALSE  TRUE
## Find column without any NA
detect(X, f = is.na, margin = 2, negate = TRUE, all = TRUE)
#> [1]  TRUE FALSE  TRUE FALSE FALSE

## Keep row without any NA
keep(X, f = is.na, margin = 1, negate = TRUE, all = TRUE)
#>      [,1] [,2] [,3] [,4] [,5]
#> [1,]    2    5    9   10    6
#> [2,]   10    7    1    3    9
## Keep row without any NA
keep(X, f = is.na, margin = 2, negate = TRUE, all = TRUE)
#>      [,1] [,2]
#> [1,]    2    9
#> [2,]    3    5
#> [3,]    4    8
#> [4,]   10    1
#> [5,]    2    8

## Remove row with any NA
discard(X, f = is.na, margin = 1, all = FALSE)
#>      [,1] [,2] [,3] [,4] [,5]
#> [1,]    2    5    9   10    6
#> [2,]   10    7    1    3    9
## Remove column with any NA
discard(X, f = is.na, margin = 2, all = FALSE)
#>      [,1] [,2]
#> [1,]    2    9
#> [2,]    3    5
#> [3,]    4    8
#> [4,]   10    1
#> [5,]    2    8

## Replace NA with zeros
replace_NA(X, value = 0)
#>      [,1] [,2] [,3] [,4] [,5]
#> [1,]    2    5    9   10    6
#> [2,]    3    1    5    7    0
#> [3,]    4    5    8    0    8
#> [4,]   10    7    1    3    9
#> [5,]    2    0    8    4    1