如何在 R 中查找具有特定数量的连续 0 和 1 的矩阵中的行

Question

I have this matrix:

      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
 [1,]    1    0    0    0    0    0    0    0
 [2,]    0    1    1    0    0    0    0    0
 [3,]    0    0    1    1    0    0    0    0
 [4,]    0    0    0    1    1    0    0    0 
 [5,]    0    0    0    0    1    1    0    0   
 [6,]    0    0    0    0    0    1    1    0   
 [7,]    0    0    0    0    0    0    1    1         

What I want to do is to filter this matrix by rows where the minimum number of consecutive 0s and 1s is n.

For example, if n = 2 , the expected output should be this:

      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
 [1,]    0    0    1    1    0    0    0    0
 [2,]    0    0    0    1    1    0    0    0 
 [3,]    0    0    0    0    1    1    0    0     
 [4,]    0    0    0    0    0    0    1    1   

As you can see the rows 1, 2 and 6 of the initial matrix had a minimum of only one consecutive 1, one consecutive 0 and one consecutive 0, respectively.

If n = 3 , the expected output should be an empty matrix since no row has a minimum of three consecutive 0s and three consecutive 1s simultaneously.

Is there a way to create a function that takes as input a matrix and the value n and gives the expected output in R?

This is the matrix of the example:

matrix(c(1, 0, 0, 0, 0, 0, 0, 0,
         0, 1, 1, 0, 0, 0, 0, 0,
         0, 0, 1, 1, 0, 0, 0, 0,
         0, 0, 0, 1, 1, 0, 0, 0, 
         0, 0, 0, 0, 1, 1, 0, 0,   
         0, 0, 0, 0, 0, 1, 1, 0,   
         0, 0, 0, 0, 0, 0, 1, 1), byrow = T, ncol = 8)

Answer 1

We can use rle row-wise and select the rows where the minimum consecutive length between numbers is at least n .

n <- 2
mat[apply(mat, 1, function(x) all(rle(x)$lengths >= n)), ]

#     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
#[1,]    0    0    1    1    0    0    0    0
#[2,]    0    0    0    1    1    0    0    0
#[3,]    0    0    0    0    1    1    0    0
#[4,]    0    0    0    0    0    0    1    1

data

mat <- structure(c(1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L), .Dim = 7:8)

Answer 2

We can use rleid from data.table to create the condition for subsetting the rows

library(data.table)
n <- 2
mat[apply(mat, 1, function(x) all(table(rleid(x))>=2)),]
#      [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
#[1,]    0    0    1    1    0    0    0    0
#[2,]    0    0    0    1    1    0    0    0
#[3,]    0    0    0    0    1    1    0    0
#[4,]    0    0    0    0    0    0    1    1

data

mat <- structure(c(1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 
0L, 0L, 1L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 1L), .Dim = 7:8)