r - 比较数据框中行的更快方法

Question

考虑下面的数据框。我想将每一行与下面的行进行比较，然后取超过 3 个值相等的行。

我写了下面的代码，但是如果你有一个大的数据框，它会很慢。

我怎么能做得更快？

data <- as.data.frame(matrix(c(10,11,10,13,9,10,11,10,14,9,10,10,8,12,9,10,11,10,13,9,13,13,10,13,9), nrow=5, byrow=T))
rownames(data)<-c("sample_1","sample_2","sample_3","sample_4","sample_5")

>data
          V1 V2 V3 V4 V5
sample_1  10 11 10 13  9
sample_2  10 11 10 14  9
sample_3  10 10  8 12  9
sample_4  10 11 10 13  9
sample_5  13 13 10 13  9

output <- data.frame(sample = NA, duplicate = NA, matches = NA)
dfrow <- 1
for(i in 1:nrow(data)) {
    sample <- data[i, ]
    for(j in (i+1):nrow(data)) if(i+1 <= nrow(data)) {
    matches <- 0
        for(V in 1:ncol(data)) {
            if(data[j,V] == sample[,V]) {       
                matches <- matches + 1
            }
        }
        if(matches > 3) {
            duplicate <- data[j, ]
            pair <- cbind(rownames(sample), rownames(duplicate), matches)
            output[dfrow, ] <- pair
            dfrow <- dfrow + 1
        }
    }
}

>output
   sample    duplicate    matches
1 sample_1   sample_2     4
2 sample_1   sample_4     5
3 sample_2   sample_4     4

Answer 1

这是一个 Rcpp 解决方案。但是，如果结果矩阵变得太大(即点击次数过多)，则会引发错误。我运行循环两次，首先获得结果矩阵的必要大小，然后填充它。可能有更好的可能性。此外，显然，这仅适用于整数。如果您的矩阵是数字，则必须处理浮点精度。

library(Rcpp)
library(inline)

#C++ code:
body <- '
const IntegerMatrix        M(as<IntegerMatrix>(MM));
const int                  m=M.ncol(), n=M.nrow();
long                        count1;
int                         count2;
count1 = 0;
for (int i=0; i<(n-1); i++)
{
   for (int j=(i+1); j<n; j++)
   {
     count2 = 0;
     for (int k=0; k<m; k++) {
        if (M(i,k)==M(j,k)) count2++;
     }
     if (count2>3) count1++;
   } 
}
IntegerMatrix              R(count1,3);
count1 = 0;
for (int i=0; i<(n-1); i++)
{
   for (int j=(i+1); j<n; j++)
   {
     count2 = 0;
     for (int k=0; k<m; k++) {
        if (M(i,k)==M(j,k)) count2++;
     }
     if (count2>3) {
        count1++;
        R(count1-1,0) = i+1;
        R(count1-1,1) = j+1;
        R(count1-1,2) = count2;
     }
   } 
}
return  wrap(R);
'

fun <- cxxfunction(signature(MM = "matrix"), 
                     body,plugin="Rcpp")

#with your data
fun(as.matrix(data))
#      [,1] [,2] [,3]
# [1,]    1    2    4
# [2,]    1    4    5
# [3,]    2    4    4

#Benchmarks
set.seed(42)
mat1 <- matrix(sample(1:10,250*26,TRUE),ncol=26)
mat2 <- matrix(sample(1:10,2500*26,TRUE),ncol=26)
mat3 <- matrix(sample(1:10,10000*26,TRUE),ncol=26)
mat4 <- matrix(sample(1:10,25000*26,TRUE),ncol=26)
library(microbenchmark)
microbenchmark(
  fun(mat1),
  fun(mat2),
  fun(mat3),
  fun(mat4),
  times=3
  )
# Unit: milliseconds
#      expr          min           lq       median           uq          max neval
# fun(mat1)     2.675568     2.689586     2.703603     2.732487     2.761371     3
# fun(mat2)   272.600480   274.680815   276.761151   276.796217   276.831282     3
# fun(mat3)  4623.875203  4643.634249  4663.393296  4708.067638  4752.741979     3
# fun(mat4) 29041.878164 29047.151348 29052.424532 29235.839275 29419.254017     3