Question

我试图将每一行与矩阵中的所有其他行进行比较，以计算每行与所有其他行的差异数。然后将结果存储在矩阵的左下角三角形中。

因此，例如当行m [1，]与行m [2，]和m [3，]进行比较时，差值计数存储在结果中mat [c（2：3），1]的位置基质

我的问题是我的输入矩阵最多可以有1e + 07行，并且由于n ^ 2比较，当前的实现（速度和内存）不会缩放。建议和帮助将不胜感激。

diffMatrix <- function(x) {

  rows <- dim(x)[1] #num of rows
  cols <- dim(x)[2] #num of columns

  if (rows <= 1) stop("'x' must have atleast two rows")

  #potential failure point
  mat <- matrix(, rows, rows)

  # fill bottom left triangle columns ignoring the diagonal
  for (row in 1:(rows-1)) { 
    rRange <- c((1+row):rows)
    m <- matrix(x[row,], nrow=rows-row, ncol=cols, byrow = T)
    mat[rRange, row] <- rowSums(m != x[-1:-row, ])
  }

  return (mat)
}   


m <- matrix(sample(1:12, 12, replace=T), ncol=2, byrow=TRUE)
m
#     [,1] [,2]
#[1,]    8    1
#[2,]    4    1
#[3,]    8    4
#[4,]    4    5
#[5,]    3    1
#[6,]    2    2

x <- diffMatrix(m)
x
#     [,1] [,2] [,3] [,4] [,5] [,6]
#[1,]   NA   NA   NA   NA   NA   NA
#[2,]    1   NA   NA   NA   NA   NA
#[3,]    1    2   NA   NA   NA   NA
#[4,]    2    1    2   NA   NA   NA
#[5,]    1    1    2    2   NA   NA
#[6,]    2    2    2    2    2   NA

m <- matrix(sample(1:5, 50000, replace=T), ncol=10, byrow=TRUE)
# system.time(x <- diffMatrix(m))
#   user  system elapsed 
#  20.39    0.38   21.43

Answer 1

以下是使用.Call的替代方法（似乎有效，但我无法保证）：

library(inline)

ff = cfunction(sig = c(R_mat = "matrix"), body = '
SEXP mat, dims, ans, dimans;

PROTECT(dims = getAttrib(R_mat, R_DimSymbol));
PROTECT(dimans = allocVector(INTSXP, 2));
R_len_t *pdims = INTEGER(dims), *pdimans = INTEGER(dimans);
PROTECT(ans = allocVector(INTSXP, pdims[0]*pdims[0]));
R_len_t *pans = INTEGER(ans);
pdimans[0] = pdims[0];
pdimans[1] = pdims[0];

for(int ina = 0; ina < LENGTH(ans); ina++) {
   pans[ina] = NA_INTEGER;
}

switch(TYPEOF(R_mat)) {
   case REALSXP:
   {
    PROTECT(mat = coerceVector(R_mat, REALSXP));
    double *pmat = REAL(mat);
    for(int i = 0; i < pdims[0]; i++) {
       R_len_t ir;
       for(ir = i+1; ir < pdims[0]; ir++) {
          R_len_t diffs = 0;
          for(int ic = 0; ic < pdims[1]; ic++) {
             if(pmat[i + ic*pdims[0]] != pmat[ir + ic*pdims[0]]) {
               diffs++;
             }
          }
          pans[ir + i*pdims[0]] = diffs;
       }
    }
    break;
   }

   case INTSXP:
   {
    PROTECT(mat = coerceVector(R_mat, INTSXP));
    R_len_t *pmat = INTEGER(mat);
    for(int i = 0; i < pdims[0]; i++) {
       R_len_t ir; 
       for(ir = i+1; ir < pdims[0]; ir++) {
          R_len_t diffs = 0;
          for(int ic = 0; ic < pdims[1]; ic++) {
             if(pmat[i + ic*pdims[0]] != pmat[ir + ic*pdims[0]]) {
               diffs++;
             }
          }
          pans[ir + i*pdims[0]] = diffs;
       }
    }
    break;
   }
}

setAttrib(ans, R_DimSymbol, dimans);

UNPROTECT(4);

return(ans);
')

m = matrix(c(8,4,8,4,3,2,1,1,4,5,1,2), ncol = 2)
ff(m)
#     [,1] [,2] [,3] [,4] [,5] [,6]
#[1,]   NA   NA   NA   NA   NA   NA
#[2,]    1   NA   NA   NA   NA   NA
#[3,]    1    2   NA   NA   NA   NA
#[4,]    2    1    2   NA   NA   NA
#[5,]    1    1    2    2   NA   NA
#[6,]    2    2    2    2    2   NA
all.equal(diffMatrix(m), ff(m))
#[1] TRUE

m2 <- matrix(sample(1:5, 50000, replace=T), ncol=10, byrow=TRUE)
library(microbenchmark)
microbenchmark(diffMatrix(m2), ff(m2), times = 10)
#Unit: milliseconds
#           expr       min        lq   median        uq        max neval
# diffMatrix(m2) 6972.9778 7049.3455 7427.807 7633.7581 11337.3154    10
#         ff(m2)  422.3195  469.5771  530.470  661.8299   862.3092    10
all.equal(diffMatrix(m2), ff(m2))
#[1] TRUE

如何矢量化比较每行矩阵与所有其他行

1 个答案: