Fatal编程技术网
  • r/
  • R 根据多列之间的连接删除数据帧的行

R 根据多列之间的连接删除数据帧的行

r

R 根据多列之间的连接删除数据帧的行,r,R,考虑到以下数据框架： # input a <- data.frame( X1=c("a","a","a","a","a","a","a","a","a","a","a","b","b","b","b","b","b","b","b","b"), X2=c(2,4,6,2,4,7,9,5,4,7,3,5,8,4,3,5,7,6,3,5), X3=c(5,6,1,4,7,5,5,4,4,2,5,4,5,2,4,7,3,5,3,7) ) #输入 a如果速度不是你主要关心的问题，我

考虑到以下数据框架：

# input 
a <- data.frame(
  X1=c("a","a","a","a","a","a","a","a","a","a","a","b","b","b","b","b","b","b","b","b"),
  X2=c(2,4,6,2,4,7,9,5,4,7,3,5,8,4,3,5,7,6,3,5),
  X3=c(5,6,1,4,7,5,5,4,4,2,5,4,5,2,4,7,3,5,3,7)
)

#输入

a如果速度不是你主要关心的问题，我认为这是很容易理解的：


library(plyr)
ddply(a, "X1", function(x) {
  n <- seq_len(nrow(x))
  m <- outer(n, n, Vectorize(function(i,j) all(x[i, 2:3] < x[j, 2:3])))
  i <- rowSums(m) > 0L
  return(x[!i, ])
})



库（plyr）
ddply（a，“X1”，函数（x）{

n函数
isRemoved
将给出
TRUE
或
FALSE
给定每行
i
的条件：


isRemoved = function(i, a) {
  out = logical(nrow(a))
  for(j in 1:nrow(a)) {
    out[j] = a[i,1]==a[j,1] & a[i,2]<a[j,2] & a[i,3]<a[j,3]
  }
  out = any(out)
  return(out)
}


并保留您想要的行：


a.new = a[!remove, ]

a.new 

   X1 X2 X3
2   a  4  6
5   a  4  7
6   a  7  5
7   a  9  5
13  b  8  5
16  b  5  7
18  b  6  5
20  b  5  7



remove = sapply(1:nrow(a), isRemoved, a=a)



a.new = a[!remove, ]

a.new 

   X1 X2 X3
2   a  4  6
5   a  4  7
6   a  7  5
7   a  9  5
13  b  8  5
16  b  5  7
18  b  6  5
20  b  5  7