rbind.ordered=function(x,y){

  diffCol = setdiff(colnames(x),colnames(y))
  if (length(diffCol)>0){
    cols=colnames(y)
    for (i in 1:length(diffCol)) y=cbind(y,NA)
    colnames(y)=c(cols,diffCol)
  }

  diffCol = setdiff(colnames(y),colnames(x))
  if (length(diffCol)>0){
    cols=colnames(x)
    for (i in 1:length(diffCol)) x=cbind(x,NA)
    colnames(x)=c(cols,diffCol)
  }
  return(rbind(x, y[, colnames(x)]))
}

rbind。从包装胶合板填充可能是你正在寻找的。

如果df1中的列是df2中的列的子集(通过列名):

df3 <- rbind(df1, df2[, names(df1)])

最近的解决方案是使用dplyr的bind_rows函数，我认为它比smartbind更有效。

df1 <- data.frame(a = c(1:5), b = c(6:10))
df2 <- data.frame(a = c(11:15), b = c(16:20), c = LETTERS[1:5])
dplyr::bind_rows(df1, df2)
    a  b    c
1   1  6 <NA>
2   2  7 <NA>
3   3  8 <NA>
4   4  9 <NA>
5   5 10 <NA>
6  11 16    A
7  12 17    B
8  13 18    C
9  14 19    D
10 15 20    E

您也可以使用sjmisc::add_rows()，它使用dplyr::bind_rows()，但与bind_rows()不同，add_rows()保留属性，因此对带标签的数据很有用。

请参阅以下带有标记数据集的示例。如果数据被标记，frq()函数打印带有值标签的频率表。

library(sjmisc)
library(dplyr)

data(efc)
# select two subsets, with some identical and else different columns
x1 <- efc %>% select(1:5) %>% slice(1:10)
x2 <- efc %>% select(3:7) %>% slice(11:20)

str(x1)
#> 'data.frame':    10 obs. of  5 variables:
#>  $ c12hour : num  16 148 70 168 168 16 161 110 28 40
#>   ..- attr(*, "label")= chr "average number of hours of care per week"
#>  $ e15relat: num  2 2 1 1 2 2 1 4 2 2
#>   ..- attr(*, "label")= chr "relationship to elder"
#>   ..- attr(*, "labels")= Named num  1 2 3 4 5 6 7 8
#>   .. ..- attr(*, "names")= chr  "spouse/partner" "child" "sibling" "daughter or son -in-law" ...
#>  $ e16sex  : num  2 2 2 2 2 2 1 2 2 2
#>   ..- attr(*, "label")= chr "elder's gender"
#>   ..- attr(*, "labels")= Named num  1 2
#>   .. ..- attr(*, "names")= chr  "male" "female"
#>  $ e17age  : num  83 88 82 67 84 85 74 87 79 83
#>   ..- attr(*, "label")= chr "elder' age"
#>  $ e42dep  : num  3 3 3 4 4 4 4 4 4 4
#>   ..- attr(*, "label")= chr "elder's dependency"
#>   ..- attr(*, "labels")= Named num  1 2 3 4
#>   .. ..- attr(*, "names")= chr  "independent" "slightly dependent" "moderately dependent" "severely dependent"

bind_rows(x1, x1) %>% frq(e42dep)
#> 
#> # e42dep <numeric> 
#> # total N=20  valid N=20  mean=3.70  sd=0.47
#>  
#>   val frq raw.prc valid.prc cum.prc
#>     3   6      30        30      30
#>     4  14      70        70     100
#>  <NA>   0       0        NA      NA

add_rows(x1, x1) %>% frq(e42dep)
#> 
#> # elder's dependency (e42dep) <numeric> 
#> # total N=20  valid N=20  mean=3.70  sd=0.47
#>  
#>  val                label frq raw.prc valid.prc cum.prc
#>    1          independent   0       0         0       0
#>    2   slightly dependent   0       0         0       0
#>    3 moderately dependent   6      30        30      30
#>    4   severely dependent  14      70        70     100
#>   NA                   NA   0       0        NA      NA

只是为了文档。你可以用下面的形式尝试Stack库和它的函数Stack:

Stack(df_1, df_2)

我也有一个印象，对于大数据集，它比其他方法更快。