data.table的替代方案:

library(data.table)
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])
rbindlist(list(df1, df2), fill = TRUE)

Rbind也可以在数据中工作。表中只要对象都转换为数据。表对象，所以

rbind(setDT(df1), setDT(df2), fill=TRUE)

也适用于这种情况。当您有几个数据时，这可能更可取。表，而不想构造列表。

rbind。从包装胶合板填充可能是你正在寻找的。

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)]))
}

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

我写了一个函数来做这件事，因为我喜欢我的代码告诉我什么是错误的。这个函数将显式地告诉您哪些列名不匹配，以及是否存在类型不匹配。然后它会尽最大努力组合data.frames。限制是一次只能合并两个data.frame。

### combines data frames (like rbind) but by matching column names
# columns without matches in the other data frame are still combined
# but with NA in the rows corresponding to the data frame without
# the variable
# A warning is issued if there is a type mismatch between columns of
# the same name and an attempt is made to combine the columns
combineByName <- function(A,B) {
    a.names <- names(A)
    b.names <- names(B)
    all.names <- union(a.names,b.names)
    print(paste("Number of columns:",length(all.names)))
    a.type <- NULL
    for (i in 1:ncol(A)) {
        a.type[i] <- typeof(A[,i])
    }
    b.type <- NULL
    for (i in 1:ncol(B)) {
        b.type[i] <- typeof(B[,i])
    }
    a_b.names <- names(A)[!names(A)%in%names(B)]
    b_a.names <- names(B)[!names(B)%in%names(A)]
    if (length(a_b.names)>0 | length(b_a.names)>0){
        print("Columns in data frame A but not in data frame B:")
        print(a_b.names)
        print("Columns in data frame B but not in data frame A:")
        print(b_a.names)
    } else if(a.names==b.names & a.type==b.type){
        C <- rbind(A,B)
        return(C)
    }
    C <- list()
    for(i in 1:length(all.names)) {
        l.a <- all.names[i]%in%a.names
        pos.a <- match(all.names[i],a.names)
        typ.a <- a.type[pos.a]
        l.b <- all.names[i]%in%b.names
        pos.b <- match(all.names[i],b.names)
        typ.b <- b.type[pos.b]
        if(l.a & l.b) {
            if(typ.a==typ.b) {
                vec <- c(A[,pos.a],B[,pos.b])
            } else {
                warning(c("Type mismatch in variable named: ",all.names[i],"\n"))
                vec <- try(c(A[,pos.a],B[,pos.b]))
            }
        } else if (l.a) {
            vec <- c(A[,pos.a],rep(NA,nrow(B)))
        } else {
            vec <- c(rep(NA,nrow(A)),B[,pos.b])
        }
        C[[i]] <- vec
    }
    names(C) <- all.names
    C <- as.data.frame(C)
    return(C)
}

您可以将它们插入到原始数据库(db1)的末尾，并添加第二个数据库的行数。db2中不包括的列将显示NA值。

db1[nrow（db1）+1：nrow（db1）+nrow（db2）， names（db2）] <- db2