Question

我的数据集中有很多NA，我需要将所有这些单元格（在行级别）向左移动。

示例 - 我的数据框：

    df=data.frame(x=c("l","m",NA,NA,"p"),y=c(NA,"b","c",NA,NA),z=c("u",NA,"w","x","y"))
    df
         x    y    z
    1    l <NA>    u
    2    m    b <NA>
    3 <NA>    c    w
    4 <NA> <NA>    x
    5    p <NA>    y

我希望上面的数据框转换成这个：

      x    y  z
    1 l    u NA
    2 m    b NA
    3 c    w NA
    4 x <NA> NA
    5 p    y NA

请帮忙。

感谢。

Answer 1

您可以使用标准apply功能：

df=data.frame(x=c("l","m",NA,NA,"p"),y=c(NA,"b","c",NA,NA),z=c("u",NA,"w","x","y"))
df2 = as.data.frame(t(apply(df,1, function(x) { return(c(x[!is.na(x)],x[is.na(x)]) )} )))
colnames(df2) = colnames(df)

> df
     x    y    z
1    l <NA>    u
2    m    b <NA>
3 <NA>    c    w
4 <NA> <NA>    x
5    p <NA>    y
> df2
  x    y    z
1 l    u <NA>
2 m    b <NA>
3 c    w <NA>
4 x <NA> <NA>
5 p    y <NA>

Answer 2

感谢@Richard Scriven的好观察

A）与is.na和order，lapply和rbind进行汇总

nosort.df<-do.call(rbind,lapply(1:nrow(df),function(x) { z=df[x,][order(is.na(df[x,]))];colnames(z)<-c("x","y","z");return(z) } ))

> nosort.df
  x    y    z
1 l    u <NA>
2 m    b <NA>
3 c    w <NA>
4 x <NA> <NA>
5 p    y <NA>

B）如果需要排序的行：

sort，lapply和rbind

sort.df<-do.call(rbind,lapply(1:nrow(df),function(x) { z=sort(df[x,],na.last=TRUE);colnames(z)<-c("x","y","z");return(z) } ))

> sort.df
  x    y    z
1 l    u <NA>
2 b    m <NA>
3 c    w <NA>
4 x <NA> <NA>
5 p    y <NA>

Answer 3

如果你不能得到更短的答案，这应该有所帮助：

df=data.frame(x=c("l","m",NA,NA,"p"),y=c(NA,"b","c",NA,NA),z=c("u",NA,"w","x","y"))
sapply(df,as.character)


for(i in 1:nrow(df)){
  sub <- df[i,c(which(!is.na(df[i,])),which(is.na(df[i,])))] 
  colnames(sub) <- colnames(df)
  df[i,] <- sub
}

Answer 4

如果您不想使用VBA，可以尝试以下步骤。

1. Select your dataset
2. Replace NA will empty cells
3. press F5 and select blanks ok
4. right click on any of the selection and delete (left)

我希望这会有所帮助。

Answer 5

另一种语法较短的答案：

df=data.frame(x=c("l","m",NA,NA,"p"),y=c(NA,"b","c",NA,NA),z=c("u",NA,"w","x","y"))

      x   y   z  
[1,] "l" NA  "u"
[2,] "m" "b" NA 
[3,] NA  "c" "w"
[4,] NA  NA  "x"
[5,] "p" NA  "y"



sorted.df <- as.data.frame(t(apply(df, 1, function(x) x[order(is.na(x))])))

     [,1] [,2] [,3]
[1,] "l"  "u"  NA  
[2,] "m"  "b"  NA  
[3,] "c"  "w"  NA  
[4,] "x"  NA   NA  
[5,] "p"  "y"  NA

Answer 6

我们也可以在这里使用 pmap 包中的 purrr 函数来获得巨大的优势：

library(dplyr)
library(purrr)

df %>% 
  pmap(., ~ c(c(...)[!is.na(c(...))], c(...)[is.na(c(...))])) %>%
  exec(rbind, !!!.) %>%
  as_tibble()

# A tibble: 5 x 3
  x     z     y    
  <chr> <chr> <chr>
1 l     u     NA   
2 m     b     NA   
3 c     w     NA   
4 x     NA    NA   
5 p     y     NA

向左移动非NA细胞

6 个答案: