将每个组扩展到最大 n 行

Question

如何将组扩展到最大组的长度：

df <- structure(list(ID = c(1L, 1L, 2L, 3L, 3L, 3L), col1 = c("A", 
"B", "O", "U", "L", "R")), class = "data.frame", row.names = c(NA, 
-6L))


ID col1
1 A
1 B
2 O
3 U
3 L
3 R

期望的输出：

1 A
1 B
NA NA
2 O
NA NA
NA NA
3 U
3 L
3 R

Answer 1

您可以利用df[n_bigger_than_nrow,]给出一排NAs的事实

\n

dplyr

\n

max_n <- max(count(df, ID)$n)\n\ndf %>% \n  group_by(ID) %>% \n  summarise(cur_data()[seq(max_n),])\n#> `summarise()` has grouped output by \'ID\'. You can override using the `.groups`\n#> argument.\n#> # A tibble: 9 \xc3\x97 2\n#> # Groups:   ID [3]\n#>      ID col1 \n#>   <int> <chr>\n#> 1     1 A    \n#> 2     1 B    \n#> 3     1 <NA> \n#> 4     2 O    \n#> 5     2 <NA> \n#> 6     2 <NA> \n#> 7     3 U    \n#> 8     3 L    \n#> 9     3 R\n

\n

碱基R

\n

n <- tapply(df$ID, df$ID, length)\nmax_n <- max(n)\ni <- lapply(n, \\(x) c(seq(x), rep(Inf, max_n - x)))\ni <- Map(`+`, i, c(0, cumsum(head(n, -1))))\ndf <- df[unlist(i),]\nrownames(df) <- NULL\ndf$ID <- rep(as.numeric(names(i)), each = max_n)\n\ndf\n#>   ID col1\n#> 1  1    A\n#> 2  1    B\n#> 3  1 <NA>\n#> 4  2    O\n#> 5  2 <NA>\n#> 6  2 <NA>\n#> 7  3    U\n#> 8  3    L\n#> 9  3    R\n

\n