按空行拆分数据帧

Question

我正在尝试根据块之间的 NA 行（即 Loc_1、Loc_2、Loc_3）将格式非常糟糕的数据帧拆分为数据帧列表。我试过基于空行拆分 R 中的数据帧，并根据空行和标题标题将数据帧划分或拆分为多个 dfs，但没有成功。我认为在我的情况下的不同之处在于我没有一个没有 NA 值的列，因为每个新块都以前两列中两行的 NA 开始，并且有大量的 NA 分散在各处。有任何想法吗？这是我的第一篇文章，所以如果我需要发布更多信息，请留言！

df <- data.frame(
  a = c(NA, NA, "Loc_1", "Loc_1", "Loc_1", NA, NA, NA, "Loc_2", "Loc_2", "Loc_2", NA, NA, NA, "Loc_3", "Loc_3", "Loc_3"),
  b = c(NA, NA, "25:11:2020", "26:11:2020", "27:11:2020", NA, NA, NA, "25:11:2020", "26:11:2020", "27:11:2020",NA, NA, NA, "25:11:2020", "26:11:2020", "27:11:2020"),
  c = c("Var1", "Unit/1", 1:3, NA, "Var3", "Unit/3", NA, 1, 2, NA,"Var1", "Unit/1", 1:3),
  d = c("Var2", "Unit/2", NA, NA, 1, NA, "Var1", "Unit/1", NA, NA, 1, NA, "Var3", "Unit/3", NA, NA, 1)
)

       a          b      c      d
1   <NA>       <NA>   Var1   Var2
2   <NA>       <NA> Unit/1 Unit/2
3  Loc_1 25:11:2020      1   <NA>
4  Loc_1 26:11:2020      2   <NA>
5  Loc_1 27:11:2020      3      1
6   <NA>       <NA>   <NA>   <NA>
7   <NA>       <NA>   Var3   Var1
8   <NA>       <NA> Unit/3 Unit/1
9  Loc_2 25:11:2020   <NA>   <NA>
10 Loc_2 26:11:2020      1   <NA>
11 Loc_2 27:11:2020      2      1
12  <NA>       <NA>   <NA>   <NA>
13  <NA>       <NA>   Var1   Var3
14  <NA>       <NA> Unit/1 Unit/3
15 Loc_3 25:11:2020      1   <NA>
16 Loc_3 26:11:2020      2   <NA>
17 Loc_3 27:11:2020      3      1

Answer 1

这个 Base R 解决方案怎么样：

n <- rowSums(is.na(df)) == ncol(df)
cs <- cumsum(n) + 1
s <- split(df[!n, ], cs[!n])

s

#> $`1`
#>       a          b      c      d
#> 1  <NA>       <NA>   Var1   Var2
#> 2  <NA>       <NA> Unit/1 Unit/2
#> 3 Loc_1 25:11:2020      1   <NA>
#> 4 Loc_1 26:11:2020      2   <NA>
#> 5 Loc_1 27:11:2020      3      1
#> 
#> $`2`
#>        a          b      c      d
#> 7   <NA>       <NA>   Var3   Var1
#> 8   <NA>       <NA> Unit/3 Unit/1
#> 9  Loc_2 25:11:2020   <NA>   <NA>
#> 10 Loc_2 26:11:2020      1   <NA>
#> 11 Loc_2 27:11:2020      2      1
#> 
#> $`3`
#>        a          b      c      d
#> 13  <NA>       <NA>   Var1   Var3
#> 14  <NA>       <NA> Unit/1 Unit/3
#> 15 Loc_3 25:11:2020      1   <NA>
#> 16 Loc_3 26:11:2020      2   <NA>
#> 17 Loc_3 27:11:2020      3      1

您可以通过以下方式将所有数据整齐地重新设置为长格式unpivotr：

library(unpivotr)
library(dplyr)
library(purrr)

map_dfr(s, 
        ~ as_cells(.x) %>% 
         behead("up", "var") %>% 
         behead("up", "uom") %>% 
         behead("left", "loc") %>% 
         behead("left", "date") %>% 
         # filter(!is.na(chr)) %>%  # do you need the NAs?
         mutate(value = as.numeric(chr)) %>% 
         select(var, uom, loc, date, value),
        .id = "df")

#> # A tibble: 18 x 6
#>    df    var   uom    loc   date       value
#>    <chr> <chr> <chr>  <chr> <chr>      <dbl>
#>  1 1     Var1  Unit/1 Loc_1 25:11:2020     1
#>  2 1     Var1  Unit/1 Loc_1 26:11:2020     2
#>  3 1     Var1  Unit/1 Loc_1 27:11:2020     3
#>  4 1     Var2  Unit/2 Loc_1 25:11:2020    NA
#>  5 1     Var2  Unit/2 Loc_1 26:11:2020    NA
#>  6 1     Var2  Unit/2 Loc_1 27:11:2020     1
#>  7 2     Var3  Unit/3 Loc_2 25:11:2020    NA
#>  8 2     Var3  Unit/3 Loc_2 26:11:2020     1
#>  9 2     Var3  Unit/3 Loc_2 27:11:2020     2
#> 10 2     Var1  Unit/1 Loc_2 25:11:2020    NA
#> 11 2     Var1  Unit/1 Loc_2 26:11:2020    NA
#> 12 2     Var1  Unit/1 Loc_2 27:11:2020     1
#> 13 3     Var1  Unit/1 Loc_3 25:11:2020     1
#> 14 3     Var1  Unit/1 Loc_3 26:11:2020     2
#> 15 3     Var1  Unit/1 Loc_3 27:11:2020     3
#> 16 3     Var3  Unit/3 Loc_3 25:11:2020    NA
#> 17 3     Var3  Unit/3 Loc_3 26:11:2020    NA
#> 18 3     Var3  Unit/3 Loc_3 27:11:2020     1

如果您不希望最后有一个唯一的数据帧，请使用map代替map_dfr并删除, .id = "df"