如何将R中分类数据的宽数据框架转变为分层数据结构？

Question

我有一个像这样的数据框：

wide_df <- data.frame(
  kingdom = c("Animalia", "Animalia", "Plantae", "Plantae"),
  phylum = c("Chordata", "Chordata", "Angiosperms", "Angiosperms"),
  class = c("Mammalia", "Mammalia", "Dicotyledons", "Dicotyledons"),
  order = c("Carnivora", "Carnivora", "Rosales", "Solanales"),
  family = c("Felidae", "Canidae", "Rosaceae", "Solanaceae"),
  count = c(2, 3, 1, 4)
)

> wide_df
   kingdom      phylum        class     order     family count
1 Animalia    Chordata     Mammalia Carnivora    Felidae    2
2 Animalia    Chordata     Mammalia Carnivora    Canidae    3
3  Plantae Angiosperms Dicotyledons   Rosales   Rosaceae    1
4  Plantae Angiosperms Dicotyledons Solanales Solanaceae    4

我想更改数据结构，使其看起来像这样：

hierarchical_df <- data.frame(
  name = c("Animalia",
           "Animalia",
           "Animalia",
           "Animalia",
           "Animalia",
           "Chordata",
           "Chordata",
           "Chordata",
           "Chordata",
           "Chordata",
           "Mammalia",
           "Mammalia",
           "Mammalia",
           "Mammalia",
           "Mammalia",
           "Carnivora",
           "Carnivora",
           "Carnivora",
           "Carnivora",
           "Carnivora",
           "Felidae",
           "Felidae",
           "Canidae",
           "Canidae",
           "Canidae",
           "Plantae",
           "Plantae",
           "Plantae",
           "Plantae",
           "Plantae",
           "Angiosperms",
           "Angiosperms",
           "Angiosperms",
           "Angiosperms",
           "Angiosperms",
           "Dicotyledons",
           "Dicotyledons",
           "Dicotyledons",
           "Dicotyledons",
           "Dicotyledons",
           "Rosales",
           "Solanales",
           "Solanales",
           "Solanales",
           "Solanales",
           "Rosaceae",
           "Solanaceae",
           "Solanaceae",
           "Solanaceae",
           "Solanaceae"),
  parent = c(NA,
             NA,
             NA,
             NA,
             NA,
             "Animalia",
             "Animalia",
             "Animalia",
             "Animalia",
             "Animalia",
             "Chordata",
             "Chordata",
             "Chordata",
             "Chordata",
             "Chordata",
             "Mammalia",
             "Mammalia",
             "Mammalia",
             "Mammalia",
             "Mammalia",
             "Carnivora",
             "Carnivora",
             "Carnivora",
             "Carnivora",
             "Carnivora",
             NA,
             NA,
             NA,
             NA,
             NA,
             "Plantae",
             "Plantae",
             "Plantae",
             "Plantae",
             "Plantae",
             "Angiosperms",
             "Angiosperms",
             "Angiosperms",
             "Angiosperms",
             "Angiosperms",
             "Dicotyledons",
             "Dicotyledons",
             "Dicotyledons",
             "Dicotyledons",
             "Dicotyledons",
             "Rosales",
             "Solanales",
             "Solanales",
             "Solanales",
             "Solanales"))


hierarchical_df
           name       parent
1      Animalia         <NA>
2      Animalia         <NA>
3      Animalia         <NA>
4      Animalia         <NA>
5      Animalia         <NA>
6      Chordata     Animalia
7      Chordata     Animalia
8      Chordata     Animalia
9      Chordata     Animalia
10     Chordata     Animalia
11     Mammalia     Chordata
12     Mammalia     Chordata
13     Mammalia     Chordata
14     Mammalia     Chordata
15     Mammalia     Chordata
16    Carnivora     Mammalia
17    Carnivora     Mammalia
18    Carnivora     Mammalia
19    Carnivora     Mammalia
20    Carnivora     Mammalia
21      Felidae    Carnivora
22      Felidae    Carnivora
23      Canidae    Carnivora
24      Canidae    Carnivora
25      Canidae    Carnivora
26      Plantae         <NA>
27      Plantae         <NA>
28      Plantae         <NA>
29      Plantae         <NA>
30      Plantae         <NA>
31  Angiosperms      Plantae
32  Angiosperms      Plantae
33  Angiosperms      Plantae
34  Angiosperms      Plantae
35  Angiosperms      Plantae
36 Dicotyledons  Angiosperms
37 Dicotyledons  Angiosperms
38 Dicotyledons  Angiosperms
39 Dicotyledons  Angiosperms
40 Dicotyledons  Angiosperms
41      Rosales Dicotyledons
42    Solanales Dicotyledons
43    Solanales Dicotyledons
44    Solanales Dicotyledons
45    Solanales Dicotyledons
46     Rosaceae      Rosales
47   Solanaceae    Solanales
48   Solanaceae    Solanales
49   Solanaceae    Solanales
50   Solanaceae    Solanales

基本上，我试图将我的数据转换为一种形式，我可以使用它来使用此包制作桑基图（https://github.com/fbreitwieser/hiervis）。我试图对给定区域中不同分类群的个体生物体的数量进行可视化。数据集中有 40,000 多个观察值。

Answer 1

这里有一个方法。
您想要的是原始宽格式 df 仅在一列中，然后第二列是该列滞后。

tmp <- wide_df[rep(row.names(wide_df), wide_df$count), ]
long_df <- stack(tmp[-6])
long_df$parent <- dplyr::lag(long_df$values, sum(long_df$ind == "family"))
rm(tmp)
names(long_df)[1L] <- "name"
long_df <- long_df[-2L]

这是发布的想要的结果

identical

，但排序不同：

# check the result
i <- order(hierarchical_df$name)
j <- order(long_df$name)
tmp1 <- hierarchical_df[i, ]
tmp2 <- long_df[j, ]
row.names(tmp1) <- NULL
row.names(tmp2) <- NULL

identical(tmp1, tmp2)
#> [1] TRUE