r - 从 dendextend::circlize_dendrogram() 的输出中提取簇颜色

Question

我正在尝试提取circlize_dendrogram. 这是一个示例代码：

library(magrittr)
library(dendextend)

cols <- c("#009000", "#FF033E", "#CB410B", "#3B444B", "#007FFF")
dend <- iris[1:40,-5] %>% dist %>% hclust %>% as.dendrogram    

dend <- color_branches(dend, k = 5, col = cols)
dend %<>% set("labels_col", value = cols, k= 5)
dend %<>% set("labels_cex", .8)
dend %<>% set("branches_lwd", 2)

circlize_dendrogram(dend)

以便使用 提取列表中的集群cutree(dend, k = 5)。有没有办法根据给定的提取树状图中簇的颜色cols？grid我需要它来使用包在图中插​​入图例。

示例，图例：簇 1 - #009000; 集群 2 - #FF033E; 集群 3 - #CB410B; 集群 4 - #3B444B; 集群 5 - #007FFF。的问题circlize_dendrogram是用于集群的颜色顺序不同。

虽然我可以手动执行此操作，但如果我可以自动执行此操作会很有效。如果我可以提取集群的颜色，这是可能的。

Answer 1

好的，这是一个非常hacky的解决方案。我相信还有更好的，但这是第一次尝试，所以请耐心等待。

这个想法是在dend对象（内部是一个列表）中搜索相应的元素名称（在这种情况下只是数字）并提取相应的颜色，将其保存在数据框中并将其用作图例。

# First we'll extract the elements and corresponding categories...
categories <- cutree(dend, k = 5)

# ... and save them in a data frame
categories_df <- data.frame(elements = as.numeric(names(categories)),
       categories = categories, 
       color = NA)

# now here's a little function that extracts the color for each element
# from the 'dend' object. It uses the list.search() function from the
# 'rlist' package

library(rlist)

extract_color <- function(element_no, dend_obj) {
  dend.search <- list.search(dend_obj, all(. == element_no))
  color <- attr(dend.search[[1]], "edgePar")$col
  return(color)
}

# I use 'dplyr' to manipulate the data
library(dplyr)

categories_df <- categories_df %>% 
  group_by(elements) %>% 
  mutate(color = extract_color(elements, dend))

现在这给了我们以下数据框：

> categories_df
Source: local data frame [40 x 3]
Groups: elements [40]

   elements categories   color
      (dbl)      (int)   (chr)
1         1          1 #CB410B
2         2          1 #CB410B
3         3          1 #CB410B
4         4          1 #CB410B
5         5          1 #CB410B
6         6          2 #009000
7         7          1 #CB410B
8         8          1 #CB410B
9         9          3 #007FFF
10       10          1 #CB410B
..      ...        ...     ...

我们可以将其总结为只有类别颜色的数据框，例如

legend_data <- categories_df %>% 
  group_by(categories) %>% 
  summarise(color = unique(color))

> legend_data
Source: local data frame [5 x 2]

  categories   color
       (int)   (chr)
1          1 #CB410B
2          2 #009000
3          3 #007FFF
4          4 #FF033E
5          5 #3B444B

现在很容易生成图例：

circlize_dendrogram(dend)
legend(-1.05, 1.05, legend = legend_data$categories, fill = legend_data$color, cex = 0.7)

这给了你：

您可以使用cutree(dend, k = 5)来确认类别颜色的数字对应于每个元素的类别。

Answer 2

除了菲利克斯的解决方案，我想发布我自己的答案：

library(magrittr)
library(grid)
library(gridExtra)
library(dendextend)

cols <- c("#009000", "#FF033E", "#CB410B", "#3B444B", "#007FFF")
dend <- iris[1:40,-5] %>% dist %>% hclust %>% as.dendrogram    

dend <- color_branches(dend, k = 5, col = cols)
dend %<>% set("labels_col", value = cols, k= 5)
dend %<>% set("labels_cex", .8)
dend %<>% set("branches_lwd", 2)

clust <- cutree(dend, k = 5)
colors <- labels_colors(dend)[clust %>% sort %>% names]
clust_labs <- colors %>% unique

circlize_dendrogram(dend)
grid.circle(x = .95, y = .9, r = .02, gp = gpar(fill = clust_labs[1])) 
grid.circle(x = .95, y = .85, r = .02, gp = gpar(fill = clust_labs[2]))
grid.circle(x = .95, y = .8, r = .02, gp = gpar(fill = clust_labs[3]))
grid.circle(x = .95, y = .75, r = .02, gp = gpar(fill = clust_labs[4]))
grid.circle(x = .95, y = .7, r = .02, gp = gpar(fill = clust_labs[5]))

grid.text(x = .95, y = .9, label = expression(bold(1)), gp = gpar(fontsize = 9, col = "white"))
grid.text(x = .95, y = .85, label = expression(bold(2)), gp = gpar(fontsize = 9, col = "white"))
grid.text(x = .95, y = .8, label = expression(bold(3)), gp = gpar(fontsize = 9, col = "white"))
grid.text(x = .95, y = .75, label = expression(bold(4)), gp = gpar(fontsize = 9, col = "white"))
grid.text(x = .95, y = .7, label = expression(bold(5)), gp = gpar(fontsize = 9, col = "white"))
grid.text(x = .91, y = .8, label = "CLUSTERS", rot = 90, gp = gpar(fontsize = 9))