在ggplot2中对饼图切片进行排序

Question

我想对我的饼图标签和数据片段进行排序。我尝试过对标签进行排序，但是数据片段仍然没有被排序。感谢你的帮助。

data = structure(list(Stage = c("Collecting Applications", "Interview Stages", 
"Offer Accepted", "Offer in Progress", "To Open"), N = c(17L, 
30L, 8L, 2L, 65L), Prop = c(14, 25, 7, 2, 53), Label = c("14%", 
"25%", "7%", "2%", "53%")), row.names = c(NA, -5L), class = c("tbl_df", 
"tbl", "data.frame"))

data$Stage = factor(data$Stage, ordered = TRUE, 
                      levels = c("To Open", "Collecting Applications", "Interview Stages", "Offer in Progress", "Offer Accepted"))

library(dplyr)
data = data %>% 
    mutate(end = 2 * pi * cumsum(N)/sum(N),
           start = lag(end, default = 0),
           middle = 0.5 * (start + end),
           hjust = ifelse(middle > pi, 1, 0),
           vjust = ifelse(middle < pi/2 | middle > 3 * pi/2, 0, 1))
data = data[order(data$Stage), ]
  
  
library(ggforce)
library(ggplot2)

ggplot(data) + 
    geom_arc_bar(aes(x0 = 0, y0 = 0, r0 = 0, r = 1,
                     start = start, end = end, fill = Stage)) +
    geom_text(aes(x = 1.05 * sin(middle), y = 1.05 * cos(middle), label = Label,
                  hjust = hjust, vjust = vjust)) +
    coord_fixed() +
    scale_x_continuous(limits = c(-1.5, 1.4),  # Adjust so labels are not cut off
                       name = "", breaks = NULL, labels = NULL) +
    scale_y_continuous(limits = c(-1.2, 1.2),      # Adjust so labels are not cut off
                       name = "", breaks = NULL, labels = NULL) +
    theme_void() +
    labs(title = paste0("Progress for ", sum(data$N), " Positions"),
         fill = NULL) +
    scale_fill_brewer(palette = "Blues")

- Gabriella

Answer 1

一个简单的修复，订单数据框行需要在hjust和vjust变异之前。虽然不完全确定背后的原因。如果有人知道，请解释一下。谢谢！

library(dplyr)
data$Stage = factor(data$Stage, ordered = TRUE, 
                      levels = c("To Open", "Collecting Applications", "Interview Stages", "Offer in Progress", "Offer Accepted"))
data = data[order(data$Stage), ]
data = data %>% 
    mutate(end = 2 * pi * cumsum(N)/sum(N),
           start = lag(end, default = 0),
           middle = 0.5 * (start + end),
           hjust = ifelse(middle > pi, 1, 0),
           vjust = ifelse(middle < pi/2 | middle > 3 * pi/2, 0, 1))
  
  
  
library(ggforce)
library(ggplot2)
  
ggplot(data) + 
    geom_arc_bar(aes(x0 = 0, y0 = 0, r0 = 0, r = 1,
                     start = start, end = end, fill = Stage)) +
    geom_text(aes(x = 1.05 * sin(middle), y = 1.05 * cos(middle), label = Label,
                  hjust = hjust, vjust = vjust)) +
    coord_fixed() +
    scale_x_continuous(limits = c(-1.5, 1.4),  # Adjust so labels are not cut off
                       name = "", breaks = NULL, labels = NULL) +
    scale_y_continuous(limits = c(-1.2, 1.2),      # Adjust so labels are not cut off
                       name = "", breaks = NULL, labels = NULL) +
    theme_void() +
    labs(title = paste0("Progress for ", sum(data$N), " Positions"),
         fill = NULL) +
    scale_fill_brewer(palette = "Blues")

- Gabriella

---

数据框需要尽早排序，以便cumsum按正确顺序对数字求和。但是，在factor()调用中不需要使用ordered = TRUE - 令人困惑的是，所有因子都有其级别的顺序，ordered = TRUE是为特殊情况而设计的，例如您可能想要使用<或者您想在模型中使用特定的对比。 - Gregor Thomas

如果您愿意，您可以使用dplyr语法，并使用data %>% mutate(Stage = factor(Stage, levels = ...)) %>% arrange(Stage) %>% mutate(...)来保留所有内容。 - Gregor Thomas

感谢您的解释和建议！ - Gabriella