R ggplot2：在堆积条形图中突出显示值

Question

我有一个名为 Participants10 的小型数据框（来自 dput()）：

structure(list(AUC_numeric = c(0.59, 0.68, 0.57, 0.59, 0.74, 
0.53, 0.63, 0.59, 0.62, 0.51, 0.78, 0.55, 0.5, 0.5, 0.61), AUC_Factor = structure(c(3L, 
2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L, 3L, 2L, 1L), .Label = c("aEMA", 
"pEMA", "fEMA"), class = "factor"), ParticipantNr = c(1L, 1L, 
1L, 2L, 2L, 2L, 3L, 3L, 3L, 4L, 4L, 4L, 5L, 5L, 5L), lab_ypos = c(0.295, 
0.93, 1.555, 0.295, 0.96, 1.595, 0.315, 0.925, 1.53, 0.255, 0.9, 
1.565, 0.25, 0.75, 1.305)), class = c("grouped_df", "tbl_df", 
"tbl", "data.frame"), row.names = c(NA, -15L), groups = structure(list(
    ParticipantNr = 1:5, .rows = list(1:3, 4:6, 7:9, 10:12, 13:15)), row.names = c(NA, 
-5L), class = c("tbl_df", "tbl", "data.frame"), .drop = TRUE))

使用 ggplot 我想创建一个这样的堆积条形图：

ggplot(data = Participants10, aes(x = ParticipantNr, y = AUC_numeric))+
  geom_col(aes(fill = factor(AUC_Factor), width = 0.5)) +
  geom_text(aes(y = lab_ypos, label = AUC_numeric, group = factor(AUC_Factor) ), color = "white", parse = T)+
  theme(legend.title = element_blank(), 
        panel.background = element_blank(),
        panel.grid = element_blank()) +
  coord_flip()

如何突出显示（例如，使用颜色、粗体文本或环绕边缘）每个 ParticipantNR 的堆叠条中的最高值？

Answer 1

可能有一个现有的包可能适合您的需求，但这是强调部分情节的一种方式。

您可以将您将在 aes() 中使用的值（如本示例中的大小和颜色）映射到您传递给 ggplot() 的数据框。

library(dplyr)
library(tibble)

Participants10 <- Participants10  %>% 
  mutate(ismax = AUC_numeric == max(AUC_numeric)) %>% 
  mutate(size = ifelse(ismax, 10, 4)) %>% #size for the text
  mutate(isline = ifelse(ismax, "grey25", NA)) %>%  #line around rectangle
  mutate(line = ifelse(ismax, 1.5, NA)) #whether to show the line around the rectangle or not

您可以稍后在使用 scales_*_identity() 指定中断时使用它们，它采用您要映射的各个值的命名向量。

Participants10 %>% 
  ggplot(aes(x = ParticipantNr, y = AUC_numeric)) +
  geom_col(aes(fill = factor(AUC_Factor),  col = isline, size = line)) + #added col and size here
  geom_text(aes(y = lab_ypos, label = AUC_numeric, group = factor(AUC_Factor), size = size), color = "white")+
  scale_size_identity(breaks = tibble::deframe(distinct(Participants10, ParticipantNr, size))) + #added scale for size
  scale_color_identity(breaks = tibble::deframe(distinct(Participants10, ParticipantNr, line))) + #added scale for color
  theme(legend.title = element_blank(), 
        panel.background = element_blank(),
        panel.grid = element_blank()) +
  coord_flip()

您可以根据输出的尺寸修改实际值。

Answer 2

一种方法是预先计算要突出显示的组。我会用dplyr:

在这里，我们将highlight 设置为"yes"，当它是每个ParticipantNr 的最大值时。然后我们可以使用scale_color_manual 根据highlight 变量改变文本颜色。

library(dplyr)
library(ggplot2)
Participants10 %>%
  group_by(ParticipantNr) %>%
  mutate(highligth = case_when(AUC_numeric == max(AUC_numeric) ~ "yes", 
                               TRUE ~ "no")) %>%
ggplot(aes(x = ParticipantNr, y = AUC_numeric)) +
  geom_col(aes(fill = factor(AUC_Factor), color = highligth),
           width = 0.5) +
  geom_text(aes(y = lab_ypos, label = AUC_numeric,
                group = factor(AUC_Factor),color = highligth )) +
  scale_color_manual(values = c("no" = "white", "yes" = "black"), guide = FALSE) + 
  theme(legend.title = element_blank(), 
        panel.background = element_blank(),
        panel.grid = element_blank()) +
  coord_flip()

不幸的是，由于条形区域之间的剪裁，轮廓选项看起来不太好。

Participants10 %>%
  group_by(ParticipantNr) %>%
  mutate(highligth = case_when(AUC_numeric == max(AUC_numeric) ~ "yes", 
                               TRUE ~ "no")) %>%
ggplot(aes(x = ParticipantNr, y = AUC_numeric)) +
  geom_col(aes(fill = factor(AUC_Factor), color = highligth), width = 0.5) +
  geom_text(aes(y = lab_ypos, label = AUC_numeric, group = factor(AUC_Factor),color = highligth ), parse = T) +
  scale_color_manual(values = c("no" = "white", "yes" = "black"), guide = FALSE) + 
  theme(legend.title = element_blank(), 
        panel.background = element_blank(),
        panel.grid = element_blank()) +
  coord_flip()