r - 如何根据ggplot/R中的不同数据源将不同的箱线图添加到同一图中？

请在下面找到 My Data。请注意，下图是我希望复制的设计示例，与 My Data 没有特别关联。
My Data 存储在 p 中。我有一个连续的协变量 p$ki67pro，它指定肿瘤样本中活跃 split 的细胞百分比(因此，范围从 0 到 100)。我有肿瘤的三个不同阶段，对应于 p$WHO.Grade==1,2,3 。每个样本代表一个有复发( p$recurrence==1 )或没有( p$recurrence==0 )复发的肿瘤患者。

所以:

head(p)
   WHO.Grade recurrence ki67pro
1          1          0       1
2          2          0      12
3          1          0       3
9          1          0       3
10         1          0       5
11         1          0       3

我希望生成下面的箱线图。如您所见，有四个点对应于每个 p$WHO.Grade 和 All samples 。每个 p$WHO.Grade + All 有两个箱线图。



根据 p$WHO.Grade 和 All ，我想要一个箱线图代表复发性肿瘤的 p$ki67pro ( p$recurrence==1 )，另一个箱线图代表非复发性肿瘤的 p$ki67pro ( p$recurrence==0 )。

IE。
p$ki67pro[p$WHO.Grade==1 & p$recurrence==0] 与
p$ki67pro[p$WHO.Grade==1 & p$recurrence==1]p$ki67pro[p$WHO.Grade==2 & p$recurrence==0] 与
p$ki67pro[p$WHO.Grade==2 & p$recurrence==1]p$ki67pro[p$WHO.Grade==3 & p$recurrence==0] 与
p$ki67pro[p$WHO.Grade==3 & p$recurrence==1]
对于 Allp$ki67pro[p$recurrence==0] 与p$ki67pro[p$recurrence==1]
到目前为止，我已经使用了以下脚本，但我可以弄清楚如何包含 All。请注意，只有一种情况 p$WHO.Grade==3

df <- data.frame(x = as.factor(c(p$WHO.Grade)),
                 y = c(p$ki67pro),
                 f = rep(c("ki67pro"), c(nrow(p))))

df <- df[!is.na(df$x),]
ggplot(df) +
  geom_boxplot(aes(x, y, fill = f, colour = f), outlier.alpha = 0, position = position_dodge(width = 0.78)) +
  scale_x_discrete(name = "", label=c("WHO-I","WHO-II","WHO-III","All")) +
  scale_y_continuous(name="x", breaks=seq(0,30,5), limits=c(0,30)) +
  stat_boxplot(aes(x, y, colour = f), geom = "errorbar", width = 0.3,position = position_dodge(0.7753)) +
  geom_point(aes(x, y, fill = f, colour = f), size = 3, shape = 21, position = position_jitterdodge()) +
  scale_fill_manual(values = c("#edf1f9", "#fcebeb"), name = "",
                    labels = c("", "")) +
  scale_colour_manual(values = c("#1C73C2", "red"), name = "",
                      labels = c("","")) + theme(legend.position="none")

My Data p

p <- structure(list(WHO.Grade = c(1L, 2L, 1L, 1L, 1L, 1L, 3L, 2L,
1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), recurrence = c(0L, 0L, 0L, 0L, 0L,
0L, 1L, 0L, 0L, 0L, 1L, 0L, 0L, 1L, 0L, 1L, 0L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 0L, 1L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L, 1L, 0L, 0L, 0L,
1L, 1L, 0L, 1L, 0L, 0L, 1L, 1L, 1L, 0L, 1L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 1L, 0L, 0L, 0L,
1L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L, 0L, 0L,
0L, 0L, 0L, 0L, 0L, 1L, 0L, 0L, 0L, 0L), ki67pro = c(1L, 12L,
3L, 3L, 5L, 3L, 20L, 25L, 7L, 4L, 5L, 12L, 3L, 15L, 4L, 5L, 7L,
8L, 3L, 12L, 10L, 4L, 10L, 7L, 3L, 2L, 3L, 7L, 4L, 7L, 10L, 4L,
5L, 5L, 3L, 5L, 2L, 5L, 3L, 3L, 3L, 4L, 4L, 3L, 2L, 5L, 1L, 5L,
2L, 3L, 1L, 2L, 3L, 3L, 5L, 4L, 20L, 5L, 0L, 4L, 3L, 0L, 3L,
4L, 1L, 2L, 20L, 2L, 3L, 5L, 4L, 8L, 1L, 4L, 5L, 4L, 3L, 6L,
12L, 3L, 4L, 4L, 2L, 5L, 3L, 3L, 3L, 2L, 5L, 4L, 2L, 3L, 4L,
3L, 3L, 2L, 2L, 4L, 7L, 4L, 3L, 4L, 2L, 3L, 6L, 2L, 3L, 10L,
5L, 10L, 3L, 10L, 3L, 4L, 5L, 2L, 4L, 3L, 4L, 4L, 4L, 5L, 3L,
12L, 5L, 4L, 3L, 2L, 4L, 3L, 4L, 2L, 1L, 6L, 1L, 4L, 12L, 3L,
4L, 3L, 2L, 6L, 5L, 4L, 3L, 4L, 4L, 4L, 3L, 5L, 4L, 5L, 4L, 1L,
3L, 3L, 4L, 0L, 3L)), class = "data.frame", row.names = c(1L,
2L, 3L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 18L, 19L, 20L,
21L, 22L, 23L, 24L, 25L, 26L, 27L, 28L, 29L, 30L, 31L, 32L, 33L,
34L, 35L, 36L, 37L, 38L, 39L, 40L, 41L, 44L, 45L, 46L, 47L, 48L,
49L, 50L, 51L, 52L, 53L, 54L, 55L, 57L, 59L, 60L, 61L, 62L, 63L,
64L, 65L, 66L, 67L, 68L, 69L, 70L, 71L, 72L, 73L, 74L, 75L, 76L,
77L, 78L, 79L, 80L, 81L, 82L, 83L, 84L, 85L, 87L, 89L, 90L, 91L,
92L, 93L, 94L, 96L, 97L, 98L, 99L, 100L, 101L, 102L, 103L, 104L,
105L, 106L, 107L, 109L, 110L, 111L, 112L, 113L, 114L, 115L, 116L,
117L, 118L, 119L, 120L, 121L, 123L, 124L, 125L, 126L, 127L, 128L,
130L, 131L, 132L, 133L, 134L, 135L, 136L, 137L, 138L, 139L, 140L,
141L, 142L, 143L, 144L, 145L, 146L, 147L, 148L, 149L, 150L, 151L,
152L, 153L, 154L, 155L, 156L, 157L, 158L, 159L, 160L, 161L, 162L,
163L, 164L, 165L, 166L, 167L, 168L, 169L, 170L, 171L, 172L, 173L,
174L, 175L))

最佳答案

可以使用的一个技巧是在 WHO.Grade 中创建一个新级别，因为它只有 3 个级别。这应该是一个临时级别，所以一个很好的方法是使用包 dplyr ，函数 mutate 。

请注意，无需创建新的数据帧 df 。

library(ggplot2)
library(dplyr)

p %>%
  bind_rows(p %>% mutate(WHO.Grade = 4)) %>%
  mutate(WHO.Grade = factor(WHO.Grade),
         recurrence = factor(recurrence)) %>%
  ggplot(aes(WHO.Grade, ki67pro,
             fill = recurrence, colour = recurrence)) +
  geom_boxplot(outlier.alpha = 0,
               position = position_dodge(width = 0.78, preserve = "single")) +
  geom_point(size = 3, shape = 21,
             position = position_jitterdodge()) +
  scale_x_discrete(name = "",
                   label = c("WHO-I","WHO-II","WHO-III","All")) +
  scale_y_continuous(name = "x", breaks=seq(0,30,5), limits=c(0,30)) +
  scale_fill_manual(values = c("#edf1f9", "#fcebeb"), name = "",
                    labels = c("", "")) +
  scale_colour_manual(values = c("#1C73C2", "red"), name = "",
                      labels = c("","")) +
  theme(legend.position="none")

关于r - 如何根据ggplot/R中的不同数据源将不同的箱线图添加到同一图中？，我们在Stack Overflow上找到一个类似的问题：https://stackoverflow.com/questions/57920622/