根据aes仅使用数据子集在ggplot中进行计算

Question

大家好，我想用我的

geom_boxplot

中的唯一 ID 来标记异常值。一般来说，我使用这个公式（无论数据列是什么）就是我想要的id：

plot +
  geom_text(aes(label = ifelse((whatever > 
                                  (quantile(whatever, 0.75) + 1.5 * IQR(whatever, 0.25))) |
                                 (whatever < 
                                    (quantile(whatever, 0.25) - 1.5 * IQR(whatever, 0.25))),
                               id, '')),
            hjust = -1)

如果我只有一个箱线图（plot_all），这效果很好。但是，如果我用一个值（例如

sex

）分隔箱线图，则异常值是根据整个日期而不是数据子集计算的。无论如何，我可以转发选定的数据来仅计算这些数据吗？

rm(list=ls())

library(tidyverse)
library(ggplot2)
library(ggbeeswarm)

set.seed(1)

male <- tibble(sex = sample('male', 1000, replace=TRUE),
               id = as.character(1:1000),
               whatever = c(runif(998, min = .75, max = 1.25), 0, 2))

female <- tibble(sex = sample('female', 1000, replace=TRUE),
                 id = as.character(1001:2000),
                 whatever = c(runif(998, min = 1.25, max = 1.75), .5, 2.5))

data <- bind_rows(male, female)

plot_all <- ggplot(data, aes("all", whatever)) +
  geom_boxplot() +
  geom_quasirandom(size = .3, alpha = .3) +
  geom_text(aes(label = ifelse((whatever > 
                                  (quantile(whatever, 0.75) + 1.5 * IQR(whatever, 0.25))) |
                                 (whatever < 
                                    (quantile(whatever, 0.25) - 1.5 * IQR(whatever, 0.25))),
                               id, '')),
            hjust = -1)

plot_sex <- ggplot(data, aes(sex, whatever)) +
  geom_boxplot() +
  geom_quasirandom(size = .3, alpha = .3) +
  geom_text(aes(label = ifelse((whatever > 
                                  (quantile(whatever, 0.75) + 1.5 * IQR(whatever, 0.25))) |
                                 (whatever < 
                                    (quantile(whatever, 0.25) - 1.5 * IQR(whatever, 0.25))),
                               id, '')),
            hjust = -1)

Answer 1

可以通过操作图层数据来做到这一点，但为什么要这么做呢？只需在进入 ggplot 的过程中修改数据即可：

data %>%
  group_by(sex) %>%
  mutate(label = ifelse(whatever > max(boxplot.stats(whatever)$stats) | 
                        whatever < min(boxplot.stats(whatever)$stats), 
                        id, '')) %>%
  ggplot(aes(sex, whatever)) +
  geom_boxplot() +
  geom_quasirandom(size = .3, alpha = .3) +
  geom_text(aes(label = label), hjust = -1)

这比更改图层数据（给出相同的结果）更整洁

  ggplot(data, aes(sex, whatever)) +
  geom_boxplot() +
  geom_quasirandom(size = .3, alpha = .3) +
  geom_text(data = . %>% group_by(sex) %>% filter((whatever > 
                                (quantile(whatever, 0.75) + 1.5 * IQR(whatever, 0.25))) |
                               (whatever < 
                               (quantile(whatever, 0.25) - 1.5 * IQR(whatever, 0.25)))), 
            aes(label = id), hjust = -1)

Answer 2

ave

即时进行每组计算：

library(ggplot2)
library(ggbeeswarm)

ggplot(data, aes(sex, whatever)) +
  geom_boxplot() +
  geom_quasirandom(size = .3, alpha = .3) +
  geom_text(
    aes(
      label = if_else(
        as.logical(
          ave(whatever, sex, FUN = \(x) {
            (x > (quantile(x, 0.75) + 1.5 * IQR(x, 0.25))) |
              (x < (quantile(x, 0.25) - 1.5 * IQR(x, 0.25)))
          })
        ),
        id,
        ""
      )
    ),
    hjust = -1
  )