Y 轴显示 ggplot 中结合的 geom_密度 和 geom_histogram 的计数

Question

通过下面的玩具数据和示例代码，我试图制作两个相同的多面图（除了颜色及其 x 值）。

我想制作一个直方图并在顶部叠加一条密度曲线。当我这样做时，如下所示，它似乎用密度范围替换了 geom_histogram y 轴（如果我单独使用 geom_histogram ，它应该是计数）。

有没有办法强制 y 轴显示直方图中的原始计数？

第二个问题是，是否有人对如何随后使两个图中的 y 轴在其范围内相同有建议，这样我就不必在右侧图中重复 y 轴刻度/标签，这将很优秀。谢谢。

library(patchwork)
library(tidyverse)

p1 <- ggplot(d, aes(x = hours)) +
  geom_histogram(aes(y = ..density..), 
                binwidth = 10, 
                fill = "goldenrod", alpha = 0.3, color = "black") +
  geom_density(aes(y = ..density..), 
               color = "dodgerblue3", lwd = 1) +  
  facet_wrap(~condition) +
  scale_x_continuous(breaks = seq(10, 90, by = 10),
                     expand = c(0, 0)) +
  labs(title = "Hours")

p2 <- ggplot(d, aes(x = money)) +
  geom_histogram(aes(y = ..density..), 
                binwidth = 10, 
                fill = "palegreen2", alpha = 0.3, color = "black") +
  geom_density(aes(y = ..density..), 
               color = "pink2", lwd = 1) +  
  facet_wrap(~condition) +
  scale_x_continuous(breaks = seq(10, 90, by = 10),
                     expand = c(0, 0)) +
  labs(title = "Money",
       y = NULL)

p1 + p2

d<-structure(list(hours = c(70, 10, 20, 10, 50, 10, 
50, 60, 50, 70, 40, 90, 40, 60, 70, 40, 50, 60, 80, 10, 90, 50, 
40, 40, 70, 50, 40, 10, 80, 70, 70, 90, 20, 10, 60, 90, 10, 20, 
90, 70, 30, 60, 90, 60, 90, 20, 20, 20, 10, 40), money = c(60, 
70, 10, 10, 40, 30, 40, 40, 50, 80, 90, 70, 50, 60, 80, 20, 10, 
90, 20, 40, 90, 40, 30, 60, 40, 60, 70, 90, 10, 20, 80, 90, 80, 
60, 70, 70, 60, 50, 60, 90, 90, 80, 60, 40, 30, 80, 30, 20, 60, 
20), condition = structure(c(4L, 5L, 5L, 5L, 5L, 2L, 4L, 4L, 
2L, 3L, 5L, 3L, 5L, 4L, 3L, 5L, 2L, 3L, 4L, 3L, 2L, 3L, 3L, 2L, 
4L, 4L, 2L, 3L, 2L, 5L, 3L, 5L, 2L, 4L, 5L, 2L, 5L, 2L, 2L, 3L, 
5L, 2L, 3L, 5L, 5L, 5L, 4L, 2L, 3L, 5L), levels = c("condition_control", 
"conditionA", "conditionB", "conditionC", "conditionD"
), class = "factor")), class = c("grouped_df", "tbl_df", "tbl", 
"data.frame"), row.names = c(NA, -50L), groups = structure(list(
    condition = structure(2:5, levels = c("condition_control", 
    "conditionA", "conditionB", "conditionC", "conditionD"
    ), class = "factor"), .rows = structure(list(c(6L, 9L, 17L, 
    21L, 24L, 27L, 29L, 33L, 36L, 38L, 39L, 42L, 48L), c(10L, 
    12L, 15L, 18L, 20L, 22L, 23L, 28L, 31L, 40L, 43L, 49L), c(1L, 
    7L, 8L, 14L, 19L, 25L, 26L, 34L, 47L), c(2L, 3L, 4L, 5L, 
    11L, 13L, 16L, 30L, 32L, 35L, 37L, 41L, 44L, 45L, 46L, 50L
    )), ptype = integer(0), class = c("vctrs_list_of", "vctrs_vctr", 
    "list"))), class = c("tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-4L), .drop = TRUE))

Answer 1

将每次出现的

..density..

替换为

after_stat(density * nrow(d))

以获取计数而不是密度。

p1 <- ggplot(d, aes(x = hours)) +
  geom_histogram(aes(y = after_stat(density * nrow(d))), 
                 binwidth = 10, 
                 fill = "goldenrod", alpha = 0.3, color = "black") +
  geom_density(aes(y = after_stat(density * nrow(d))), 
               color = "dodgerblue3", lwd = 1) +  
  facet_wrap(~condition) +
  scale_x_continuous(breaks = seq(10, 90, by = 10),
                     expand = c(0, 0)) +
  labs(title = "Hours")
p1

p2 <- ggplot(d, aes(x = money)) +
  geom_histogram(aes(y = after_stat(density * nrow(d))), 
                 binwidth = 10, 
                 fill = "palegreen2", alpha = 0.3, color = "black") +
  geom_density(aes(y = after_stat(density * nrow(d))), 
               color = "pink2", lwd = 1) +  
  facet_wrap(~condition) +
  scale_x_continuous(breaks = seq(10, 90, by = 10),
                     expand = c(0, 0)) +
  labs(title = "Money",
       y = NULL)

p1 + p2