ggplot2中帶有分組密度線的直方圖

對于ggplot2比我更熟悉的人來說，這可能是一項簡單的任務。我有這種型別的資料，increase_max按 分組role，它有兩個級別：

df <- structure(list(role = c("Recipient", "Speaker", "Recipient", 
                           "Recipient", "Recipient", "Speaker", "Recipient", "Recipient", 
                           "Speaker", "Speaker", "Recipient", "Speaker", "Recipient", "Recipient", 
                           "Recipient", "Speaker", "Recipient", "Speaker", "Recipient", 
                           "Speaker", "Recipient", "Recipient", "Speaker", "Recipient", 
                           "Recipient", "Speaker", "Speaker", "Speaker", "Recipient", "Speaker", 
                           "Speaker", "Recipient", "Speaker", "Recipient", "Recipient", 
                           "Speaker", "Recipient", "Recipient", "Recipient", "Speaker", 
                           "Speaker", "Recipient", "Speaker", "Recipient", "Speaker", "Recipient", 
                           "Speaker", "Speaker", "Recipient", "Recipient", "Speaker", "Recipient", 
                           "Recipient", "Speaker", "Recipient", "Recipient", "Recipient", 
                           "Speaker", "Recipient", "Speaker", "Recipient", "Speaker", "Recipient", 
                           "Recipient", "Speaker", "Recipient", "Recipient", "Speaker", 
                           "Recipient", "Recipient", "Recipient", "Speaker", "Recipient", 
                           "Speaker", "Recipient", "Speaker", "Recipient", "Recipient", 
                           "Recipient", "Recipient", "Speaker", "Recipient", "Recipient", 
                           "Recipient", "Speaker", "Recipient", "Speaker", "Recipient", 
                           "Recipient", "Speaker", "Recipient", "Recipient", "Speaker", 
                           "Recipient", "Recipient", "Recipient", "Speaker", "Recipient", 
                           "Speaker", "Recipient"), increase_max = c(0.008, 0.118, NA, NA, 
                                                                     NA, 0.209, NA, 0.001, 0.111, NA, NA, NA, NA, NA, 0.007, 0.002, 
                                                                     0.006, 0.255, 0.009, NA, 0.004, 0.232, NA, 0.007, 0.004, 0.095, 
                                                                     0.09, NA, 0.002, NA, 0.05, NA, 0.02, 0.045, 0.002, NA, NA, 0.005, 
                                                                     0.012, NA, 0.037, NA, 0.066, NA, 0.019, 0.002, 0.136, NA, 0.003, 
                                                                     NA, 0.128, 0.004, 0.003, NA, NA, NA, 0.03, 0.042, NA, 0.138, 
                                                                     0.139, 0.126, 0.002, NA, 0.005, NA, 0.002, 0.01, 0.001, NA, 0.005, 
                                                                     0.003, NA, NA, 0.002, NA, 0.005, NA, NA, 0.015, 0.007, 0.021, 
                                                                     NA, NA, NA, NA, NA, 0.171, 0.02, 0.036, 0.026, 0.001, 0.033, 
                                                                     0.127, 0.339, 0.075, 0.037, 0.083, NA, 0.041)), class = c("tbl_df", 
                                                                                                                               "tbl", "data.frame"), row.names = c(NA, -100L))

我制作情節的方式至少基本上是有效的，但肯定是完全笨拙和復雜的：

# variable 1:
speaker_0 <- df %>%
  filter(!is.na(increase_max)
         & role == "Speaker") %>%
  pull(increase_max)

# variable 2:
recipient_0 <- df %>%
  filter(!is.na(increase_max)
         & role == "Recipient") %>%
  pull(increase_max)

# subset both variables on certain range:
speaker <- data.frame(Max_EDA_increase = speaker_0[speaker_0 >= 0.05 & speaker_0 <= 0.5])
recipient <- data.frame(Max_EDA_increase = recipient_0[recipient_0 >= 0.05 & recipient_0 <= 0.5])

# bind together:
both <- rbind(speaker, recipient)

# plot histogram with density lines:
ggplot(both, aes(x = Max_EDA_increase))   
  geom_histogram(aes(y = after_stat(density)), data = speaker, fill = "red", alpha = 0.35, binwidth = 0.05)   
  geom_line(data = speaker, color = "red", stat = "density", alpha = 0.35)  
  geom_histogram(aes(y = after_stat(density)), data = recipient, fill = "blue", alpha = 0.35, binwidth = 0.05)  
  geom_line(data = recipient, color = "blue", stat = "density", alpha = 0.35)

結果圖：

我確定一定有更直接的方法來生成繪圖，它還添加了一個圖例來區分兩組/兩條密度線！

uj5u.com熱心網友回復：

我認為讓這個不那么笨重的方法是不要按角色拆分組合。您可以過濾一次資料，然后設定fill = role或colour = role。

library(ggplot2)

# Omitted for brevity
# df <- structure(...)

df2 <- subset(df, !is.na(increase_max) & 
                increase_max >= 0.05 & 
                increase_max <= 0.5)
ggplot(df2, aes(x = increase_max))  
  geom_histogram(aes(y = after_stat(density), fill = role),
                 binwidth = 0.05, position = "identity",
                 alpha = 0.35)  
  geom_density(aes(colour = role))  
  scale_colour_manual(
    aesthetics = c("fill", "colour"),
    values = c("blue", "red")
  )

^{由reprex 包(v2.0.1)于 2021 年 12 月 14 日創建}

標籤：r ggplot2

上一篇：有沒有辦法回傳滿足設定標準的資料百分比？

下一篇：在向量中添加缺失值