Question

数据：

df = structure(list(obs_date = structure(c(17728, 17759, 17750, 17751, 
                                    17759, 17777, 17778, 17779, 17780, 17751, 17759, 17773, 17779, 
                                    17759, 17773, 17777, 17784, 17722, 17759, 17750, 17759, 17724, 
                                    17759, 17760, 17780, 17781, 17740, 17759, 17779, 17780, 17777, 
                                    17759, 17765, 17759, 17760, 17766, 17774, 17750, 17759, 17779, 
                                    17740, 17759, 17779, 17716, 17732, 17735, 17736, 17760, 17740, 
                                    17759, 17765), class = "Date", tzone = "Australia/Sydney"), 
             obs_value = c(0.104669, 0.109833, 0.196295, 0.2, 0.21, 0.21422, 0.21, 0.202339, 0.2, 
                           0.24, 0.24, 0.25, 0.24, 0.209645, 0.204462, 0.204462, 0.2042, 
                           NA, NA, 0.204, 0.224486, 0.142, 0.142, 0.144, 0.144, 0.15, NA, 
                           0.22, 0.22, 0.22, 0.23, 0.208, 0.208, 0.213781, 0.213781, 0.23111, 
                           0.23111, 0.2, 0.190581, 0.188411, 0.318, 0.208, 0.204, 0.31, 
                           0.31, 0.21, 0.21, 0.21, 0.25, 0.21, 0.21), 
             obs_id = c("2HN", "2HN", "4GJ", "4GJ", "4GJ", "4GJ", "4GJ", "4GJ", "4GJ", "KFM", 
                        "KFM", "KFM", "KFM", "N9S", "N9S", "N9S", "N9S", "NF7", "NF7", 
                        "7Q6", "7Q6", "M6Q", "M6Q", "M6Q", "M6Q", "M6Q", "MW6", "YP0", 
                        "YP0", "YP0", "ZG9", "D14", "D14", "MDY", "MDY", "MDY", "MDY", 
                        "G3S", "G3S", "G3S", "J6Z", "J6Z", "J6Z", "6RU", "6RU", "6RU", 
                        "6RU", "6RU", "6ZE", "6ZE", "6ZE")), class = "data.frame", row.names = c(NA, -51L))

在数据帧df中：

obs_id是估计变量的特定值的个人。 obs_value是此人观察到的值。观察会一直持续到根据观察日期记录新观察为止。

观察结果的图显示如下：

library(plotly)
plot_ly(data = df, x = ~obs_date, y = ~obs_value, 
            type = 'scatter', mode = 'lines', 
            line = list(shape = "hvh"),
            color = ~obs_id)

问题：有没有办法在同一张图表中叠加/显示中值/平均观察值（在整个观察期内）？

Answer 1

您可以尝试tidyverse

library(tidyverse)
df %>%
  group_by(obs_id) %>% 
  mutate(start = min(obs_date),
         end= max(obs_date), 
         Mean = mean(obs_value, na.rm = T)) %>% 
  ggplot(aes(obs_date, obs_value,color= obs_id)) + 
    geom_point() + 
    geom_segment(data= . %>% distinct(obs_id, start, end, Mean), 
                 aes(x=start, xend = end, y = Mean, yend =Mean))

然后，您可以尝试使用library(plotly);ggplotly(the_plot)

将图转换为图

根据您的评论，您可以尝试

df %>%
  group_by(obs_id) %>% 
  mutate(start = min(obs_date),
         end= max(obs_date), 
         Mean = mean(obs_value, na.rm = T)) %>% 
  ggplot(aes(obs_date, obs_value)) + 
  geom_point(aes(color= obs_id)) + 
  stat_summary(fun.y = "mean", geom="bar", alpha=0.2)

绘制一组观测值的均值或中位数

1 个答案: