1

该代码使用计算的每周回归线绘制数据。我想将图例与根据每周斜率计算的每周翻倍时间结合起来。

很高兴解决问题：我可以使用 geom_smooth 获得每周回归线。但是，我无法从 geom_smooth 中提取斜率系数（计算倍增时间）。因此，我不得不在 ggplot 部分之外进行等效回归。
有什么建议可以更优雅地做到这一点吗？

主要问题：如何将图例与计算的倍增时间列结合起来？经过大量的摆弄，我可以将图例放在这些计算出的倍增时间旁边。它看起来不太好，当我包含另一个数据点时，我不得不重新开始摆弄。建议将不胜感激。谢谢你。

library(ggplot2)
library(gridExtra)

# Input data: Daily number of cases starting at day0 
cases <- c(1,1,2,3,7,10,13,16,24,38,51,62,85,116,150,202,240,274,402,554,709, 927) 
day0 <- as.Date("2020-03-04")

# actual dates by counting from day0
dates <- day0 + 1:length(cases) 

# week number as factor to obtain regression line for each week
week <- as.factor(1 + (1:length(cases) ) %/% 7)

# tibble with daily data, also with week number 
datatib <- tibble( dates, cases, week)

# tibble with computed doubling time per week
resulttib <- tibble(Week=unique(week), Doubling_Time=NA)

# linear regression on log of dependent variable
for (wk in unique(week) ) {
  resulttib[wk,'Doubling_Time'] <- 
    round( log(2) / lm(log(cases) ~ dates, data=datatib[week==wk,] )$coef['dates'], 2 )
}

# insert row at top for second line of column heading
resulttib <- add_row(resulttib, Week = '', Doubling_Time = '(days)', .before = 1) 

doublingtime = tableGrob(resulttib[,'Doubling_Time'], rows=NULL)

gp <- 
  ggplot(datatib, aes(dates, cases, color = week ) ) +
  geom_point() +
  geom_smooth( method = "lm", se = FALSE) +
  scale_x_date() +
  scale_y_continuous(trans="log10") +
  labs(x = "", y = "Number of Cases") +
  ggtitle("Number of Cases with Weekly Doubling Times") +
  theme(plot.title = element_text(hjust = 0.5)) +

  theme(legend.position=c(0.75,0), 
        legend.justification=c(1.2, -0.1), legend.text=element_text(size=14) ) +
  annotation_custom( doublingtime, 
      xmin=dates[length(cases)]-2, xmax=dates[length(cases)], ymin=-2.65 )

e

4

1 回答 1

1

作为对您的主要问题的回答……试试这个。我只是将加倍时间加入到您的主 df 中，并创建了一个新的 var 组合 no。周和倍增时间。然后将颜色映射到这个新变量上。

关于第二个问题：有一些方法可以根据 geom_smooth/stat_smooth 的计算值计算斜率。但是，在我看来，您计算斜率的方法是解决您要解决的问题的更简单方法。

library(ggplot2)
library(dplyr)
library(gridExtra)

# Input data: Daily number of cases starting at day0 
cases <- c(1,1,2,3,7,10,13,16,24,38,51,62,85,116,150,202,240,274,402,554,709, 927) 
day0 <- as.Date("2020-03-04")

# actual dates by counting from day0
dates <- day0 + 1:length(cases) 

# week number as factor to obtain regression line for each week
week <- as.factor(1 + (1:length(cases) ) %/% 7)

# tibble with daily data, also with week number 
datatib <- tibble( dates, cases, week)

# tibble with computed doubling time per week
resulttib <- tibble(Week=unique(week), Doubling_Time=NA)

# linear regression on log of dependent variable
for (wk in unique(week) ) {
  resulttib[wk,'Doubling_Time'] <- 
    round( log(2) / lm(log(cases) ~ dates, data=datatib[week==wk,] )$coef['dates'], 2 )
}

# insert row at top for second line of column heading
#resulttib <- add_row(resulttib, Week = '', Doubling_Time = '(days)', .before = 1) 

#doublingtime = tableGrob(resulttib[,'Doubling_Time'], rows=NULL)

datatib1 <- datatib %>% 
  left_join(resulttib, by = c("week" = "Week")) %>% 
  mutate(week1 = paste0(week, " (", Doubling_Time, ")"))

gp <- 
  ggplot(datatib1, aes(dates, cases, color = week1 ) ) +
  geom_point() +
  geom_smooth( method = "lm", se = FALSE) +
  scale_x_date() +
  scale_y_continuous(trans="log10") +
  labs(x = "", y = "Number of Cases") +
  ggtitle("Number of Cases with Weekly Doubling Times") +
  theme(plot.title = element_text(hjust = 0.5)) +
  theme(
    legend.position = c(.95, .05),
    legend.justification = c("right", "bottom"),
    legend.box.just = "right",
    legend.margin = margin(6, 6, 6, 6)
  ) +
  labs(color = "Week (Doubling time in days)")

gp

由reprex 包（v0.3.0）于 2020 年 3 月 27 日创建

于 2020-03-27T08:21:48.937 回答