ggplot2 中的回归线帮助

Question

我正在尝试将回归线添加到我的 ggplot 中。下面是我用来制作绘图的代码。我想在第一个图（L5andDownTempAvgPlot）中绘制回归线，但不断遇到以下错误。我还想知道是否有一种方法可以得到 ggplot 中两条线的最佳拟合线（来自 DailyAvgL5 和 DailyDownGaugeAvg 的线）。我不确定这是否可能，但如果可以的话，这就是我最终希望能够做到的。

#create plot of daily avgs
library(ggplot)
library(dplyr)

L5andDownTempAvgPlot <- (ggplot(NULL, aes(Date, mean_temp)) +
    geom_line(data = DailyAvgL5, color = "black") +
    geom_line(data = DailyDownGaugeAvg, color = "red") +
    geom_smooth(data = DailyDownGaugeAvg, method = 'lm', formula = DailyDownGaugeAvg$Date~DailyDownGaugeAvg$mean_temp)
)

DownGaugeHeightAvgPlot <- (ggplot(DailyDownGaugeAvg, aes(Date, DailyGaugeHeightAvg)) +
                             geom_line(data = DailyDownGaugeAvg, color = "blue") +
                             geom_smooth(method = 'lm')
)

DownGaugeHeightAvgPlot + L5andDownTempAvgPlot

`geom_smooth()` using formula = 'y ~ x'
Warning message:
Failed to fit group -1.
Caused by error in `Ops.Date()`:
! * not defined for "Date" objects 

dput(head(DailyDownGaugeAvg))
structure(list(Date = structure(c(19789, 19790, 19791, 19792, 
19793, 19794), class = "Date"), mean_temp = c(7.94, 8.465625, 
7.965625, 7.64673913043478, 8.63645833333333, 9.146875), DailyGaugeHeightAvg = c(15.5787368421053, 
12.3515625, 9.34770833333333, 12.2685869565217, 15.6577083333333, 
16.4609375)), row.names = c(NA, -6L), class = c("tbl_df", "tbl", 
"data.frame"))

> dput(head(DailyAvgL5))
structure(list(Date = structure(c(19791, 19792, 19793, 19794, 
19795, 19796), class = "Date"), mean_temp = c(9.98765502929687, 
9.884833984375, 8.01781209309896, 8.70198394775391, 9.21991678873698, 
9.69807739257812)), row.names = c(NA, -6L), class = c("tbl_df", 
"tbl", "data.frame"))

我认为这与我试图将回归线拟合到 ggplot (data,...) 中第一个参数中未详细说明的数据有关，但老实说不确定。我对 r 很陌生，所以我问了很多问题，但我很感谢您的帮助。我也无法显示下游仪表mean_temp 和L5mean_temp 之间的相关性，但我相信这超出了这个范围。谢谢。

Answer 1

对于公式，不要使用数据框中的值

# this will fail
ggplot(data)+
  geom_smooth(
    aes(x = Date, y = mean_temp.x), 
    method = 'lm', 
    formula = data$Date ~ data$mean_temp.x,
    se = TRUE)

# this works
ggplot(data)+
  geom_smooth(
    aes(x = Date, y = mean_temp.x), 
    method = 'lm', 
    formula = y ~ x,
    se = TRUE)

# this works too
ggplot(data)+
  geom_smooth(
    aes(x = Date, y = mean_temp.x), 
    method = 'lm', 
    formula = y ~ poly(x, 2),
    se = TRUE)

# so does this    
ggplot(data)+
  geom_smooth(
    aes(x = Date, y = mean_temp.x), 
    method = 'lm', 
    formula = y ~ log(x),
    se = TRUE)