ggplot(data=NULL时添加分组图例的问题与解决方案

问题 #

作为R语言新手，使用ggplot2绘图时遇到如下问题：当ggplot()的data参数设为NULL时，无法给代表“Tailwater Gauge”和“Site L5”的两条线添加区分图例。网上多数方案是在ggplot()的aes()中添加color映射，但对该场景不适用。

初始绘图代码 #

ggplot(DailyDownGaugeAvg, aes(Date, DailyGaugeHeightAvg)) +
  geom_line(
    data = DailyDownGaugeAvg,
    color = "blue")

ggplot(NULL, aes(Date, mean_temp)) +
  geom_smooth(data = DailyAvgL5, alpha = 0.3) +
  geom_line(data = DailyAvgL5, color = "blue") +
  
  geom_smooth(data = DailyDownGaugeAvg, color = "red", alpha = 0.3) +
  geom_line(data = DailyDownGaugeAvg, color = "red") +
  
  xlab('Date') + ylab('Daily Average Temperature (Celcius)') +
  ggtitle("Daily Average Temperature
Site L5 vs Tailwater Gauge")

数据集预览 #

# DailyAvgL5数据集前6行
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), ciInf = c(8.5062704241455, 8.40344937922362, 
6.53642748794758, 7.22059934260253, 7.7385321835856, 8.21669278742675
), ciSup = c(11.4690396344483, 11.3662185895264, 9.49919669825033, 
10.1833685529053, 10.7013013938884, 11.1794619977295)), row.names = c(NA, 
-6L), class = c("tbl_df", "tbl", "data.frame"))

# DailyDownGaugeAvg数据集前6行
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), ciInf = c(6.75421576137529, 7.27984076137529, 6.77984076137529, 
6.46095489181007, 7.45067409470863, 7.96109076137529), ciSup = c(9.12578423862471, 
9.65140923862471, 9.15140923862471, 8.83252336905949, 9.82224257195804, 
10.3326592386247)), row.names = c(NA, -6L), class = c("tbl_df", 
"tbl", "data.frame"))

解决代码 #

ggplot(DailyDownGaugeAvg, aes(Date, DailyGaugeHeightAvg)) +
  geom_line(
    data = DailyDownGaugeAvg,
    color = "blue")

ggplot(L5DownDailyMerge, aes(Date, NULL, color())) +
  geom_smooth(aes(x = Date, y = DailyAvgL5Temp), alpha = 0.25) +
  geom_line(aes(x = Date, y = DailyAvgL5Temp, color = "L5")) +
  
  geom_smooth(aes(x = Date, y = DailyAvgDownstreamGaugeTemp, colour = "Tailwater Gauge"), alpha = 0.25) +
  geom_line(aes(x = Date, y = DailyAvgDownstreamGaugeTemp, colour = "Tailwater Gauge")) +
  
  scale_colour_manual("",
                     values = c("L5"="blue", "Tailwater Gauge"="red")) +
  theme(legend.position = "bottom") +
  xlab('Date') + ylab('Daily Average Temperature (Celcius)') +
  ggtitle("Daily Average Temperature
Site L5 vs Tailwater Gauge")

方案说明 #

原代码的问题在于直接在geom_line()/geom_smooth()中设置color="blue"这类固定颜色，这属于手动颜色赋值，ggplot不会将其识别为需要生成图例的分类变量。

解决方案的核心是：

• 在每个geom层的aes()内部设置color为分组名称（如color = "L5"），让ggplot将这些名称当作离散分类变量处理，从而触发图例生成。
• 使用scale_colour_manual()手动指定每个分组对应的颜色，并设置图例标题（这里设为空字符串）。
• 通过theme(legend.position = "bottom")调整图例位置，提升可读性。

内容的提问来源于stack exchange，提问作者Matt Schaaf