166

I have a question about legends in ggplot2. I managed to plot three lines in the same graph and want to add a legend with the three colors used. This is the code used

library(ggplot2)    
require(RCurl)

link<-getURL("https://dl.dropbox.com/s/ds5zp9jonznpuwb/dat.txt")
datos<- read.csv(textConnection(link),header=TRUE,sep=";")
datos$fecha <- as.POSIXct(datos[,1], format="%d/%m/%Y")    

temp = ggplot(data=datos,aes(x=fecha, y=TempMax,colour="1")) + 
           geom_line(colour="red") + opts(title="TITULO") +
           ylab("Temperatura (C)") + xlab(" ") + 
           scale_y_continuous(limits = c(-10,40)) + 
           geom_line(aes(x=fecha, y=TempMedia,colour="2"),colour="green") + 
           geom_line(aes(x=fecha, y=TempMin,colour="2"),colour="blue") +
           scale_colour_manual(values=c("red","green","blue"))

temp

and the output

ggplot three lines

I'd like to add a legend with the three colours used and the name of the variable (TempMax,TempMedia and TempMin). I have tried 

scale_colour_manual

but can't find the exact way.

Unfortunately original data were deleted from linked site and could not be recovered. But they came from meteo data files with this format

"date","Tmax","Tmin","Tmed","Precip.diaria","Wmax","Wmed"
2000-07-31 00:00:00,-1.7,-1.7,-1.7,-99.9,20.4,20.4
2000-08-01 00:00:00,22.9,19,21.11,-99.9,6.3,2.83
2000-08-03 00:00:00,24.8,12.3,19.23,-99.9,6.8,3.87
2000-08-04 00:00:00,20.3,9.4,14.4,-99.9,8.3,5.29
2000-08-08 00:00:00,25.7,14.4,19.5,-99.9,7.9,3.22
2000-08-09 00:00:00,29.8,16.2,22.14,-99.9,8.5,3.27
2000-08-10 00:00:00,30,17.8,23.5,-99.9,7.7,3.61
2000-08-11 00:00:00,27.5,17,22.68,-99.9,8.8,3.85
2000-08-12 00:00:00,24,13.3,17.32,-99.9,8.4,3.49
4

3 回答 3

229

由于@Etienne询问如何在不融化数据的情况下执行此操作（这通常是首选方法，但我承认在某些情况下可能无法做到这一点），我提出了以下替代方案。

从原始数据的子集开始：

datos <-
structure(list(fecha = structure(c(1317452400, 1317538800, 1317625200, 
1317711600, 1317798000, 1317884400, 1317970800, 1318057200, 1318143600, 
1318230000, 1318316400, 1318402800, 1318489200, 1318575600, 1318662000, 
1318748400, 1318834800, 1318921200, 1319007600, 1319094000), class = c("POSIXct", 
"POSIXt"), tzone = ""), TempMax = c(26.58, 27.78, 27.9, 27.44, 
30.9, 30.44, 27.57, 25.71, 25.98, 26.84, 33.58, 30.7, 31.3, 27.18, 
26.58, 26.18, 25.19, 24.19, 27.65, 23.92), TempMedia = c(22.88, 
22.87, 22.41, 21.63, 22.43, 22.29, 21.89, 20.52, 19.71, 20.73, 
23.51, 23.13, 22.95, 21.95, 21.91, 20.72, 20.45, 19.42, 19.97, 
19.61), TempMin = c(19.34, 19.14, 18.34, 17.49, 16.75, 16.75, 
16.88, 16.82, 14.82, 16.01, 16.88, 17.55, 16.75, 17.22, 19.01, 
16.95, 17.55, 15.21, 14.22, 16.42)), .Names = c("fecha", "TempMax", 
"TempMedia", "TempMin"), row.names = c(NA, 20L), class = "data.frame")

您可以通过以下方式获得所需的效果（这也清理了原始绘图代码）：

ggplot(data = datos, aes(x = fecha)) +
  geom_line(aes(y = TempMax, colour = "TempMax")) +
  geom_line(aes(y = TempMedia, colour = "TempMedia")) +
  geom_line(aes(y = TempMin, colour = "TempMin")) +
  scale_colour_manual("", 
                      breaks = c("TempMax", "TempMedia", "TempMin"),
                      values = c("red", "green", "blue")) +
  xlab(" ") +
  scale_y_continuous("Temperatura (C)", limits = c(-10,40)) + 
  labs(title="TITULO")

colour这个想法是通过将美学映射到一个常量字符串来为每条线赋予一种颜色。选择要在图例中出现的字符串是最简单的。在这种情况下，它与正在绘制的变量的名称相同这一事实y并不重要；它可以是任何一组字符串。这在aes调用内部非常重要；您正在创建到此“变量”的映射。

scale_colour_manual现在可以将这些字符串映射到适当的颜色。结果是 在此处输入图像描述

在某些情况下，需要通过命名手动比例中的值来明确级别和颜色之间的映射（感谢@DaveRGP指出这一点）：

ggplot(data = datos, aes(x = fecha)) +
  geom_line(aes(y = TempMax, colour = "TempMax")) +
  geom_line(aes(y = TempMedia, colour = "TempMedia")) +
  geom_line(aes(y = TempMin, colour = "TempMin")) +
  scale_colour_manual("", 
                      values = c("TempMedia"="green", "TempMax"="red", 
                                 "TempMin"="blue")) +
  xlab(" ") +
  scale_y_continuous("Temperatura (C)", limits = c(-10,40)) + 
  labs(title="TITULO")

（给出与以前相同的数字）。使用命名值，可以使用中断来设置图例中的顺序，并且可以在值中使用任何顺序。

ggplot(data = datos, aes(x = fecha)) +
  geom_line(aes(y = TempMax, colour = "TempMax")) +
  geom_line(aes(y = TempMedia, colour = "TempMedia")) +
  geom_line(aes(y = TempMin, colour = "TempMin")) +
  scale_colour_manual("", 
                      breaks = c("TempMedia", "TempMax", "TempMin"),
                      values = c("TempMedia"="green", "TempMax"="red", 
                                 "TempMin"="blue")) +
  xlab(" ") +
  scale_y_continuous("Temperatura (C)", limits = c(-10,40)) + 
  labs(title="TITULO")

于 2012-04-27T18:20:20.250 回答
91

我倾向于发现，如果我在多个几何图形中指定单个颜色，我做错了。以下是我将如何绘制您的数据：

##Subset the necessary columns
dd_sub = datos[,c(20, 2,3,5)]
##Then rearrange your data frame
library(reshape2)
dd = melt(dd_sub, id=c("fecha"))

剩下的就是一个简单的 ggplot 命令：

ggplot(dd) + geom_line(aes(x=fecha, y=value, colour=variable)) +
  scale_colour_manual(values=c("red","green","blue"))

示例图

在此处输入图像描述

于 2012-04-27T10:57:18.527 回答
2

我真的很喜欢@Brian Diggs 提出的解决方案。但是，在我的情况下，我在循环中创建线图而不是明确给出它们，因为我不知道先验我将拥有多少地块。当我尝试调整@Brian 的代码时，我在正确处理颜色方面遇到了一些问题。原来我需要修改美学功能。如果有人遇到同样的问题，这里是对我有用的代码。

我使用了与@Brian 相同的数据框：

data <- structure(list(month = structure(c(1317452400, 1317538800, 1317625200, 1317711600, 
                                       1317798000, 1317884400, 1317970800, 1318057200, 
                                       1318143600, 1318230000, 1318316400, 1318402800, 
                                       1318489200, 1318575600, 1318662000, 1318748400, 
                                       1318834800, 1318921200, 1319007600, 1319094000), 
                                     class = c("POSIXct", "POSIXt"), tzone = ""),
                   TempMax = c(26.58, 27.78, 27.9, 27.44, 30.9, 30.44, 27.57, 25.71, 
                               25.98, 26.84, 33.58, 30.7, 31.3, 27.18, 26.58, 26.18, 
                               25.19, 24.19, 27.65, 23.92), 
                   TempMed = c(22.88, 22.87, 22.41, 21.63, 22.43, 22.29, 21.89, 20.52,
                                 19.71, 20.73, 23.51, 23.13, 22.95, 21.95, 21.91, 20.72, 
                                 20.45, 19.42, 19.97, 19.61), 
                   TempMin = c(19.34, 19.14, 18.34, 17.49, 16.75, 16.75, 16.88, 16.82, 
                               14.82, 16.01, 16.88, 17.55, 16.75, 17.22, 19.01, 16.95, 
                               17.55, 15.21, 14.22, 16.42)), 
              .Names = c("month", "TempMax", "TempMed", "TempMin"), 
              row.names = c(NA, 20L), class = "data.frame")

就我而言，我是动态生成my.cols的my.names，但我不想让事情变得不必要的复杂，所以我在这里明确地给出它们。这三行使图例的排序和颜色分配更容易。

my.cols <- heat.colors(3, alpha=1)
my.names <- c("TempMin", "TempMed", "TempMax")
names(my.cols) <- my.names

这是情节：

p <-  ggplot(data, aes(x = month))

for (i in 1:3){
  p <- p + geom_line(aes_(y = as.name(names(data[i+1])), colour = 
colnames(data[i+1])))#as.character(my.names[i])))
}
p + scale_colour_manual("", 
                        breaks = as.character(my.names),
                        values = my.cols)
p

在此处输入图像描述

于 2018-05-02T17:35:25.183 回答