R语言 显示折线图的数值 r语言绘制两条折线图

2.折线图

这个系列是关于R中基础图形和进阶图形的绘制。视频课程会陆续更新到我的B站【木舟笔记】，希望大家多多支持！

折线图通常用来对两个连续变量的相互依存关系进行可视化，其中，x轴对应于自变量，y轴对应于因变量。折线图的x轴通常对应的是连续型变量或者有序离散型变量。

• 2.1 绘制简单折线图
• 2.2 向折线图添加数据表记
• 2.3 绘制多重折线图
• 2.4 修改线条样式
• 2.5 修改数据标记样式
• 2.6 绘制面积图
• 2.7 绘制堆积面积图
• 2.8 绘制百分比面积堆积图
• 2.9 添加置信域
• 参考书籍

2.1 绘制简单折线图

library(ggplot2)
ggplot(BOD, aes(x = Time, y = demand)) + geom_line()

BOD

##   Time demand
## 1    1    8.3
## 2    2   10.3
## 3    3   19.0
## 4    4   16.0
## 5    5   15.6
## 6    7   19.8

BOD1 <- BOD  # Make a copy of the data
BOD1$Time <- factor(BOD1$Time) #转为因子型变量
ggplot(BOD1, aes(x = Time, y = demand, group = 1)) + geom_line()

数据集BOD中没有对应于Time=6的数据点，因此Time被转化为因子型变量时，它并没有6这个水平。

可以运行ylim()设定y轴范围或者运行含一个参数的expand_limit()扩展y轴的范围。

# 以下结果都是相同的
ggplot(BOD, aes(x = Time, y = demand)) + geom_line() + ylim(0, max(BOD$demand))
ggplot(BOD, aes(x = Time, y = demand)) + geom_line() + expand_limits(y = 0)

2.2 向折线图添加数据表记

ggplot(BOD, aes(x = Time, y = demand)) + geom_line() + geom_point()

library(gcookbook) 
# wordlpop 对应的采集时间间隔不是常数。时间越近的采集频率越高。
ggplot(worldpop, aes(x = Year, y = Population)) + geom_line() + geom_point()

# 当y轴取对数时也一样
ggplot(worldpop, aes(x = Year, y = Population)) + geom_line() + geom_point() +     scale_y_log10()

2.3 绘制多重折线图

# 载入plyr，便于使用ddply() 创建样本数据集
library(plyr)
# 汇总ToothGrowth 数据集
tg <- ddply(ToothGrowth, c("supp", "dose"), summarise, length=mean(len))
# 将 supp 映射给 colour
ggplot(tg, aes(x=dose, y=length, colour=supp)) + geom_line()

# 将 supp 映射给 线型 linetype
ggplot(tg, aes(x=dose, y=length, linetype=supp)) + geom_line()

# 
ggplot(tg, aes(x=factor(dose), y=length, colour=supp, group=supp)) + geom_line()

# 不能缺失group=supp语句，否则ggplot()会不知如何将数据组合在一起，从而报错
ggplot(tg, aes(x=factor(dose), y=length, colour=supp)) + geom_line()

plot of chunk unnamed-chunk-3

# 分组不正确也有可能变成锯齿状
ggplot(tg, aes(x=dose, y=length)) + geom_line()

plot of chunk unnamed-chunk-3

ggplot(tg, aes(x=dose, y=length, shape=supp)) + geom_line() +    geom_point(size=4)           # 更大的点

ggplot(tg, aes(x=dose, y=length, fill=supp)) + geom_line() +    geom_point(size=4, shape=21) #使用有填充色的点

# 数据标记相互重叠，需要相应的移动标记点以及连接线。
ggplot(tg, aes(x=dose, y=length, shape=supp)) + 
  geom_line(position=position_dodge(0.2)) +#将连接线左右移动0.2    
  geom_point(position=position_dodge(0.2), size=4)  # 将点的位置左右移动0.2

2.4 修改线条样式

通过设置线型(linetype)、线宽(size) 和颜色(colour)参数可以分别修改折现的线型、线宽和颜色。

ggplot(BOD, aes(x = Time, y = demand)) + 
  geom_line(linetype = "dashed", size = 1,  colour = "blue")

library(plyr)
tg <- ddply(ToothGrowth, c("supp", "dose"), summarise, length = mean(len))
ggplot(tg, aes(x = dose, y = length, colour = supp)) + 
  geom_line() + 
  scale_colour_brewer(palette = "Set1"))

# 在aes()函数外部设定参数则会对所有折线图有效
ggplot(tg, aes(x = dose, y = length, group = supp)) + 
  geom_line(colour = "darkgreen", size = 1.5)

# supp被映射给了颜色，所以自动作为分组变量
ggplot(tg, aes(x = dose, y = length, colour = supp)) + 
  geom_line(linetype = "dashed") +     
  geom_point(shape = 22, size = 3, fill = "white")

2.5 修改数据标记样式

# geom_point()设置点大小、颜色、填充
ggplot(BOD,aes(x = Time,y = demand)) + 
  geom_line() + 
  geom_point(size = 4,shape = 22,colour = "darkred",fill = "pink")

ggplot(BOD, aes(x = Time, y = demand)) + 
  geom_line() + 
  geom_point(size = 4,shape = 21, fill = "white")

pd <- position_dodge(0.2)
ggplot(tg, aes(x = dose, y = length, fill = supp)) + 
  geom_line(position = pd) +     
  geom_point(shape = 21, size = 3, position = pd) + 
  scale_fill_manual(values = c("black","white"))

2.6 绘制面积图

运行 geom_area() 函数即可绘制面积图

# 将sunspot.year数据集转化为数据框，便于本例使用
sunspotyear <- data.frame(Year = as.numeric(time(sunspot.year)), Sunspots = as.numeric(sunspot.year))ggplot(sunspotyear, aes(x = Year, y = Sunspots)) + geom_area()

# 颜色、透明度设置
ggplot(sunspotyear, aes(x = Year, y = Sunspots)) + 
  geom_area(colour = "black",fill = "blue", alpha = 0.2)

# 去掉底部横线 不设定colour，使用geom_line()绘制轨迹
ggplot(sunspotyear, aes(x = Year, y = Sunspots)) + 
  geom_area(fill = "blue",alpha = 0.2) + 
  geom_line()

2.7 绘制堆积面积图

library(gcookbook) 
ggplot(uspopage, aes(x = Year, y = Thousands, fill = AgeGroup)) + geom_area()

head(uspopage)

> head(uspopage)
  Year AgeGroup Thousands
1 1900       <5      9181
2 1900     5-14     16966
3 1900    15-24     14951
4 1900    25-34     12161
5 1900    35-44      9273
6 1900    45-54      6437

# 通过设定breaks翻转堆积顺序
# 透明度、颜色、大小设置
ggplot(uspopage, aes(x = Year, y = Thousands, fill = AgeGroup)) + 
  geom_area(colour = "black", size = 0.2, alpha = 0.4) + 
  scale_fill_brewer(palette = "Blues", breaks = rev(levels(uspopage$AgeGroup)))

# 设定order = desc(AgeGroup) 可以对堆积顺序进行反转
library(plyr)  
ggplot(uspopage, aes(x = Year, y = Thousands, fill = AgeGroup, order = desc(AgeGroup))) +     
  geom_area(colour = "black", size = 0.2, alpha = 0.4) + 
  scale_fill_brewer(palette = "Blues")

# 去掉框线
ggplot(uspopage, aes(x = Year, y = Thousands, fill = AgeGroup, order = desc(AgeGroup))) +     
  geom_area(colour = NA, alpha = 0.4) + 
  scale_fill_brewer(palette = "Blues") +     
  geom_line(position = "stack", size = 0.2)

2.8 绘制百分比面积堆积图

# 先计算百分比
uspopage_prop <- ddply(uspopage, "Year", transform, Percent = Thousands/sum(Thousands) * 100)
ggplot(uspopage_prop, aes(x = Year, y = Percent, fill = AgeGroup)) + 
  geom_area(colour = "black", size = 0.2, alpha = 0.4) + 
  scale_fill_brewer(palette = "Blues", breaks = rev(levels(uspopage$AgeGroup)))

head(uspopage)

> head(uspopage)
  Year AgeGroup Thousands
1 1900       <5      9181
2 1900     5-14     16966
3 1900    15-24     14951
4 1900    25-34     12161
5 1900    35-44      9273
6 1900    45-54      6437

uspopage_prop <- ddply(uspopage, "Year", transform, Percent = Thousands/sum(Thousands) * 100)

2.9 添加置信域

运行 geom_ribbon()分别映射一个变量给 ymin 和 ymax。

climate数据集中的Anomaly10y变量表示了各年温度相对于1950-1980平均水平变异的10年移动平均。Unc10y表示其95%置信区间。

library(gcookbook) 
# 抓取 climate 数据的一个子集
clim <- subset(climate, Source == "Berkeley", select = c("Year", "Anomaly10y",     "Unc10y"))
head(clim)

> head(clim)
  Year Anomaly10y Unc10y
1 1800     -0.435  0.505
2 1801     -0.453  0.493
3 1802     -0.460  0.486
4 1803     -0.493  0.489
5 1804     -0.536  0.483
6 1805     -0.541  0.475

# 将置信域绘制为阴影
# 注意一下图层的顺序
ggplot(clim, aes(x = Year, y = Anomaly10y)) + 
  geom_ribbon(aes(ymin = Anomaly10y - Unc10y, ymax = Anomaly10y + Unc10y), alpha = 0.2) + 
  geom_line()

# 使用虚线表示置信域的上下边界
ggplot(clim, aes(x = Year, y = Anomaly10y)) + 
  geom_line(aes(y = Anomaly10y -Unc10y), colour = "grey50", linetype = "dotted") + 
  geom_line(aes(y = Anomaly10y +Unc10y), colour = "grey50", linetype = "dotted") + 
  geom_line()

参考书籍

• R Graphics Cookbook, 2nd edition.