r语言ggplot2修改画布尺寸 r语言ggplot2绘图教程

 第19章 使用ggplot2进行高级绘图

 # 目的：使用性状、颜色和尺寸来对多元数据进行可视化
#主要绘图包：ggplot2包 gridExtra包(或cowplot包)
#主要数据集：lattice包中的singer数据集、mtcars数据集、car包中的Salaries数据集

#观察各个数据集的基本情况

data(singer,package="lattice")
 head(singer,5)
 str(singer)

head(mtcars,5)
 str(mtcars)

data(Salaries)
 head(Salaries,5)
 str(Salaries)

19.1 R中的四种图形系统

基础图形系统：R自带/grid包/lattice包/ggplot2包
grid图形系统(grid包)：
用户在图像设备上随意创建矩形区域并定义坐标系统，然后使用绘图基础单元来控制图形元素的摆放与外观。对图形的灵活性很高，适用于软件开发者，但不提供生成统计图形以及完整绘图的函数，不适合数据分析师。
lattice图形系统(lattice包):
绘制网格图形，其显示一个变量的分布或者变量之间的关系，分别显示一个或多个变量的各个水平。基于grid包创建，处理多元数据的可视化功能很强。（一般为绘图的备选方案）
ggplot2图形系统(ggplot2包)：
最常用的图形系统，一种全面的，基于语法的，连贯一致的图形生成系统。

19.2 ggplot2 包介绍

ggplot2语法：每一个函数修改属于自己的部分，函数与函数之间用（+）号函数串联

library(ggplot2)
 ggplot(data=mtcars,aes(x=wt,y=mpg))+
   geom_point()+
   labs(title = "Automobile data",x="Miles per gallon")

#对散点图的点样式/颜色和大小进行设置；添加拟合曲线并设置线条的颜色和类型

ggplot(data=mtcars,aes(x=wt,y=mpg))+
   geom_point(pch=17,color="forestgreen",size=2)+
   geom_smooth(method = "lm",color="red",linetype=2)
   labs(title = "Automobile data",x="Miles per gallon")

 #使用分面

#对mtcars数据进行必要处理
#将am/vs和cyl转化成因子
 mtcars$am <- factor(mtcars$am,levels = c(0,1),
                     labels = c("auto","manual"))
 mtcars$vs <- factor(mtcars$vs,levels = c(0,1),
                     labels = c("v-engine","s-engine"))  
 mtcars$cyl <- factor(mtcars$cyl)  
 #绘图
 ggplot(data=mtcars,aes(x=hp,y=mpg,shape=cyl,color=cyl))+         #cyl是分组变量
   geom_point(size=3)+
   facet_grid(am~vs)+                                                                        #am和vs是刻面变量
   labs(title = "Automobile data by engine type",x="horsepower",y="Miles per gallon")

19.3 用几何函数指定图的类型

常用几何函数

几何函数的常见选项

 绘图符号和线条类型

      

ggplot(data=Salaries,aes(x=rank,y=salary))+
   geom_boxplot(fill="skyblue",color="black",notch = TRUE)+
   geom_point(position = "jitter",color="blue",alpha=0.5,size=1)+
   geom_rug(sides = "l",color="grey40")+
   labs(title = "Automobile data by engine type",x="horsepower",y="Miles per gallon")

ggplot(data=singer,aes(x=voice.part,y=height))+
   geom_violin(fill="lightblue")+
   geom_boxplot(fill = "lightgreen",width=0.2)
   labs(title = "violin combined with boxplot",x="Voice.part",y="height")

19.4 分组

在一个图中画出两个或多组的观察值，在R中一般通过分类变量的水平（因子）来定义

ggplot(data=Salaries,aes(x=salary,fill=rank))+
     geom_density(alpha=0.3)

ggplot(data=Salaries,aes(x=yrs.since.phd,y=salary,color=rank,shape=sex))+
     geom_point()

# 按学术等级和性别划分的教授数量

p1 <- ggplot(Salaries,aes(x=rank,fill=sex)) +
   geom_bar(position="stack") + labs(title='position="stack"')p2 <- ggplot(Salaries,aes(x=rank,fill=sex)) +
   geom_bar(position="dodge") + labs(title='position="dodge"')p3 <- ggplot(Salaries,aes(x=rank,fill=sex)) +
   geom_bar(position="fill") + labs(title='position="fill"',y="proportion")library(cowplot)
 plot_grid(p1,p2,p3,ncol=3)

p1 <- ggplot(Salaries,aes(x=rank,fill=sex)) + geom_bar()
p2 <- ggplot(Salaries,aes(x=rank)) + geom_bar(fill="red")
p3 <- ggplot(Salaries,aes(x=rank,fill="red")) + geom_bar()
 plot_grid(p1,p2,p3,ncol=3)

#通常来说，变量应该设在aes()函数内，分配常数应该设在aes()函数外

19.5 刻面

ggplot2的刻面图函数

分别对以上语法进行实践，可以对比一下几张图的差异

ggplot(singer,aes(height)) +
   geom_histogram(bins = 25,fill="forestgreen",color="black") +
   facet_wrap(~voice.part,nrow = 4)

ggplot(singer,aes(height)) +
   geom_histogram(bins = 25,fill="forestgreen",color="black") +
   facet_wrap(~voice.part,ncol = 4)

library(car)
 ggplot(Salaries,aes(x=yrs.since.phd,y=salary,color=rank,shape=rank)) +
   geom_point(size=2) +  facet_grid(.~sex)

ggplot(Salaries,aes(x=yrs.since.phd,y=salary,color=rank,shape=rank)) +
   geom_point(size=2) +  facet_grid(sex~.)

ggplot(Salaries,aes(x=yrs.since.phd,y=salary,color=rank,shape=rank)) +
   geom_point(size=2) +  facet_grid(discipline~sex)

ggplot(singer,aes(x=height,fill=voice.part)) +
   geom_density() +
   facet_grid(voice.part~.)

19.6 添加光滑曲线

# 探究博士毕业年数与薪水的关系 95%置信区间的非参数光滑曲线

ggplot(Salaries,aes(x=yrs.since.phd,y=salary))+
          geom_smooth()+geom_point()

 

#按性别拟合一个二次多项式回归

ggplot(Salaries,aes(x=yrs.since.phd,y=salary,linetype=sex,shape=sex,color=sex))  +
   geom_smooth(method = lm,formula = y~poly(x,2),se=FALSE,size=1) +
   geom_point(size=0.8,alpha=0.5)

 19.7  修改ggplot2图形的外观

19.7.1 坐标轴

ggplot(Salaries,aes(x=rank,y=salary,fill=sex)) +
   geom_boxplot() +
   scale_x_discrete(breaks = c("AsstProf","AssocProf","Prof"),
                    labels = c("Assistant\nProfessor",
                               "Associate\nProfessor",
                               "Full\nProfessor")) +
   scale_y_continuous(breaks = c(50000,100000,150000,200000),
                      labels = c("$50K","$100K","$150K","$200K")) +
   labs(title = "Faculty salary by rank and sex")

19.7.2 图例

图例是指出如何利用颜色，形状，尺寸等视觉特效来表示数据特征的指南。更改图例标题时
需要考虑图例是否基于颜色，形状，尺寸等具体内容，如下图中fill=sex图例代表性别，基于fill审美，可以通过将fill=“mytitle”添加到labs（）函数中来改变标题；
图例位置通过theme（）函数中的legend.position参数选项进行修改，参数值：left，right（默认），top，bottom，none（删除）或向量参数指定位置c（x,y）其中x,y的范围均在0~1之间，表示距离左侧边缘x底部边缘y

ggplot(Salaries,aes(x=rank,y=salary,fill=sex)) +
   geom_boxplot() +
   scale_x_discrete(breaks = c("AsstProf","AssocProf","Prof"),
                    labels = c("Assistant\nProfessor",
                               "Associate\nProfessor",
                               "Full\nProfessor")) +
   scale_y_continuous(breaks = c(50000,100000,150000,200000),
                      labels = c("$50K","$100K","$150K","$200K")) +
   labs(title = "Faculty salary by rank and sex",x="Rank",y="Salary",fill="Gender")+
   theme(legend.position = c(0.15,0.85))

19.7.3 标尺

ggplot(mtcars,aes(x=wt,y=mpg,size=disp))+
   geom_point(shape = 21, color = "black", fill = "pink") +
   labs(title="Bublle chart",x="Weight",y="Miles per gallon",
        size="Engine \ndisplacement")

ggplot(mtcars,aes(wt,mpg,fill = disp,size=disp))+
   geom_point( shape = 21, color = "black") +
   labs(title="Bublle chart",x="Weight",y="Miles per gallon",
        size="Engine \ndisplacement")+
   scale_fill_continuous(low = "yellow",high = "green")

 

离散型标尺将带有因子水平的视觉线索（如颜色，形状，尺寸，线条类型和透明度）关联起来
scale_color_manual（values）指定颜色
scale_color_brewer(palette =" name") 使用预先设定好的颜色集
display.brewer.all() 展示所有的内置颜色集，既name

ggplot(Salaries,aes(x=yrs.since.phd,y=salary,color=rank)) +
   scale_color_manual(values=c("orange","olivedrab","navy")) +
   geom_point(size=2)

#对比一下不同的颜色，将palette设置成不同的值即可获得，如Set1 Set2等
p1 <- ggplot(Salaries,aes(x=yrs.since.phd,y=salary,color=rank)) +
   scale_color_brewer(palette ="Set1") +
   geom_point(size=2)+labs(title="Set1")......
 plot_grid(p1,p2,p3,p4,p5,p6,p7,p8,ncol = 4)

#颜色相关 

library(RColorBrewer)
 display.brewer.all()

R内置颜色集

#brewer.pal(3~n,name=)
# 3~n 表示颜色数量,3是最小值; n根据颜色集name中数量而定，name为R内置颜色集
 display.brewer.pal(name = "Accent",n=5)
 brewer.pal(5,name="Accent")
#：  "#7FC97F" "#BEAED4" "#FDC086" "#FFFF99" "#386CB0"

ggplot(Salaries,aes(x=yrs.since.phd,y=salary)) +  geom_point(color="#386CB0")

 

colorRampPalette(colors = c("red","blue"))(4)
# "#FF0000" "#AA0055" "#5500AA" "#0000FF"

还可以参见 RColorBrewer与ggplot2 - 简书 (jianshu.com)

#可以参见 http://colorbrewer2.org/#将设置好的统一的主题保存起来，可以应用到多个图中

mytheme <- theme(
   plot.title = element_text(face = "bold.italic",size = 14,color = "brown"),
   axis.title = element_text(face = "bold.italic",size = 10,color = "brown"),
   axis.text = element_text(face = "bold",size = 9,color = "darkblue"),
   panel.background = element_rect(fill = "white",color = "darkblue"),
   panel.grid.major.y = element_line(color = "grey",linetype = 1),
   panel.grid.minor.y = element_line(color = "grey",linetype = 2),
   panel.grid.minor.x = element_blank(),
   legend.position = "top")
   
 ggplot(Salaries,aes(x=rank,y=salary,fill=sex)) +
   geom_boxplot() +
   labs(title = "Salary by Rank and Sex",x="Rank",y="Salary") +
   mytheme

19.7.5 多重图

p1 <- ggplot(Salaries,aes(x=rank)) +
   geom_bar() p2 <- ggplot(Salaries,aes(x=sex)) +
   geom_bar()p3 <- ggplot(Salaries,aes(x=yrs.since.phd,y=salary)) +
   geom_point() plot_grid(p1,p2,p3,ncol=3)

#保存图像

ggsave("mypicture.pdf", width =16,
        height =16, units = "cm",dpi=300)#pdf可以是png ps tiff svg wmf jepg tex bmp 等其它格式