chap3 ggplot2包数据可视化

作者：带土；Daitu; Adam 邮箱：2505131775@qq.com

在程序开头设置所有绘图风格

library(ggplot2)
theme_set(theme_bw(base_family = "STKaiti"))

3.1 ggplot2包初探

ggplot()函数的介绍、图像显示主题的介绍、颜色、大小、形状

ggplot2包的数据可视化基本流程

library(ggplot2)
library(gridExtra)
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 指定绘图的数据和坐标系变量
ggplot(data = mpg,aes(x=displ,y = cty))+
  ## 设置绘图的基本主题情况
  theme_bw(base_family = "STKaiti")+
  ## 绘制图像的类型，并绘制图像是否根据不同的类以不同样式显示
  geom_point(aes(colour = fl,shape = fl))+
  ## 设置图像的轴标签和名称
  labs(x = "发动机排量",y = "油耗",title = "mpg数据集")+
  ## 对名称位置和图例位置进行调整
  theme(plot.title = element_text(hjust = 0.5),
        legend.position = c(0.8,0.7))+
  ## 对坐标轴的内容进行调整
  scale_x_continuous(labels = function(x) paste(x,"升",sep = ""))+
  ## 对图例中的颜色映射进行调整
  scale_color_brewer(palette = "Set1")

绘制图像的不同显示主题

data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 绘制不同主题的散点图
p1 <- ggplot(mpg,aes(x=displ,y = cty))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  ggtitle("主题为:theme_bw")
p2 <- ggplot(mpg,aes(x=displ,y = cty))+
  theme_classic(base_family = "STKaiti")+
  geom_point(colour = "red")+
  ggtitle("主题为:theme_classic")
p3 <- ggplot(mpg,aes(x=displ,y = cty))+
  theme_dark(base_family = "STKaiti")+
  geom_point(colour = "red")+
  ggtitle("主题为:theme_dark")
p4 <- ggplot(mpg,aes(x=displ,y = cty))+
  theme_gray(base_family = "STKaiti")+
  geom_point(colour = "red")+
  ggtitle("主题为:theme_gray")
p5 <- ggplot(mpg,aes(x=displ,y = cty))+
  theme_light(base_family = "STKaiti")+
  geom_point(colour = "red")+
  ggtitle("主题为:theme_light")
p6 <- ggplot(mpg,aes(x=displ,y = cty))+
  theme_minimal(base_family = "STKaiti")+
  geom_point(colour = "red")+
  ggtitle("主题为:theme_minimal")

grid.arrange(p1,p2,p3,p4,p5,p6,nrow = 2)

在程序开头设置所有绘图风格

theme_set(theme_bw(base_family = "STKaiti"))

ggplot2包中的几何对象和主题

几何对象函数的介绍

data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 绘制不同主题的散点图
p1 <- ggplot(mpg,aes(x=displ,y = cty))+
  geom_point(colour = "red")+
  geom_smooth(method = "loess")+
  ggtitle("geom_point + geom_smooth")

mpgclass <- as.data.frame(table(mpg$class))
colnames(mpgclass) <- c("class","Freq")
mpgclass$ymin <- mpgclass$Freq -2 
mpgclass$ymax <- mpgclass$Freq + 2 

p2 <- ggplot(mpgclass,aes(x = class ,y = Freq))+
  geom_bar(stat = "identity",fill = "red",
           alpha = 0.5)+
  geom_errorbar(aes(ymin = ymin,ymax=ymax),
                width = 0.25,colour = "blue")+
  ggtitle("geom_bar + geom_errorbar")

p3 <- ggplot(mpg,aes(x=as.factor(cyl),y = displ))+
  geom_boxplot(colour = "red",weight = 0.5)+
  geom_jitter(aes(colour = displ))+
  theme(legend.position = "none")+
  ggtitle("geom_boxplot + geom_jitter")

p4 <- ggplot(mpg,aes(displ))+
  geom_histogram(fill = "red",binwidth = 0.25,
                 alpha = 0.5)+
  ggtitle("geom_histogram")

p5 <- ggplot(mpg,aes(x=displ,y = cty))+
  geom_hex(bins = 30)+
  geom_density2d()+
  theme(legend.position = "none")+
  ggtitle("geom_hex + geom_density2d")

library(zoo)

## 
## Attaching package: 'zoo'

## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric

library(stringr)
library(RColorBrewer)
## 数据准备
data(AirPassengers)
AirPas <- as.data.frame(AirPassengers)
AirPas$x <- as.numeric(AirPas$x)
AirPas$yearmonth <- yearmon(time(AirPassengers))
AirPas$year <- format(AirPas$yearmonth,format = "%Y")
AirPas$month <- format(AirPas$yearmonth,"%B")
## 热力图分析数据的变化
AirPas$month <- factor(AirPas$month,levels = c("一月","二月","三月",
                               "四月","五月", "六月","七月",
                               "八月","九月", "十月","十一月",
                               "十二月"))


p6 <- ggplot(AirPas,aes(x=year,y=month))+
  geom_tile(aes(fill = x))+
  scale_fill_gradientn(colours=rev(brewer.pal(10,"RdYlGn")))+
  geom_text(aes(label=x),size=2.5)+
  theme(legend.position = "none")+
  ggtitle("geom_tile + geom_text")
p6 

grid.arrange(p1,p2,p3,p4,p5,p6,nrow = 3)

## `geom_smooth()` using formula 'y ~ x'

3、theme（）函数的介绍

library(ggplot2)
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 调整绘图主题的示例
ggplot(data = mpg)+theme_bw(base_family = "STKaiti")+
  geom_boxplot(aes(x = as.factor(cyl),y = displ,
                   colour = as.factor(year)))+
  labs(x = "气缸数量",y = "发动机排量",title = "mpg数据集",
       colour = "时间",subtitle = "主题调整的例子")+
  scale_x_discrete(labels = function(x) paste(x,"个",sep = ""))+
  ## 对图像主体进行调整
  theme(plot.title = element_text(hjust = 0.5),
        plot.subtitle = element_text(hjust = 1),
        ## 调整背景
        plot.background = element_rect(fill = "gray"),
        ## 绘图区的边框
        panel.border = element_rect(colour ="blue",size = 2),
        ## 网格线的设置
        panel.grid = element_line(linetype = 2),
        ## 坐标轴标签和值刻度的设置
        axis.title.x = element_text(colour = "red"),
        axis.title.y = element_text(hjust = 0),
        axis.text.x  = element_text(angle = 60),
        ## 刻度线的设置
        axis.ticks.y = element_line(colour = "red",size = 2),
        ## 图例的设置
        legend.position = "bottom",
        legend.background = element_rect(fill = "greenyellow"),
        legend.title = element_text(colour = "red"))

ggplot2分面和颜色标度

分面1

## 网格分面，多行多列
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 调整绘图主题的示例
ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_grid(rows = vars(cyl),cols = vars(year))+
  labs(x = "油耗",y = "发动机排量",title = "mpg数据集")

ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_grid(cyl~year)+
  labs(x = "油耗",y = "发动机排量",title = "mpg数据集")

分面2

## 封装型分面，
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 调整绘图主题的示例
ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_wrap(vars(class),nrow = 3)+
  labs(x = "油耗",y = "发动机排量",title = "mpg数据集")

ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_wrap(~class,ncol = 3)+
  labs(x = "油耗",y = "发动机排量",title = "mpg数据集")

分面3

## 分面时的标度控制
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 调整绘图主题的示例
p1 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_wrap(~cyl,scales = "fixed")+
  labs(title = ' scales = "fixed" ')

p2 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_wrap(~cyl,scales = "free")+
  labs(title = ' scales = "free" ')

p3 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_wrap(~cyl,scales = "free_x")+
  labs(title = ' scales = "free_x" ')

p4 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(colour = "red")+
  facet_wrap(~cyl,scales = "free_y")+
  labs(title = ' scales = "free_y" ')

gridExtra::grid.arrange(p1,p2,p3,p4,nrow = 2)

颜色标度，连续颜色

head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 连续型，根据颜色梯度划分：
p1 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(aes(colour = cty))+
  scale_color_gradient(low = "blue",high = "red")+
  ggtitle('scale_color_gradient(low = "blue",high = "red")')

p2 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(aes(colour = cty-20))+
  scale_color_gradient2(low = "red",mid = "white",high = "blue")+
  ggtitle('scale_color_gradient2(low = "red",mid = "white",high = "blue")')


p3 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(aes(colour = cty / 35))+
  scale_color_gradientn(
    colours = c("red","yellow","green","lightblue"),
    values = c(1,0.75,0.5,0.25,0))+
  ggtitle('scale_color_gradientn(colours=c("red","yellow","green","lightblue"),\nvalues = c(1,0.75,0.5,0.25,0)))')

grid.arrange(p1,p2,p3,nrow = 3)

颜色标度，离散颜色

head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

## 离散型颜色，
p1 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(aes(colour = class))+
  scale_color_brewer(palette = "BrBG")+
  ggtitle('Diverging:scale_color_brewer(palette = "BrBG")')

p2 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(aes(colour = class))+
  scale_color_brewer(palette = "Set1")+
  ggtitle('Qualitative:scale_color_brewer(palette = "Set1")')

p3 <- ggplot(data = mpg,aes(x = cty,y = displ))+
  theme_bw(base_family = "STKaiti")+
  geom_point(aes(colour = class))+
  scale_color_brewer(palette = "BuGn")+
  ggtitle('Sequential:scale_color_brewer(palette = "BuGn")')

gridExtra::grid.arrange(p1,p2,p3,nrow = 3)

## 3.5 ggplot2的统计变换和坐标系

ggplot2中常用的统计变换形式

library(ggplot2)
library(gridExtra)
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

p1 <- ggplot(mpg,aes(displ))+
  geom_histogram(aes(y = ..count..),fill = "lightblue")+
  ggtitle("统计变换为：count")
p2 <- ggplot(mpg,aes(displ))+
  geom_histogram(aes(y = ..density..),fill = "lightblue")+
  ggtitle("统计变换为：density")
p3 <- ggplot(mpg,aes(displ))+
  geom_histogram(aes(y = ..ncount..),fill = "lightblue")+
  ggtitle("统计变换为：ncount")
p4 <- ggplot(mpg,aes(displ))+
  geom_histogram(aes(y = ..ndensity..),fill = "lightblue")+
  ggtitle("统计变换为：ndensity")

grid.arrange(p1,p2,p3,p4,nrow = 2)

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot2中的图元位置

## 图元位置
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

p1 <- ggplot(mpg)+
  geom_bar(aes(x = class,fill = drv),position = "stack")+
  ggtitle('position = "stack"')+
  theme(axis.text.x = element_text(angle = 15))
p2 <- ggplot(mpg)+
  geom_bar(aes(x = class,fill = drv),position = "dodge")+
  ggtitle('position = "dodge"')+
  theme(axis.text.x = element_text(angle = 15))
p3 <- ggplot(mpg)+
  geom_bar(aes(x = class,fill = drv),position = "fill")+
  ggtitle('position = "fill"')+
  theme(axis.text.x = element_text(angle = 15))
p4 <- ggplot(mpg)+
  geom_bar(aes(x = class,fill = drv),position = "identity")+
  ggtitle('position = "identity"')+
  theme(axis.text.x = element_text(angle = 15))

grid.arrange(p1,p2,p3,p4,nrow = 2)

ggplot2包中的坐标系样式

## 坐标系样式

p1 <- ggplot(mpg,aes(class))+
  geom_bar(aes(fill = class),show.legend = FALSE)+
  ggtitle("条形图")

p2 <- ggplot(mpg,aes(class))+
  geom_bar(aes(fill = class),show.legend = FALSE)+
  coord_flip()+ggtitle("条形图+coord_flip()")
p3 <- ggplot(mpg,aes(class))+
  geom_bar(aes(fill = class),show.legend = FALSE)+
  coord_polar()+ggtitle("条形图+coord_polar()")
p4 <- ggplot(mpg)+
  geom_bar(aes(x = factor(1),fill = class),
           width = 1,show.legend = FALSE)+
  coord_polar(theta = "y")+
  ggtitle('条形图+coord_polar()')

grid.arrange(p1,p2,p3,p4,nrow = 2)

3.5 ggplot2可视化常见的统计图1

library(ggplot2)
library(gridExtra)
data("mpg")
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

1条形图

### 条形图

## 常见的条形图p
p1 <- ggplot(mpg)+
  geom_bar(aes(x = cyl,fill = as.factor(cyl)))+
  labs(title = "条形图")

p1 

##根据数量的多少进行排序的条形图
newdata <- as.data.frame(table(mpg$cyl))
newdata

##   Var1 Freq
## 1    4   81
## 2    5    4
## 3    6   79
## 4    8   70

p2 <- ggplot(newdata)+
  geom_bar(aes(x = reorder(Var1,Freq),y = Freq,fill = Var1),
           stat = "identity")+
  labs(title = "条形图+升序排列")

p2 

## 条形图+降序排
p3 <- ggplot(newdata)+
  geom_bar(aes(x = reorder(Var1,-Freq),y = Freq,fill = Var1),
           stat = "identity")+
  labs(title = "条形图+降序排列")

p3 

## 添加误差范围的条形图
newdata$Freqmin <- newdata$Freq - 2 ##下界的取值
newdata$Freqmax <- newdata$Freq + 5 ##上界的取值
newdata

##   Var1 Freq Freqmin Freqmax
## 1    4   81      79      86
## 2    5    4       2       9
## 3    6   79      77      84
## 4    8   70      68      75

p4 <- ggplot(newdata,aes(x = reorder(Var1,-Freq),y = Freq))+
  geom_bar(aes(fill = Var1),stat = "identity")+
  geom_errorbar(aes(ymin = Freqmin,ymax = Freqmax),
                colour = "black",width = 0.25)+
  labs(title = "条形图+errorbar")

p4 

## 水平条形图
p5 <- ggplot(newdata,aes(x = reorder(Var1,Freq),y = Freq))+
  geom_bar(aes(fill = Var1),stat = "identity")+
  geom_errorbar(aes(ymin = Freqmin,ymax = Freqmax),
                colour = "black",width = 0.25)+
  coord_flip()+
  labs(title = "水平条形图+errorbar")

p5 

## 分组条形图
p6 <- ggplot(mpg,aes(class,fill = drv))+
  geom_bar(position = "dodge2")+
  ggtitle("分组条形图+dodge2")

p6

## 归一化的堆叠条形图，可看出每部分所占的比例
p7 <- ggplot(mpg,aes(class,fill = drv))+
  geom_bar(position = "fill")+
  ggtitle("分组条形图+fill")

p7

## 双向条形图
set.seed(123)
newdata <- data.frame(x = c(1:30),y1 = abs(round(10*rnorm(30))),
                         y2 = -abs(round(6.8*rnorm(30))))
head(newdata)

##   x y1 y2
## 1 1  6 -3
## 2 2  2 -2
## 3 3 16 -6
## 4 4  1 -6
## 5 5  1 -6
## 6 6 17 -5

p8 <- ggplot(newdata,aes(x = x))+
  geom_bar(aes(y = y1),stat = "identity",fill = "red",alpha = 0.5)+
  geom_text(aes(y = y1+1,label = y1),size = 3)+
  geom_bar(aes(y = y2),stat = "identity",fill = "lightblue")+
  geom_text(aes(y = y2-1,label = y2),size = 3)+
  ggtitle("双向条形图")
  

p8

grid.arrange(p1,p2,p3,p4,p5,p6,p7,p8,ncol = 2)

2 饼图

head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

newdata <- as.data.frame(table(mpg$class))
newdata

##         Var1 Freq
## 1    2seater    5
## 2    compact   47
## 3    midsize   41
## 4    minivan   11
## 5     pickup   33
## 6 subcompact   35
## 7        suv   62

### 基础的饼图
p1 <- ggplot(newdata)+
  geom_bar(aes(x = "",y = Freq,fill = Var1),stat = "identity")+
  coord_polar(theta = "y")+
  labs(title = "基础的饼图")
p1

## 调整饼图的细节
p2 <- ggplot(newdata,aes(x = "",y = Freq,fill = Var1))+
  geom_bar(width = 1,stat = "identity")+
  coord_polar(theta = "y")+
  ## 调整图像的细节
  theme_minimal(base_family = "STKaiti")+
  theme(axis.text = element_blank(),
        axis.ticks=element_blank(),
        panel.grid=element_blank(),
        axis.title.x = element_blank(),
        axis.title.y = element_blank())+
  scale_fill_brewer(palette = "Set1")+
  labs(title = "精修的饼图")
  

p2

## 甜甜圈图
p3 <- ggplot(newdata,aes(x = "",y = Freq,fill = Var1))+
  geom_bar(width = 1,stat = "identity")+
  coord_polar(theta = "y")+
  ## 调整图像的细节
  theme_minimal(base_family = "STKaiti")+
  theme(axis.text = element_blank(),
        axis.ticks=element_blank(),
        panel.grid=element_blank(),
        axis.title.x = element_blank(),
        axis.title.y = element_blank())+
  scale_fill_brewer(palette = "Set1")+
  annotate("text",x = 0,y = 0,label =  "Label")+
  labs(title = "甜甜圈图")
  
p3

## 玫瑰图
p4 <- ggplot(newdata,aes(x = Var1,y = Freq,fill = Var1))+
  geom_bar(width = 0.8,stat = "identity")+
  geom_text(aes(y = Freq+2,label = Freq))+
  scale_fill_brewer(palette = "Set1")+
  coord_polar(theta = "x")+
  theme_minimal(base_family = "STKaiti")+
  theme(axis.text = element_blank(),
        axis.ticks=element_blank(),
        axis.title.x = element_blank(),
        axis.title.y = element_blank())+
  labs(title = "玫瑰图")
  
p4

grid.arrange(p1,p2,p3,p4,ncol = 2)

3 直方图系列

### 直方图
data("airquality")
head(airquality)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

p1 <- ggplot(airquality)+
  geom_histogram(aes(Wind),bins = 25,fill = "lightblue")+
  ggtitle("直方图")

p1

## 绘制直方图时分面
p2 <- ggplot(airquality)+
  geom_histogram(aes(Wind),bins = 25,fill = "lightblue")+
  facet_wrap(~Month)+
  ggtitle("直方图分面")

p2

## 根据其它变量设置填充颜色，堆积直方图
p3 <- ggplot(airquality)+
  geom_histogram(aes(Wind,fill = as.factor(Month)),bins = 25)+
  ggtitle("堆积直方图")

p3

## 根据自身变量设置填充颜色，堆积直方图
p4 <- ggplot(airquality)+
  geom_histogram(aes(Wind,fill = cut(Wind,10)),bins = 30,
                 show.legend = F)+
  scale_fill_discrete(h = c(0, 180) + 15, c = 50, l = 65)+
  ggtitle("渐变直方图")

p4

grid.arrange(p1,p2,p3,p4,nrow = 2)

4 箱线图和小提琴图系列

### 箱线图和小提琴图
data("airquality")
head(airquality)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

## 一个分组变量的箱线图
p1 <- ggplot(airquality,aes(x = as.factor(Month),y = Temp))+
  geom_boxplot()+
  ggtitle("箱线图")
p1

## 小提琴图加抖动散点图
p2 <- ggplot(airquality,aes(x = as.factor(Month),y = Temp))+
  geom_violin(fill = "lightblue")+
  geom_jitter(aes(colour = Temp),width = 0.1)+
  scale_color_gradient(low = "blue",high = "red")+
  ggtitle("小提琴图加抖动散点图")

p2

##  二个分组变量的箱线图
p3 <- ggplot(airquality,aes(x = as.factor(Month),y = Temp))+
  geom_boxplot(aes(colour = cut(Wind,3)))+
  ggtitle("分组箱线图")

p3

## 分组小提琴图
p4 <- ggplot(airquality,aes(x = as.factor(Month),y = Temp))+
  geom_violin(aes(fill = cut(Wind,3)))+
  ggtitle("分组小提琴图")

p4

##  二个分组变量的箱线图分面
p5 <- ggplot(airquality,aes(x = as.factor(Month),y = Temp))+
  geom_boxplot(aes(colour = cut(Wind,3)),show.legend = F)+
  facet_wrap(~cut(Wind,3))+
  ggtitle("分面＋分组箱线图")

p5

## 分组小提琴图+分面
p6 <- ggplot(airquality,aes(x = as.factor(Month),y = Temp))+
  geom_violin(aes(fill = cut(Wind,3)))+
  facet_wrap(~cut(Wind,3))+
  ggtitle("分面＋分组小提琴图")

p6

grid.arrange(p1,p2,p3,p4,p5,p6,ncol = 2)

## 3.6 ggplot2可视化常见的统计图2

5 散点图＋平滑曲线

### 散点图
data("airquality")
head(airquality)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

## 基础的散点图
p1 <- ggplot(airquality,aes(x = Wind,y = Temp))+
  geom_point(colour = "red")+
  ggtitle("散点图")

p1

## 散点图＋平滑曲线
p2 <- ggplot(airquality,aes(x = Wind,y = Temp))+
  geom_point(colour = "red")+
  geom_smooth(method = "loess")+
  ggtitle("散点图+平滑曲线")
p2

## `geom_smooth()` using formula 'y ~ x'

## 分组散点图＋平滑曲线
p3 <- ggplot(airquality,aes(x = Wind,y = Temp))+
  geom_point(aes(colour = as.factor(Month)))+
  geom_smooth(aes(colour = as.factor(Month)),method = "loess")+
  scale_color_brewer(palette = "Set1")+
  ggtitle("分组散点图+平滑曲线")

p3

## `geom_smooth()` using formula 'y ~ x'

## 分面散点图＋平滑曲线
p4 <- ggplot(airquality,aes(x = Wind,y = Temp))+
  geom_point(aes(colour = as.factor(Month)))+
  geom_smooth(aes(colour = as.factor(Month)),method = "loess")+
  facet_wrap(~as.factor(Month))+
  scale_color_brewer(palette = "Set1")+
  theme(legend.position = "none")+
  ggtitle("分面散点图+平滑曲线")

p4

## `geom_smooth()` using formula 'y ~ x'

## 气泡图
p5 <- ggplot(airquality,aes(x = Wind,y = Temp))+
  geom_point(aes(size = 1+ (Day / 10),colour = 1+ (Day / 10)),
             show.legend = F)+
  ggtitle("气泡图")

p5

## 气泡图+分面
p6 <- ggplot(airquality,aes(x = Wind,y = Temp))+
  geom_point(aes(size = 1+ (Day / 10),colour = 1+ (Day / 10)),
             show.legend = F)+
  facet_wrap(~Month)+
  ggtitle("分面气泡图")

p6

grid.arrange(p1,p2,p3,p4,p5,p6,ncol = 2)

## `geom_smooth()` using formula 'y ~ x'
## `geom_smooth()` using formula 'y ~ x'
## `geom_smooth()` using formula 'y ~ x'

### 6 密度曲线系列

head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

head(airquality)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

### 密度曲线
p1 <- ggplot(airquality)+
  geom_density(aes(Temp),fill = "red",alpha = 0.5)+
  ggtitle("密度曲线")
p1

### 分组数据的密度曲线
p2  <- ggplot(airquality)+
  geom_density(aes(Temp,colour = as.factor(Month),
                   fill = as.factor(Month)),alpha = 0.5)+
  ggtitle("分组密度曲线")
p2

### 分组数据的密度曲线进行分面
p3  <- ggplot(airquality)+
  geom_density(aes(Temp),fill = "red",alpha = 0.5)+
  facet_wrap(~Month,nrow = 2)+
  ggtitle("分面密度曲线")
p3

### 分面分组数据的密度曲线进行
head(mpg)

## # A tibble: 6 x 11
##   manufacturer model displ  year   cyl trans      drv     cty   hwy fl    class 
##   <chr>        <chr> <dbl> <int> <int> <chr>      <chr> <int> <int> <chr> <chr> 
## 1 audi         a4      1.8  1999     4 auto(l5)   f        18    29 p     compa…
## 2 audi         a4      1.8  1999     4 manual(m5) f        21    29 p     compa…
## 3 audi         a4      2    2008     4 manual(m6) f        20    31 p     compa…
## 4 audi         a4      2    2008     4 auto(av)   f        21    30 p     compa…
## 5 audi         a4      2.8  1999     6 auto(l5)   f        16    26 p     compa…
## 6 audi         a4      2.8  1999     6 manual(m5) f        18    26 p     compa…

p4  <- ggplot(mpg)+
  geom_density(aes(displ,fill = drv,colour = drv),
               alpha = 0.5)+
  facet_wrap(~year,nrow = 2)+
  ggtitle("分面分组密度曲线")
p4

## 二维密度曲线
p5 <- ggplot(airquality)+
  geom_density2d(aes(x = Temp,y = Wind))+
  ggtitle("二维密度曲线")

p5

## 二维密度曲线分组＋分面
p6 <- ggplot(airquality)+
  geom_density2d(aes(x = Temp,y = Wind,colour = as.factor(Month)),
                 show.legend = F)+
  facet_wrap(~Month)+
  ggtitle("分面二维密度曲线")

p6

grid.arrange(p1,p2,p3,p4,p5,p6,ncol = 2)

7 线图系列

library(tidyr)
## 数据准备
set.seed(123)
linedata1 <- data.frame(index = 1:100,
                       x1 = cumsum(rnorm(100,0,5)),
                       x2 = cumsum(rnorm(100,1,4)),
                       x3 = cumsum(rnorm(100,0,10)),
                       group = "class1")

head(linedata1)

##   index        x1         x2       x3  group
## 1     1 -2.802378 -1.8416263 21.98810 class1
## 2     2 -3.953266  0.1859086 35.11223 class1
## 3     3  3.840276  0.1991411 32.46078 class1
## 4     4  4.192818 -0.1910293 37.89272 class1
## 5     5  4.839257 -2.9975036 33.74932 class1
## 6     6 13.414581 -2.1776145 28.98685 class1

set.seed(1234)
linedata2 <- data.frame(index = 1:100,
                       x1 = cumsum(rnorm(100,0,8)),
                       x2 = cumsum(rnorm(100,1,4)),
                       x3 = cumsum(rnorm(100,0,10)),
                       group = "class2")
linedataall <- rbind(linedata1,linedata2)
head(linedataall)

##   index        x1         x2       x3  group
## 1     1 -2.802378 -1.8416263 21.98810 class1
## 2     2 -3.953266  0.1859086 35.11223 class1
## 3     3  3.840276  0.1991411 32.46078 class1
## 4     4  4.192818 -0.1910293 37.89272 class1
## 5     5  4.839257 -2.9975036 33.74932 class1
## 6     6 13.414581 -2.1776145 28.98685 class1

### 折线图
p1 <- ggplot(linedata1)+
  geom_line(aes(x = index,y = x1),colour = "red")+
  ggtitle("单个变量折线图")

p1

### 多个变量折线图
## 宽数据转化维长数据
linedata1_long <- tidyr::gather(linedata1,key = "X",
                                value = "value",x1:x3)
head(linedata1_long)

##   index  group  X     value
## 1     1 class1 x1 -2.802378
## 2     2 class1 x1 -3.953266
## 3     3 class1 x1  3.840276
## 4     4 class1 x1  4.192818
## 5     5 class1 x1  4.839257
## 6     6 class1 x1 13.414581

p2 <- ggplot(linedata1_long)+
  geom_line(aes(x = index,y = value,colour = X,
                linetype = X))+
  ggtitle("多个变量折线图")

p2

### 多个变量的分组折线图
## 宽数据转化维长数据
linedataall_long <- gather(linedataall,key = "X",
                           value = "value",x1:x3)
head(linedataall_long)

##   index  group  X     value
## 1     1 class1 x1 -2.802378
## 2     2 class1 x1 -3.953266
## 3     3 class1 x1  3.840276
## 4     4 class1 x1  4.192818
## 5     5 class1 x1  4.839257
## 6     6 class1 x1 13.414581

p3 <- ggplot(linedataall_long)+
  geom_line(aes(x = index,y = value,colour = X,
                linetype = X))+
  facet_wrap(~group,ncol = 1,scales = "free_y")+
  ggtitle("多个变量分面折线图")

p3

## 分面折线图
p4 <- ggplot(linedataall_long)+
  geom_line(aes(x = index,y = value),colour = "red")+
  facet_grid(X~group,scales = "free_y")+
  ggtitle("网格分面折线图")

p4

## 面积图
head(linedataall)

##   index        x1         x2       x3  group
## 1     1 -2.802378 -1.8416263 21.98810 class1
## 2     2 -3.953266  0.1859086 35.11223 class1
## 3     3  3.840276  0.1991411 32.46078 class1
## 4     4  4.192818 -0.1910293 37.89272 class1
## 5     5  4.839257 -2.9975036 33.74932 class1
## 6     6 13.414581 -2.1776145 28.98685 class1

p5 <- ggplot(linedataall,aes(x = index))+
  geom_area(aes(y = x1,colour = group,fill = group),alpha = 0.25)+
  ggtitle("单个变量分组面积图")

p5

## 面积图2
p6 <- ggplot(linedataall_long,aes(x = index))+
  geom_area(aes(y = value,colour = group,fill = group),
            alpha = 0.25)+
  facet_grid(X~group,scales = "free_y")+
  ggtitle("多个变量网格分面面积图")

p6

## 面积图3,通过Y轴的最大最小值指定面积
head(linedataall_long)

##   index  group  X     value
## 1     1 class1 x1 -2.802378
## 2     2 class1 x1 -3.953266
## 3     3 class1 x1  3.840276
## 4     4 class1 x1  4.192818
## 5     5 class1 x1  4.839257
## 6     6 class1 x1 13.414581

## 数据准备
areadata <- linedataall_long[,c("index","group","X")]
areadata$ymin <- linedataall_long$value
areadata$ymax <- 
  areadata$ymin + abs(rnorm(length(areadata$ymin),0,20))
head(areadata)

##   index  group  X      ymin      ymax
## 1     1 class1 x1 -2.802378  8.796762
## 2     2 class1 x1 -3.953266 15.112308
## 3     3 class1 x1  3.840276  7.428848
## 4     4 class1 x1  4.192818 24.388982
## 5     5 class1 x1  4.839257  5.311789
## 6     6 class1 x1 13.414581 26.395146

p7 <- ggplot(areadata,aes(x = index))+
  geom_ribbon(aes(ymin = ymin,ymax = ymax,fill = X),alpha = 0.85)+
  facet_wrap(~group,ncol = 1,scales = "free_y")+
  ggtitle("分面面积图geom_ribbon")

p7

## 堆积面积图
p8 <- ggplot(areadata,aes(x = index))+
  geom_area(aes(y = abs(ymax),fill = X,color = X),
              alpha = 0.85,position = "fill")+
  facet_wrap(~group,ncol = 1,scales = "free_y")+
  ggtitle("分面堆积面积图")

p8

grid.arrange(p1,p2,p3,p4,p5,p6,p7,p8,ncol = 2)

8 热力图等

## 热力图
library(zoo)
library(stringr)
library(RColorBrewer)
## 数据准备
data(AirPassengers)
AirPas <- as.data.frame(AirPassengers)
AirPas$x <- as.numeric(AirPas$x)
AirPas$yearmonth <- yearmon(time(AirPassengers))
AirPas$year <- format(AirPas$yearmonth,format = "%Y")
AirPas$month <- format(AirPas$yearmonth,"%B")
## 热力图分析数据的变化
AirPas$month <- factor(AirPas$month,
                       levels = c("一月","二月","三月",
                               "四月","五月", "六月","七月",
                               "八月","九月", "十月","十一月",
                               "十二月"))
head(AirPas)

##     x yearmonth year month
## 1 112    1 1949 1949  一月
## 2 118    2 1949 1949  二月
## 3 132    3 1949 1949  三月
## 4 129    4 1949 1949  四月
## 5 121    5 1949 1949  五月
## 6 135    6 1949 1949  六月

p1 <- ggplot(AirPas,aes(x=year,y=month))+
  geom_tile(aes(fill = x))+
  scale_fill_gradient(low = "lightblue", high = "red")+
  geom_text(aes(label=x),size=2.5)+
  ggtitle("热力图")

p1

## 热力图分面
## 数据准备
data("airquality")
head(airquality)

##   Ozone Solar.R Wind Temp Month Day
## 1    41     190  7.4   67     5   1
## 2    36     118  8.0   72     5   2
## 3    12     149 12.6   74     5   3
## 4    18     313 11.5   62     5   4
## 5    NA      NA 14.3   56     5   5
## 6    28      NA 14.9   66     5   6

## 数据转化维长数据
airlong <- gather(airquality,key = "var",
                  value = "value",c("Ozone","Solar.R"))
head(airlong)

##   Wind Temp Month Day   var value
## 1  7.4   67     5   1 Ozone    41
## 2  8.0   72     5   2 Ozone    36
## 3 12.6   74     5   3 Ozone    12
## 4 11.5   62     5   4 Ozone    18
## 5 14.3   56     5   5 Ozone    NA
## 6 14.9   66     5   6 Ozone    28

p2 <- ggplot(airlong,aes(x = Day,y = Month))+
  geom_tile(aes(fill = value))+
  scale_fill_gradientn(colours=rev(brewer.pal(10,"RdYlGn")))+
  facet_wrap(~var,ncol = 1)+
  geom_text(aes(label=value),size=2,na.rm = TRUE)+
  scale_x_continuous(breaks = 1:31,labels = c(1:31))+
  ggtitle("热力图分面")
p2

grid.arrange(p1,p2,ncol = 1)